Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Nov 8;13:6753. doi: 10.1038/s41467-022-34275-9

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 3 — a The threshold for splitting the patients’ prediction scores to low and high is tuned in the BCCA cross-validation. Bottom: The sorted prediction scores of the patients, versus the percentage of patients classified below the threshold. Top: The cross-validation sensitivity of the system, versus the percentage of patients classified below the threshold (i.e., classified as low-PS), showing a trade-off between the two. The threshold was selected as 0.5, resulting in a sensitivity of 0.92 for BCCA-CV with 58% of the patients in the low-PS group. b Applying the selected threshold to the BCCA test patients (top) and MA31 patients (bottom). Following the system’s predictions allows the pathologists to focus on reviewing the cases classified as low-PS by the system and positive by the pathologist, which may be prone to miss-interpretation or deficient PD-L1 staining. After removing the discordant cases from the analysis, the sensitivity was increased (BCCA-test-con and MA31-con), revealing the inter-pathologist variability. In addition to quality assurance, the system could be used to allow pathologists to spare IHC staining and interpretation from more than 70% of the patients while retaining 100% sensitivity for PD-L1 expression in MA31.