1. Multimodal survival prediction in advanced pancreatic cancer using machine learning.
- Author
-
Keyl J, Kasper S, Wiesweg M, Götze J, Schönrock M, Sinn M, Berger A, Nasca E, Kostbade K, Schumacher B, Markus P, Albers D, Treckmann J, Schmid KW, Schildhaus HU, Siveke JT, Schuler M, and Kleesiek J
- Subjects
- Humans, C-Reactive Protein, Retrospective Studies, CA-19-9 Antigen, Proto-Oncogene Proteins p21(ras), Neoplasm Staging, Prognosis, Machine Learning, Pancreatic Neoplasms, Pancreatic Neoplasms diagnosis, Adenocarcinoma pathology
- Abstract
Background: Existing risk scores appear insufficient to assess the individual survival risk of patients with advanced pancreatic ductal adenocarcinoma (PDAC) and do not take advantage of the variety of parameters that are collected during clinical care., Methods: In this retrospective study, we built a random survival forest model from clinical data of 203 patients with advanced PDAC. The parameters were assessed before initiation of systemic treatment and included age, CA19-9, C-reactive protein, metastatic status, neutrophil-to-lymphocyte ratio and total serum protein level. Separate models including imaging and molecular parameters were built for subgroups., Results: Over the entire cohort, a model based on clinical parameters achieved a c-index of 0.71. Our approach outperformed the American Joint Committee on Cancer (AJCC) staging system and the modified Glasgow Prognostic Score (mGPS) in the identification of high- and low-risk subgroups. Inclusion of the KRAS p.G12D mutational status could further improve the prediction, whereas radiomics data of the primary tumor only showed little benefit. In an external validation cohort of PDAC patients with liver metastases, our model achieved a c-index of 0.67 (mGPS: 0.59)., Conclusions: The combination of multimodal data and machine-learning algorithms holds potential for personalized prognostication in advanced PDAC already at diagnosis., Competing Interests: Disclosure SK reports honoraria (self) from Merck, Amgen, Roche, Sanofi, Aventis, Servier and Lilly; honoraria (institution) from Merck, Amgen, Roche and Lilly; advisory/consultancy roles with Merck, Amgen, Roche, Sanofi, Aventis, Servier and Lilly; research grants/funding (self) from Merck, Bristol Myers Squibb, Roche and Lilly; research grants/funding (institution) from Merck and Lilly; and travel/accommodation expenses from Merck, Amgen, Roche, Sanofi, Aventis, Servier, Pierre Fabre and Lilly. MW reports honoraria from Amgen, Boehringer Ingelheim, Novartis, Roche and Takeda; and received research funding from Bristol Myers Squibb and Takeda. JTS reports honoraria as consultant or for continuing medical education presentations from AstraZeneca, Bayer, Immunocore, Roche and Servier. His institution receives research funding from Bristol Myers Squibb, Celgene, Roche. He holds ownership and serves on the Board of Directors of Pharma15, all outside the submitted work. MS reports compensated consultancy from Amgen, AstraZeneca, BIOCAD, Boehringer Ingelheim, Bristol Myers Squibb, GlaxoSmithKline, Janssen, Merck Serono, Novartis, Roche, Sanofi and Takeda; honoraria for continuing medical education presentations from Amgen, Boehringer Ingelheim, Bristol Myers Squibb, Janssen and Novartis; and received research funding to his institution from AstraZeneca and Bristol Myers Squibb. All other authors have declared no conflicts of interest. Data sharing De-identified datasets analyzed in this study are available from the corresponding author upon reasonable request., (Copyright © 2022 The Authors. Published by Elsevier Ltd.. All rights reserved.)
- Published
- 2022
- Full Text
- View/download PDF