A machine learning predictive model for recurrence of resected distal cholangiocarcinoma: Development and validation of predictive model using artificial intelligence.

Autor: Perez M; Hepato Pancreato Biliary Division, Hospital Del Mar, Universitat Pompeu Fabra, Barcelona, Spain. Electronic address: marcpxaus@gmail.com., Palnaes Hansen C; Department of Surgery, Rigshospitalet, University of Copenhagen, Denmark. Electronic address: Carsten.Palnaes.Hansen@regionh.dk., Burdio F; Hepato Pancreato Biliary Division, Hospital Del Mar, Universitat Pompeu Fabra, Barcelona, Spain. Electronic address: fburdio@hotmail.com., Sanchez-Velázquez P; Hepato Pancreato Biliary Division, Hospital Del Mar, Universitat Pompeu Fabra, Barcelona, Spain. Electronic address: psanchezvelazquez@psmar.cat., Giuliani A; Unit of General Surgery, San Giuseppe Moscati Hospital, Aversa, Italy. Electronic address: giuldoc@hotmail.com., Lancellotti F; Department of Hepato-Pancreato-Biliary Surgery, Manchester Royal Infirmary, University of Manchester, Manchester, United Kingdom. Electronic address: francesco.lancellotti87@gmail.com., de Liguori-Carino N; Department of Hepato-Pancreato-Biliary Surgery, Manchester Royal Infirmary, University of Manchester, Manchester, United Kingdom. Electronic address: Nicola.DeLiguoriCarino@mft.nhs.uk., Malleo G; Unit of General and Pancreatic Surgery, The Pancreas Institute, University of Verona Hospital Trust, Italy. Electronic address: giuseppe.malleo@aovr.veneto.it., Marchegiani G; Hepato Biliary Pancreatic (HPB) and Liver Transplant Surgery, Department of Surgery, Oncology and Gastroenterology (DiSCOG), Padova University, Padova, Italy. Electronic address: Giovanni.marchegiani@unipd.it., Podda M; Department of Surgical Science, University of Cagliari, Cagliari, Italy. Electronic address: mauropodda@ymail.com., Pisanu A; Department of Surgical Science, University of Cagliari, Cagliari, Italy. Electronic address: adolfo.pisanu@unica.it., De Luca GM; University of Bari 'A. Moro', Department of Biomedical Sciences and Human Oncology, Unit of Academic General Surgery ' V. Bonomo', Bari, Italy. Electronic address: max-de-luca@libero.it., Anselmo A; Department of Surgery, HPB and Transplant Surgery Unit, Policlinico Tor Vergata, Rome, Italy. Electronic address: alessandroanselmo.ptv@gmail.com., Siragusa L; Division of Colon and Rectal Surgery, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy. Electronic address: leandros93@hotmail.it., Kobbelgaard Burgdorf S; Department of Surgery, Rigshospitalet, University of Copenhagen, Denmark. Electronic address: stefan.kobbelgaard.burgdorf.02@regionh.dk., Tschuor C; Department of Surgery, Rigshospitalet, University of Copenhagen, Denmark. Electronic address: christoph.tschuor@regionh.dk., Cacciaguerra AB; HPB Surgery and Transplantation Unit, Department of Clinical and Experimental Medicine, Polytechnic University of Marche, Ancona, Italy. Electronic address: dott.benedetti@gmail.com., Koh YX; Department of Hepatopancreatobiliary and Transplant Surgery, Singapore General Hospital, Singapore. Electronic address: koh.ye.xin@singhealth.com.sg., Masuda Y; Department of Hepatopancreatobiliary and Transplant Surgery, Singapore General Hospital, Singapore. Electronic address: y.masuda@u.nus.edu., Hao Xuan MY; HPB Unit, Department of Surgery, Cantonal Hospital of Winterthur, Winterthur, Switzerland. Electronic address: markyeohx@u.nus.edu., Seeger N; HPB Unit, Department of Surgery, Cantonal Hospital of Winterthur, Winterthur, Switzerland. Electronic address: nico.seeger@ksw.ch., Breitenstein S; HPB Unit, Department of Surgery, Cantonal Hospital of Winterthur, Winterthur, Switzerland. Electronic address: Stefan.Breitenstein@ksw.ch., Grochola FL; HPB Unit, Department of Surgery, Cantonal Hospital of Winterthur, Winterthur, Switzerland. Electronic address: lukaszfilip.grochola@ksw.ch., Di Martino M; Department of Health Sciences, University of Piemonte Orientale, Novara, Italy. Electronic address: marcello.dimartino@uniupo.it., Secanella L; University Hospital Bellvitge, Barcelona, Spain. Electronic address: lsecanella@bellvitgehospital.cat., Busquets J; University Hospital Bellvitge, Barcelona, Spain. Electronic address: jbusquets@bellvitgehospital.cat., Dorcaratto D; Department of General Surgery, Biomedical Research Institute INCLIVA, Hospital Clínico Universitario, University of Valencia, Spain. Electronic address: dorcaratto.dimitri@gmail.com., Mora-Oliver I; Department of General Surgery, Biomedical Research Institute INCLIVA, Hospital Clínico Universitario, University of Valencia, Spain. Electronic address: isab_mora@hotmail.com., Ingallinella S; IRCCS San Raffaele Scientific Institute, Milan, Italy. Electronic address: sara.ingallinella@gmail.com., Salvia R; Unit of General and Pancreatic Surgery, The Pancreas Institute, University of Verona Hospital Trust, Italy. Electronic address: roberto.salvia@univr.it., Abu Hilal M; Department of Surgery, Fondazione Poliambulanza, Brescia, Italy. Electronic address: abuhilal9@gmail.com., Aldrighetti L; IRCCS San Raffaele Scientific Institute, Milan, Italy. Electronic address: aldrighetti.luca@hsr.it., Ielpo B; Hepato Pancreato Biliary Division, Hospital Del Mar, Universitat Pompeu Fabra, Barcelona, Spain. Electronic address: ielpo.b@gmail.com.
Jazyk: angličtina
Zdroj: European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology [Eur J Surg Oncol] 2024 Jul; Vol. 50 (7), pp. 108375. Date of Electronic Publication: 2024 May 09.
DOI: 10.1016/j.ejso.2024.108375
Abstrakt: Introduction: Distal Cholangiocarcinoma (dCCA) represents a challenge in hepatobiliary oncology, that requires nuanced post-resection prognostic modeling. Conventional staging criteria may oversimplify dCCA complexities, prompting the exploration of novel prognostic factors and methodologies, including machine learning algorithms. This study aims to develop a machine learning predictive model for recurrence after resected dCCA.
Material and Methods: This retrospective multicentric observational study included patients with dCCA from 13 international centers who underwent curative pancreaticoduodenectomy (PD). A LASSO-regularized Cox regression model was used to feature selection, examine the path of the coefficient and create a model to predict recurrence. Internal and external validation and model performance were assessed using the C-index score. Additionally, a web application was developed to enhance the clinical use of the algorithm.
Results: Among 654 patients, LNR (Lymph Node Ratio) 15, neural invasion, N stage, surgical radicality, and differentiation grade emerged as significant predictors of disease-free survival (DFS). The model showed the best discrimination capacity with a C-index value of 0.8 (CI 95 %, 0.77%-0.86 %) and highlighted LNR15 as the most influential factor. Internal and external validations showed the model's robustness and discriminative ability with an Area Under the Curve of 92.4 % (95 % CI, 88.2%-94.4 %) and 91.5 % (95 % CI, 88.4%-93.5 %), respectively. The predictive model is available at https://imim.shinyapps.io/LassoCholangioca/.
Conclusions: This study pioneers the integration of machine learning into prognostic modeling for dCCA, yielding a robust predictive model for DFS following PD. The tool can provide information to both patients and healthcare providers, enhancing tailored treatments and follow-up.
(© 2024 Elsevier Ltd, BASO ∼ The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights are reserved, including those for text and data mining, AI training, and similar technologies.)
Databáze: MEDLINE
Externí odkaz: