Gu-Wei Ji1,2,3, Ke Wang1,2,3, Yong-Xiang Xia1,2,3, Jin-Song Wang4, Xue-Hao Wang5,6,7, Xiang-Cheng Li8,9,10. 1. Hepatobiliary Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People's Republic of China. 2. Key Laboratory of Liver Transplantation, Chinese Academy of Medical Sciences, Nanjing, People's Republic of China. 3. NHC Key Laboratory of Living Donor Liver Transplantation (Nanjing Medical University), Nanjing, People's Republic of China. 4. Department of Pathology, Nanjing First Hospital, Nanjing, People's Republic of China. 5. Hepatobiliary Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People's Republic of China. wangxh@njmu.edu.cn. 6. Key Laboratory of Liver Transplantation, Chinese Academy of Medical Sciences, Nanjing, People's Republic of China. wangxh@njmu.edu.cn. 7. NHC Key Laboratory of Living Donor Liver Transplantation (Nanjing Medical University), Nanjing, People's Republic of China. wangxh@njmu.edu.cn. 8. Hepatobiliary Center, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People's Republic of China. drxcli@njmu.edu.cn. 9. Key Laboratory of Liver Transplantation, Chinese Academy of Medical Sciences, Nanjing, People's Republic of China. drxcli@njmu.edu.cn. 10. NHC Key Laboratory of Living Donor Liver Transplantation (Nanjing Medical University), Nanjing, People's Republic of China. drxcli@njmu.edu.cn.
Abstract
BACKGROUND: Improved methods are needed to predict outcomes in biliary tract cancers (BTCs). We aimed to build an immune-related signature and establish holistic models using machine learning. METHODS: Samples were from 305 BTC patients treated with curative-intent resection, divided into derivation and validation cohorts in a two-to-one ratio. Spatial resolution of T cell infiltration and PD-1/PD-L1 expression was assessed by immunohistochemistry. An immune signature was constructed using classification and regression tree. Machine learning was applied to develop prediction models for disease-specific survival (DSS) and recurrence-free survival (RFS). RESULTS: The immune signature composed of CD3+, CD8+, and PD-1+ cell densities and PD-L1 expression within tumor epithelium significantly stratified patients into three clusters, with median DSS varying from 11.7 to 80.8 months and median RFS varying from 6.2 to 62.0 months. Gradient boosting machines (GBM) outperformed rival machine-learning algorithms and selected the same 11 covariates for DSS and RFS prediction: immune signature, tumor site, age, bilirubin, albumin, carcinoembryonic antigen, cancer antigen 19-9, tumor size, tumor differentiation, resection margin, and nodal metastasis. The clinical-immune GBM models accurately predicted DSS and RFS, with respective concordance index of 0.776-0.816 and 0.741-0.781. GBM models showed significantly improved performance compared with tumor-node-metastasis staging system. CONCLUSIONS: The immune signature promises to stratify prognosis and allocate treatment in resected BTC. The clinical-immune GBM models accurately predict recurrence and death from BTC following surgery.
BACKGROUND: Improved methods are needed to predict outcomes in biliary tract cancers (BTCs). We aimed to build an immune-related signature and establish holistic models using machine learning. METHODS: Samples were from 305 BTC patients treated with curative-intent resection, divided into derivation and validation cohorts in a two-to-one ratio. Spatial resolution of T cell infiltration and PD-1/PD-L1 expression was assessed by immunohistochemistry. An immune signature was constructed using classification and regression tree. Machine learning was applied to develop prediction models for disease-specific survival (DSS) and recurrence-free survival (RFS). RESULTS: The immune signature composed of CD3+, CD8+, and PD-1+ cell densities and PD-L1 expression within tumor epithelium significantly stratified patients into three clusters, with median DSS varying from 11.7 to 80.8 months and median RFS varying from 6.2 to 62.0 months. Gradient boosting machines (GBM) outperformed rival machine-learning algorithms and selected the same 11 covariates for DSS and RFS prediction: immune signature, tumor site, age, bilirubin, albumin, carcinoembryonic antigen, cancer antigen 19-9, tumor size, tumor differentiation, resection margin, and nodal metastasis. The clinical-immune GBM models accurately predicted DSS and RFS, with respective concordance index of 0.776-0.816 and 0.741-0.781. GBM models showed significantly improved performance compared with tumor-node-metastasis staging system. CONCLUSIONS: The immune signature promises to stratify prognosis and allocate treatment in resected BTC. The clinical-immune GBM models accurately predict recurrence and death from BTC following surgery.
Authors: John N Primrose; Richard P Fox; Daniel H Palmer; Hassan Z Malik; Raj Prasad; Darius Mirza; Alan Anthony; Pippa Corrie; Stephen Falk; Meg Finch-Jones; Harpreet Wasan; Paul Ross; Lucy Wall; Jonathan Wadsley; Jeff T R Evans; Deborah Stocken; Raaj Praseedom; Yuk Ting Ma; Brian Davidson; John P Neoptolemos; Tim Iveson; James Raftery; Shihua Zhu; David Cunningham; O James Garden; Clive Stubbs; Juan W Valle; John Bridgewater Journal: Lancet Oncol Date: 2019-03-25 Impact factor: 41.316
Authors: Sumera Rizvi; Shahid A Khan; Christopher L Hallemeier; Robin K Kelley; Gregory J Gores Journal: Nat Rev Clin Oncol Date: 2017-10-10 Impact factor: 66.675
Authors: B Groot Koerkamp; J K Wiggers; M Gonen; A Doussot; P J Allen; M G H Besselink; L H Blumgart; O R C Busch; M I D'Angelica; R P DeMatteo; D J Gouma; T P Kingham; T M van Gulik; W R Jarnagin Journal: Ann Oncol Date: 2015-06-30 Impact factor: 32.976
Authors: Franck Pagès; Bernhard Mlecnik; Florence Marliot; Gabriela Bindea; Fang-Shu Ou; Carlo Bifulco; Alessandro Lugli; Inti Zlobec; Tilman T Rau; Martin D Berger; Iris D Nagtegaal; Elisa Vink-Börger; Arndt Hartmann; Carol Geppert; Julie Kolwelter; Susanne Merkel; Robert Grützmann; Marc Van den Eynde; Anne Jouret-Mourin; Alex Kartheuser; Daniel Léonard; Christophe Remue; Julia Y Wang; Prashant Bavi; Michael H A Roehrl; Pamela S Ohashi; Linh T Nguyen; SeongJun Han; Heather L MacGregor; Sara Hafezi-Bakhtiari; Bradly G Wouters; Giuseppe V Masucci; Emilia K Andersson; Eva Zavadova; Michal Vocka; Jan Spacek; Lubos Petruzelka; Bohuslav Konopasek; Pavel Dundr; Helena Skalova; Kristyna Nemejcova; Gerardo Botti; Fabiana Tatangelo; Paolo Delrio; Gennaro Ciliberto; Michele Maio; Luigi Laghi; Fabio Grizzi; Tessa Fredriksen; Bénédicte Buttard; Mihaela Angelova; Angela Vasaturo; Pauline Maby; Sarah E Church; Helen K Angell; Lucie Lafontaine; Daniela Bruni; Carine El Sissy; Nacilla Haicheur; Amos Kirilovsky; Anne Berger; Christine Lagorce; Jeffrey P Meyers; Christopher Paustian; Zipei Feng; Carmen Ballesteros-Merino; Jeroen Dijkstra; Carlijn van de Water; Shannon van Lent-van Vliet; Nikki Knijn; Ana-Maria Mușină; Dragos-Viorel Scripcariu; Boryana Popivanova; Mingli Xu; Tomonobu Fujita; Shoichi Hazama; Nobuaki Suzuki; Hiroaki Nagano; Kiyotaka Okuno; Toshihiko Torigoe; Noriyuki Sato; Tomohisa Furuhata; Ichiro Takemasa; Kyogo Itoh; Prabhu S Patel; Hemangini H Vora; Birva Shah; Jayendrakumar B Patel; Kruti N Rajvik; Shashank J Pandya; Shilin N Shukla; Yili Wang; Guanjun Zhang; Yutaka Kawakami; Francesco M Marincola; Paolo A Ascierto; Daniel J Sargent; Bernard A Fox; Jérôme Galon Journal: Lancet Date: 2018-05-10 Impact factor: 79.321
Authors: Rachna T Shroff; Erin B Kennedy; Melinda Bachini; Tanios Bekaii-Saab; Christopher Crane; Julien Edeline; Anthony El-Khoueiry; Mary Feng; Matthew H G Katz; John Primrose; Heloisa P Soares; Juan Valle; Shishir K Maithel Journal: J Clin Oncol Date: 2019-03-11 Impact factor: 50.717