AUTHORS
Sangjoon Choi1(Equally contritubed as first authors.), Soo Ick Cho2(Equally contritubed as first authors.) , Minuk Ma2, Seonwook Park2, Sergio Pereira2, Brian Jaehong Aum2, Seunghwan Shin2, Kyunghyun Paeng2, Donggeun Yoo2, Wonkyung Jung2, Chan-Young Ock2, Se-Hoon Lee3, Yoon-La Choi4, Jin-Haeng Chung5, Tony S. Mok6, Hyojin Kim7, Seokhwi Kim8.
1. Department of Pathology and Translational Genomics, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
2. Lunit Inc., Seoul, Republic of Korea
3. Division of Hematology-Oncology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
4. Department of Pathology and Translational Genomics, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
5. Department of Pathology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea
6. Corresponding author:State Key Laboratory of Translational Oncology, Department of Clinical Oncology, Chinese University of Hong Kong, Hong Kong, China
7. Corresponding author: Department of Pathology, Seoul National University Bundang Hospital, 300 Gumi-dong, Bundang-gu, Seongnam 463-707, Republic of Korea.
8. Corresponding author: Department of Pathology, Ajou University School of Medicine, 164, Worldcup-ro, Yeongtong-gu, Suwon 16499, Republic of Korea.
PUBLISHED
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.