Healthcare and Policy Design: Comparison of Clinical Guidelines Guidance and Machine Learning
Author(s)
Huttin C
Endepusresearchinc and Univ Aix Marseille, Cambridge, MA, USA
OBJECTIVES: This presentation discusses the generation of alternatives for integrating choice experiments for healthcare policy design (Huttin and Hausman, 2019; Huttin, 2014, 2020); best practices for value assessment framework consider discrete choice experiments as a major methodology to help economic evaluation of medical technologies, with multi stakeholders. METHODS: case studies are selected for decision support aiding for pharmaceuticals and medical devices policies. As the decision-making process for pharmacotherapies is not dominated anymore by pharmaceutical companies, even with the growing role of biotech, additional cases of medical technology are selected for their fast innovation rate: tests, in vitro devices,.... The selection of choice sets is performed to adjust heterogeneity of individual choices, codes are run to check the irrelevant alternative cases , this research is designed for user tools, technology or digital platforms. RESULTS: The first alternatives for a drug choice set uses data from a project on mixed logit on diabetic type II; the generation of alternatives is from the researcher 'sperspective (integrating controversies in guidelines, findings from machine learning, pharmacologic reommendations from pharmacists and physicians and limitations of data). Additional choice sets are test choices, disposition procedures and devices and take into account the competitive and conflictural context of various procedures and stages of digitalization. CONCLUSIONS: This case study approach provides insights on how the choice of researchers for generation of alternatives for discrete choice experiments can be useful for policy design and integration of various innovative pathways, facing the R&D ecosystem of life science and IT industries and resource allocation constraints. It provides a contribution to the design theory, called the C-K theory, proposed for public decision making process (e.g. Pluchinotta; Kazakcj, Giordano et Tsoukias, 2019; Ferreti et ales, 2019; Vanda et ales,2018) for applications in the field of health policies and help the design of main algorithms for medical markets.
Conference/Value in Health Info
2021-05, ISPOR 2021, Montreal, Canada
Value in Health, Volume 24, Issue 5, S1 (May 2021)
Code
PNS96
Topic
Health Service Delivery & Process of Care, Methodological & Statistical Research
Topic Subcategory
Artificial Intelligence, Machine Learning, Predictive Analytics, Treatment Patterns and Guidelines
Disease
Diabetes/Endocrine/Metabolic Disorders