Efficacy Evaluation of Artificial Intelligence-Assisted Breast Cancer Imaging Diagnosis and Exploration of Doctor-Patient Mental Health Interaction Mechanism
Xupeng Lu, Junxiu Wang, Hazirah Bee bt Yusof Alia, Jingang LiuAbstract
Objective
Breast cancer screening inevitably brings intense psychological pressure and frequent emotional fluctuations to suspected patients, triggering unstable mental states and seriously threatening individual mental health during clinical diagnosis. This study evaluates the diagnostic efficacy of artificial intelligence-assisted breast cancer imaging technology. It further explores the internal doctor-patient psychological emotional interaction mechanism, aiming to reduce patients’ diagnostic psychological pressure and comprehensively improve their overall mental health status.
Subjects and Methods
This study selects clinical breast cancer screening patients and professional imaging clinicians as formal research subjects. It adopts controlled diagnostic experiments and standardized psychological scale evaluation methods. It compares the diagnostic accuracy and efficiency of traditional and AI-assisted imaging modes, and collects valid data on doctors’ and patients’ psychological pressure, emotional changes and real-time mental states throughout the diagnosis process.
Results
AI-assisted imaging diagnosis significantly improves clinical diagnostic efficiency and accuracy. It effectively relieves patients’ diagnostic anxiety and cumulative psychological pressure, stabilizes their negative mental states caused by disease concerns, and reduces clinicians’ long-term working psychological burden, thereby comprehensively optimizing the overall mental health level of both doctors and patients.
Conclusions
Artificial intelligence-assisted breast cancer imaging diagnosis possesses superior and reliable clinical efficacy. The benign doctor-patient psychological interaction formed by AI intervention can effectively alleviate bilateral psychological pressure, regulate abnormal mental states of both parties, and provide a novel practical clinical strategy for optimizing diagnostic experience and protecting doctor-patient mental health.
Acknowledgements
This research was supported by 1. Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi “Research on Key Technologies in Deep Learning-Based Radiomics for Quantitative Analysis of Breast Cancer Diagnosis and Prognosis” (2023L354); 2. Taiyuan Institute of Technology Scientific Research Initial Funding “Research on Key Technologies for AI-Based Quantitative Analysis of Breast Cancer Diagnosis and Prognosis” (2023KJ041); 3. Program for the Discipline Leaders of Taiyuan Institute of Technology “Research on a Multimodal Radiomics Deep Learning for Molecular Subtyping and Treatment Response Prediction in Breast Cancer” (24020105).
Corresponding Author
Junxiu Wang, Taiyuan Institute of Technology, Taiyuan 030008, Shanxi, China.