Search

Purpose: This study aims to identify key genes regulating tumor infiltrating plasma cells (PC) and provide new insights for innovative immunotherapy. Methods: Key genes related to PC were identified using machine learning in lung adenocarcinoma (LUAD) patients. A prognostic model called PC scores was developed using TCGA data and validated with GEO cohorts. We assessed the molecular background, immune features, and drug sensitivity of the high PC scores group. Real-time PCR was utilized to assess the expression of hub genes in both localized LUAD patients and LUAD cell lines. Results: We constructed PC scores based on seventeen PC-related hub genes (ELOVL6, MFI2, FURIN, DOK1, ERO1LB, CLEC7A, ZNF431, KIAA1324, NUCB2, TXNDC11, ICAM3, CR2, CLIC6, CARNS1, P2RY13, KLF15, and SLC24A4). Higher age, TNM stage, and PC scores independently predicted shorter overall survival. The AUC value of PC scores for one year, three years, and five years of overall survival were 0.713, 0.716, and 0.690, separately. The nomogram model that integrated age, stage, and PC scores showed significantly higher predictive value than stage alone (P < 0.01). High PC scores group exhibited an immune suppressing microenvironment with lower B, CD8 + T, CD4 + T, and dendritic cell infiltration. Docetaxel, gefitinib, and erlotinib had lower IC50 in high PC groups (P < 0.001). After validation through the local cohort and in vitro experiments, we ultimately confirmed three key potential targets: MFI2, KLF15, and CLEC7A. Conclusion: We proposed a prediction mode which can effectively identify high-risk LUAD patients and found three novel genes closely correlated with PC tumor infiltration. [ABSTRACT FROM AUTHOR]

Accurate corrections for ionospheric total electron content (TEC) and early warning information are crucial for global navigation satellite system (GNSS) applications under the influence of space weather. In this study, we propose to use a new machine learning model—the Prophet model, to predict the global ionospheric TEC by establishing a short-term ionospheric prediction model. We use 15th-order spherical harmonic coefficients provided by the Center for Orbit Determination in Europe (CODE) as the training data set. Historical spherical harmonic coefficient data from 7 days, 15 days, and 30 days are used as the training set to model and predict 256 spherical harmonic coefficients. We use the predicted coefficients to generate a global ionospheric TEC forecast map based on the spherical harmonic function model and select a year with low solar activity (63.4 < F10.7 < 81.8) and a year with the high solar activity (79.5 < F10.7 < 255.0) to carry out a sliding 2-day forecast experiment. Meanwhile, we verify the model performance by comparing the forecasting results with the CODE forecast product (COPG) and final product (CODG). The results show that we obtain the best predictions by using 15 days of historical data as the training set. Compared with the results of CODE'S 1-Day (C1PG) and CODE'S 2-Day (C2PG). The number of days with RMSE better than COPG on the first and second day of the low-solar-activity year is 151 and 158 days, respectively. This statistic for high-solar-activity year is 183 days and 135 days. [ABSTRACT FROM AUTHOR]

This article discusses the use of machine learning methods to predict intraventricular hemorrhage (IVH) in preterm infants. IVH is a common complication of preterm birth and is associated with adverse neurodevelopmental outcomes. The study used electronic medical records and antenatal data to develop a predictive model for IVH. The model achieved good accuracy and stability, with an area under the curve (AUC) of 0.88. The study identified several important risk factors for IVH, including gestational age, birth weight, hepatitis B and C infection, and red cell distribution width. However, the study has limitations, including being a single-center study and potential selection bias. Further research is needed to validate and improve the predictive model. [Extracted from the article]

Background: Mitochondrial outer membrane permeabilisation (MOMP) plays a pivotal role in cellular death and immune activation. A deeper understanding of the impact of tumour MOMP on immunity will aid in guiding more effective immunotherapeutic strategies. Methods: A comprehensive pan‐cancer dataset comprising 30 cancer‐type transcriptomic cohorts, 20 immunotherapy transcriptomic cohorts and three immunotherapy scRNA‐seq datasets was collected and analysed to determine the influence of tumour MOMP activity on clinical prognosis, immune infiltration and immunotherapy effectiveness. Leveraging 65 scRNA‐Seq datasets, the MOMP signature (MOMP.Sig) was developed to accurately reflect tumour MOMP activity. The clinical predictive value of MOMP.Sig was explored through machine learning models. Integration of the MOMP.Sig model and a pan‐cancer immunotherapy CRISPR screen further investigated potential targets to overcome immunotherapy resistance, which subsequently underwent clinical validation. Results: Our research revealed that elevated MOMP activity reduces mortality risk in cancer patients, drives the formation of an anti‐tumour immune environment and enhances the response to immunotherapy. This finding emphasises the potential clinical application value of MOMP activity in immunotherapy. MOMP.Sig, offering a more precise indicator of tumour cell MOMP activity, demonstrated outstanding predictive efficacy in machine‐learning models. Moreover, with the assistance of the MOMP.Sig model, FOXO1 was identified as a core modulator that promotes immune resistance. Finally, these findings were successfully validated in clinical immunotherapy cohorts of skin cutaneous melanoma and triple‐negative breast cancer patients. Conclusions: This study enhances our understanding of MOMP activity in immune modulation, providing valuable insights for more effective immunotherapeutic strategies across diverse tumours. [ABSTRACT FROM AUTHOR]

Intensive care unit (ICU) readmission of patients following liver transplantation (LT) is associated with poor outcomes. However, its risk factors remain unclarified. Nowadays, machine learning methods are widely used in many aspects of medical health. This study aims to develop a reliable prognostic model for ICU readmission for post-LT patients using machine learning methods. In this paper, a single center cohort (N = 5 4 3) was studied, of which 5.9% (N = 3 2) were readmitted to the ICU during hospitalization for LT. A retrospective review of baseline and perioperative factors possibly related to ICU readmission was performed. Three feature selection techniques were used to detect the best features influencing ICU readmission. Moreover, seven machine learning classifiers were proposed and compared to detect the risk of ICU readmission. Alanine transaminase (ALT) at hospital admission, intraoperative fresh frozen plasma (FFP) and red blood cell (RBC) transfusion, and N-Terminal pro-brain natriuretic peptide (NT-proBNP) after LT were found to be essential features for ICU readmission risk prediction. And the stacking model produced the best performance, identifying patients that were readmitted to the ICU after LT at an accuracy of 97.50%, precision of 96.34%, recall of 96.32%, and F1-score of 96.32%. RBC transfusion is the most crucial feature of the stacking classification model, which produced the best performance with overall accuracy, precision, recall, and F1-score of 88.49%, 88.66%, 76.01%, and 81.84%, respectively. [ABSTRACT FROM AUTHOR]

A machine learning‐based microwave spectrum detection method based on the nitrogen vacancy (NV) color centers in diamonds is proposed. The functional relationship between the fluorescence spectrum and standard microwave spectrum is established. The response matrix is calculated using the Tikhonov regularization technique, and an unknown microwave spectrum is reconstructed. Diamond particles with a size of only 5 × 5 μm2 are placed in the microfluidic structures. Consequently, the frequency detection range of the microwave spectrum is from 2.892 to 6.214 GHz with a resolution of 22 kHz. The proposed research opens new paths for microwave spectrum detection and imaging at the microscopic scale. [ABSTRACT FROM AUTHOR]

Damping technology has been widely used because of its good vibration control effect. However, due to the strong nonlinearity of the added dampers, accurately predicting the seismic response of damped structures remains a challenge. This study investigates the application of interpretable machine learning (ML)-based and deep learning-based approaches to the prediction of the maximum inter-storey displacement of a damped structure. A comprehensive database consisting of 13,855 structural responses to ground motions was collected. Seven traditional interpretable ML algorithms including random forest and extreme gradient boosting (XGBoost), a convolutional neural network based on large receptive field, and seismic wave transformer (SWT) model based on a transformer network were developed. The predictions show that the error of the SWT based on unsupervised feature extraction is reduced by 50.90% compared with that of the optimal XGBoost in ensemble learning. Although the SWT has the highest global accuracy, XGBoost is found to have a smaller error when the structure is in a linear state with peak ground acceleration as partition index, so an aggregation model (AM)-based structural response prediction method was also proposed. The accuracy of the AM improved by 27.95% compared with that of the SWT. In contrast with other ML models, the proposed AM is more advantageous in terms of computational efficiency and accuracy. • Numerical model of a damped steel frame was developed using OpenSees based on shaking table test results. • A prediction dataset was built based on the numerical results of a damped structure. • Seven interpretable machine learning-based techniques were utilised to predict the maximum structural inter-storey drift. • The deep learning algorithm based on unsupervised feature extraction can obtain more satisfactory results when the structure enters strong nonlinearity. • The developed aggregation model exhibits higher prediction accuracy. [ABSTRACT FROM AUTHOR]

Cumin and fennel are two types of food raw materials that have similar appearances but great differences in efficacy. Therefore, the efficient identification of these two types of food is very important to the related food processing industry and the development of food detection technology. In this study, a deep learning algorithm was designed to process Fourier NIR spectral data for the classification of cumin and fennel. The method was based on the difference in the signal intensity in NIR spectra between cumin and fennel, and the identification was performed by combining the improved multiscale fusion convolutional neural network (MCNN) and the bidirectional long-short-term memory network (BILSTM) based on NIR spectra. The classification accuracies of the MCNN and BILSTM models were 100% and 98.57%, respectively. The models have high sensitivity and fast analysis speed, which directly promote the development of real-time identification technology of cumin and fennel and verify the feasibility of deep learning algorithms in the field of food detection. [ABSTRACT FROM AUTHOR]