Automatically explaining machine learning prediction results: a demonstration on type 2 diabetes risk prediction. Issue 1 (December 2016)

• Record Type: Journal Article
• Authors: Luo, Gang
• Is Part Of: Health information science and systems. Volume 4:Issue 1(2016)
• Page Start: 1
• Page End: 9
• Publication Date: 2016-12
• Subjects: Decision support techniques -- Patient care management -- Forecasting -- Machine learning -- Type 2 diabetes; Medical informatics -- Periodicals; Medicine -- Data processing -- Periodicals; Medical Informatics -- Periodicals; Medical informatics; Medicine -- Data processing; Periodicals; Electronic journals; 610.28
• DOI: 10.1186/s13755-016-0015-4
• Languages: English
• ISSNs: 2047-2501

Abstract

Abstract Background Predictive modeling is a key component of solutions to many healthcare problems. Among all predictive modeling approaches, machine learning methods often achieve the highest prediction accuracy, but suffer from a long-standing open problem precluding their widespread use in healthcare. Most machine learning models give no explanation for their prediction results, whereas interpretability is essential for a predictive model to be adopted in typical healthcare settings. Methods This paper presents the first complete method for automatically explaining results for any machine learning predictive model without degrading accuracy. We did a computer coding implementation of the method. Using the electronic medical record data set from the Practice Fusion diabetes classification competition containing patient records from all 50 states in the United States, we demonstrated the method on predicting type 2 diabetes diagnosis within the next year. Results For the champion machine learning model of the competition, our method explained prediction results for 87.4 % of patients who were correctly predicted by the model to have type 2 diabetes diagnosis within the next year. Conclusions Our demonstration showed the feasibility of automatically explaining results for any machine learning predictive model without degrading accuracy.