Tyler J Loftus1, Amanda C Filiberto1, Yanjun Li2, Jeremy Balch1, Allyson C Cook3, Patrick J Tighe4, Philip A Efron1, Gilbert R Upchurch1, Parisa Rashidi5, Xiaolin Li2, Azra Bihorac6. 1. Department of Surgery, University of Florida Health, Gainesville, FL. 2. NSF Center for Big Learning, University of Florida, Gainesville, FL. 3. Department of Medicine, University of California, San Francisco, CA. 4. Departments of Anesthesiology, Orthopedics, and Information Systems/Operations Management, University of Florida Health, Gainesville, FL. 5. Departments of Biomedical Engineering, Computer and Information Science and Engineering, and Electrical and Computer Engineering, University of Florida, Gainesville, FL; Precision and Intelligence in Medicine, Department of Medicine, University of Florida Health, Gainesville, FL. 6. Department of Medicine, University of California, San Francisco, CA; Precision and Intelligence in Medicine, Department of Medicine, University of Florida Health, Gainesville, FL. Electronic address: abihorac@ufl.edu.
Abstract
BACKGROUND: Surgical patients incur preventable harm from cognitive and judgment errors made under time constraints and uncertainty regarding patients' diagnoses and predicted response to treatment. Decision analysis and techniques of reinforcement learning theoretically can mitigate these challenges but are poorly understood and rarely used clinically. This review seeks to promote an understanding of decision analysis and reinforcement learning by describing their use in the context of surgical decision-making. METHODS: Cochrane, EMBASE, and PubMed databases were searched from their inception to June 2019. Included were 41 articles about cognitive and diagnostic errors, decision-making, decision analysis, and machine-learning. The articles were assimilated into relevant categories according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. RESULTS: Requirements for time-consuming manual data entry and crude representations of individual patients and clinical context compromise many traditional decision-support tools. Decision analysis methods for calculating probability thresholds can inform population-based recommendations that jointly consider risks, benefits, costs, and patient values but lack precision for individual patient-centered decisions. Reinforcement learning, a machine-learning method that mimics human learning, can use a large set of patient-specific input data to identify actions yielding the greatest probability of achieving a goal. This methodology follows a sequence of events with uncertain conditions, offering potential advantages for personalized, patient-centered decision-making. Clinical application would require secure integration of multiple data sources and attention to ethical considerations regarding liability for errors and individual patient preferences. CONCLUSION: Traditional decision-support tools are ill-equipped to accommodate time constraints and uncertainty regarding diagnoses and the predicted response to treatment, both of which often impair surgical decision-making. Decision analysis and reinforcement learning have the potential to play complementary roles in delivering high-value surgical care through sound judgment and optimal decision-making.
BACKGROUND: Surgical patients incur preventable harm from cognitive and judgment errors made under time constraints and uncertainty regarding patients' diagnoses and predicted response to treatment. Decision analysis and techniques of reinforcement learning theoretically can mitigate these challenges but are poorly understood and rarely used clinically. This review seeks to promote an understanding of decision analysis and reinforcement learning by describing their use in the context of surgical decision-making. METHODS: Cochrane, EMBASE, and PubMed databases were searched from their inception to June 2019. Included were 41 articles about cognitive and diagnostic errors, decision-making, decision analysis, and machine-learning. The articles were assimilated into relevant categories according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines. RESULTS: Requirements for time-consuming manual data entry and crude representations of individual patients and clinical context compromise many traditional decision-support tools. Decision analysis methods for calculating probability thresholds can inform population-based recommendations that jointly consider risks, benefits, costs, and patient values but lack precision for individual patient-centered decisions. Reinforcement learning, a machine-learning method that mimics human learning, can use a large set of patient-specific input data to identify actions yielding the greatest probability of achieving a goal. This methodology follows a sequence of events with uncertain conditions, offering potential advantages for personalized, patient-centered decision-making. Clinical application would require secure integration of multiple data sources and attention to ethical considerations regarding liability for errors and individual patient preferences. CONCLUSION: Traditional decision-support tools are ill-equipped to accommodate time constraints and uncertainty regarding diagnoses and the predicted response to treatment, both of which often impair surgical decision-making. Decision analysis and reinforcement learning have the potential to play complementary roles in delivering high-value surgical care through sound judgment and optimal decision-making.
Authors: Matthew R Lammi; Brianne Aiello; Gregory T Burg; Tayyab Rehman; Ivor S Douglas; Arthur P Wheeler; Bennett P deBoisblanc Journal: Chest Date: 2015-10 Impact factor: 9.410
Authors: Armando E Giuliano; Kelly K Hunt; Karla V Ballman; Peter D Beitsch; Pat W Whitworth; Peter W Blumencranz; A Marilyn Leitch; Sukamal Saha; Linda M McCall; Monica Morrow Journal: JAMA Date: 2011-02-09 Impact factor: 56.272
Authors: Vivian S Lee; Kensaku Kawamoto; Rachel Hess; Charlton Park; Jeffrey Young; Cheri Hunter; Steven Johnson; Sandi Gulbransen; Christopher E Pelt; Devin J Horton; Kencee K Graves; Tom H Greene; Yoshimi Anzai; Robert C Pendleton Journal: JAMA Date: 2016-09-13 Impact factor: 56.272
Authors: Anas Taha; Vincent Ochs; Leos N Kayhan; Bassey Enodien; Daniel M Frey; Lukas Krähenbühl; Stephanie Taha-Mehlitz Journal: Medicina (Kaunas) Date: 2022-03-22 Impact factor: 2.948