Personalized Cardiovascular Therapy With Ai

Abstract

Background: AI is the trend being adopted in cardiovascular care to assist in early diagnosis, risk prediction, and tailoring of treatment. Perceptions of both the patients and the clinicians are crucial when adopting AI-based personalized cardiovascular therapy successfully.

Objective: The purpose of the study was to measure the perception, acceptance, and demographic factors affecting the willingness to adopt AI-based personalized cardiovascular therapy and to test a newly written questionnaire to measure the levels of awareness, perceived benefits, trust, and willingness to adopt AI-based personalized cardiovascular therapy.

Methods: It was a mixed-methods cross-sectional study that was carried out among 283 cardiovascular patients and 283 cardiology healthcare professionals. The questionnaire applied was a structured one with four main scales (Awareness, Benefits, Trust, Willingness) as well as an open-ended one. Cronbach's alpha was used to measure internal consistency; the Kaiser-Meyer Olkin (KMO) test and Bartlett test of Sphericity were used to assess the validity. The normality tests were conducted to examine group differences. Independent samples t-tests, one-way ANOVA, Kruskal-Wallis, Chi-square, Pearson correlation, and multiple regression were conducted to examine group differences and predictors of willingness to adopt AI.

Results: The questionnaire was found to be highly reliable (Cronbach, α = 0.82-0.91) and strongly constructed (KMO = 0.83); so, the Bartlett p was less than 0.001. All constructs had normal distributions of data (p > 0.05). T reportedly have a higher awareness and perceived benefits than females ( p < 0.05). Trust and willingness depended strongly upon education level (p < 0.05), and age weakly affected the willingness to adopt. Awareness, benefits, trust, and willingness were positively correlated with each other (r = 0.66375). The regression analysis indicated that trust was the best predictor of willingness, then benefits, awareness, and age, which explained 74 percent of the variability in intent to adopt.

Conclusion: AI-based individualized cardiovascular treatment is strongly embraced by participants, especially when they trust it and have a belief in the perceived positive outcomes. The validated questionnaire proves to be reliable and apt to measure the acceptance of AI in a cardiology context. Perspectives to enhance comprehension, sustain data confidentiality, and augment clinician support should be practiced to enhance acceptance in a variety of populations