A software package for simple and rigorous survival machine learning analysis in biomedical research

Cancer Survival Prediction through Multifactorial Analysis with Machine Learning

survkl: an R package for transfer-learning-based integrated Cox models

The survkl software is introduced, which enables the incorporation of external summary-level information with newly collected time-to-event data to support more robust and accurate predictions in survival analysis.

Integration of Advanced Machine Learning and Statistical Methods for High-Dimensional Genomic Data Analysis

Introduction: The growing volume of high-throughput genomic data has enabled opportunities for cancer prognosis, patient stratification and biomarker identification. But gene expression data typically consist of thousands of molecular variables and relatively few patient observations, making the data analytically challenging in terms of dimensionality, redundancy, noise, overfitting, and interpretability. To overcome these problems this work proposes a hybrid statistical and machine-learning framework to analyze breast cancer gene-expression profiles. Methodology: The proposed workflow was tested on the dataset of Molecular Taxonomy of Breast Cancer International Consortium (METABRIC), that combines genomic measurements with related clinical data. The data preparation stages included missing-value treatment, standardisation of features, variance-based filtering, hypothesis-driven statistical screening based on t-tests and analysis of variance (ANOVA), correlation analysis, and dimensionality reduction using principal component analysis. After feature engineering, several predictive and exploratory algorithms were designed, such as: Random Forest, Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), K-Means clustering, and Ensemble Learning. The accuracy, precision, recall, F1 score, Receiver Operating Characteristic Area Under the Curve (ROC-AUC), cross validation performance and silhouette coefficient measures were used to assess model effectiveness. Results: Experimental results showed that MLP classifier outperformed other classifiers in terms of prediction accuracy while ensemble model resulted in the best ROC-AUC value. Conclusion: The findings suggest that statistical feature selection combined with machine learning-based feature importance analysis can boost predictive power while simultaneously providing greater importance for biologically relevant features. The overall proposed framework offers a comprehensive strategy for genomic classification, prioritisation of candidates as biomarkers, and the creation of data-driven decision-support tools in the context of breast cancer research and precision oncology applications.

A Repeated-Evaluation Comparison of Traditional, Machine Learning, and Deep Learning Survival Models Across Static and Longitudinal Data

Survival analysis plays a central role in medical research. Although the Cox proportional hazards (CoxPH) model remains the standard approach, machine learning and deep learning methods have been increasingly adopted. However, many published comparisons have relied on a single train–test split, which may produce unreliable performance estimates, particularly for unstable modelling approaches. This study compared CoxPH (LASSO-selected), Random Survival Forest (RSF), and Long Short-Term Memory (LSTM) networks using four survival datasets: breast cancer (n=4024), heart failure (n=299), recidivism (n=4618), and the Mayo Clinic Primary Biliary Cholangitis Sequential Dataset (PBC2; n=312) containing time-varying covariates. Model performance was evaluated using a two-stage protocol comprising a conventional 80–20 stratified train–test split followed by 100 repeated stratified 80–20 train–test splits. Performance was assessed using the concordance index (C-index), integrated Brier score (IBS), and time-dependent area under the receiver operating characteristic curve (AUC), with statistical significance determined through distributional assumption testing, adaptive omnibus tests, and Bonferroni-adjusted pairwise comparisons. For the three static datasets, single train–test splits suggested moderate LSTM performance (C-index: 0.65–0.70); however, repeated evaluation showed that this finding was not robust. Across 100 iterations, CoxPH and RSF consistently outperformed LSTM (all p<0.001), achieving mean C-index values ranging from 0.66 to 0.73 compared with 0.31 to 0.42 for LSTM, with very large effect sizes (Cohen’s d: 6–30). In contrast, on the longitudinal PBC2 dataset, the LSTM-based model achieved the highest repeated C-index (0.806±0.040), compared with 0.777±0.042 for CoxPH and 0.779±0.040 for RSF, with only 1.2% performance degradation under repeated evaluation. These findings indicate that reliance on a single train–test split can produce unstable and potentially unrepresentative estimates of model performance. Traditional survival models were more accurate and stable for datasets containing only static baseline covariates, whereas the LSTM-based model showed higher discrimination on longitudinal survival data with genuine temporal structure, though this advantage is confounded with greater access to patient history and cannot be attributed to architecture alone. Overall, the results underscored the importance of repeated evaluation as a more reliable framework for comparing survival models, and are consistent with, though do not conclusively establish, the importance of matching model architecture to data characteristics.

Integrating Survival Forests, Survival Trees, and Promotion Time Cure Models: Evidence from Breast Cancer Patients in Paraíba, Brazil

Predicting time-to-event clinical outcomes with multivariate repeated measurements of patient-level covariates: A systematic review

OBJECTIVE Repeated measurements capture the progression of health over time and may inform survival prediction. The goal of this review is to identify and compare how the presented methodologies for survival prediction with repeated measurements have been applied to predict survival outcomes with multivariate structured repeated measurements and cluster them into families of methodologies. METHODS We performed a search on MEDLINE via Ovid, PubMed, Web of Science, and Embase. We included original peer-reviewed publications where a Time-To-Event (TTE) prediction model was developed, based on multivariate repeated measurements of health data. The protocol was registered in PROSPERO (CRD42024529572). The main outcome of interest was the strategy used for dealing with repeated measurements. We assigned a score to each methodology in terms of temporal modelling, ease of implementation, interpretability and explainability, flexibility, computational power, scalability, ability to deal with irregular sampling and dynamic prediction, based on the data extracted from the corresponding studies. RESULTS After screening 4029 records, we included 58 studies in the review. The studies were categorized based on the underlying survival models into traditional statistics and machine learning methodologies. In parallel, four families of methodologies to deal with repeated measurements were identified: joint models (statistics n = 18), deep learning based methods (machine learning n = 9), landmarking (statistics n = 13, machine learning n = 6) and data manipulation (statistics n = 3, machine learning n = 9). Statistical studies had a higher risk of bias, reported models trained on less longitudinal covariates and were based on smaller sample sizes, while machine learning could deal less often with irregular sampling of measurements. Joint models and deep learning were generally more suitable when dealing with complex temporal dependencies, while landmarking and data manipulation were simpler and computationally lighter options. CONCLUSIONS This systematic review identified and compared published studies that developed TTE prediction methodologies using repeated covariate measurements to predict clinical outcomes. Greater emphasis on external validation, transparent reporting, interpretability and explainability, and multimodal data integration is crucial to advance the field and enhance its impact on health outcomes.