Development of an artificial intelligence-derived histologic signature associated with adjuvant gemcitabine treatment outcomes in pancreatic cancer

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt

Dokumenter

  • Fulltext

    Forlagets udgivne version, 3,81 MB, PDF-dokument

  • Vivek Nimgaonkar
  • Viswesh Krishna
  • Vrishab Krishna
  • Ekin Tiu
  • Anirudh Joshi
  • Damir Vrabac
  • Hriday Bhambhvani
  • Katelyn Smith
  • Johansen, Julia Sidenius
  • Shalini Makawita
  • Benjamin Musher
  • Arnav Mehta
  • Andrew Hendifar
  • Zev Wainberg
  • Davendra Sohal
  • Christos Fountzilas
  • Aatur Singhi
  • Pranav Rajpurkar
  • Eric A. Collisson
Pancreatic ductal adenocarcinoma (PDAC) has been left behind in the evolution of personalized medicine. Predictive markers of response to therapy are lacking in PDAC despite various histological and transcriptional classification schemes. We report an artificial intelligence (AI) approach to histologic feature examination that extracts a signature predictive of disease-specific survival (DSS) in patients with PDAC receiving adjuvant gemcitabine. We demonstrate that this AI-generated histologic signature is associated with outcomes following adjuvant gemcitabine, while three previously developed transcriptomic classification systems are not (n = 47). We externally validate this signature in an independent cohort of patients treated with adjuvant gemcitabine (n = 46). Finally, we demonstrate that the signature does not stratify survival outcomes in a third cohort of untreated patients (n = 161), suggesting that the signature is specifically predictive of treatment-related outcomes but is not generally prognostic. This imaging analysis pipeline has promise in the development of actionable markers in other clinical settings where few biomarkers currently exist.
OriginalsprogEngelsk
Artikelnummer101013
TidsskriftCell Reports Medicine
Vol/bind4
Udgave nummer4
Antal sider11
ISSN2666-3791
DOI
StatusUdgivet - 2023

Bibliografisk note

Funding Information:
The authors thank Anirban Maitra and David Ting for their advice and guidance. Figures 1A, 1B, and 2A were created with BioRender.com. The study was funded by Valar Labs, Inc., V.N. Viswesh Krishna, A.J. D.V. P.R. and E.A.C. were involved in developing the study, and Viswesh Krishna and P.R. were involved in supervising the study. Vrishab Krishna and E.T. processed the images. Viswesh Krishna and Vrishab Krishna developed the model and ran the statistical tests. Vrishab Krishna and V.N. produced the figures. V.N. and Viswesh Krishna drafted the manuscript. K.S. and A.S. were involved in acquisition of the UPMC samples, and J.S.J. was involved in the acquisition of the Copenhagen samples. All authors critically edited the manuscript. Viswesh Krishna, A.J. D.V. and P.R. are founders of Valar Labs, Inc. and may own stocks. V.N. Vrishab Krishna, E.T. and H.B. are employees of Valar Labs, Inc. E.A.C. D.S. and A.H. are advisors to Valar Labs, Inc.

Funding Information:
The authors thank Anirban Maitra and David Ting for their advice and guidance. Figures 1 A, 1B, and 2 A were created with BioRender.com . The study was funded by Valar Labs, Inc.

Publisher Copyright:
© 2023 Valar Labs, Inc.

ID: 362891544