CohortFinder: an open-source tool for data-driven partitioning of digital pathology and imaging cohorts to yield robust machine-learning models.

Batch effects (BEs) refer to systematic technical differences in data collection unrelated to biological variations whose noise is shown to negatively impact machine learning (ML) model generalizability. Here we release CohortFinder (http://cohortfinder.com), an open-source tool aimed at mitigating BEs via data-driven cohort partitioning. We demonstrate CohortFinder improves ML model performance in downstream digital pathology and medical image processing tasks. CohortFinder is freely available for download at cohortfinder.com.

Informations de copyright

© The Author(s) 2024.

Déclaration de conflit d'intérêts

Competing interestsAM is an equity holder in Picture Health, Elucid Bioimaging, and Inspirata Inc. Currently he serves on the advisory board of Picture Health, Aiforia Inc, and SimBioSys. He also currently consults for SimBioSys. He also has sponsored research agreements with AstraZeneca, Boehringer-Ingelheim, Eli-Lilly and Bristol Myers-Squibb. His technology has been licensed to Picture Health and Elucid Bioimaging. He is also involved in three different R01 grants with Inspirata Inc. VHK has acted as an invited speaker for Sharing Progress in Cancer Care (SPCC) and Indica Labs, is on an advisory board of Takeda, and holds sponsored research agreements with Roche and IAG unrelated to the content of this study. S.V. has received sponsored research funding from Pfizer. AJ provides consulting for Merck, Lunaphore, and Roche, the latter of which he also has a sponsored research agreement. L.B. is a consultant for Sangamo and Protalix and is on the scientific advisory boards of Vertex and Nephcure.