Year: 2022
Type: article
Abstract: 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.
Source: Communications Medicine
Authors: Wei Qiu, Hugh Chen, Ayse Berceste Dincer, Scott Lundberg, Matt Kaeberlein, Su-In Lee
Institutions: University of Washington, Microsoft (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,290
Awards: CAREER: Learning the Chromatin Network from ChIP-Seq Data, G1207158260, G1271175822, G1786123482, Collaborative Research: ABI Innovation: Interpretable Machine Learning to Identify Molecular Markers for Complex Phenotypes, Graduate Research Fellowship Program (GRFP), Interpretable Machine Learning to Identify Alzheimer's Disease Therapeutic Targets, Nathan Shock Ctr of Excellence in Basic Biology of Aging, ABI Innovation: A Probabilistic Approach to Meta-Analysis of Biological Network Interface, G5850737185, G6360247949, Opening the Black Box of Machine Learning Models, G8555350935, G9000002045, G9000075980
OpenAlex ID: W4300537824