Communications Medicine · 2022 · 103 citations · 57 references
ComputingBiostatisticsData ScienceEpidemiologyMachine LearningPredictive AnalyticsEnsemble LearningEnsemble MethodsExplainable Machine LearningMortality AnalysisMortality ModelingRisk PredictionClinical Risk ScoresExplainable Artificial IntelligenceExternal Validation Of Risk ModelsInterpretable ModelingMachine Learning Prediction ModelsMortality PredictionPredictive Mortality ModelingRisk Prediction Scores
Background: Unlike linear models which are traditionally used to study all-cause mortality, complex machine learning models can capture non-linear interrelations and provide opportunities to identify unexplored risk factors. Explainable artificial intelligence can improve prediction accuracy over linear models and reveal great insights into outcomes like mortality. This paper comprehensively analyzes all-cause mortality by explaining complex machine learning models. Methods: We propose the IMPACT framework that uses XAI technique to explain a state-of-the-art tree ensemble mortality prediction model. We apply IMPACT to understand all-cause mortality for 1-, 3-, 5-, and 10-year follow-up times within the NHANES dataset, which contains 47,261 samples and 151 features. Results: We show that IMPACT models achieve higher accuracy than linear models and neural networks. Using IMPACT, we identify several overlooked risk factors and interaction effects. Furthermore, we identify relationships between laboratory features and mortality that may suggest adjusting established reference intervals. Finally, we develop highly accurate, efficient and interpretable mortality risk scores that can be used by medical professionals and individuals without medical expertise. We ensure generalizability by performing temporal validation of the mortality risk scores and external validation of important findings with the UK Biobank dataset. Conclusions: IMPACT's unique strength is the explainable prediction, which provides insights into the complex, non-linear relationships between mortality and features, while maintaining high accuracy. Our explainable risk scores could help individuals improve self-awareness of their health status and help clinicians identify patients with high risk. IMPACT takes a consequential step towards bringing contemporary developments in XAI to epidemiology.
57
Advances in neural information processing systems 7
Krzysztof J. Cios, Mark E. Shields · Neurocomputing · 1997 · 22.3K citations
Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness
Michiru Nishita, Seung‐Yeol Park, Tadashi Nishio et al. · Scientific Reports · 2017 · 16.1K citations · Full text
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations
Dermatologist-level classification of skin cancer with deep neural networks
Andre Esteva, Brett Kuprel, Roberto A. Novoa et al. · Nature · 2017 · 13.8K citations · Full text
From local explanations to global understanding with explainable AI for trees
Scott Lundberg, Gabriel Erion, Hugh Chen et al. · Nature Machine Intelligence · 2020 · 8.9K citations · Full text