Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma.

Clinical Cancer Research : an Official Journal of the American Association for Cancer Research
Paul JohannetIman Osman

Abstract

Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma. We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan-Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400). The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400). Histology slides and patients' clinicodem...Continue Reading

References

Aug 18, 2005·British Journal of Cancer·L M McShaneUNKNOWN Statistics Subcommittee of the NCI-EORTC Working Group on Cancer Diagnostics
Jun 8, 2010·The New England Journal of Medicine·F Stephen HodiWalter J Urba
Nov 18, 2014·The New England Journal of Medicine·Caroline RobertPaolo A Ascierto
Nov 26, 2015·European Journal of Cancer : Official Journal for European Organization for Research and Treatment of Cancer (EORTC) [and] European Association for Cancer Research (EACR)·Stefan DiemJames Larkin
Jan 15, 2016·European Journal of Cancer : Official Journal for European Organization for Research and Treatment of Cancer (EORTC) [and] European Association for Cancer Research (EACR)·J M MichotO Lambotte
May 11, 2016·IEEE Transactions on Medical Imaging·Abhishek VahadaneNassir Navab
Mar 24, 2017·Biomarker Research·Laurence P Diggs, Eddy C Hsueh
Sep 21, 2017·Nature Communications·N JacquelotL Zitvogel
Nov 9, 2017·Journal of Translational Medicine·Maria A PizzichettaUNKNOWN Italian Melanoma Intergroup (IMI)
May 31, 2018·Annals of Oncology : Official Journal of the European Society for Medical Oncology·H A HaenssleUNKNOWN Reader study level-I and level-II Groups
Jun 19, 2018·Journal of the National Cancer Institute·Michael LattanziIman Osman
Jan 16, 2019·Nature Genetics·Robert M SamsteinLuc G T Morris
Aug 20, 2019·Chinese Medical Journal·Cheng-Xu LiYong Cui
Oct 23, 2019·Clinical Cancer Research : an Official Journal of the American Association for Cancer Research·Prathamesh M KulkarniYvonne M Saenger

❮ Previous
Next ❯

Citations

Apr 4, 2021·Cancer Discovery·Bhavneet BhinderOlivier Elemento
Jul 2, 2021·Journal of Translational Medicine·Paolo A AsciertoMagdalena Thurin
Sep 28, 2021·Expert Opinion on Investigational Drugs·Frederick M HowardRita Nanda

❮ Previous
Next ❯

Related Concepts

Related Feeds

Cancer Genomics (Keystone)

Cancer genomics approaches employ high-throughput technologies to identify the complete catalog of somatic alterations that characterize the genome, transcriptome and epigenome of cohorts of tumor samples. Discover the latest research using such technologies in this feed.