Ai-Powered Predictive Analytics In General Surgery: Improving Patient Safety And Surgical Outcomes

Abstract

Background: The role of AI-based predictive analytics in general surgery. The use of artificial intelligence (AI) tools in surgical environments is influenced by several factors including perceived usefulness, usability, and trust between professionals. This study focused on the core factors of acceptance and use of artificial intelligence-24 predictive analytics in surgery with the use of the technology acceptance model (TAM).

Methods: A cross-sectional quantitative survey was conducted on 273 healthcare providers (general surgeons, surgical residents, anesthesiologists, operating room nurses, and hospital administrators). A questionnaire was designed to measure the Perceived Usefulness (PU), Perceived Ease of Use (PEU), Trust, and Behavioral Intention (BI) to use AI. We measured the survey on a 5-point Likert scale and data analysis was performed using descriptive statistics, reliability testing (Cronbach’s Alpha), correlation analysis, and multiple regression modeling to find the relationship between the TAM factors and AI adoption.

Results: The results demonstrated that trust in AI (Trust_Q14) was the only significant predictor variable when considering the behavioral intention to use AI (p = 0.023), while perceived usefulness and ease of use did not significantly affect AI adoption. The Cronbach’s Alpha score (0.087) was low, which means the internal consistency of the survey instrument should be improved. The regression analysis found a low R-squared (0.029), which indicates that TAM is not the only factor that drives AI adoption; other factors like regulatory policies, ethical considerations, and institutional support systems may also be very important. Similarly, the Shapiro-Wilk normality test substantiated the non-normal distribution of the dataset (all variables: p < 0.05), necessitating the use of alternative analytical methods in forthcoming studies.

Conclusion: We identify trust as the dominant driver of AI adoption in surgical contexts and provide evidence of limitations in using TAM as a standalone framework for predicting adoption behavior. The results indicate that a commitment to support AI transparency, development of training programs, and setting up ethical regulatory frameworks will help build trust to adopt the AI [dimensional] X-ray imaging diagnosis solution. Marked limitations of the current model involved using TAM only, incorporating other external influencing factors, and using advanced statistical techniques in future research to provide further insights into AI adoption trends in surgery. While there are challenges to be overcome, AI-powered predictive analytics has the potential to improve patient safety, surgical procedure optimization, and healthcare decision-making