Towards machine learning for moral choice analysis in health economics: A literature review and research agenda.

BACKGROUND: Discrete choice models (DCMs) for moral choice analysis will likely lead to erroneous model outcomes and misguided policy recommendations, as only some characteristics of moral decision-making are considered. Machine learning (ML) is recently gaining interest in the field of discrete choice modelling. This paper explores the potential of combining DCMs and ML to study moral decision-making more accurately and better inform policy decisions in healthcare. METHODS: An interdisciplinary literature search across four databases - PubMed, Scopus, Web of Science, and Arxiv - was conducted to gather papers. Based on the Preferred Reporting Items for Systematic and Meta-analyses (PRISMA) guideline, studies were screened for eligibility on inclusion criteria and extracted attributes from eligible papers. Of the 6285 articles, we included 277 studies. RESULTS: DCMs have shortcomings in studying moral decision-making. Whilst the DCMs' mathematical elegance and behavioural appeal hold clear interpretations, the models do not account for the 'moral' cost and benefit in an individual's utility calculation. The literature showed that ML obtains higher predictive power, model flexibility, and ability to handle large and unstructured datasets. Combining the strengths of ML methods with DCMs has the potential for studying moral decision-making. CONCLUSIONS: By providing a research agenda, this paper highlights that ML has clear potential to i) find and deepen the utility specification of DCMs, and ii) enrich the insights extracted from DCMs by considering the intrapersonal determinants of moral decision-making.

Patient preferences for treatment of lumbar disc herniation: a discrete choice experiment.

OBJECTIVE: Lumbar discectomy is a frequently performed procedure to treat sciatica caused by lumbar disc herniation. Multiple surgical techniques are available, and the popularity of minimally invasive surgical techniques is increasing worldwide. Clinical outcomes between these techniques may not show any substantial differences. As lumbar discectomy is an elective procedure, patients' own preferences play an important role in determining the procedure they will undergo. The aims of the current study were to determine the relative preference weights patients apply to various attributes of lumbar discectomy, determine if patient preferences change after surgery, identify preference heterogeneity for choosing surgery for sciatica, and calculate patient willingness to pay for other attributes. METHODS: A discrete choice experiment (DCE) was conducted among patients with sciatica caused by lumbar disc herniation. A questionnaire was administered to patients before they underwent surgery and to an independent sample of patients who had already undergone surgery. The DCE required patients to choose between two surgical techniques or to opt out from 12 choice sets with alternating characteristic levels: waiting time for surgery, out-of-pocket costs, size of the scar, need of general anesthesia, need for hospitalization, effect on leg pain, and duration of the recovery period. RESULTS: A total of 287 patients were included in the DCE analysis. All attributes, except scar size, had a significant influence on the overall preferences of patients. The effect on leg pain was the most important characteristic in the decision for a surgical procedure (by 44.8%). The potential out-of-pocket costs for the procedure (28.8%), the wait time (12.8%), need for general anesthesia (7.5%), need for hospitalization (4.3%), and the recovery period (1.8%) followed. Preferences were independent of the scores on patient-reported outcome measures and baseline characteristics. Three latent classes could be identified with specific preference patterns. Willingness-to-pay was the highest for effectiveness on leg pain, with patients willing to pay €3133 for a treatment that has a 90% effectiveness instead of 70%. CONCLUSIONS: Effect on leg pain is the most important factor for patients in deciding to undergo surgery for sciatica. Not all proposed advantages of minimally invasive spine surgery (e.g., size of the scar, no need of general anesthesia) are necessarily perceived as advantages by patients. Spine surgeons should propose surgical techniques for sciatica, not only based on own ability and proposed eligibility, but also based on patient preferences as is part of shared decision making.