Effectiveness and Cost-effectiveness of Artificial Intelligence–assisted Pathology for Prostate Cancer Diagnosis in Sweden: A Microsimulation Study

• Published in: European urology oncology
• Main Authors: Du, Xiaoyang, Hao, Shuang, Olsson, Henrik, Kartasalo, Kimmo, Mulliqi, Nita, Rai, Balram, Menges, Dominik, Heintz, Emelie, Egevad, Lars, Eklund, Martin, Clements, Mark
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 23-05-2024
• Subjects: Artificial intelligence; Cost effectiveness; Medicin och hälsovetenskap; Microsimulation; Pathology; Prostate cancer; Sweden; Pathology; Sweden; Microsimulation; Cost effectiveness; Artificial intelligence; Prostate cancer
• ISSN: 2588-9311; 2588-9311
• DOI: 10.1016/j.euo.2024.05.004

According to our simulation results, use of artificial intelligence to filter out benign biopsy cores in pathology examination for prostate cancer diagnosis would reduce the workload of pathologists, would not affect patient quality of life, and would save costs in Sweden.
Image-based artificial intelligence (AI) methods have shown high accuracy in prostate cancer (PCa) detection. Their impact on patient outcomes and cost effectiveness in comparison to human pathologists remains unknown. Our aim was to evaluate the effectiveness and cost-effectiveness of AI-assisted pathology for PCa diagnosis in Sweden.
We modeled quadrennial prostate-specific antigen (PSA) screening for men between the ages of 50 and 74 yr over a lifetime horizon using a health care perspective. Men with PSA ≥3 ng/ml were referred for standard biopsy (SBx), for which cores were either examined via AI followed by a pathologist for AI-labeled positive cores, or a pathologist alone. The AI performance characteristics were estimated using an internal STHLM3 validation data set. Outcome measures included the number of tests, PCa incidence and mortality, overdiagnosis, quality-adjusted life years (QALYs), and the potential reduction in pathologist-evaluated biopsy cores if AI were used. Cost-effectiveness was assessed using the incremental cost-effectiveness ratio.
In comparison to a pathologist alone, the AI-assisted workflow increased the number of PSA tests, SBx procedures, and PCa deaths by ≤0.03%, and slightly reduced PCa incidence and overdiagnosis. AI would reduce the proportion of biopsy cores evaluated by a pathologist by 80%. At a cost of €10 per case, the AI-assisted workflow would cost less and result in <0.001% lower QALYs in comparison to a pathologist alone. The results were sensitive to the AI cost.
According to our model, AI-assisted pathology would significantly decrease the workload of pathologists, would not affect patient quality of life, and would yield cost savings in Sweden when compared to a human pathologist alone.
We compared outcomes for prostate cancer patients and relevant costs for two methods of assessing prostate biopsies in Sweden: (1) artificial intelligence (AI) technology and review of positive biopsies by a human pathologist; and (2) a human pathologist alone for all biopsies. We found that addition of AI would reduce the pathology workload and save money, and would not affect patient outcomes when compared to a human pathologist alone. The results suggest that adding AI to prostate pathology in Sweden would save costs.