|
|
 |
| |
|
|
|
Impact of AI Decision Support Systems on Clinical and Operational Outcomes in Chinese Hospitals |
|
|
|
PP: 1427-1436 |
|
|
|
doi:10.18576/amis/190616
|
|
|
|
Author(s) |
|
|
|
Dan He,
Mohamad Nasir Saludin,
Anas Tajudin,
Bao Liao,
|
|
|
|
Abstract |
|
|
| This study evaluates the effects of AI decision support systems on clinical and operational performance in Chinese hospitals. These hospitals face exceptionally high patient volumes and resource constraints, where efficiency gains are critical to sustaining care quality and patient safety. The research aimed to address the problem of limited empirical evidence on how AI impacts diagnostic accuracy, decision-making speed, and user adoption in such demanding healthcare contexts. A quantitative survey design was employed, collecting responses from 270 healthcare professionals across multiple departments. Data analysis included descriptive statistics, ANOVA, Levene’s test, and multiple regression to assess variations in perceptions and predictors of AI adoption. Findings indicate that AI improves diagnostic precision and accelerates decision-making, with broad acceptance across roles and levels of experience. ANOVA results showed no significant departmental differences in perceptions of AI system access speed (F = 2.12, p = 0.079), while Levene’s test confirmed homogeneity of variances (p = 0.722). Regression analysis further revealed that neither self-designated role nor years of experience were significant predictors of adoption attitudes, with the model explaining less than 1% of the variance (R2 = 0.0034, adj. R2 = −0.0041). These results suggest that contextual and organizational factors may play a more decisive role in shaping attitudes toward AI implementation than individual professional characteristics. The study highlights the potential of AI decision support systems to enhance diagnostic accuracy and operational efficiency in resource-constrained healthcare settings. However, effective integration requires targeted training programs and organizational strategies to address contextual barriers to adoption. By systematically evaluating AI’s clinical and organizational impact, this research provides evidence-based insights for hospitals seeking to leverage AI for sustainable improvements in patient care. |
|
|
|
|
|
|
|
