Precision radiotherapy via information integration of expert human knowledge and AI recommendation to optimize clinical decision making. (June 2022)

• Record Type: Journal Article
• Authors: Sun, Wenbo; Niraula, Dipesh; El Naqa, Issam; Ten Haken, Randall K; Dinov, Ivo D; Cuneo, Kyle; Jin, Judy (Jionghua)
• Is Part Of: Computer methods and programs in biomedicine. Volume 221(2022)
• Publication Date: 2022-06
• Subjects: Precision medicine -- Decision making -- Artificial intelligence -- Computer model calibration -- Gaussian process modeling; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106927
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Develop an integrative system to help physicians design radiotherapy by combining human knowledge and AI recommendation. Quantify the uncertainty of the treatment outcome based on black-box AI algorithms and physicians' prescriptions. Use the data analytic results to educate physicians and improve the AI recommendations. Demonstrate the proposed method using real patient data from radiotherapy. Abstract: In the precision medicine era, there is a growing need for precision radiotherapy where the planned radiation dose needs to be optimally determined by considering a myriad of patient-specific information in order to ensure treatment efficacy. Existing artificial-intelligence (AI) methods can recommend radiation dose prescriptions within the scope of this available information. However, treating physicians may not fully entrust the AI's recommended prescriptions due to known limitations or at instances when the AI recommendation may go beyond physicians' current knowledge. This paper lays out a systematic method to integrate expert human knowledge with AI recommendations for optimizing clinical decision making. Towards this goal, Gaussian process (GP) models are integrated with deep neural networks (DNNs) to quantify the uncertainty of the treatment outcomes given by physicians and AI recommendations, respectively, which are further used as a guideline to educate clinical physicians and improve AI models performance. The proposed method is demonstrated in a comprehensive dataset where patient-specific information and treatment outcomes are prospectively collected during radiotherapy of 67 non-small cell lung cancer (NSCLC) patients and are retrospectively analyzed.