BAIT: A New Medical Decision Support Technology Based on Discrete Choice Theory

Annebel Ten Broeke,Nicolaas Heyning,Elisabeth Kooi,Caspar Chorus,Jan Hulscher

doi:10.1177/0272989x211001320

Annebel Ten Broeke, Nicolaas Heyning + Show 3 more

Open Access

https://doi.org/10.1177/0272989x211001320

Copy DOI

Abstract

We present a novel way to codify medical expertise and to make it available to support medical decision making. Our approach is based on econometric techniques (known as conjoint analysis or discrete choice theory) developed to analyze and forecast consumer or patient behavior; we reconceptualize these techniques and put them to use to generate an explainable, tractable decision support system for medical experts. The approach works as follows: using choice experiments containing systematically composed hypothetical choice scenarios, we collect a set of expert decisions. Then we use those decisions to estimate the weights that experts implicitly assign to various decision factors. The resulting choice model is able to generate a probabilistic assessment for real-life decision situations, in combination with an explanation of which factors led to the assessment. The approach has several advantages, but also potential limitations, compared to rule-based methods and machine learning techniques. We illustrate the choice model approach to support medical decision making by applying it in the context of the difficult choice to proceed to surgery v. comfort care for a critically ill neonate.

Highlights

IntroductionWe present a novel way to codify medical expertise and to make it available to support medical decision making
We present a third way to capture and codify medical expertise and to make it available to support medical decision making
Behavioral Artificial Intelligence Technology (BAIT) presents a clear alternative to conventional approaches

Summary

Introduction

We present a novel way to codify medical expertise and to make it available to support medical decision making. The approach works as follows: using choice experiments containing systematically composed hypothetical choice scenarios, we collect a set of expert decisions. We illustrate the choice model approach to support medical decision making by applying it in the context of the difficult choice to proceed to surgery v. Our approach, called Behavioral Artificial Intelligence Technology (BAIT), uses choice analysis techniques traditionally employed to identify preferences of large groups of consumers, citizens, or patients and to make predictions regarding their future choice behavior.[7,8,9] We reconceptualize these econometric techniques and put them into practice for codifying the expertise of small groups of experts and supporting their decision making. To illustrate the workings of BAIT, we focus on one of the most difficult (moral) choices in medicine: to proceed to surgery v. comfort care for a critically ill neonate.[10,11]

Methods

Results

Conclusion