Search

Abstract Despite the extensive research on hepatocellular carcinoma (HCC) exploring various treatment strategies, the survival outcomes have remained unsatisfactory. The aim of this research was to evaluate the ability of machine learning (ML) methods in predicting the survival probability of HCC patients. The study retrospectively analyzed cases of patients with stage 1–4 HCC. Demographic, clinical, pathological, and laboratory data served as input variables. The researchers employed various feature selection techniques to identify the key predictors of patient mortality. Additionally, the study utilized a range of machine learning methods to model patient survival rates. The study included 393 individuals with HCC. For early-stage patients (stages 1–2), the models reached recall values ​​of up to 91% for 6-month survival prediction. For advanced-stage patients (stage 4), the models achieved accuracy values ​​of up to 92% for 3-year overall survival prediction. To predict whether patients are ex or not, the accuracy was 87.5% when using all 28 features without feature selection with the best performance coming from the implementation of weighted KNN. Further improvements in accuracy, reaching 87.8%, were achieved by applying feature selection methods and using a medium Gaussian SVM. This study demonstrates that machine learning techniques can reliably predict survival probabilities for HCC patients across all disease stages. The research also shows that AI models can accurately identify a high proportion of surviving individuals when assessing various clinical and pathological factors.

Objective‍ ‍To investigate the prognostic factors affecting survival in patients with natural killer T-cell lymphoma (NKTL), and then develop a prognostic model for predicting their overall survival (OS) based on random survival forest (RSF) algorithm. Methods‍ ‍Demographic and clinical pathological data of NKTL patients were collected from the SEER database during 2000 and 2020. The patients were divided into a training cohort (n=471) and a validation cohort (n=203) in a 7∶3 ratio. Cox regression analysis was performed to identify prognostic factors affecting OS, and a nomogram model was constructed based on the obtained factors. Meanwhile, RSF algorithm was used to determine prognostic factors affecting OS to build the RSF model. The models were evaluated using receiver operating characteristic (ROC) curve, calibration curve, decision curve, net reclassification improvement (NRI), and integrated discrimination improvement (IDI), and the predictive performances of the 2 models were compared. Risk scores for each patient were calculated using the 2 models. Then the patients were divided into high- and low-risk groups based on the median risk score, and survival curve was plotted for comparison. Results‍ ‍Ann Arbor stage, age, radiotherapy, combined treatment, and type of disease were identified as significant prognostic variables associated with OS. In the validation cohort, the area under the ROC curve (AUC) for the nomogram model at 1, 3, and 5 years was 0.745, 0.771, and 0.748, respectively, while the AUC for the RSF model was 0.764, 0.792, and 0.761 at the same time points. ROC curve analysis indicated that both models demonstrated good accuracy and discrimination in predicting OS. Calibration curve analysis showed a strong consistency between the predicted and actual OS for both models. Both models effectively stratified the patients into poor and favorable prognosis groups, with the OS of patients in the poor prognosis group being significantly shorter than that of the favorable prognosis group (P

Abstract Objective Despite the identification of various prognostic factors for anaplastic thyroid carcinoma (ATC) patients over the years, a precise prognostic tool for these patients is still lacking. This study aimed to develop and validate a prognostic model for predicting survival outcomes for ATC patients using random survival forests (RSF), a machine learning algorithm. Methods A total of 1222 ATC patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into a training set of 855 patients and a validation set of 367 patients. We developed an RSF model and a traditional Cox model using the training cohort and further compared their performance based on calibration and discrimination. integrated brier score (iBS) was used to estimate the calibration ability. The Brier score, C-index value, the receiver operating characteristic (ROC) curve with the area under the curve (AUC) and Decision Curves Analysis (DCA) were evaluated. Furthermore, we assessed the feature importance within the RSF model and validated its performance using the validation group. Results An RSF model and a traditional Cox model were successfully developed in training set. The Brier score for the RSF model was 0.055, which is lower than the Cox model’s score of 0.063, indicating better performance since a lower Brier score signifies superior model accuracy. The RSF model exceeded the Cox model in performance based on the C-index and AUC. Additionally, the DCA curve indicated that the RSF model provided substantial clinical benefit. And we further ranked the time-dependent features according to their permutation importance and observed that surgery, radiotherapy, and chemotherapy were the most influential predictors initially. Moreover, according to the RSF model predictions, the ATC patients were successfully stratified into 2 prognostic groups displaying significant difference in survival. Conclusions This prognostic study first revealed that RSF offers more precise overall survival predictions and superior prognostic stratification compared to the Cox regression model for ATC patients.

Abstract Purpose Induction chemotherapy (IC) for patients with locally advanced stage Head and Neck Squamous Cell Carcinomas (HNSCC) before radio-chemotherapy (RCT) or surgery remains a potential treatment option. This study analyzed how the response to IC correlates with survival outcomes. Methods We conducted a retrospective single-center study at a tertiary cancer center. Tumors were categorized by anatomical site and response to IC (non-responders vs. responders). Data were analyzed using Kaplan-Meier survival curves and Cox regression analysis. Results A total of 48 patients received IC. Of these, 33 patients were radiologically evaluable for response. The majority of evaluable patients received either TPF (Docetaxel, Cisplatin, 5-Fluorouracil) (58%) or TP (Docetaxel, Cisplatin) (24%) as their IC regimen. Tumor reduction of 30% or more was observed in 23 patients (69.7%), the tumor control rate was 97%. The 2-year event-free survival (EFS) in the IC evaluable population was 53.1%, overall survival (OS) was 63.6%, and recurrence-free survival (RFS) was 62.5%. Patients with laryngeal or hypopharyngeal tumors that did not respond to IC had a significantly poorer prognosis. This effect was not statistically significant in tumors of the oral cavity or oropharynx, where it was only observed as a trend. Conclusion IC is highly effective in treating locally advanced stage HNSCC. The response to IC is prognostic for survival, particularly in cancers of the larynx and hypopharynx.

Abstract Glioblastoma Multiforme (GBM), classified as a grade IV glioma by the World Health Organization (WHO), is a prevalent and notably aggressive form of brain tumor derived from glial cells. It stands as one of the most severe forms of primary brain cancer in humans. The median survival time of GBM patients is only 12–15 months, making it the most lethal type of brain tumor. Every year, about 200,000 people worldwide succumb to this disease. GBM is also highly heterogeneous, meaning that its characteristics and behavior vary widely among different patients. This leads to different outcomes and survival times for each individual. Predicting the survival of GBM patients accurately can have multiple benefits. It can enable optimal and personalized treatment planning based on the patient's condition and prognosis. It can also support the patients and their families to cope with the possible outcomes and make informed decisions about their care and quality of life. Furthermore, it can assist the researchers and scientists to discover the most relevant biomarkers, features, and mechanisms of the disease and to design more effective and personalized therapies. Artificial intelligence methods, such as machine learning and deep learning, have been widely applied to survival prediction in various fields, such as breast cancer, lung cancer, gastric cancer, cervical cancer, liver cancer, prostate cancer, and covid 19. This systematic review summarizes the current state-of-the-art methods for predicting glioblastoma survival using different types of input data, such as clinical features, molecular markers, imaging features, radiomics features, omics data or a combination of them. Following PRISMA guidelines, we searched databases from 2015 to 2024, reviewing 107 articles meeting our criteria. We analyzed the data sources, methods, performance metrics and outcomes of the studies. We found that random forest was the most popular method, and a combination of radiomics and clinical data was the most common input data.

Abstract Breast cancer is one of the most prevalent cancers with an increasing trend in both incidence and mortality rates in Iran. Survival analysis is a pivotal measure in setting appropriate care plans. To the best of our knowledge, this study is pioneering in Iran, introducing a multi-method approach using a Deep Neural Network (DNN) and 11 conventional machine learning (ML) methods to predict the 5 year survival of women with breast cancer. Supplying data from two centers comprising a total of 2644 records and incorporating external validation further distinguishes the study. Thirty-four features were selected based on a literature review and common variables in both datasets. Feature selection was also performed using a p value criterion (

Abstract Squamous cell lung cancer (SQCLC), which is fatal to humans, is heterogeneous with different genetic and histological features. We used SBMOI, a multi-omics data integration method from previous study, to integrate clinical, gene expression, and somatic mutation data of SQCLC to construct new patient features. Next, random survival forest (RSF) model and SimpleMKL model were constructed to predict the survival of SQCLC patients, and K-means model was constructed to perform molecular subtyping. The results of the RSF model showed that when the dimension of the patient features were 11 × 364 and the hard threshold was 0.2, we obtained the best results, and the AUC value of the 1-year time-dependent ROC curve was 0.706. The SimpleMKL model, constructed using the same patient features, performed exceptionally well, with 1-year, 5-year, and 10-year survival prediction AUC values of 0.944, 0.947 and 0.950, respectively. We used K-means analysis to identify three SQCLC molecular subtypes with significant survival differences. The patient features constructed by SBMOI were used to effectively predict the survival and molecular subtyping of SQCLC patients. In addition, our study further confirmed the effectiveness in multi-omics data integration task and broad applicability of SBMOI.

Abstract Background This multicentre retrospective observational study aims to develop imaging-based prognostic and predictive models for relapsed/refractory (R/R) B-cell lymphoma patients undergoing CAR-T therapy by integrating clinical data and imaging features. Specifically, our aim was to predict 3- and 6-month treatment response, overall survival (OS), progression-free survival (PFS), and the occurrence of the immune effector cell-associated neurotoxicity syndrome (ICANS). Results Sixty-five patients of R/R B-cell lymphoma treated with CAR-T cells in two centres were included. Pre-infusion [18F]FDG PET/CT scans and clinical data were systematically collected, and imaging features, including kurtosis, entropy, maximum diameter, standardized uptake value (SUV) related features (SUVmax, SUVmean, SUVstd, SUVmedian, SUVp25, SUVp75), total metabolic tumour volume (MTVtotal), and total lesion glycolysis (TLGtotal), were extracted using the Quibim platform. The median age was 62 (range 21–76) years and the median follow-up for survivors was 10.47 (range 0.20–45.80) months. A logistic regression model accurately predicted neurotoxicity (AUC: 0.830), and Cox proportional-hazards models for CAR-T response at 3 and 6 months demonstrated high accuracy (AUC: 0.754 and 0.818, respectively). Median predicted OS after CAR-T therapy was 4.73 months for high MTVtotal and 37.55 months for low MTVtotal. Median predicted PFS was 2.73 months for high MTVtotal and 11.83 months for low MTVtotal. For all outcomes, predictive models, combining imaging features and clinical variables, showed improved accuracy compared to models using only clinical variables or imaging features alone. Conclusion This study successfully integrates imaging features and clinical variables to predict outcomes in R/R B-cell lymphoma patients undergoing CAR-T. Notably, the identified MTVtotal cut-off effectively stratifies patients, as evidenced by significant differences in OS and PFS. Additionally, the predictive models for neurotoxicity and CAR-T response show promising accuracy. This comprehensive approach holds promise for risk stratification and personalized treatment strategies which may become a helpful tool for optimizing CAR-T outcomes in R/R lymphoma patients.

Abstract Background The rate of 30-day all-cause hospital readmissions can affect the funding a hospital receives. An accurate and reliable readmission prediction model could save money and increase quality-of-care. Few projects have explored formulating this task as a survival prediction problem, where models can exploit a real-valued time-to-readmission target. This paper demonstrates the effectiveness of a survival-inspired readmission model, especially when paired with a longitudinal patient representation that is agnostic to disease-cohort and predictive task. Methods We forecast readmissions for a population-level cohort of 421,088 patients discharged in 2015 and 2016 from hospitals in Alberta, Canada. Clinical features and sequences of historical medical codes (calculated from at least four full years prior to discharge) from linked administrative sources serve as model inputs. We trained binary 30-day readmission models (XGBoost and a Deep Neural Network) and time-to-event readmission models (CoxPH and N-MTLR) with and without machine-learned medical knowledge at initialization, then compared against the popular LACE-based model using the AUROC score at 30 days (AUROC@30). Survival models are additionally evaluated using concordance, Integrated Brier, and L1-loss scores. Results All models that utilize sequence features markedly out-perform even the best models trained on only clinical features. Further, a time-to-event target improves predictive performance at 30 days, given the same model inputs and architecture. N-MTLR, using solely sequence inputs and initialized with pre-learned medical knowledge, achieves an average AUROC@30 of 0.8460 over five folds with a standard deviation of 0.003. All trained models match or out-perform the LACE baseline of 0.6587±0.003. Conclusion Sequences of administrative medical codes contain rich predictive information for forecasting readmissions, and embedding medical knowledge a priori using machine learning provides readmission models an advantageous foundation for training. When combined with a model that can leverage a time-to-event target, excellent performance is possible on the 30-day all-cause readmission task using only administrative data.

Abstract Background The 3-variable number-of-risk-factors (NRF) model is a prognostic tool for patients undergoing palliative radiotherapy (PRT). However, there is little research on the NRF model for patients with painful non-bone-metastasis tumours treated with PRT, and the efficacy of the NRF model in predicting survival is unclear to date. Therefore, we aimed to assess the prognostic accuracy of a 3-variable NRF model in patients undergoing PRT for bone and non- bone-metastasis tumours. Methods This was a secondary analysis of studies on PRT for bone-metastasis (BM) and PRT for miscellaneous painful tumours (MPTs), including non-BM tumours. Patients were grouped in the NRF model and survival was compared between groups. Discrimination was evaluated using a time-independent C-index and a time-dependent area under the receiver operating characteristic curve (AUROC). A calibration curve was used to assess the agreement between predicted and observed survival. Results We analysed 485 patients in the BM group and 302 patients in the MPT group. The median survival times in the BM group for groups I, II, and III were 35.1, 10.1, and 3.3 months, respectively (P

Abstract Ovarian cancer is a formidable health challenge that demands accurate and timely survival predictions to guide clinical interventions. Existing methods, while commendable, suffer from limitations in harnessing the temporal evolution of patient data and capturing intricate interdependencies among different data elements. In this paper, we present a novel methodology which combines Temporal Analysis and Graph Neural Networks (GNNs) to significantly enhance ovarian cancer survival rate predictions. The shortcomings of current processes originate from their disability to correctly seize the complex interactions amongst diverse scientific information units in addition to the dynamic modifications that arise in a affected person`s nation over time. By combining temporal information evaluation and GNNs, our cautioned approach overcomes those drawbacks and, whilst as compared to preceding methods, yields a noteworthy 8.3% benefit in precision, 4.9% more accuracy, 5.5% more advantageous recall, and a considerable 2.9% reduction in prediction latency. Our method’s Temporal Analysis factor uses longitudinal affected person information to perceive good-sized styles and tendencies that offer precious insights into the direction of ovarian cancer. Through the combination of GNNs, we offer a robust framework able to shoot complicated interactions among exclusive capabilities of scientific data, permitting the version to realize diffused dependencies that would affect survival results. Our paintings have tremendous implications for scientific practice. Prompt and correct estimation of the survival price of ovarian most cancers allows scientific experts to customize remedy regimens, manipulate assets efficiently, and provide individualized care to patients. Additionally, the interpretability of our version`s predictions promotes a collaborative method for affected person care via way of means of strengthening agreement among scientific employees and the AI-driven selection help system. The proposed approach not only outperforms existing methods but also has the possible to develop ovarian cancer treatment by providing clinicians through a reliable tool for informed decision-making. Through a fusion of Temporal Analysis and Graph Neural Networks, we conduit the gap among data-driven insights and clinical practice, proposing a capable opportunity for refining patient outcomes in ovarian cancer management operations.

Background: Oral squamous cell carcinoma (OSCC) is a prevalent malignancy with significant morbidity and mortality, particularly in low- and middle-income countries. Despite advancements in treatment, prognostic tools integrating clinical, histopathological, and molecular data remain underdeveloped, limiting personalized risk stratification and survival prediction. Objective: This study aimed to develop and validate a prediction model for overall survival (OS) and progression-free survival (PFS) in OSCC, incorporating clinical, histopathological, and molecular factors. Methods: A retrospective cohort of 132 patients with histopathologically confirmed OSCC was analyzed. Data on demographic, clinical (tumor stage, lymph node involvement), histopathological (tumor grade, perineural invasion), and molecular (HPV status) variables were collected. Logistic regression and machine learning algorithms were used to build the prediction model. Internal validation was conducted using bootstrapping, and model performance was assessed using the area under the receiver operating characteristic (ROC) curve, calibration plots, and decision curve analysis (DCA). Results: The model demonstrated robust predictive performance, with an area under the ROC curve (AUC) of 0.85 for OS and 0.83 for PFS. Tumor stage, lymph node involvement, and HPV status were identified as key predictors of survival. Kaplan-Meier analysis showed steep declines in OS probabilities during the first 24 months, emphasizing the need for early interventions. Calibration plots indicated strong agreement between predicted and observed outcomes, supporting the model's reliability. Conclusion: This study developed a validated prediction model for OS and PFS in OSCC, demonstrating high discriminatory ability and calibration. Integrating clinical, histopathological, and molecular data enhances personalized risk stratification and treatment planning in oral oncology.

Background: Electrocardiogram (ECG) abnormalities have demonstrated potential as prognostic indicators of patient survival. However, the traditional statistical approach is constrained by structured data input, limiting its ability to fully leverage the predictive value of ECG data in prognostic modeling. Methods: This study aims to introduce and evaluate a deep-learning model to simultaneously handle censored data and unstructured ECG data for survival analysis. We herein introduce a novel deep neural network called ECG-surv, which includes a feature extraction neural network and a time-to-event analysis neural network. The proposed model is specifically designed to predict the time to 1-year mortality by extracting and analyzing unique features from 12-lead ECG data. ECG-surv was evaluated using both an independent test set and an external set, which were collected using different ECG devices. Results: The performance of ECG-surv surpassed that of the Cox proportional model, which included demographics and ECG waveform parameters, in predicting 1-year all-cause mortality, with a significantly higher concordance index (C-index) in ECG-surv than in the Cox model using both the independent test set (0.860 [95% CI: 0.859–0.861] vs. 0.796 [95% CI: 0.791–0.800]) and the external test set (0.813 [95% CI: 0.807–0.814] vs. 0.764 [95% CI: 0.755–0.770]). ECG-surv also demonstrated exceptional predictive ability for cardiovascular death (C-index of 0.891 [95% CI: 0.890–0.893]), outperforming the Framingham risk Cox model (C-index of 0.734 [95% CI: 0.715–0.752]). Conclusion: ECG-surv effectively utilized unstructured ECG data in a survival analysis. It outperformed traditional statistical approaches in predicting 1-year all-cause mortality and cardiovascular death, which makes it a valuable tool for predicting patient survival.

Background: Machine learning has tremendous potential in acute medical care, particularly in the field of precise medical diagnosis, prediction, and classification of brain tumors. Malignant gliomas, due to their aggressive growth and dismal prognosis, stand out among various brain tumor types. Recent advancements in understanding the genetic abnormalities that underlie these tumors have shed light on their histo-pathological and biological characteristics, which support in better classification and prognosis. Objectives: This review aims to predict gene alterations and establish structured correlations among various tumor types, extending the prediction of genetic mutations and structures using the latest machine learning techniques. Specifically, it focuses on multi-modalities of Magnetic Resonance Imaging (MRI) and histopathology, utilizing Convolutional Neural Networks (CNN) for image processing and analysis. Methods: The review encompasses the most recent developments in MRI, and histology image processing methods across multiple tumor classes, including Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. It identifies challenges in tumor classification, segmentation, datasets, and modalities, employing various neural network architectures. A competitive analysis assesses the performance of CNN. Furthermore it also implies K-MEANS clustering to predict Genetic structure, Genes Clusters prediction and Molecular Alteration of various types and grades of tumors e.g. Glioma, Meningioma, Pituitary, Oligodendroglioma, and Astrocytoma. Results: CNN and KNN structures, with their ability to extract highlights in image-based information, prove effective in tumor classification and segmentation, surmounting challenges in image analysis. Competitive analysis reveals that CNN and outperform others algorithms on publicly available datasets, suggesting their potential for precise tumor diagnosis and treatment planning. Conclusion: Machine learning, especially through CNN and SVM algorithms, demonstrates significant potential in the accurate diagnosis and classification of brain tumors based on imaging and histo-pathological data. Further advancements in this area hold promise for improving the accuracy and efficiency of intra-operative tumor diagnosis and treatment.

BackgroundBreast cancer (BC), as a leading cause of cancer mortality in women, demands robust prediction models for early diagnosis and personalized treatment. Artificial Intelligence (AI) and Machine Learning (ML) algorithms offer promising solutions for automated survival prediction, driving this study’s systematic review and meta-analysis.MethodsThree online databases (Web of Science, PubMed, and Scopus) were comprehensively searched (January 2016-August 2023) using key terms (“Breast Cancer”, “Survival Prediction”, and “Machine Learning”) and their synonyms. Original articles applying ML algorithms for BC survival prediction using clinical data were included. The quality of studies was assessed via the Qiao Quality Assessment tool.ResultsAmongst 140 identified articles, 32 met the eligibility criteria. Analyzed ML methods achieved a mean validation accuracy of 89.73%. Hybrid models, combining traditional and modern ML techniques, were mostly considered to predict survival rates (40.62%). Supervised learning was the dominant ML paradigm (75%). Common ML methodologies included pre-processing, feature extraction, dimensionality reduction, and classification. Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), emerged as the preferred modern algorithm within these methodologies. Notably, 81.25% of studies relied on internal validation, primarily using K-fold cross-validation and train/test split strategies.ConclusionThe findings underscore the significant potential of AI-based algorithms in enhancing the accuracy of BC survival predictions. However, to ensure the robustness and generalizability of these predictive models, future research should emphasize the importance of rigorous external validation. Such endeavors will not only validate the efficacy of these models across diverse populations but also pave the way for their integration into clinical practice, ultimately contributing to personalized patient care and improved survival outcomes.Systematic Review Registrationhttps://www.crd.york.ac.uk/prospero/, identifier CRD42024513350.

Abstract Background Predicting an individual’s risk of death from COVID-19 is essential for planning and optimising resources. However, since the real-world mortality rate is relatively low, particularly in places like Hong Kong, this makes building an accurate prediction model difficult due to the imbalanced nature of the dataset. This study introduces an innovative application of graph convolutional networks (GCNs) to predict COVID-19 patient survival using a highly imbalanced dataset. Unlike traditional models, GCNs leverage structural relationships within the data, enhancing predictive accuracy and robustness. By integrating demographic and laboratory data into a GCN framework, our approach addresses class imbalance and demonstrates significant improvements in prediction accuracy. Methods The cohort included all consecutive positive COVID-19 patients fulfilling study criteria admitted to 42 public hospitals in Hong Kong between January 23 and December 31, 2020 (n = 7,606). We proposed the population-based graph convolutional neural network (GCN) model which took blood test results, age and sex as inputs to predict the survival outcomes. Furthermore, we compared our proposed model to the Cox Proportional Hazard (CPH) model, conventional machine learning models, and oversampling machine learning models. Additionally, a subgroup analysis was performed on the test set in order to acquire a deeper understanding of the relationship between each patient node and its neighbours, revealing possible underlying causes of the inaccurate predictions. Results The GCN model was the top-performing model, with an AUC of 0.944, considerably outperforming all other models (p

Abstract The tumor microenvironment (TME) plays a fundamental role in tumorigenesis, tumor progression, and anti-cancer immunity potential of emerging cancer therapeutics. Understanding inter-patient TME heterogeneity, however, remains a challenge to efficient drug development. This article applies recent advances in machine learning (ML) for survival analysis to a retrospective study of NSCLC patients who received definitive surgical resection and immune pathology following surgery. ML methods are compared for their effectiveness in identifying prognostic subtypes. Six survival models, including Cox regression and five survival machine learning methods, were calibrated and applied to predict survival for NSCLC patients based on PD-L1 expression, CD3 expression, and ten baseline patient characteristics. Prognostic subregions of the biomarker space are delineated for each method using synthetic patient data augmentation and compared between models for overall survival concordance. A total of 423 NSCLC patients (46% female; median age [inter quantile range]: 67 [60–73]) treated with definite surgical resection were included in the study. And 219 (52%) patients experienced events during the observation period consisting of a maximum follow-up of 10 years and median follow up 78 months. The random survival forest (RSF) achieved the highest predictive accuracy, with a C-index of 0.84. The resultant biomarker subtypes demonstrate that patients with high PD-L1 expression combined with low CD3 counts experience higher risk of death within five-years of surgical resection.

Abstract Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions. We demonstrate that baseline methods achieve comparable or superior performance compared to more complex models on survival predictions tasks. DL representation methods, however, are the most efficient to predict the gene essentiality of cell lines. We show that auto-encoders (AE) are consistently improved by techniques such as masking and multi-head training. Our results suggest that the impact of DL representations and of pretraining are highly task- and architecture-dependent, highlighting the need for adopting rigorous evaluation guidelines. These guidelines for robust evaluation are implemented in a pipeline made available to the research community.

ABSTRACT Background The incidence of small cell lung cancer (SCLC) among Asian patients is on the rise. Nevertheless, there remains a deficiency in precise prognostic models tailored to the specific needs of this patient population. It is imperative to develop a novel nomogram aimed at forecasting the prognosis of Asian SCLC patients. Methods The SEER database supplied data on 661 Asian SCLC patients, who were then divided into training and internal validation sets through a random selection process. In addition, we identified 212 patients from a Chinese medical institution for the purpose of creating an external validation cohort. To forecast survival, we employed both univariate and multivariate analyses. The performance of our nomogram was assessed through calibration plots, the concordance index (C‐index), and decision curve analysis (DCA). Results Five independent prognostic factors were determined and integrated into the nomogram. C‐index values for the training and internal validation cohorts were 0.774 (95% confidence interval [CI] = 0.751–0.797) and 0.731 (95%CI = 0.690–0.772), respectively. In the external validation cohort, the C‐index is 0.712 (95% CI = 0.655–0.7692). Calibration curves demonstrated highly accurate predictions. When compared to the AJCC staging system, our model exhibited improved net benefits in DCA. Furthermore, the risk stratification system effectively differentiated patients with varying survival risks. Conclusion We have created a novel nomogram for predicting the survival of Asian patients with SCLC. This nomogram has been subjected to external validation and has shown its superiority over the conventional TNM staging system. It offers a more precise and reliable means of forecasting the prognosis of Asian SCLC patients.

ObjectiveNasopharyngeal carcinoma (NPC) patients frequently present with distant metastasis (DM), which is typically associated with poor prognosis. This study aims to develop and apply machine learning models to predict DM, overall survival (OS), and cancer-specific survival (CSS) in NPC patients to provide optimal tools for improved predictive accuracy and performance.MethodsWe retrieved over 8,000 NPC patient samples with associated clinical information from the Surveillance, Epidemiology, and End Results (SEER) database. Utilizing two methods for handling missing values—imputation or deletion—we created various cohorts: DM-all, DM-slim, OS-all, OS-slim, CSS-all, and CSS-slim. Five machine learning models were deployed for the binary classification task of DM, and their performance was evaluated using the area under the curve (AUC). For the survival prediction tasks of OS and CSS, we constructed 45 combinations using nine survival machine learning algorithms. The Concordance Index (C-index), 5-year AUC, and Brier score assessed model accuracy. Patients were stratified into two risk groups for survival analysis, and the survival curves were presented.ResultsThis study examines the relationships between clinical factors and survival in NPC patients. The analysis, visualized through forest plots, indicates that demographic and clinical variables like gender, marital status, tumor grade, and stage significantly affect metastatic risks and survival. Specifically, factors such as advanced stages increase metastasis and survival risks, while enhanced treatments improve survival rates. In the cohort for DM prediction, results revealed that the random forest model was the most effective, with an AUC of 0.687. In contrast, when predicting overall survival (OS), the random survival forest (RSF) model consistently showed superior performance with the highest mean C-index of 0.802, a 5-year AUC of 0.857, and a Brier score of 0.167. Similarly, for cancer-specific survival (CSS) prediction, the RSF model demonstrated a mean C-index of 0.822, a 5-year AUC of 0.884, and a Brier score of 0.165. An online Shiny server was developed to allow the models to be used freely and efficiently via http://npcml.shinyapps.io/NPCpre.ConclusionThis study successfully established an online tool by machine learning models for NPC metastasis and survival prediction, providing valuable references for clinicians.

Abstract Osteosarcoma is a primary malignant tumor that commonly affects children and adolescents, with a poor prognosis. The existence of tumor heterogeneity leads to different molecular subtypes and survival outcomes. Recently, lipid metabolism has been identified as a critical characteristic of cancer. Therefore, our study aims to identify osteosarcoma's lipid metabolism molecular subtype and develop a signature for survival outcome prediction. Four multicenter cohorts—TARGET-OS, GSE21257, GSE39058, and GSE16091—were amalgamated into a unified Meta-Cohort. Through consensus clustering, novel molecular subtypes within Meta-Cohort patients were delineated. Subsequent feature selection processes, encompassing analyses of differentially expressed genes between subtypes, univariate Cox analysis, and StepAIC, were employed to pinpoint biomarkers related to lipid metabolism in TARGET-OS. We selected the most effective algorithm for constructing a Lipid Metabolism-Related Signature (LMRS) by utilizing four machine-learning algorithms reconfigured into ten unique combinations. This selection was based on achieving the highest concordance index (C-index) in the test cohort of GSE21257, GSE39058, and GSE16091. We identified two distinct lipid metabolism molecular subtypes in osteosarcoma patients, C1 and C2, with significantly different survival rates. C1 is characterized by increased cholesterol, fatty acid synthesis, and ketone metabolism. In contrast, C2 focuses on steroid hormone biosynthesis, arachidonic acid, and glycerolipid and linoleic acid metabolism. Feature selection in the TARGET-OS identified 12 lipid metabolism genes, leading to a model predicting osteosarcoma patient survival. The LMRS, based on the 12 identified genes, consistently accurately predicted prognosis across TARGET-OS, testing cohorts, and Meta-Cohort. Incorporating 12 published signatures, LMRS showed robust and significantly superior predictive capability. Our results offer a promising tool to enhance the clinical management of osteosarcoma, potentially leading to improved clinical outcomes.

Abstract Medulloblastoma is a malignant neuroepithelial tumor of the central nervous system. Accurate prediction of prognosis is essential for therapeutic decisions in medulloblastoma patients. We analyzed data from 2,322 medulloblastoma patients using the SEER database and randomly divided the dataset into training and testing datasets in a 7:3 ratio. We chose three models to build, one based on neural networks (DeepSurv), one based on ensemble learning that Random Survival Forest (RSF), and a typical Cox Proportional-hazards (CoxPH) model. The DeepSurv model outperformed the RSF and classic CoxPH models with C-indexes of 0.751 and 0.763 for the training and test datasets. Additionally, the DeepSurv model showed better accuracy in predicting 1-, 3-, and 5-year survival rates (AUC: 0.767–0.793). Therefore, our prediction model based on deep learning algorithms can more accurately predict the survival rate and survival period of medulloblastoma compared to other models.

Abstract The present study explored the risk factors associated with radiotherapy in seniors diagnosed with limited-stage small cell lung cancer (LS-SCLC) to construct and validate a prognostic nomogram. The study retrospectively included 137 elderly patients with LS-SCLC who previously received radiotherapy. Univariate and multivariate COX analyses were conducted to identify independent risk factors and determine optimal cut-off values. Kaplan–Meier survival curves and nomograms were constructed to predict survival. Calibration and receiver operating characteristic (ROC) curves were used to evaluate the accuracy and consistency of the nomogram. Illness rating scale-geriatric (CIRS-G) score, treatment strategy, lymphocyte-to-monocyte ratio (LMR), white blood cell-to-monocyte ratio (WMR), and prognostic nutritional index (PNI) were discovered to be independent prognostic factors. Based on the findings of our multivariate analysis, a risk nomogram was developed to assess patient prognosis. Internal bootstrap resampling was utilized to validate the model, and while the accuracy of the AUC curve at 1 year was modest at 0.657 (95% CI 0.458–0.856), good results were achieved in predicting 3- and 5 year survival with AUCs of 0.757 (95% CI 0.670–0.843) and 0.768 (95% CI 0.643–0.893), respectively. Calibration curves for 1-, 3-, and 5 year overall survival probabilities demonstrated good cocsistency between expected and actual outcomes. Patients with concurrent chemoradiotherapy, CIRS-G score > 5 points and low PNI, WMR and LMR correlated with poor prognosis. The nomogram model developed based on these factors demonstrated good predictive performance and provides a simple, accessible, and practical tool for clinicians to guide clinical decision-making and study design.

Abstract Background Acute Type A aortic dissection (ATAAD) is a life-threatening cardiovascular disease associated with high mortality rates, where surgical intervention remains the primary life-saving treatment. However, the mortality rate for ATAAD operations continues to be alarmingly high. To address this critical issue, our study aimed to assess the correlation between preoperative laboratory examination, clinical imaging data, and postoperative mortality in ATAAD patients. Additionally, we sought to establish a reliable prediction model for evaluating the risk of postoperative death. Methods In this study, a total of 384 patients with acute type A aortic dissection (ATAAD) who were admitted to the emergency department for surgical treatment were included. Based on preoperative laboratory examination and clinical imaging data of ATAAD patients, logistic analysis was used to obtain independent risk factors for postoperative in-hospital death. The survival prediction model was based on cox regression analysis and displayed as a nomogram. Results Logistic analysis identified several independent risk factors for postoperative in-hospital death, including Marfan syndrome, previous cardiac surgery history, previous renal dialysis history, direct bilirubin, serum phosphorus, D-dimer, white blood cell, multiple aortic ruptures and age. A survival prediction model based on cox regression analysis was established and presented as a nomogram. The model exhibited good discrimination and significantly improved the prediction of death risk in ATAAD patients. Conclusions In this study, we developed a novel survival prediction model for acute type A aortic dissection based on preoperative clinical features. The model demonstrated good discriminatory power and improved accuracy in predicting the risk of death in ATAAD patients undergoing open surgery.

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.

Background: The advent of Deep Learning initiated a new era in which neural networks relying solely on Whole-Slide Images can estimate the survival time of cancer patients. Remarkably, despite deep learning’s potential in this domain, no prior research has been conducted on image-based survival analysis specifically for peritoneal mesothelioma. Prior studies performed statistical analysis to identify disease factors impacting patients’ survival time. Methods: Therefore, we introduce MPeMSupervisedSurv, a Convolutional Neural Network designed to predict the survival time of patients diagnosed with this disease. We subsequently perform patient stratification based on factors such as their Peritoneal Cancer Index and on whether patients received chemotherapy treatment. Results: MPeMSupervisedSurv demonstrates improvements over comparable methods. Using our proposed model, we performed patient stratification to assess the impact of clinical variables on survival time. Notably, the inclusion of information regarding adjuvant chemotherapy significantly enhances the model’s predictive prowess. Conversely, repeating the process for other factors did not yield significant performance improvements. Conclusions: Overall, MPeMSupervisedSurv is an effective neural network which can predict the survival time of peritoneal mesothelioma patients. Our findings also indicate that treatment by adjuvant chemotherapy could be a factor affecting survival time.

Abstract Cancer is one of the leading causes of deaths worldwide. Survival analysis and prediction of cancer patients is of great significance for their precision medicine. The robustness and interpretability of the survival prediction models are important, where robustness tells whether a model has learned the knowledge, and interpretability means if a model can show human what it has learned. In this paper, we propose a robust and interpretable model SurvConvMixer, which uses pathways customized gene expression images and ConvMixer for cancer short-term, mid-term and long-term overall survival prediction. With ConvMixer, the representation of each pathway can be learned respectively. We show the robustness of our model by testing the trained model on absolutely untrained external datasets. The interpretability of SurvConvMixer depends on gradient-weighted class activation mapping (Grad-Cam), by which we can obtain the pathway-level activation heat map. Then wilcoxon rank-sum tests are conducted to obtain the statistically significant pathways, thereby revealing which pathways the model focuses on more. SurvConvMixer achieves remarkable performance on the short-term, mid-term and long-term overall survival of lung adenocarcinoma, lung squamous cell carcinoma and skin cutaneous melanoma, and the external validation tests show that SurvConvMixer can generalize to external datasets so that it is robust. Finally, we investigate the activation maps generated by Grad-Cam, after wilcoxon rank-sum test and Kaplan–Meier estimation, we find that some survival-related pathways play important role in SurvConvMixer.

Abstract Purpose Heart failure (HF) is a widespread ailment and is a primary contributor to hospital admissions. The focus of this study was to identify factors affecting the extended-term survival of patients with HF, anticipate patient outcomes through cause-of-death analysis, and identify risk elements for preventive measures. Methods A total of 435 HF patients were enrolled from the medical records of the Rajaie Cardiovascular Medical and Research Center, covering data collected between March and August 2018. After a five-year follow-up (July 2023), patient outcomes were assessed based on the cause of death. The survival analysis was performed with the AFT method with the Bayesian approach in the presence of competing risks. Results Based on the results of the best model for HF-related mortality, age [time ratio = 0.98, confidence interval 95%: 0.96–0.99] and ADHF [TR = 0.11, 95% (CI): 0.01–0.44] were associated with a lower survival time. Chest pain in HF-related mortality [TR = 0.41, 95% (CI): 0.10–0.96] and in non-HF-related mortality [TR = 0.38, 95% (CI): 0.12–0.86] was associated with a lower survival time. The next significant variable in HF-related mortality was hyperlipidemia (yes): [TR = 0.34, 95% (CI): 0.13–0.64], and in non-HF-related mortality hyperlipidemia (yes): [TR = 0.60, 95% (CI): 0.37–0.90]. CAD [TR = 0.65, 95% (CI): 0.38–0.98], CKD [TR = 0.52, 95% (CI): 0.28–0.87], and AF [TR = 0.53, 95% (CI): 0.32–0.81] were other variables that were directly related to the reduction in survival time of patients with non-HF-related mortality. Conclusion The study identified distinct predictive factors for overall survival among patients with HF-related mortality or non-HF-related mortality. This differentiated approach based on the cause of death contributes to the estimation of patient survival time and provides valuable insights for clinical decision-making.

Non-small cell Lung Cancer (NSCLC) is one of the most common types of lung cancer, accounting for approximately 80% to 85% of lung cancer cases, and survival prediction in this cancer is an essential medical task. Traditional survival prediction methods, which only rely on demographic and clinical variables, fail to fully characterize patients’ pathological characteristics and clinical factors, thus limiting the prediction effect. With the development of medical imaging technology and genomic methods, survival prediction studies have ushered in new analytical perspectives in recent years. However, most of the existing advanced techniques only rely on one class and few classes of medical data, which do not comprehensively characterize patients’ pathological features and clinical conditions, and similarly limit the predictive effect. To this end, in this paper a new method is proposed to solve this problem, that is, using flexible interpretable graph structure to fuse and model the multimodal data (including clinical data and CT images, etc.) of patients, so as to solve the problem of fragmentation and one-sidedness among multi-class data of survival prediction. A new multi-modal fusion graph convolutional network (FGCN) is proposed according to the characteristics of multi-modal graph data. The main body of the network structure is composed of a SAGE graph convolution layer with the self-attention mechanism, which accelerates the convergence of the model compared to the traditional one and ensures that the risk predicted by the model is as close to the actual situation as possible. More importantly, this study is the first to introduce the TopKPooling strategy in this model to address the problems of feature redundancy and excessive noise features arising from multimodal data fusion and to reduce the model complexity. A large number of ablation and comparison experiments and analyses on public non-small cell lung cancer datasets show that the method proposed in this paper achieves better prediction results, with a C-index value of 0.76, which exceeds the currently known advanced techniques, and fully proves the effectiveness and superiority of the method in this paper.

Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.

Predicting survival outcomes in critical accidents has been a focal point in machine learning research. This study addresses several limitations of existing methods, including insufficient management of data imbalance, lack of emphasis on hyperparameter tuning, and proneness to overfitting. Many existing models struggle to generalize effectively on imbalanced datasets or depend on default hyperparameter settings, resulting in biased predictions. By integrating Principal Component Analysis (PCA), hyperparameter optimization, and resampling methods, as well as combining Edited Nearest Neighbors (ENN) with the Synthetic Minority Oversampling Technique (SMOTE), the model significantly improves predictive accuracy and model generalization. An ensemble model combining seven machine learning algorithms—Logistic Regression, Support Vector Machine, KNN, Random Forest, XGBoost, LightGBM, and CatBoost—was applied to predict survival outcomes. Stochastic Weighted Averaging (SWA) was applied to mitigate overfitting and enhance generalization. The accuracy increased from 91.97% to 94.89% after SWA was applied in this specific scenario. The combination of PCA-based dimensionality reduction, hyperparameter tuning, and resampling techniques (ENN + SMOTE) ensured the model handled data imbalance and optimized predictive accuracy. The final model demonstrated excellent performance, with Area Under the Curve (AUC) and Average Precision (AP) values both reaching 0.98, indicating high accuracy and precision. These improvements were validated using the Titanic dataset in a binary classification problem of predicting passenger survival. The results emphasize that ensemble learning, enhanced by SWA, offers a powerful framework for handling imbalanced and complex datasets, providing significant advancements in predictive modeling accuracy. This study provides insights into how machine learning techniques can be effectively combined to solve classification challenges in real-world scenarios.

Abstract Background For the purpose to examine lower limb melanoma (LLM) and its long-term survival rate, we used data from the Surveillance, Epidemiology and End Results (SEER) database. To estimate the prognosis of LLM patients and assess its efficacy, we used a powerful deep learning and neural network approach called DeepSurv. Methods We gathered data on those who had an LLM diagnosis between 2000 and 2019 from the SEER database. We divided the people into training and testing cohorts at a 7:3 ratio using a random selection technique. To assess the likelihood that LLM patients would survive, we compared the results of the DeepSurv model with those of the Cox proportional-hazards (CoxPH) model. Calibration curves, the time-dependent area under the receiver operating characteristic curve (AUC), and the concordance index (C-index) were all used to assess how accurate the predictions were. Results In this study, a total of 26,243 LLM patients were enrolled, with 7873 serving as the testing cohort and 18,370 as the training cohort. Significant correlations with age, gender, AJCC stage, chemotherapy status, surgery status, regional lymph node removal and the survival outcomes of LLM patients were found by the CoxPH model. The CoxPH model’s C-index was 0.766, which signifies a good degree of predicted accuracy. Additionally, we created the DeepSurv model using the training cohort data, which had a higher C-index of 0.852. In addition to calculating the 3-, 5-, and 8-year AUC values, the predictive performance of both models was evaluated. The equivalent AUC values for the CoxPH model were 0.795, 0.767, and 0.847, respectively. The DeepSurv model, in comparison, had better AUC values of 0.872, 0.858, and 0.847. In comparison to the CoxPH model, the DeepSurv model demonstrated greater prediction performance for LLM patients, as shown by the AUC values and the calibration curve. Conclusion We created the DeepSurv model using LLM patient data from the SEER database, which performed better than the CoxPH model in predicting the survival time of LLM patients.

BackgroundLiver transplantation (LT) is one of the main curative treatments for hepatocellular carcinoma (HCC). Milan criteria has long been applied to candidate LT patients with HCC. However, the application of Milan criteria failed to precisely predict patients at risk of recurrence. As a result, we aimed to establish and validate a deep learning model comparing with Milan criteria and better guide post-LT treatment.MethodsA total of 356 HCC patients who received LT with complete follow-up data were evaluated. The entire cohort was randomly divided into training set (n = 286) and validation set (n = 70). Multi-layer-perceptron model provided by pycox library was first used to construct the recurrence prediction model. Then tabular neural network (TabNet) that combines elements of deep learning and tabular data processing techniques was utilized to compare with Milan criteria and verify the performance of the model we proposed.ResultsPatients with larger tumor size over 7 cm, poorer differentiation of tumor grade and multiple tumor numbers were first classified as high risk of recurrence. We trained a classification model with TabNet and our proposed model performed better than the Milan criteria in terms of accuracy (0.95 vs. 0.86, p < 0.05). In addition, our model showed better performance results with improved AUC, NRI and hazard ratio, proving the robustness of the model.ConclusionA prognostic model had been proposed based on the use of TabNet on various parameters from HCC patients. The model performed well in post-LT recurrence prediction and the identification of high-risk subgroups.

In oncology drug development, tumor dynamics modeling is widely applied to predict patients' overall survival (OS) via parametric models. However, the current modeling paradigm, which assumes a disease-specific link between tumor dynamics and survival, has its limitations. This is particularly evident in drug development scenarios where the clinical trial under consideration contains patients with tumor types for which there is little to no prior institutional data. In this work, we propose the use of a pan-indication solid tumor machine learning (ML) approach whereby all three tumor metrics (tumor shrinkage rate, tumor regrowth rate and time to tumor growth) are simultaneously used to predict patients' OS in a tumor type independent manner. We demonstrate the utility of this approach in a clinical trial of cancer patients treated with the tyrosine kinase inhibitor, pralsetinib. We compared the parametric and ML models and the results showed that the proposed ML approach is able to adequately predict patient OS across RET-altered solid tumors, including non-small cell lung cancer, medullary thyroid cancer as well as other solid tumors. While the findings of this study are promising, further research is needed for evaluating the generalizability of the ML model to other solid tumor types.

Background: Survival prediction is one of the crucial goals in precision medicine, as accurate survival assessment can aid physicians in selecting appropriate treatment for individual patients. To achieve this aim, extensive data must be utilized to train the prediction model and prevent overfitting. However, the collection of patient data for disease prediction is challenging due to potential variations in data sources across institutions and concerns regarding privacy and ownership issues in data sharing. To facilitate the integration of cancer data from different institutions without violating privacy laws, we developed a federated learning-based data integration framework called AdFed, which can be used to evaluate patients’ survival while considering the privacy protection problem by utilizing the decentralized federated learning technology and regularization method. Results: AdFed was tested on different cancer datasets that contain the patients’ information from different institutions. The experimental results show that AdFed using distributed data can achieve better performance in cancer survival prediction (AUC = 0.605) than the compared federated-learning-based methods (average AUC = 0.554). Additionally, to assess the biological interpretability of our method, in the case study we list 10 identified genes related to liver cancer selected by AdFed, among which 5 genes have been proved by literature review. Conclusions: The results indicate that AdFed outperforms better than other federated-learning-based methods, and the interpretable algorithm can select biologically significant genes and pathways while ensuring the confidentiality and integrity of data.

Background: Lesion network mapping (LNM) is a popular framework to assess clinical syndromes following brain injury. The classical approach involves embedding lesions from patients into a normative functional connectome and using the corresponding functional maps as proxies for disconnections. However, previous studies indicated limited predictive power of this approach in behavioral deficits. We hypothesized similarly low predictiveness for overall survival (OS) in glioblastoma (GBM). Methods: A retrospective dataset of patients with GBM was included (n = 99). Lesion masks were registered in the normative space to compute disconnectivity maps. The brain functional normative connectome consisted in data from 173 healthy subjects obtained from the Human Connectome Project. A modified version of the LNM was then applied to core regions of GBM masks. Linear regression, classification, and principal component (PCA) analyses were conducted to explore the relationship between disconnectivity and OS. OS was considered both as continuous and categorical (low, intermediate, and high survival) variable. Results: The results revealed no significant associations between OS and network disconnection strength when analyzed at both voxel-wise and classification levels. Moreover, patients stratified into different OS groups did not exhibit significant differences in network connectivity patterns. The spatial similarity among the first PCA of network maps for each OS group suggested a lack of distinctive network patterns associated with survival duration. Conclusions: Compared with indirect structural measures, functional indirect mapping does not provide significant predictive power for OS in patients with GBM. These findings are consistent with previous research that demonstrated the limitations of indirect functional measures in predicting clinical outcomes, underscoring the need for more comprehensive methodologies and a deeper understanding of the factors influencing clinical outcomes in this challenging disease.

ObjectiveThe objective of this study was to provide a multi-modal deep learning framework for forecasting the survival of rectal cancer patients by utilizing both digital pathological images data and non-imaging clinical data.Materials and methodsThe research included patients diagnosed with rectal cancer by pathological confirmation from January 2015 to December 2016. Patients were allocated to training and testing sets in a randomized manner, with a ratio of 4:1. The tissue microarrays (TMAs) and clinical indicators were obtained. Subsequently, we selected distinct deep learning models to individually forecast patient survival. We conducted a scanning procedure on the TMAs in order to transform them into digital pathology pictures. Additionally, we performed pre-processing on the clinical data of the patients. Subsequently, we selected distinct deep learning algorithms to conduct survival prediction analysis using patients’ pathological images and clinical data, respectively.ResultsA total of 292 patients with rectal cancer were randomly allocated into two groups: a training set consisting of 234 cases, and a testing set consisting of 58 instances. Initially, we make direct predictions about the survival status by using pre-processed Hematoxylin and Eosin (H&E) pathological images of rectal cancer. We utilized the ResNest model to extract data from histopathological images of patients, resulting in a survival status prediction with an AUC (Area Under the Curve) of 0.797. Furthermore, we employ a multi-head attention fusion (MHAF) model to combine image features and clinical features in order to accurately forecast the survival rate of rectal cancer patients. The findings of our experiment show that the multi-modal structure works better than directly predicting from histopathological images. It achieves an AUC of 0.837 in predicting overall survival (OS).ConclusionsOur study highlights the potential of multi-modal deep learning models in predicting survival status from histopathological images and clinical information, thus offering valuable insights for clinical applications.

Background: In Japan, the number of patients with aggressive hematological malignancies (PHMs) admitted at the palliative care unit (PCU) in their end-of-life (EOL) stage was fewer than that of patients with solid tumors due to several reasons. The assessment of patient characteristics and the methods of survival prediction among PHMs in the EOL stage are warranted. Objectives: This study aimed to identify the current medical status and the method of survival prediction among PHMs treated at the PCU. Setting/Subjects/Measurements: We retrospectively analyzed the clinical data of 25 PHMs treated at our PCU between January 2017 and December 2020. The association between survival time and the palliative prognostic score (PAP) and palliative prognostic index (PPI) was analyzed. Results: The average age of the PHMs was higher than that of patients with lung cancer as a control. The median survival time of the PHMs was shorter than the control group. Most PHMs could not receive standard chemotherapy, and the most common cause of death was disease-related organ failure. Significant associations were observed between the survival time and each PAP/PPI value in patients with malignant lymphoma, but not in those with leukemia. Conclusion: The PHMs in the PCU had a lower median survival time than the control group. These results were induced by the result of patient selection to avoid treatment-related severe toxicity. The survival prediction using the PAP and PPI was less accurate in patients with leukemia.

Abstract Radiomics is widely used in adult tumors but has been rarely applied to the field of pediatrics. Promoting the application of radiomics in pediatric diseases, especially in the early diagnosis and stratified treatment of tumors, is of great value to the realization of the WHO 2030 “Global Initiative for Childhood Cancer.” This paper discusses the general characteristics of radiomics, the particularity of its application to pediatric diseases, and the current status and prospects of pediatric radiomics. Radiomics is a data‐driven science, and the combination of medicine and engineering plays a decisive role in improving data quality, data diversity, and sample size. Compared with adult radiomics, pediatric radiomics is significantly different in data type, disease spectrum, disease staging, and progression. Some progress has been made in the identification, classification, stratification, survival prediction, and prognosis of tumor diseases. In the future, big data applications from multiple centers and cross‐talent training should be strengthened to improve the benefits for clinical workers and children.

Background: Prognostics for patients with cancer is especially important for the supportive care of those who are terminally ill. We previously found that symptom scores as patient-reported outcomes (PROs)?such as dyspnea and fatigue scores?some biochemical parameters, the palliative performance scale (PPS) scores, and symptom clusters were useful prognostic factors; however, the predictability of a prognosis based on these factors remains unclear. Objective: To identify appropriate three-week survival predictive factor(s), in terms of performance, in patients who were terminally ill. Design: We collected symptom scores as PROs using the Japanese version of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 15 Palliative Care (EORTC QLQ-C15-PAL). Setting/Subjects: We used data from terminally ill patients with cancer who were hospitalized at the palliative care unit of the Higashisumiyoshi-Morimoto Hospital (Osaka, Japan) from June 2018 to December 2019 (n?=?130), as well as additional data obtained from the same clinical study from January to March 2020 (n?=?31). Measurements: To evaluate predictive performance, indices such as sensitivity, specificity, positive predictive value, negative predictive value, and overall accuracy were calculated. Results: We found that the presence of a symptom cluster showed high sensitivity but low specificity and that a higher PPS value (>30) showed high specificity but low sensitivity, suggesting that these factors could provide relevant information for survival prognosis (less than or equal to three weeks). Conclusion: Symptom clusters obtained from patients is important for effective supportive care of those who are terminally ill.

Abstract Recently, lung cancer prediction based on imaging genomics has attracted great attention. However, such studies often have many challenges, such as small sample size, high-dimensional information redundancy, and the inefficiency of multimodal fusion. Therefore, in this paper, a deep convolution cascade attention fusion network (DCCAFN) based on imaging genomics is proposed for the prediction of lung cancer patients’ survival. The network consists of three modules: an image feature extraction module (IFEM), a gene feature extraction module (GFEM), and an attention fusion network (AFN). In the IFEM, a pretrained residual network based on transfer learning is used to extract deep image features to fully capture the computed tomography (CT) image information conducive to prognosis prediction. In the GFEM, the F-test is first used for gene screening to eliminate redundant information, and then, a cascade network with the convolution cascade module (CCM) that contains a convolution operation, a pooling operation, and an ensemble forest classifier is designed to better extract the gene features. In the AFN, a bimodal attention fusion mechanism is proposed to fuse deep image features and gene features to improve the performance of predicting lung cancer survival. The experimental results show that the DCCAFN model achieves good performance, and its accuracy and AUC are 0.831 and 0.816, respectively. It indicates that the model is an effective multimodal data fusion method for predicting the survival prognosis of lung cancer, which can greatly help physicians stratify patients' risks, and achieve personalized treatment for improving the quality of patients' lives.

Background Glioma is a primary, malignant, highly aggressive brain tumor, with patients having an average life expectancy of 14 to 16 months after diagnosis. Magnetic resonance imaging (MRI) scans of these patients can be used to extract and analyze quantifiable features with potential clinical significance. We hypothesize that there is a correlation between radiomic features extracted from MRI scans and survival. Along with clinical data, the radiomic features could be used in survival prediction of patients, providing beneficial information for clinicians to design personalized treatment plans. Methods In our study, we have utilized 3D Slicer for tumor segmentation and feature extraction and performed survival prediction of patients with glioma using four different machine learning models. Results and Conclusion Among the models compared, we have achieved a maximum prediction accuracy of 64.4% using the k-nearest neighbors model, which was trained and tested on a combination of clinical data and radiomic features extracted from MRI images provided in the BraTS 2020 dataset.

Abstract Backgrounds The incidence of gastric cardiac cancer (GCC) has obviously increased recently with poor prognosis. It’s necessary to compare GCC prognosis with other gastric sites carcinoma and set up an effective prognostic model based on a neural network to predict the survival of GCC patients. Methods In the population-based cohort study, we first enrolled the clinical features from the Surveillance, Epidemiology and End Results (SEER) data (n = 31,397) as well as the public Chinese data from different hospitals (n = 1049). Then according to the diagnostic time, the SEER data were then divided into two cohorts, the train cohort (patients were diagnosed as GCC in 2010–2014, n = 4414) and the test cohort (diagnosed in 2015, n = 957). Age, sex, pathology, tumor, node, and metastasis (TNM) stage, tumor size, surgery or not, radiotherapy or not, chemotherapy or not and history of malignancy were chosen as the predictive clinical features. The train cohort was utilized to conduct the neural network-based prognostic predictive model which validated by itself and the test cohort. Area under the receiver operating characteristics curve (AUC) was used to evaluate model performance. Results The prognosis of GCC patients in SEER database was worse than that of non GCC (NGCC) patients, while it was not worse in the Chinese data. The total of 5371 patients were used to conduct the model, following inclusion and exclusion criteria. Neural network-based prognostic predictive model had a satisfactory performance for GCC overall survival (OS) prediction, which owned 0.7431 AUC in the train cohort (95% confidence intervals, CI, 0.7423–0.7439) and 0.7419 in the test cohort (95% CI, 0.7411–0.7428). Conclusions GCC patients indeed have different survival time compared with non GCC patients. And the neural network-based prognostic predictive tool developed in this study is a novel and promising software for the clinical outcome analysis of GCC patients.

Abstract Background Predictive analytics is gaining popularity as an aid to treatment planning for patients with bone metastases, whose expected survival should be considered. Decreased psoas muscle area (PMA), a morphometric indicator of suboptimal nutritional status, has been associated with mortality in various cancers, but never been integrated into current survival prediction algorithms (SPA) for patients with skeletal metastases. This study investigates whether decreased PMA predicts worse survival in patients with extremity metastases and whether incorporating PMA into three modern SPAs (PATHFx, SORG‐NG, and SORG‐MLA) improves their performance. Methods One hundred eighty‐five patients surgically treated for long‐bone metastases between 2014 and 2019 were divided into three PMA tertiles (small, medium, and large) based on their psoas size on CT. Kaplan–Meier, multivariable regression, and Cox proportional hazards analyses were employed to compare survival between tertiles and examine factors associated with mortality. Logistic regression analysis was used to assess whether incorporating adjusted PMA values enhanced the three SPAs' discriminatory abilities. The clinical utility of incorporating PMA into these SPAs was evaluated by decision curve analysis (DCA). Results Patients with small PMA had worse 90‐day and 1‐year survival after surgery (log‐rank test p 0.5 after the addition of adjusted PMA to these SPAs. Conclusions Decreased PMA on CT is associated with worse survival in surgically treated patients with extremity metastases, even after controlling for three contemporary SPAs. Physicians should consider the additional prognostic value of PMA on survival in patients undergoing consideration for operative management due to extremity metastases.

In medicine, an important objective is predicting patients’ survival based on their molecular and clinical characteristics. In this context, neural networks have recently been used for their ability to capture complex interactions in the data. Measuring the uncertainty associated with survival estimates obtained by neural networks is essential to enhance predictions’ reliability. We compared four methods adapted to multilayer perceptrons (MLPs) for building confidence intervals at the patient level. The methods were based either on bootstrap with Boot (Efron, 1979), ensembling with DeepEns (Lakshminarayanan et al., 2016), or Monte-Carlo Dropout with MCDrop and BMask (Gal and Ghahramani, 2016; Mancini et al., 2020). A comparison was made through MLP-based survival models: CoxCC and CoxTime (Kvamme et al., 2019) in a continuous time framework, DeepHit (Lee et al., 2018) and PLANN (Biganzoli et al., 1998) in a discrete time framework. We applied the methods to a simulation study, enabling us to estimate a coverage rate of the estimated confidence intervals. We also applied them to real-world datasets, and predicted the survival probability for patients with breast cancer and patients with lung cancer.In the simulation study, CoxCC and CoxTime obtained the mean C-indices numerically closest to those from the Oracle model (mean C-index of 0.723 for CoxCC, 0.726 for CoxTime, versus 0.743 for the Oracle model). Regarding the confidence intervals of survival probabilities, Boot with CoxCC obtained a coverage rate of 96.5%, the closest to the nominal value of 95%. MCDrop was slightly anticonservative and obtained a coverage rate of 89.8% with CoxTime. This method may represent a reasonable compromise in terms of coverage with regards of computational time. In the breast cancer cohort, MLPs had difficulty capturing additional prognostic information from the molecular data. In contrast, in the lung cancer cohort, the models led to substantially stronger discrimination values when adding molecular data to the clinical variables. In conclusion, we were able to represent uncertainty in the survival estimates at particular time points at the patient level using MLPs in the form of 95% confidence intervals. We recommend using CoxTime with either Boot or, for a less intensive computation time, MCDrop.

Abstract Background Treatment plans for squamous cell carcinoma of the head and neck (SCCHN) are individually decided in tumor board meetings but some treatment decision-steps lack objective prognostic estimates. Our purpose was to explore the potential of radiomics for SCCHN therapy-specific survival prognostication and to increase the models’ interpretability by ranking the features based on their predictive importance. Methods We included 157 SCCHN patients (male, 119; female, 38; mean age, 64.39 ± 10.71 years) with baseline head and neck CT between 09/2014 and 08/2020 in this retrospective study. Patients were stratified according to their treatment. Using independent training and test datasets with cross-validation and 100 iterations, we identified, ranked and inter-correlated prognostic signatures using elastic net (EN) and random survival forest (RSF). We benchmarked the models against clinical parameters. Inter-reader variation was analyzed using intraclass-correlation coefficients (ICC). Results EN and RSF achieved top prognostication performances of AUC = 0.795 (95% CI 0.767–0.822) and AUC = 0.811 (95% CI 0.782–0.839). RSF prognostication slightly outperformed the EN for the complete (ΔAUC 0.035, p = 0.002) and radiochemotherapy (ΔAUC 0.092, p

In a pressing global health concern with substantial morbidity and mortality rates, accurate survival prediction is paramount for informed decision-making and enhanced patient well-being. This study presented a comparative investigation aimed at predicting the survival events of heart failure (HF) patients through the utilization of both machine learning and statistical algorithms. A comprehensive dataset drawn from Allied Hospital and the Faisalabad Institute of Cardiology, Faisalabad, Pakistan, was used. The Synthetic Minority Over-Sampling Technique (SMOTE) was employed on the data to rectify the imbalance, and a notable improvement was observed. To ascertain significant variables, statistical methods (Mann-Whitney and Chi-Square) were compared with machine learning-based feature selection to identify pivotal features for survival prediction, namely ejection fraction and serum creatinine. Remarkably, on final training with these features, the Random Forest Classifier emerges as the top-performing model, boasting an accuracy exceeding 90%. These findings hold the potential to substantially enhance patient prognosis, management, and outcomes, consequently alleviating the strain on healthcare systems. Doi: 10.28991/SciMedJ-2023-05-02-01 Full Text: PDF

Abstract Background In identifying prognostic markers in cancer, the roles of tumor‐adjacent normal tissues are often confined to drawing expression differences between tumor and normal tissues rather than being treated as the main targets of investigations. Thus, differential expression analysis between tumors and adjacent normal tissues is performed prior to prognostic analysis in previous studies. However, recent studies have suggested that the prognostic relevance of differentially expressed genes (DEGs) is insignificant for some cancers, contradicting conventional approaches Methods This study investigated the prognostic efficacy of transcriptomic data from tumors and adjacent normal tissues using The Cancer Genome Atlas dataset. Prognostic analysis using Cox regression models and survival prediction using machine‐learning models and feature selection methods were employed. Results The results revealed that for kidney, liver, and head and neck cancer, adjacent normal tissues harbored higher proportions of prognostic genes and exhibited better survival prediction performance than tumor tissues and DEGs in machine‐learning models. Furthermore, the application of a distance correlation‐based feature selection method to kidney and liver cancer using external datasets revealed that the selected genes for adjacent normal tissues exhibited higher prediction performance than those for tumor tissues. The study results suggest that the expression levels of genes in adjacent normal tissues are potential prognostic markers. The source code of this study is available at https://github.com/DMCB‐GIST/Survival_Normal.