Artificial intelligence–powered programmed death ligand 1 analyser reduces interobserver variation in tumour proportion score for non–small cell lung cancer with better prediction of immunotherapy response. (July 2022)

• Record Type: Journal Article
• Authors: Choi, Sangjoon; Cho, Soo Ick; Ma, Minuk; Park, Seonwook; Pereira, Sergio; Aum, Brian Jaehong; Shin, Seunghwan; Paeng, Kyunghyun; Yoo, Donggeun; Jung, Wonkyung; Ock, Chan-Young; Lee, Se-Hoon; Choi, Yoon-La; Chung, Jin-Haeng; Mok, Tony S.; Kim, Hyojin; Kim, Seokhwi
• Is Part Of: European journal of cancer. Volume 170(2022)
• Page Start: 17
• Page End: 26
• Publication Date: 2022-07
• Subjects: Artificial intelligence -- Deep learning -- PD-L1 -- Non–small cell lung cancer -- Digital pathology; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2022.04.011
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Background: Manual evaluation of programmed death ligand 1 (PD-L1) tumour proportion score (TPS) by pathologists is associated with interobserver bias. Objective: This study explored the role of artificial intelligence (AI)-powered TPS analyser in minimisation of interobserver variation and enhancement of therapeutic response prediction. Methods: A prototype model of an AI-powered TPS analyser was developed with a total of 802 non–small cell lung cancer (NSCLC) whole-slide images. Three independent board-certified pathologists labelled PD-L1 TPS in an external cohort of 479 NSCLC slides. For cases of disagreement between each pathologist and the AI model, the pathologists were asked to revise the TPS grade (<1%, 1%–49% and ≥50%) with AI assistance. The concordance rates among the pathologists with or without AI assistance and the effect of the AI-assisted revision on clinical outcome upon immune checkpoint inhibitor (ICI) treatment were evaluated. Results: Without AI assistance, pathologists concordantly classified TPS in 81.4% of the cases. They revised their initial interpretation by using the AI model for the disagreement cases between the pathologist and the AI model ( N = 91, 93 and 107 for each pathologist). The overall concordance rate among the pathologists was increased to 90.2% after the AI assistance ( P < 0.001). A reduction in hazard ratio for overall survival and progression-free survival upon ICI treatment was identified in the TPS subgroups after the AI-assisted TPS revision. Conclusion: The AI-powered TPS analyser assistance improves the pathologists' consensus of reading and prediction of the therapeutic response, raising a possibility of standardised approach for the accurate interpretation. Highlights: Inter-observer bias of PD-L1 reading limits prediction of clinical outcome of NSCLC. We developed an AI model to detect PD-L1 expression in tumour and to calculate TPS. Discrepancy among pathologists on TPS interpretation was reduced by AI assistance. AI-assisted TPS reading leads to better prediction of therapeutic outcome of ICI.