Integrating AI-Driven Clinical Decision Support Systems to Improve Diagnostic Accuracy and Treatment Planning in Healthcare
Loading...
Authors
Brown, Jr., Samuel
Issue Date
2026-05
Type
Dissertation
Language
en
Keywords
Healthcare Innovation & Delivery , Business, Engineering, Science, & Technological Innovation , AI-Driven Clinical Decision Support Systems , Diagnostic Accuracy , Treatment Planning
Alternative Title
Abstract
The purpose of this quantitative, correlational study was to examine the extent to which perceived ease of use, perceived usefulness, relative advantage, compatibility, and complexity predicted healthcare professionals’ intention to use artificial intelligence–driven Clinical Decision Support Systems (AI-CDSS) to improve diagnostic accuracy and treatment planning. Guided by an integrated framework combining the Technology Acceptance Model (TAM) and Diffusion of Innovation theory, this study investigated how these perceptions influenced behavioral intention to use AI-CDSS. Data were collected through an online survey administered to licensed healthcare professionals. Of the 152 individuals who accessed the survey, 109 responses met the inclusion criteria and were retained for analysis, resulting in a usable response rate of 71.7%. Multiple linear regression analysis showed that the overall model was statistically significant, F (5, 103) = 19.55, p < .001, explaining 48.7% of the variance in intention to use AI-CDSS (R² = .487, adjusted R² = .462). Relative advantage emerged as the strongest significant predictor, followed by complexity, whereas perceived ease of use, perceived usefulness, and compatibility were not statistically significant in the full model. Findings indicate that clinicians’ adoption intentions are influenced more by comparative value and manageable implementation burden than by usability or workflow alignment alone. Practical implications include emphasizing meaningful clinical advantage while reducing perceived complexity. Future research should examine trust, organizational readiness, and perceived risk using longitudinal and intervention-based designs.