Search

Lung cancer's radiomic phenotype may potentially inform clinical decision-making with respect to radical radiotherapy. At present there are no validated biomarkers available for the individualisation of radical radiotherapy in lung cancer and the mortality rate of this disease remains the highest of all other solid tumours. MEDLINE was searched using the terms 'radiomics' and 'lung cancer' according to the Preferred Reporting Items for Systematic Reviews and Met-Analyses (PRISMA) guidance. Radiomics studies were defined as those manuscripts describing the extraction and analysis of at least 10 quantifiable imaging features. Only those studies assessing disease control, survival or toxicity outcomes for patients with lung cancer following radical radiotherapy ± chemotherapy were included. Study titles and abstracts were reviewed by two independent reviewers. The Radiomics Quality Score was applied to the full text of included papers. Of 244 returned results, 44 studies met the eligibility criteria for inclusion. End points frequently reported were local (17%), regional (17%) and distant control (31%), overall survival (79%) and pulmonary toxicity (4%). Imaging features strongly associated with clinical outcomes include texture features belonging to the subclasses Gray level run length matrix, Gray level co-occurrence matrix and kurtosis. The median cohort size for model development was 100 (15-645); in the 11 studies with external validation in a separate independent population, the median cohort size was 84 (21-295). The median number of imaging features extracted was 184 (10-6538). The median Radiomics Quality Score was 11% (0-47). Patient-reported outcomes were not incorporated within any studies identified. No studies externally validated a radiomics signature in a registered prospective study. Imaging-derived indices attained through radiomic analyses could equip thoracic oncologists with biomarkers for treatment response, patterns of failure, normal tissue toxicity and survival in lung cancer. Based on routine scans, their non-invasive nature and cost-effectiveness are major advantages over conventional pathological assessment. Improved tools are required for the appraisal of radiomics studies, as significant barriers to clinical implementation remain, such as standardisation of input scan data, quality of reporting and external validation of signatures in randomised, interventional clinical trials.

Cardiovascular diseases are regarded as the most common reason for worldwide deaths. As per World Health Organization, nearly $ 17.9 $ million people die of heart-related diseases each year. The high shares of cardiovascular-related diseases in total worldwide deaths motivated researchers to focus on ways to reduce the numbers. In this regard, several works focused on the development of machine learning techniques/algorithms for early detection, diagnosis, and subsequent treatment of cardiovascular-related diseases. These works focused on a variety of issues such as finding important features to effectively predict the occurrence of heart-related diseases to calculate the survival probability. This research contributes to the body of literature by selecting a standard well defined, and well-curated dataset as well as a set of standard benchmark algorithms to independently verify their performance based on a set of different performance evaluation metrics. From our experimental evaluation, it was observed that decision tree is the best performing algorithm in comparison to logistic regression, support vector machines, and artificial neural networks. Decision trees achieved $ 14 $% better accuracy than the average performance of the remaining techniques. In contrast to other studies, this research observed that artificial neural networks are not as competitive as the decision tree or support vector machine.

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

Purpose The aims of the present study were to investigate the symptom clusters in terminally ill patients with cancer using the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 15 Palliative Care (EORTC QLQ-C15-PAL), and to examine whether these symptom clusters influenced prognosis. Methods We analyzed data from 130 cancer patients hospitalized in the palliative care unit from June 2018 to December 2019 in an observational study. Principal component analysis was used to detect symptom clusters using the scored date of 14 items in the QLQ-C15-PAL, except for overall QOL, at the time of hospitalization. The influence of the existence of these symptom clusters and Palliative Performance Scale (PPS) on survival was analyzed by Cox proportional hazards regression analysis, and survival curves were compared between the groups with or without existing corresponding symptom clusters using the log-rank test. Results The following symptom clusters were identified: cluster 1 (pain, insomnia, emotional functioning), cluster 2 (dyspnea, appetite loss, fatigue, and nausea), and cluster 3 (physical functioning). Cronbach’s alpha values for the symptom clusters ranged from 0.72 to 0.82. An increased risk of death was significantly associated with the existence of cluster 2 and poor PPS (log-rank test, p = 0.016 and p Conclusion In terminally ill patients with cancer, three symptom clusters were detected based on QLQ-C15-PAL scores. Poor PPS and the presence of symptom cluster that includes dyspnea, appetite loss, fatigue, and nausea indicated poor prognosis.

We describe a novel machine learning methodology which we call Coherent Voting Network (CVN) and we demonstrate its usefulness by building a 5-years prognostic predictor for post-surgery breast cancer patients based on CVNs. Coherent Voting Network (CVN) is a supervised learning paradigm designed explicitly to uncover non-linear, combinatorial patterns in complex data, within a statistical robust framework. Breast Cancer patients after surgery may receive several types of post-surgery adjuvant therapeutic regimen (endocrine, radio- or chemo-therapy, and combinations thereof) aiming at reducing relapse and the formation of metastases, and thus favouring log term survival. We wish to predict the outcome of adjuvant therapy using just small molecular fingerprints (mRNA) of the patient’s transcriptome. Our aim is to have simultaneously high scores for PPV (positive predictive value) and NPV (negative predictive value) as these are important indices for the final clinical applications of the predictor. A Training-validate-test protocol is applied onto CVN built on patient data from the Metabric Consortium (about 2000 patients). For the testing pool of 82 lymph node positive patients we obtain PPV 0.77 and NPV 0.78 (Odds Ratio 11.50); for the pool of 61 lymph node negative patients we obtain PPV 0.68 and NPV 0.88 (Odds Ratio 16.07). Improved results are obtained on some specific sub-types of BC. For the testing pool of 16 TNBC patients we obtain PPV 1.0 and NPV 0.83 (Odds Ratio 45.00). For the testing pool of 18 HER2+ patients we obtain PPV 0.91 and NPV 1.0 (Odds Ratio 40.00). For the testing pool of 41 Luminal B patients we obtain PPV 0.75 and NPV 0.95 (Odds Ratio 60.00). Effectiveness of the selected fingerprints is confirmed also on several independent data sets (for a total of 601 patients) from the NCBI Gene Expression Omnibus (GEO).

Backgroud: Accurately forecasting the prognosis could improve therapeutic management of cancer patients, however, the currently used clinical features are difficult to provide enought information. The purpose of this study is to develop a survival prediction model for cervical cancer patients with big data and machine learning algorithms. Results: The cancer genome atlas cervical cancer data, including the expression of 1046 microRNAs and the clinical information of 309 cervical and endocervical cancer and 3 control samples, were downloaded. Missing values and outliers imputation, samples normalization, log transformation and features scaling were performed for preprocessing and 3 control, 2 metastatic samples and 707 microRNAs with missing values ≥ 20% were excluded. By Cox Proportional-Hazards analysis, 55 prognosis-related microRNAs (20 positively and 35 negatively correlated with survival) were identified. K-means clustering analysis showed that the cervical cancer samples can be separated into two and three subgroups with top 20 identified survival-related microRNAs for best stratification. By Support Vector Machine algorithm, two prediction models were developed which can segment the patients into two and three groups with different survival rate, respectively. The models exhibite high performance : for two classes, Area under the curve = 0.976 (training set), 0.972 (test set), 0.974 (whole data set); for three classes, AUC = 0.983, 0.996 and 0.991 (group1, 2 and 3 in training set), 0.955, 0.989 and 0.991 (group 1, 2 and 3 in test set), 0.974, 0.993 and 0.991 (group 1, 2 and 3 in whole data set) .Conclusion: The survival prediction models for cervical cancer were developed. The patients with very low survival rate (≤ 40%) can be separated by the three classes prediction model first. The rest patients can be identified by the two classes prediction model as high survival rate (≈ 75%) and low survival rate (≈ 50%).

Treatment of hepatocellular carcinoma (HCC) depends on the stage of disease. In the Western Hemisphere, the Barcelona Clinic Liver Cancer classification (BCLC) is the preferred staging system. Approximately one-third of patients initially present with intermediate-stage disease. For these patients, transarterial chemoembolization (TACE) is the treatment of choice. However, the intermediate-stage comprises a heterogeneous subgroup of patients with considerable differences in tumor burden and liver function. In addition, differences in individual factors that are not captured by the BCLC framework, such as the tumor growth pattern, degree of hypervascularity, and vascular supply, complicate further evaluation of these patients. Due to these differences, not all patients benefit equally from TACE. Several tools and scoring systems have been devised to provide decision-making support. All of these have shown promising initial results but failed external evaluation and have not been translated to the clinic. Nevertheless, criteria for objectifying treatment decisions in daily clinical practice are needed in all stages of disease. Therefore, this review provides a concise practical step-by-step guide on current strategies for patient selection and decision-making, with a focus on TACE, to critically evaluate the existing decision-support tools and provide a summary of the latest updates in the field.

The scarcity of liver transplants necessitates prioritizing patients based on their health condition to minimize deaths on the waiting list. Recently, machine learning methods have gained popularity for automatizing liver transplant allocation systems, which enables prompt and suitable selection of recipients. Nevertheless, raw medical data often contain complexities such as missing values and class imbalance that reduce the reliability of the constructed model. This paper aims at eliminating the respective challenges to ensure the reliability of the decision-making process. To this aim, we first propose a novel deep learning method to simultaneously eliminate these challenges and predict the patients’ survival chance. Secondly, a hybrid framework is designed that contains three main modules for missing data imputation, class imbalance learning, and classification, each of which employing multiple advanced techniques for the given task. Furthermore, these two approaches are compared and evaluated using a real clinical case study. The experimental results indicate the robust and superior performance of the proposed deep learning method in terms of F-measure and area under the receiver operating characteristic curve (AUC).

Purpose Carbohydrate antigen (CA) 19-9 has been established as the main serum marker for patients with intrahepatic cholangiocarcinoma (ICC). The aim of this study was to compare the prognostic value of CA 19-9 changes versus response determined by imaging in patients with ICC undergoing chemotherapy. Methods Between 2003 and 2018, 151 patients with histopathologically confirmed ICC underwent chemotherapy at our tertiary care center for non-resectable or recurrent ICC, of whom 121 were included in this study. Serum CA 19-9 levels and imaging were retrospectively evaluated during chemotherapy. Log-rank testing and optimal stratification were used to classify patients into risk groups. Results Prior to chemotherapy, baseline serum CA 19-9 levels above the previously published cut-off of 37 U/ml were associated with poor survival (median OS 8.7 vs. 12.4 months, p = 0.003). After the beginning of chemotherapy, an increase in CA 19-9 of more than 40 U/ml resulted in impaired residual survival (median OS 5.0 vs. 12.1 months, p p Conclusion In our study, the disease control rate—that is, the absence of progressive disease—was the strongest predictor of prolonged residual OS. To this end, both CA 19-9 changes and progressive disease on initial follow-up showed remarkable discriminatory power, with the latter slightly outperforming the former. Therefore, imaging should remain the mainstay of patient evaluation during follow-up.

The possible uses of artificial intelligence (AI) in radiation oncology are diverse and wide ranging. Herein, the authors discuss the potential applications of AI at each step of the radiation oncology workflow, which might improve the efficiency and overall quality of radiation therapy for patients with cancer. The authors also describe the associated challenges and provide their perspective on how AI platforms might change the roles of radiation oncology medical professionals. Artificial intelligence (AI) has the potential to fundamentally alter the way medicine is practised. AI platforms excel in recognizing complex patterns in medical data and provide a quantitative, rather than purely qualitative, assessment of clinical conditions. Accordingly, AI could have particularly transformative applications in radiation oncology given the multifaceted and highly technical nature of this field of medicine with a heavy reliance on digital data processing and computer software. Indeed, AI has the potential to improve the accuracy, precision, efficiency and overall quality of radiation therapy for patients with cancer. In this Perspective, we first provide a general description of AI methods, followed by a high-level overview of the radiation therapy workflow with discussion of the implications that AI is likely to have on each step of this process. Finally, we describe the challenges associated with the clinical development and implementation of AI platforms in radiation oncology and provide our perspective on how these platforms might change the roles of radiotherapy medical professionals.

The modeling of comorbid cancer patients' survivability has theoretical significance and practical needs. Cancer survivability prediction may provide guidance for clinical decision making and personalized medicine. The Surveillance, Epidemiology, and End Results(SEER) program provides large data sets suitable for analysis with machine learning methods. In this study, we consider survival prediction to be a two-stage problem. The first is to predict the five-year survivability of patients. For those whom the predicted outcome is `death', the second stage predicts the remaining survival time. Male and female comorbid cancer cases(male-genital and urinary cancer for men and breast and female-genital cancer for women) were identified from the SEER database and labeled. In the classification stage,the dataset was processed with improved infinite feature selection(Iinf-FS) and random undersampling-based data balancing. These two methods resolved the issues of biased data set and poor classification accuracy. In the lifespan prediction stage, unsupervised infinite feature selection (UinfFS) was applied. The results indicate that the proposed method is effective.

The problem of dynamic prediction with time-dependent covariates, given by biomarkers, repeatedly measured over time, has received much attention over the last decades. Two contrasting approaches have become in widespread use. The first is joint modelling, which attempts to jointly model the longitudinal markers and the event time. The second is landmarking, a more pragmatic approach that avoids modelling the marker process. Landmarking has been shown to be less efficient than correctly specified joint models in simulation studies, when data are generated from the joint model. When the mean model is misspecified, however, simulation has shown that joint models may be inferior to landmarking. The objective of this paper is to develop methods that improve the predictive accuracy of landmarking, while retaining its relative simplicity and robustness. We start by fitting a working longitudinal model for the biomarker, including a temporal correlation structure. Based on that model, we derive a predictable time-dependent process representing the expected value of the biomarker after the landmark time, and we fit a time-dependent Cox model based on the predictable time-dependent covariate. Dynamic predictions based on this approach for new patients can be obtained by first deriving the expected values of the biomarker, given the measured values before the landmark time point, and then calculating the predicted probabilities based on the time-dependent Cox model. We illustrate the approach in predicting overall survival in liver cirrhosis patients based on prothrombin index., 24 pages, 6 figures, 4 tables

Gastric cancer (GC) is a typical heterogeneous malignant tumor, whose insensitivity to chemotherapy is a common cause of tumor recurrence and metastasis. There is no doubt regarding the effectiveness of adjuvant chemotherapy (ACT) for GC, but the population for whom it is indicated and the selection of specific options remain the focus of present research. The conventional pathological TNM prediction focuses on cancer cells to predict prognosis, while they do not provide sufficient prediction. Enhanced computed tomography (CT) scanning is a validated tool that assesses the involvement of careful identification of the tumor, lymph node involvement, and metastatic spread. Using the radiomics approach, we selected the least absolute shrinkage and selection operator (LASSO) Cox regression model to build a radiomics signature for predicting the overall survival (OS) and disease-free survival (DFS) of patients with complete postoperative gastric cancer and further identifying candidate benefits from ACT. The radiomics trait-associated genes captured clinically relevant molecular pathways and potential chemotherapeutic drug metabolism mechanisms. Our results of precise surrogates using radiogenomics can lead to additional benefit from adjuvant chemotherapy and then survival prediction in postoperative GC patients.

Most electronic medical records, such as free-text radiological reports, are unstructured; however, the methodological approaches to analyzing these accumulating unstructured records are limited. This article proposes a deep-transfer-learning-based natural language processing model that analyzes serial magnetic resonance imaging reports of rectal cancer patients and predicts their overall survival. To evaluate the model, a retrospective cohort study of 4,338 rectal cancer patients was conducted. The experimental results revealed that the proposed model utilizing pre-trained clinical linguistic knowledge could predict the overall survival of patients without any structured information and was superior to the carcinoembryonic antigen in predicting survival. The deep-transfer-learning model using free-text radiological reports can predict the survival of patients with rectal cancer, thereby increasing the utility of unstructured medical big data.

The aim of this work is to investigate the applicability of radiomic features alone and in combination with clinical information for the prediction of renal cell carcinoma (RCC) patients’ overall survival after partial or radical nephrectomy. Clinical studies of 210 RCC patients from The Cancer Imaging Archive (TCIA) who underwent either partial or radical nephrectomy were included in this study. Regions of interest (ROIs) were manually defined on CT images. A total of 225 radiomic features were extracted and analyzed along with the 59 clinical features. An elastic net penalized Cox regression was used for feature selection. Accelerated failure time (AFT) with the shared frailty model was used to determine the effects of the selected features on the overall survival time. Eleven radiomic and twelve clinical features were selected based on their non-zero coefficients. Tumor grade, tumor malignancy, and pathology t-stage were the most significant predictors of overall survival (OS) among the clinical features (p p

Simple SummaryGlioblastoma (GBM) is the most common and aggressive primary brain tumor. Diffusion kurtosis imaging (DKI) has characterized non-Gaussian diffusion behaviors in brain normal tissue and gliomas, but there are very limited efforts in investigating treatment responses of kurtosis in GBM. This study aimed to investigate whether any parameter derived from the DKI is a significant predictor of overall survival (OS). We found that the large mean, 80 and 90 percentile kurtosis values in the contrast enhanced gross tumor volume (Gd-GTV) on post-Gd T1-weighted images pre-RT were significantly associated with reduced OS. In the multivariate Cox model, the mean kurtosis Gd-GTV pre-RT after considering effects of age, extent of surgery, and methylation were significant predictors of OS. In addition, the 80 and 90 percentile kurtosis values in Gd-GTV post RT were significantly associated with progression free survival (PFS). The DKI model demonstrates the potential to predict outcomes in the patients with GBM.PurposeNon-Gaussian diffusion behaviors in gliomas have been characterized by diffusion kurtosis imaging (DKI). But there are very limited efforts in investigating the kurtosis in glioblastoma (GBM) and its prognostic and predictive values. This study aimed to investigate whether any of the diffusion kurtosis parameters derived from DKI is a significant predictor of overall survival.Methods and MaterialsThirty-three patients with GBM had pre-radiation therapy (RT) and mid-RT diffusion weighted (DW) images. Kurtosis and diffusion coefficient (DC) values in the contrast enhanced gross tumor volume (Gd-GTV) on post-Gd T1 weighted images pre-RT and mid-RT were calculated. Univariate and multivariate Cox models were used to evaluate the DKI parameters and clinical factors for prediction of OS and PFS.ResultsThe large mean kurtosis values in the Gd-GTV pre-RT were significantly associated with reduced OS (p = 0.02), but the values at mid-RT were not (p > 0.8). In the multivariate Cox model, the mean kurtosis in the Gd-GTV pre-RT (p = 0.009) was still a significant predictor of OS after adjusting effects of age, O6-Methylguanine-DNA Methyl transferase (MGMT) methylation and extent of resection. In Gd-GTV post-RT, 80 and 90 percentile kurtosis values were significant predictors (p ≤ 0.05) for progression free survival (PFS).ConclusionThe DKI model demonstrates the potential to predict OS and PFS in the patients with GBM. Further development and histopathological validation of the DKI model will warrant its role in clinical management of GBM.

One pivotal feature of transcriptomics data is the unwanted variations caused by disparate experimental handling, known as handling effects. Various data normalization methods were developed to alleviate the adverse impact of handling effects in the setting of differential expression analysis. However, little research has been done to evaluate their performance in the setting of survival outcome prediction, an important analysis goal for transcriptomics data in biomedical research. Leveraging a unique pair of datasets for the same set of tumor samples—one with handling effects and the other without, we developed a benchmarking tool for conducting such an evaluation in microRNA microarrays. We applied this tool to evaluate the performance of three popular normalization methods—quantile normalization, median normalization and variance stabilizing normalization—in survival prediction using various approaches for model building and designs for sample assignment. We showed that handling effects can have a strong impact on survival prediction and that quantile normalization, a most popular method in current practice, tends to underperform median normalization and variance stabilizing normalization. We demonstrated with a small example the reason for quantile normalization’s poor performance in this setting. Our finding highlights the importance of putting normalization evaluation in the context of the downstream analysis setting and the potential of improving the development of survival predictors by applying median normalization. We make available our benchmarking tool for performing such evaluation on additional normalization methods in connection with prediction modeling approaches.

Elderly patients with non-small-cell lung cancer (NSCLC) exhibit worse reactions to anticancer treatments. Adenocarcinoma (AC) is the predominant histologic subtype of NSCLC, is diverse and heterogeneous, and shows different outcomes and responses to treatment. The aim of this study was to establish a nomogram that includes the important prognostic factors based on the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. We collected 53,694 patients of older than 60 who have been diagnosed with lung AC from the SEER database. Univariate and multivariate Cox regression analyses were used to screen the independent prognostic factors, which were used to construct a nomogram for predicting survival rates in elderly AC patients. The nomogram was evaluated using the concordance index (C-index), calibration curves, net reclassification index (NRI), integrated discrimination improvement (IDI), and decision-curve analysis (DCA). Elderly AC patients were randomly divided into a training cohort and validation cohort. The nomogram model included the following 11 prognostic factors: age, sex, race, marital status, tumor site, histologic grade, American Joint Committee for Cancer (AJCC) stage, surgery status, radiotherapy status, chemotherapy status, and insurance type. The C-indexes of the training and validation cohorts for cancer-specific survival (CSS) (0.832 and 0.832, respectively) based on the nomogram model were higher than those of the AJCC model (0.777 and 0.774, respectively). The CSS discrimination performance as indicated by the AUC was better in the nomogram model than the AJCC model at 1, 3, and 5 years in both the training cohort (0.888 vs. 0.833, 0.887 vs. 0.837, and 0.876 vs. 0.830, respectively) and the validation cohort (0.890 vs. 0.832, 0.883 vs. 0.834, and 0.880 vs. 0.831, respectively). The predicted CSS probabilities showed optimal agreement with the actual observations in nomogram calibration plots. The NRI, IDI, and DCA for the 1-, 3-, and 5-year follow-up examinations verified the clinical usability and practical decision-making effects of the new model. We have developed a reliable nomogram for determining the prognosis of elderly AC patients, which demonstrated excellent discrimination and clinical usability and more accurate prognosis predictions. The nomogram may improve clinical decision-making and prognosis predictions for elderly AC patients.

Background The clinical outcomes of patients with resected T1-3N0–2M0 non-small cell lung cancer (NSCLC) with the same tumor-node-metastasis (TNM) stage are diverse. Although other prognostic factors and prognostic prediction tools have been reported in many published studies, a convenient, accurate and specific prognostic prediction software for clinicians has not been developed. The purpose of our research was to develop this type of software that can analyze subdivided T and N staging and additional factors to predict prognostic risk and the corresponding mean and median survival time and 1–5-year survival rates of patients with resected T1-3N0–2M0 NSCLC. Results Using a Cox proportional hazard regression model, we determined the independent prognostic factors and obtained a prognostic index (PI) eq. PI = ∑βixi. =0.379X1–0.403X2–0.267X51–0.167X61–0.298X62 + 0.460X71 + 0.617X72–0.344X81–0.105X91–0.243X92 + 0.305X101 + 0.508X102 + 0.754X103 + 0.143X111 + 0.170X112 + 0.434X113–0.327X122–0.247X123 + 0.517X133 + 0.340X134 + 0.457X143 + 0.419X144 + 0.407X145. Using the PI equation, we determined the PI value of every patient. According to the quantile of the PI value, patients were divided into three risk groups: low-, intermediate-, and high-risk groups with significantly different survival rates. Meanwhile, we obtained the mean and median survival times and 1–5-year survival rates of the three groups. We developed the RNSCLC-PRSP software which is freely available on the web at http://www.rnsclcpps.com with all major browsers supported to determine the prognostic risk and associated survival of patients with resected T1-3N0–2 M0 non-small cell lung cancer. Conclusions After prognostic factor analysis, prognostic risk grouping and corresponding survival assessment, we developed a novel software program. It is practical and convenient for clinicians to evaluate the prognostic risk and corresponding survival of patients with resected T1-3N0–2M0 NSCLC. Additionally, it has guiding significance for clinicians to make decisions about complementary treatment for patients. Electronic supplementary material The online version of this article (10.1186/s13040-019-0205-0) contains supplementary material, which is available to authorized users.

To explore prognostic and predictive values of a novel quantitative feature set describing intra-tumor heterogeneity in patients with lung cancer treated with concurrent and sequential chemoradiotherapy.Longitudinal PET-CT images of 30 patients with non-small cell lung cancer were analysed. To describe tumor cell heterogeneity, the tumors were partitioned into one to ten concentric regions depending on their sizes, and, for each region, the change in average intensity between the two scans was calculated for PET and CT images separately to form the proposed feature set. To validate the prognostic value of the proposed method, radiomics analysis was performed and a combination of the proposed novel feature set and the classic radiomic features was evaluated. A feature selection algorithm was utilized to identify the optimal features, and a linear support vector machine was trained for the task of overall survival prediction in terms of area under the receiver operating characteristic curve (AUROC).The proposed novel feature set was found to be prognostic and even outperformed the radiomics approach with a significant difference (AUROCA novel feature set designed for capturing intra-tumor heterogeneity was introduced. Judging by their prognostic power, the proposed features have a promising potential for early survival prediction.

Background: Toward the goal of predicting individual long-term cancer survival to guide treatment decisions, this study evaluated the ability of a probabilistic neural network (PNN), an established model used for decision-making in research and clinical settings, to predict the 10-year overall survival in patients with cervical cancer who underwent primary surgical treatment. Patients and Method: The input dataset was derived from 102 patients with cervical cancer FIGO stage IA2-IIB treated by radical hysterectomy. We identified 4 demographic parameters, 13 tumor-related parameters, and 6 selected perioperative variables for each patient and performed computer simulations with DTREG software. The predictive ability of the model was determined on the basis of its error, sensitivity, and specificity, as well as area under the receiver operating characteristic curve. The results of the PNN predictive model were compared with those of logistic regression analysis and a single decision tree as reference models. Results: The PNN model had very high predictive ability, with a sensitivity of 0.949, a specificity of 0.679, and an error rate of 12.5%. The PNN's area under the receiver operating characteristic curve was high, 0.809, a value greater than those for both logistic regression analysis and the single decision tree. Conclusion: The PNN model effectively and reliably predicted 10-year overall survival in women with operable cervical cancer, and may therefore serve as a tool for decision-making process in cancer treatment.

ObjectivesThe Prognostic Nutritional Index (PNI) and Controlling Nutritional Status (CONUT) score are immunonutritive scoring systems with proven predictive ability in various cancer entities, including hepatocellular carcinoma (HCC). We performed the first evaluation of the CONUT score for patients undergoing transarterial chemoembolization (TACE) and compared CONUT and PNI in the ability to predict median overall survival (OS).MethodsBetween 2010 and 2020, we retrospectively identified 237 treatment-naïve patients with HCC who underwent initial TACE at our institution. Both scores include the albumin level and total lymphocyte count. The CONUT additionally includes the cholesterol level. Both scores were compared in univariate and multivariate regression analyses taking into account established risk factors. In a second step, a subgroup analysis was performed on BCLC stage B patients, for whom TACE is the recommended first-line treatment.ResultsA high CONUT score and low PNI were associated with impaired median OS (8.7 vs. 22.3 months, pvs. 20.1 months, pvs. 17.9 months, pvs. 22.0 months, pConclusionBoth scores were able to stratify patients according to their median OS, but only the PNI remained an independent prognostic factor. Therefore, PNI should be preferred when evaluating the nutritional status of patients undergoing TACE.

Survival prediction models may serve as decision-support tools for clinicians who have to assign the right treatment to each patient, in a manner whereby harmful over- or undertreatment is avoided as much as possible. Current models differ regarding their components, the overall number of components and the weighting of individual components. Some of the components are easy to assess, such as age or primary tumor type. Others carry the risk of inter-assessor inconsistency and time-dependent variation. The present publication focuses on issues related to assessment of extracranial metastases and potential surrogates, e.g. blood biomarkers. It identifies areas of controversy and provides recommendations for future research projects, which may contribute to prognostic models with improved accuracy. (c) 2021 Elsevier B.V. All rights reserved. Radiotherapy and Oncology 159 (2021) 17-20

Glioblastoma Multiforme (GBM) is an aggressive form of glioma, exhibiting very poor survival. Genomic input, in the form of RNA sequencing data (RNA-seq), is expected to provide vital information about the characteristics of the genes that affect the Overall Survival (OS) of patients. This could have a significant impact on treatment planning. We present a new Autoencoder (AE)-based strategy for the prediction of survival (low or high) of GBM patients, using the RNA-seq data of 129 GBM samples from The Cancer Genome Atlas (TCGA). This is a novel interdisciplinary approach to integrating genomics with deep learning towards survival prediction. First, the Differentially Expressed Genes (DEGs) were selected using EdgeR. These were further reduced using correlation-based analysis. This was followed by the application of ranking with different feature subset selection and feature extraction algorithms, including the AE. In each case, fifty features were selected/extracted, for subsequent prediction with different classifiers. An exhaustive study for survival group prediction, using eight different classifiers with the accuracy and Area Under the Curve (AUC), established the superiority of the AE-based feature extraction method, called DeepSGP. It produced a very high accuracy (0.83) and AUC (0.90). Of the eight classifiers, using the extracted features by DeepSGP, the MLP was the best at Overall Survival (OS) prediction with an accuracy of 0.89 and an AUC of 0.97. The biological significance of the genes extracted by the AE were also analyzed to establish their importance. Finally, the statistical significance of the predicted output of the DeepSGP algorithm was established using the concordance index.

High-dimensional omics data contains intrinsic biomedical information that is crucial for personalised medicine. Nevertheless, it is challenging to capture them from the genome-wide data due to the large number of molecular features and small number of available samples, which is also called 'the curse of dimensionality' in machine learning. To tackle this problem and pave the way for machine learning aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules. The deep embedding module learnt an omics embedding that mapped multiple omics data types into a latent space with lower dimensionality. Based on the new representation of multi-omics data, different downstream task modules were trained simultaneously and efficiently with the multi-task strategy to predict the comprehensive phenotype profile of each sample. OmiEmbed support multiple tasks for omics data including dimensionality reduction, tumour type classification, multi-omics integration, demographic and clinical feature reconstruction, and survival prediction. The framework outperformed other methods on all three types of downstream tasks and achieved better performance with the multi-task strategy comparing to training them individually. OmiEmbed is a powerful and unified framework that can be widely adapted to various application of high-dimensional omics data and has a great potential to facilitate more accurate and personalised clinical decision making., 14 pages, 8 figures, 7 tables

Background Little data is available on prognostic biomarkers and effective treatment options for Kidney Renal Papillary Cell Carcinoma (KIRP) patients, to find potential prognostic biomarkers and new targets was an urgent mission for KIRP therapy. Methods The differentially expressed autophagy-related genes (DEARGs) were screened out according to the RNA sequencing data in The Cancer Genome Atlas database, then identified survival-related DEARGs to establish a prognostic model for survival predicting of KIRP patients. Then we verified the robustness and validity of the prognostic risk model through clinicopathological data. At last, we evaluate the prognostic value of genes that formed the prognostic risk model individually. Results We analyzed the expression of 232 autophagy-related genes (ARGs) in 289 KIRP and 32 non-tumor tissue cases, and 40 mRNAs were screened out as DEARGs. The functional and pathway enrichment analysis was done and protein–protein interaction network was constructed for all DEARGs. To sift candidate DEARGs associated with KIRP patients’ survival and create an autophagy-related risk prognostic model, univariate and multivariate Cox regression analysis were did separately. Eventually 3 desirable independent prognostic DEARGs (P4HB, NRG1, and BIRC5) were picked out and used for construct the autophagy-related risk model. The accuracy of the prognostic risk model for survival prediction was assessed by Kaplan–Meier plotter, receiver-operator characteristic curve, and clinicopathological correlational analyses. The prognostic value of above 3 genes was verified individually by survival analysis and expression analysis on mRNA and protein level. Conclusions The autophagy-related prognostic model is accurate and applicable, it can predict OS independently for KIRP patients. Three independent prognostic DEARGs can benefit for facilitate personalized target treatment too.

Background The clinical use of patient-reported outcomes as compared to inflammatory biomarkers for predicting cancer survival remains a challenge in palliative care settings. We evaluated the role of the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 15 Palliative scores (EORTC QLQ-C15-PAL) and the inflammatory biomarkers C-reactive protein (CRP), albumin (Alb), and neutrophil-lymphocyte ratio (NLR) for survival prediction in patients with advanced cancer. Methods This was an observational study in terminally ill patients with cancer hospitalized in a palliative care unit between June 2018 and December 2019. Patients’ data collected at the time of hospitalization were analyzed. Cox regression was performed to examine significant factors influencing survival. A receiver operating characteristic (ROC) analysis was performed to estimate cut-off values for predicting survival within 3 weeks, and a log-rank test was performed to compare survival curves between groups divided by the cut-off values. Results Totally, 130 patients participated in the study. Cox regression suggested that the QLQ-C15-PAL dyspnea and fatigue scores and levels of CRP, Alb, and NLR were significantly associated with survival time, and cut-off values were 66.67, 66.67, 3.0 mg/dL, 2.5 g/dL, and 8.2, respectively. The areas under ROC curves of these variables were 0.6–0.7. There were statistically significant differences in the survival curves between groups categorized using each of these cut-off values (p Conclusion Our findings suggest that the assessment of not only objective indicators for the systemic inflammatory response but also patient-reported outcomes using EORTC QLQ-C15-PAL is beneficial for the prediction of short-term survival in terminally ill patients with cancer.

Introduction There is significant potential to analyse and model routinely collected data for radiotherapy patients to provide evidence to support clinical decisions, particularly where clinical trials evidence is limited or non-existent. However, in practice there are administrative, ethical, technical, logistical and legislative barriers to having coordinated data analysis platforms across radiation oncology centres. Methods A distributed learning network of computer systems is presented, with software tools to extract and report on oncology data and to enable statistical model development. A distributed or federated learning approach keeps data in the local centre, but models are developed from the entire cohort. Results The feasibility of this approach is demonstrated across six Australian oncology centres, using routinely collected lung cancer data from oncology information systems. The infrastructure was used to validate and develop machine learning for model-based clinical decision support and for one centre to assess patient eligibility criteria for two major lung cancer radiotherapy clinical trials (RTOG-9410, RTOG-0617). External validation of a 2-year overall survival model for non-small cell lung cancer (NSCLC) gave an AUC of 0.65 and C-index of 0.62 across the network. For one centre, 65% of Stage III NSCLC patients did not meet eligibility criteria for either of the two practice-changing clinical trials, and these patients had poorer survival than eligible patients (10.6 m vs. 15.8 m, P = 0.024). Conclusion Population-based studies on routine data are possible using a distributed learning approach. This has the potential for decision support models for patients for whom supporting clinical trial evidence is not applicable.

Background Existing clinical methods for prognosis evaluating for Epithelial Ovarian Cancer (EOC) patients had defects of invasive, unsystematic and subjective and little data are available for individualizing treatment, therefore, to identify potential prognostic markers and new therapeutic targets for EOC is urgently required. Results Expression of 232 autophagy-related genes (ARGs) in 354 EOC and 56 human ovarian surface epithelial specimens from 7 independent laboratories were analyzed, 31 mRNAs were identified as DEARGs. We did functional and pathway enrichment analysis and constructed protein–protein interaction network for all DEARGs. To screen out candidate DEARGs related to EOC patients’ survival and construct an autophagy-related prognostic risk signature, univariate and multivariate Cox proportional hazards models were established separately. Finally, 5 optimal independent prognostic DEARGs (PEX3, DNAJB9, RB1, HSP90AB1 and CXCR4) were confirmed and the autophagy-related risk model was established by the 5 prognostic DEARGs. The accuracy and robustness of the prognostic risk model for survival prediction were evaluated and verified by analyzing the correlation between EOC patients’ survival status, clinicopathological features and risk scores. Conclusions The autophagy-related prognostic risk model can be independently used to predict overall survival in EOC patients, it can also potentially assist in individualizing treatment and biomarker development.

Background Gene mutations play critical roles in tumorigenesis and cancer development. Our study aimed to screen survival-related mutations and explore a novel gene signature to predict the overall survival in pancreatic cancer. Methods Somatic mutation data from three cohorts were used to identify the common survival-related gene mutation with Kaplan-Meier curves. RNA-sequencing data were used to explore the signature for survival prediction. First, Weighted Gene Co-expression Network Analysis was conducted to identify candidate genes. Then, the ICGC-PACA-CA cohort was applied as the training set and the TCGA-PAAD cohort was used as the external validation set. A TP53-associated signature calculating the risk score of every patient was developed with univariate Cox, least absolute shrinkage and selection operator, and stepwise regression analysis. Kaplan-Meier and receiver operating characteristic curves were plotted to verify the accuracy. The independence of the signature was confirmed by the multivariate Cox regression analysis. Finally, a prognostic nomogram including 359 patients was constructed based on the combined expression data and the risk scores. Results TP53 mutation was screened to be the robust and survival-related mutation type, and was associated with immune cell infiltration. Two thousand, four hundred fifty-five genes included in the six modules generated in the WGCNA were screened as candidate survival related TP53-associated genes. A seven-gene signature was constructed: Risk score = (0.1254 × ERRFI1) - (0.1365 × IL6R) - (0.4400 × PPP1R10) - (0.3397 × PTOV1-AS2) + (0.1544 × SCEL) - (0.4412 × SSX2IP) – (0.2231 × TXNL4A). Area Under Curves of 1-, 3-, and 5-year ROC curves were 0.731, 0.808, and 0.873 in the training set and 0.703, 0.677, and 0.737 in the validation set. A prognostic nomogram including 359 patients was constructed and well-calibrated, with the Area Under Curves of 1-, 3-, and 5-year ROC curves as 0.713, 0.753, and 0.823. Conclusions The TP53-associated signature exhibited good prognostic efficacy in predicting the overall survival of PC patients.

BackgroundThe aim was to develop a personalized survival prediction deep learning model for adenosarcoma patients using the surveillance, epidemiology and end results (SEER) database.MethodsA total of 797 uterine adenosarcoma patients were enrolled in this study. Duplicated and useless variables were excluded, and 15 variables were selected for further analyses, including age, grade, positive lymph nodes or not, marital status, race, tumor extension, stage, and surgery or not. We created our deep survival learning (DSL) model to manipulate the data, which was randomly split into a training set (n = 519, 65%), validation set (n = 143, 18%) and testing set (n = 143, 18%). The Cox proportional hazard (CPH) model was also included comparatively. Finally, personalized survival curves were plotted for randomly selected patients.ResultsThe c-index for the CPH model was 0.726, and the Brier score was 0.17. For our deep survival learning model, we achieved a c-index of 0.774 and a Brier score of 0.14 in the external testing set. In addition, the limitations of the traditional staging system were revealed, and a personalized survival prediction system based on our risk scoring grouping was developed.ConclusionsOur study developed a deep neural network model for adenosarcoma. The performance of this model was superior to that of the traditional Cox proportional hazard model. In addition, a personalized survival prediction system was developed based on our deep survival learning model, which provided more accurate prognostic information for adenosarcoma patients.

Background and Objective: Primary lung cancer is a lethal and rapidly-developing cancer type and is one of the most leading causes of cancer deaths. Materials and Methods: Statistical methods such as Cox regression are usually used to detect the prognosis factors of a disease. This study investigated survival prediction using machine learning algorithms. The clinical data of 28,458 patients with primary lung cancers were collected from the Surveillance, Epidemiology, and End Results (SEER) database. Results: This study indicated that the survival rate of women with primary lung cancer was often higher than that of men (p &lt, 0.001). Seven popular machine learning algorithms were utilized to evaluate one-year, three-year, and five-year survival prediction The two classifiers extreme gradient boosting (XGB) and logistic regression (LR) achieved the best prediction accuracies. The importance variable of the trained XGB models suggested that surgical removal (feature “Surgery”) made the largest contribution to the one-year survival prediction models, while the metastatic status (feature “N” stage) of the regional lymph nodes was the most important contributor to three-year and five-year survival prediction. The female patients’ three-year prognosis model achieved a prediction accuracy of 0.8297 on the independent future samples, while the male model only achieved the accuracy 0.7329. Conclusions: This data suggested that male patients may have more complicated factors in lung cancer than females, and it is necessary to develop gender-specific diagnosis and prognosis models.

Liver cancer kills approximately 800 thousand people annually worldwide, and its most common subtype is hepatocellular carcinoma (HCC), which usually affects people with cirrhosis. Predicting survival of patients with HCC remains an important challenge, especially because technologies needed for this scope are not available in all hospitals. In this context, machine learning applied to medical records can be a fast, low-cost tool to predict survival and detect the most predictive features from health records. In this study, we analyzed medical data of 165 patients with HCC: we employed computational intelligence to predict their survival, and to detect the most relevant clinical factors able to discriminate survived from deceased cases. Afterwards, we compared our data mining results with those obtained through statistical tests and scientific literature findings. Our analysis revealed that blood levels of alkaline-phosphatase (ALP), alpha-fetoprotein (AFP), and hemoglobin are the most effective prognostic factors in this dataset. We found literature supporting association of these three factors with hepatoma, even though only AFP has been used in a prognostic index. Our results suggest that ALP and hemoglobin can be candidates for future HCC prognostic indexes, and that physicians could focus on ALP, AFP, and hemoglobin when studying HCC records.

Glioblastoma (GBM) is the most malignant primary brain tumor for which no curative treatment options exist. Non-invasive qualitative (Visually Accessible Rembrandt Images (VASARI)) and quantitative (radiomics) imaging features to predict prognosis and clinically relevant markers for GBM patients are needed to guide clinicians. A retrospective analysis of GBM patients in two neuro-oncology centers was conducted. The multimodal Cox-regression model to predict overall survival (OS) was developed using clinical features with VASARI and radiomics features in isocitrate dehydrogenase (IDH)-wild type GBM. Predictive models for IDH-mutation, 06-methylguanine-DNA-methyltransferase (MGMT)-methylation and epidermal growth factor receptor (EGFR) amplification using imaging features were developed using machine learning. The performance of the prognostic model improved upon addition of clinical, VASARI and radiomics features, for which the combined model performed best. This could be reproduced after external validation (C-index 0.711 95% CI 0.64–0.78) and used to stratify Kaplan–Meijer curves in two survival groups (p-value &lt, 0.001). The predictive models performed significantly in the external validation for EGFR amplification (area-under-the-curve (AUC) 0.707, 95% CI 0.582–8.25) and MGMT-methylation (AUC 0.667, 95% CI 0.522–0.82) but not for IDH-mutation (AUC 0.695, 95% CI 0.436–0.927). The integrated clinical and imaging prognostic model was shown to be robust and of potential clinical relevance. The prediction of molecular markers showed promising results in the training set but could not be validated after external validation in a clinically relevant manner. Overall, these results show the potential of combining clinical features with imaging features for prognostic and predictive models in GBM, but further optimization and larger prospective studies are warranted.

Purpose Glioma is the most common type of primary brain tumor in adults, and it causes significant morbidity and mortality, especially in high‐grade glioma (HGG) patients. The accurate prognostic prediction of HGG is vital and helpful for clinicians when developing therapeutic strategies. Therefore, we propose a machine learning‐based survival prediction model by analyzing clinical and dose‐volume histogram (DVH) parameters, to improve the performance of the risk model in HGG patients. Methods Eight clinical variables and 39 DVH parameters were extracted for each patient, who received radiotherapy for HGG with active follow‐up. Ninety‐five patients were randomly divided into training and testing cohorts, and we employed random survival forest (RSF), support vector machine (SVM), and Cox proportional hazards (CPHs) models to predict survival. Calibration plots, concordance indexes, and decision curve analyses were used to evaluate the calibration, discrimination, and clinical utility of these three models. Results The RSF model showed the best performance among the three models, with concordance indexes of 0.824 and 0.847 in the training and testing sets, respectively, followed by the SVM (0.792/0.823) and CPH (0.821/0.811) models. Specifically, in the RSF model, we identified age, gross tumor volume (GTV), grade, Karnofsky performance status (KPS), isocitrate dehydrogenase (IDH), and D99 as important variables associated with survival. The AUCs of the testing set were 92.4%, 87.7%, and 84.0% for 1‐, 2‐, and 3‐year survival, respectively. According to this model, HGG patients can be divided into high‐ and low‐risk groups. Conclusion The machine learning‐based RSF model integrating both clinical and DVH variables is an improved and useful tool for predicting the survival of HGG patients., We propose the machine learning‐based RSF and SVM models, and the classical CPH model, to identify predictors for survival and examine treatment outcomes in patients with HGG by integrating clinical and DVH parameters.The RSF model showed the best performance among the three models and is an improved and useful tool for the survival prediction of HGG.

Background Squamous cell carcinoma (SCC) is a main pathological type of non-small cell lung cancer. It is common among elderly patients with poor prognosis. We aimed to establish an accurate nomogram to predict survival for elderly patients (≥ 60 years old) with SCC based on the Surveillance, Epidemiology, and End Results (SEER) database. Methods The gerontal patients diagnosed with SCC from 2010 to 2015 were collected from the Surveillance, Epidemiology, and End Results (SEER) database. The independent prognostic factors were identified using multivariate Cox proportional hazards regression analysis, which were utilized to conduct a nomogram for predicting survival. The novel nomogram was evaluated by Concordance index (C-index), calibration curves, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA). Results 32,474 elderly SCC patients were included in the analysis, who were randomly assigned to training cohort (n = 22,732) and validation cohort (n = 9742). The following factors were contained in the final prognostic model: age, sex, race, marital status, tumor site, AJCC stage, surgery, radiation and chemotherapy. Compared to AJCC stage, the novel nomogram exhibited better performance: C-index (training group: 0.789 vs. 0.730, validation group: 0.791 vs. 0.733), the areas under the receiver operating characteristic curve of the training set (1-year AUC: 0.846 vs. 0.791, 3-year AUC: 0.860 vs. 0.801, 5-year AUC: 0.859 vs. 0.794) and the validation set (1-year AUC: 0.846 vs. 0.793, 3-year AUC: 0.863 vs. 0.806, 5-year AUC: 0.866 vs. 0.801), and the 1-, 3- and 5-year calibration plots. Additionally, the NRI and IDI and 1-, 3- and 5-year DCA curves all confirmed that the nomogram was a great prognosis tool. Conclusions We constructed a novel nomogram that could be practical and helpful for precise evaluation of elderly SCC patient prognosis, thus helping clinicians in determining the appropriate therapy strategies for individual SCC patients.

This study aimed to investigate the performance of a deep learning-based survival-prediction model, which predicts the overall survival (OS) time of glioblastoma patients who have received surgery followed by concurrent chemoradiotherapy (CCRT). The medical records of glioblastoma patients who had received surgery and CCRT between January 2011 and December 2017 were retrospectively reviewed. Based on our inclusion criteria, 118 patients were selected and semi-randomly allocated to training and test datasets (3:1 ratio, respectively). A convolutional neural network–based deep learning model was trained with magnetic resonance imaging (MRI) data and clinical profiles to predict OS. The MRI was reconstructed by using four pulse sequences (22 slices) and nine images were selected based on the longest slice of glioblastoma by a physician for each pulse sequence. The clinical profiles consist of personal, genetic, and treatment factors. The concordance index (C-index) and integrated area under the curve (iAUC) of the time-dependent area-under-the-curve curves of each model were calculated to evaluate the performance of the survival-prediction models. The model that incorporated clinical and radiomic features showed a higher C-index (0.768 (95% confidence interval (CI): 0.759, 0.776)) and iAUC (0.790 (95% CI: 0.783, 0.797)) than the model using clinical features alone (C-index = 0.693 (95% CI: 0.685, 0.701); iAUC = 0.723 (95% CI: 0.716, 0.731)) and the model using radiomic features alone (C-index = 0.590 (95% CI: 0.579, 0.600); iAUC = 0.614 (95% CI: 0.607, 0.621)). These improvements to the C-indexes and iAUCs were validated using the 1000-times bootstrapping method; all were statistically significant (p < 0.001). This study suggests the synergistic benefits of using both clinical and radiomic parameters. Furthermore, it indicates the potential of multi-parametric deep learning models for the survival prediction of glioblastoma patients.

International audience; Hepatocellular carcinoma (HCC) is the sixth more frequent cancer worldwide. This type of cancer has a poor overall survival rate mainly due to underlying cirrhosis and risk of recurrence outside the treated lesion. Quantitative imaging within a radiomics workflow may help assessing the probability of survival and potentially may allow tailoring personalized treatments. In radiomics a large amount of features can be extracted, which may be correlated across a population and very often can be surrogates of the same physiopathology. This issues are more pronounced and difficult to tackle with imbalanced data. Feature selection strategies are therefore required to extract the most informative with the increased predictive capabilities. In this paper, we compared different unsupervised and supervised strategies for feature selection in presence of imbalanced data and optimize them within a machine learning framework. Multi-parametric Magnetic Resonance Images from 81 individuals (19 deceased) treated with stereotactic body radiation therapy (SBRT) for inoperable (HCC) were analyzed. Pre-selection of a reduced set of features based on Affinity Propagation clustering (non supervised) achieved a significant improvement in AUC compared to other approaches with and without feature pre-selection. By including the synthetic minority over-sampling technique (SMOTE) for imbalanced data and Random Forest classification this workflow emerges as an appealing feature selection strategy for survival prediction within radiomics studies. © 2020 IEEE.

The severe spread of the COVID-19 pandemic has created a situation of public health emergency and global awareness. In our research, we analyzed the demographical factors affecting the global pandemic spread along with the features that lead to death due to the infection. Modeling results stipulate that the mortality rate increase as the age increase and it is found that most of the death cases belong to the age group 60-80. Cluster-based analysis of age groups is also conducted to analyze the maximum targeted age-groups. An association between positive COVID-19 cases and deceased cases are also presented, with the impact on male and female death cases due to corona. Additionally, we have also presented an artificial intelligence-based statistical approach to predict the survival chances of corona infected people in South Korea with the analysis of the impact on the exploratory factors, including age-groups, gender, temporal evolution, etc. To analyze the coronavirus cases, we applied machine learning with hyperparameters tuning and deep learning models with an autoencoder-based approach for estimating the influence of the disparate features on the spread of the disease and predict the survival possibilities of the quarantined patients in isolation. The model calibrated in the study is based on positive corona infection cases and presents the analysis over different aspects that proven to be impactful to analyze the temporal trends in the current situation along with the exploration of deceased cases due to coronavirus. Analysis delineates key points in the outbreak spreading, indicating that the models driven by machine intelligence and deep learning can be effective in providing a quantitative view of the epidemical outbreak.

BACKGROUND Investigating molecular biomarkers that accurately predict prognosis is of considerable clinical significance. Accumulating evidence suggests that long non-coding ribonucleic acids (lncRNAs) are frequently aberrantly expressed in colorectal cancer (CRC). AIM To elucidate the prognostic function of multiple lncRNAs serving as biomarkers in CRC. METHODS We performed lncRNA expression profiling using the lncRNA mining approach in large CRC cohorts from The Cancer Genome Atlas (TCGA) database. Receiver operating characteristic analysis was performed to identify the optimal cutoff point at which patients could be classified into the high-risk or low-risk groups. Based on the Cox coefficient of the individual lncRNAs, we identified a nine-lncRNA signature that was associated with the survival of CRC patients in the training set (n = 175). The prognostic value of this nine-lncRNA signature was validated in the testing set (n = 174) and TCGA set (n = 349). The prognostic models, consisting of these nine CRC-specific lncRNAs, performed well for risk stratification in the testing set and TCGA set. Time-dependent receiver operating characteristic analysis indicated that this predictive model had good performance. RESULTS Multivariate Cox regression and stratification analysis demonstrated that this nine-lncRNA signature was independent of other clinical features in predicting overall survival. Functional enrichment analysis of Kyoto Encyclopedia of Genes and Genomes pathways and Gene Ontology terms further indicated that these nine prognostic lncRNAs were closely associated with carcinogenesis-associated pathways and biological functions in CRC. CONCLUSION A nine-lncRNA expression signature was identified and validated that could improve the prognosis prediction of CRC, thereby providing potential prognostic biomarkers and efficient therapeutic targets for patients with CRC.

Introduction A machine learning technique that imitates neural system and brain can provide better than traditional methods like logistic regression for survival prediction and create an algorithm by determining influential factors. Aim To determine the influential factors on survival time of palliative care cancer patients and to compare two statistical methods for better prediction of survival. Methods One-year data is gathered from the patients that we followed in the palliative care clinic of our hospital (2017-2018) (n = 189). All data were retrospectively evaluated. After descriptive statistics, we used Pearson and Spearman correlations for parametric and non-parametric variables. The Artificial Neural Networks (ANN) and logistic regression model were applied to parameters which have a significant correlation with short survival. Results Significantly correlated variables with short survival were Palliative Performance Scale (PPS), Edmonton Symptom Assessment System (ESAS), Karnofsky Performance Scale (KPS), brain, liver, and distant metastasis, hemogram parameters, cero-reactive protein (CRP) and albumin (ALB). ANN model showed 89.3% prediction accuracy while the logistic regression model showed 73.0%. ANN model achieved a better AUC value of 0.86 than logistic regression model (0.76). Discussion There are several prognostic evaluation tools such as PPS, KPS, CRP, albumin, leukocytes, neutrophil were reported several studies as survival-related parameters in logistic regression models, also. Many studies compare ANN with logistic regression. When we evaluated these parameters totally, we observed the same relations with survival then we used the same parameters in the ANN model. The effectivity of the survival prediction models can be improved with the use of ANN. Conclusion ANN provides a more accurate estimation than logistic regression. ANN model is an important statistical method for survival prediction of cancer patients.

In the last years, several scoring systems based on pre- and post-transplant parameters have been developed to predict early post-LT graft function. However, some of them showed poor diagnostic abilities. This study aims to evaluate the role of the comprehensive complication index (CCI) as a useful scoring system for accurately predicting 90-day and 1-year graft loss after liver transplantation. A training set (n = 1262) and a validation set (n = 520) were obtained. The study was registered at https://www.ClinicalTrials.gov (ID: NCT03723317). CCI exhibited the best diagnostic performance for 90 days in the training (AUC = 0.94; p p p p p Clinical Trial Notification: NCT03723317.

Highlights • Machine learning models might be a better analytic approach in cervical cancer prognostic prediction than traditional methods. • Our models can provide multitask predictions, which can estimate the individual probability of overall survival, overall recurrence, and site-specific recurrence as well as RFS and OS times at the same time. • A web-based calculator was developed and externally validated to predict prognosis for cervical cancer., Background Machine learning (ML) has been gradually integrated into oncologic research but seldom applied to predict cervical cancer (CC), and no model has been reported to predict survival and site-specific recurrence simultaneously. Thus, we aimed to develop ML models to predict survival and site-specific recurrence in CC and to guide individual surveillance. Methods We retrospectively collected data on CC patients from 2006 to 2017 in four hospitals. The survival or recurrence predictive value of the variables was analyzed using multivariate Cox, principal component, and K-means clustering analyses. The predictive performances of eight ML models were compared with logistic or Cox models. A novel web-based predictive calculator was developed based on the ML algorithms. Results This study included 5112 women for analysis (268 deaths, 343 recurrences): (1) For site-specific recurrence, larger tumor size was associated with local recurrence, while positive lymph nodes were associated with distant recurrence. (2) The ML models exhibited better prognostic predictive performance than traditional models. (3) The ML models were superior to traditional models when multiple variables were used. (4) A novel predictive web-based calculator was developed and externally validated to predict survival and site-specific recurrence. Conclusion ML models might be a better analytic approach in CC prognostic prediction than traditional models as they can predict survival and site-specific recurrence simultaneously, especially when using multiple variables. Moreover, our novel web-based calculator may provide clinicians with useful information and help them make individual postoperative follow-up plans and further treatment strategies.

Background & Aims Acute-on-chronic liver failure (ACLF) is usually associated with a precipitating event and results in the failure of other organ systems and high short-term mortality. Current prediction models fail to adequately estimate prognosis and need for liver transplantation (LT) in ACLF. This study develops and validates a dynamic prediction model for patients with ACLF that uses both longitudinal and survival data. Methods Adult patients on the UNOS waitlist for LT between 11.01.2016-31.12.2019 were included. Repeated model for end-stage liver disease-sodium (MELD-Na) measurements were jointly modelled with Cox survival analysis to develop the ACLF joint model (ACLF-JM). Model validation was carried out using separate testing data with area under curve (AUC) and prediction errors. An online ACLF-JM tool was created for clinical application. Results In total, 30,533 patients were included. ACLF grade 1 to 3 was present in 16.4%, 10.4% and 6.2% of patients, respectively. The ACLF-JM predicted survival significantly (p, Graphical abstract, Highlights • ACLF is a dynamic disease that can rapidly change over time, which greatly influences patient survival without LT. • Currently, the MELD-Na score is used to prioritize patients for LT, but MELD-Na underestimates ACLF disease severity. • The ACLF joint model (ACLF-JM) was developed to dynamically predict survival. • The ACLF-JM significantly outperformed the MELD-Na score for the prediction of mortality on the LT waiting list. • The ACLF-JM can be used online to predict survival in individual patients.

Background Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database. Methods We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC). Findings The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset. Interpretation Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

Background Kidney transplantation is the optimal treatment for patients with end-stage renal disease. Short- and long-term kidney graft survival is influenced by a number of donor and recipient factors. Predicting the success of kidney transplantation is important for optimizing kidney allocation. Objective The aim of this study was to predict the risk of kidney graft failure across three temporal cohorts (within 1 year, within 5 years, and after 5 years following a transplant) based on donor and recipient characteristics. We analyzed a large data set comprising over 50,000 kidney transplants covering an approximate 20-year period. Methods We applied machine learning–based classification algorithms to develop prediction models for the risk of graft failure for three different temporal cohorts. Deep learning–based autoencoders were applied for data dimensionality reduction, which improved the prediction performance. The influence of features on graft survival for each cohort was studied by investigating a new nonoverlapping patient stratification approach. Results Our models predicted graft survival with area under the curve scores of 82% within 1 year, 69% within 5 years, and 81% within 17 years. The feature importance analysis elucidated the varying influence of clinical features on graft survival across the three different temporal cohorts. Conclusions In this study, we applied machine learning to develop risk prediction models for graft failure that demonstrated a high level of prediction performance. Acknowledging that these models performed better than those reported in the literature for existing risk prediction tools, future studies will focus on how best to incorporate these prediction models into clinical care algorithms to optimize the long-term health of kidney recipients.

Background: The Cox proportional hazards (CPH) model is the most commonly used statistical method for nasopharyngeal carcinoma (NPC) prognostication. Recently, machine learning (ML) models are increasingly adopted for this purpose. However, only a few studies have compared the performances between CPH and ML models. This study aimed at comparing CPH with two state-of-the-art ML algorithms, namely, conditional survival forest (CSF) and DeepSurv for disease progression prediction in NPC. Methods: From January 2010 to March 2013, 412 eligible NPC patients were reviewed. The entire dataset was split into training cohort and testing cohort in a ratio of 90%:10%. Ten features from patient-related, disease-related, and treatment-related data were used to train the models for progression-free survival (PFS) prediction. The model performance was compared using the concordance index (c-index), Brier score, and log-rank test based on the risk stratification results. Results: DeepSurv (c-index = 0.68, Brier score = 0.13, log-rank test p = 0.02) achieved the best performance compared to CSF (c-index = 0.63, Brier score = 0.14, log-rank test p = 0.38) and CPH (c-index = 0.57, Brier score = 0.15, log-rank test p = 0.81). Conclusions: Both CSF and DeepSurv outperformed CPH in our relatively small dataset. ML-based survival prediction may guide physicians in choosing the most suitable treatment strategy for NPC patients.

Improving the quality of life in terminal stage cancer patients and their families are at utmost importance. The End of Life Needs Assessment Form is adapted from Palliative Performance Scale; to assess patients' needs toward the end of their life. We studied for the first time the practicality, applicability and usefulness of this tool in a unique Turkish hospital providing services to patients from extensive number of countries in this region.

Contains fulltext : 175108.pdf (Publisher’s version ) (Open Access) BACKGROUND AND PURPOSE: In this study we investigated the interchangeability of planning CT and cone-beam CT (CBCT) extracted radiomic features. Furthermore, a previously described CT based prognostic radiomic signature for non-small cell lung cancer (NSCLC) patients using CBCT based features was validated. MATERIAL AND METHODS: One training dataset of 132 and two validation datasets of 62 and 94stage I-IV NSCLC patients were included. Interchangeability was assessed by performing a linear regression on CT and CBCT extracted features. A two-step correction was applied prior to model validation of a previously published radiomic signature. Results 13.3% (149 out of 1119) of the radiomic features, including all features of the previously published radiomic signature, showed an R2 above 0.85 between intermodal imaging techniques. For the radiomic signature, Kaplan-Meier curves were significantly different between groups with high and low prognostic value for both modalities. Harrell's concordance index was 0.69 for CT and 0.66 for CBCT models for dataset 1. Conclusions The results show that a subset of radiomic features extracted from CT and CBCT images are interchangeable using simple linear regression. Moreover, a previously developed radiomics signature has prognostic value for overall survival in three CBCT cohorts, showing the potential of CBCT radiomics to be used as prognostic imaging biomarker.

// Sebastien Rinaldetti 1 , Ralph Markus Wirtz 2 , Thomas Stefan Worst 3 , Markus Eckstein 4 , Cleo Aaron Weiss 5 , Johannes Breyer 6 , Wolfgang Otto 6 , Christian Bolenz 7 , Arndt Hartmann 4 and Philipp Erben 3 1 Department of Hematology and Oncology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 2 Stratifyer Molecular Pathology GmbH, 50935 Koln, Germany 3 Department of Urology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 4 Institute of Pathology, University Erlangen-Nuremberg, 91054 Erlangen, Germany 5 Institute of Pathology, University Medical Center Mannheim, Medical Faculty Mannheim, University of Heidelberg, 68167 Mannheim, Germany 6 Department of Urology, University of Regensburg, 93053 Regensburg, Germany 7 Department of Urology, University of Ulm, 89075 Ulm, Germany Correspondence to: Sebastien Rinaldetti, email: sebastienrinal@hotmail.com Keywords: FOXM1, muscle invasive bladder cancer, KI67, subclassification, survival prediction Received: December 28, 2016 Accepted: April 10, 2017 Published: April 24, 2017 ABSTRACT Forkhead box M1 (FOXM1) is a late cell cycle gene that plays a crucial role in carcinogenesis and chemotherapeutic drug resistance. In this study, the impact of FOXM1 expression on patient outcome was investigated for the first time in formalin fixed and paraffin embedded (FFPE) samples of chemotherapy naive muscle-invasive bladder cancer (MIBC) patients. Expression analyses were performed on the Mannheim cohort (n=84) and validated on the independent Chungbuk cohort (n=61). In a Cox’ proportional hazards model, a distinct FOXM1 expression cut-off dividing both cohorts in a ‘high-risk’ and ‘low-risk’ group has been determined. Multivariate analyses showed that FOXM1 is an independent risk factor for outcome prediction superior to the TNM system. The FOXM1 ‘high-risk’ group had a 4- to 7-fold increased risk of death (p