Developing patient-driven artificial intelligence based on personal rankings of care decision making steps

TL;DR

This paper introduces a novel methodology using patient self-ratings and statistical analysis to understand decision-making steps in healthcare, aiming to develop personalized AI support for patient care.

Contribution

It presents a new approach combining questionnaires and statistical patterns to analyze healthcare decision-making processes for AI development.

Findings

Significant differences in ratings based on respondent backgrounds.

Dependencies between initial ratings and subsequent reordering.

Methodology enables analysis of personalized care decision paths.

Abstract

We propose and experimentally motivate a new methodology to support decision-making processes in healthcare with artificial intelligence based on personal rankings of care decision making steps that can be identified with our methodology, questionnaire data and its statistical patterns. Our longitudinal quantitative cross-sectional three-stage study gathered self-ratings for 437 expression statements concerning healthcare situations on Likert scales in respect to "the need for help", "the advancement of health", "the hopefulness", "the indication of compassion" and "the health condition", and 45 answers about the person's demographics, health and wellbeing, also the duration of giving answers. Online respondents between 1 June 2020 and 29 June 2021 were recruited from Finnish patient and disabled people's organizations, other health-related organizations and professionals, and educational institutions (n=1075). With Kruskal-Wallis test, Wilcoxon rank-sum test (i.e., Mann-Whitney U test), Wilcoxon rank-sum pairwise test, Welch's t test and one-way analysis of variance (ANOVA) between groups test we identified statistically significant differences of ratings and their durations for each expression statement in respect to respondent groupings based on the answer values of each background question. Frequencies of the later reordering of rating rankings showed dependencies with ratings given earlier in respect to various interpretation task entities, interpretation dimensions and respondent groupings. Our methodology, questionnaire data and its statistical patterns enable analyzing with self-rated expression statements the representations of decision making steps in healthcare situations and their chaining, agglomeration and branching in knowledge entities of personalized care paths. Our results support building artificial intelligence solutions to address the patient's needs concerning care.