Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques

Abstract

Background Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians. Methods In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques. Results Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years. Conclusion In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables. Trial registration Retrospective data were provided by the Scientific Registry of Transplant Recipients under Data Use Agreement number 9477 for analysis of risk factors after liver transplantation.

iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients

“…7 demonstrate that the proposed deep learning method can achieve much superior performance over the benchmark CPH model and the RSF model. A previous study 43 demonstrated that the CPH model normally has limited performance owing to the proportional hazard assumption, and the RSF model is more suitable for complicated applications as it can build a nonlinear relationship between the variables and outcomes. However, RSF is a nondifferentiable model and is widely recognized in processing discrete variables (e.g., the symptoms and comorbidities investigated in this study).…”

Machine Learning Applications in Solid Organ Transplantation and Related Complications

“…At its most basic level, machine learning may not offer improvement over currently existing statistical methods. Kantidakis et al (22) demonstrated only a marginal improvement in IBS and C-index for predicting survival in kidney transplants with their advanced computational models; Miller et al (31) demonstrated no added benefit of their models to current risk indices.…”

“…( 30 ) generated a tree of predictors for cardiac transplant and Kantidakis et al. ( 22 ) demonstrated improved predictability using random forest survival analysis in kidney transplant compared with Cox models. Bertsimas et al.…”

“…Predicted patient survivorship and outcomes are an inseparable part of these discussions; machine learning may be able to offer more equitable estimates–and possible inclusion of alternative outcomes–to guide both individual and system-wide organ allocation. Several authors have validated their work on national datasets ( 16 , 17 , 22 , 31 ) and would benefit from trials of integration of these models into electronic medical records to help guide the physician-patient discussion. Eventual changes to national allocation algorithms would require both further validation and weighting of stake holder realities.…”

“…Secondly, machine learning models may fail to offer improvement over current models. As mentioned above, multiple studies have no additional benefit in predictive ability despite the extra computing power ( 22 , 31 , 40 ).…”