학술논문
Explainable artificial intelligence prediction-based model in laparoscopic liver surgery for segments 7 and 8: an international multicenter study.
Document Type
Academic Journal
Author
Lopez-Lopez V; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Morise Z; Department of Surgery, Fujita Health University School of Medicine Okazaki Medical Center, Okazaki, Aichi, Japan.; Albaladejo-González M; Department of Information and Communication Engineering, Murcia University, Murcia, Spain.; Gavara CG; Department of HPB Surgery and Transplants, Vall d'Hebron University Hospital, Barcelona Autonomic University, Barcelona, Spain.; Goh BKP; Department of Hepatopancreatobiliary and Transplant Surgery, Singapore General Hospital and National Cancer Centre Singapore, Singapore, Singapore.; Surgery Academic Clinical Programme, Duke-National University of Singapore Medical School, Singapore, Singapore.; Koh YX; Department of Hepatopancreatobiliary and Transplant Surgery, Singapore General Hospital and National Cancer Centre Singapore, Singapore, Singapore.; Surgery Academic Clinical Programme, Duke-National University of Singapore Medical School, Singapore, Singapore.; Paul SJ; Department of Surgery, Fondazione Poliambulanza Istituto Ospedaliero, Brescia, Italy.; Hilal MA; Department of Surgery, Fondazione Poliambulanza Istituto Ospedaliero, Brescia, Italy.; Department of Surgery, University Hospital Southampton NHS Foundation Trust, Southampton, UK.; Mishima K; Department of Surgery, Ageo Central General Hospital, Ageo, Japan.; Krürger JAP; Serviço de Cirurgia do Fígado, Divisão de Cirurgia do Aparelho Digestivo, Departamento de Gastroenterologia, Faculdade de Medicina, Hospital das Clínicas HCFMUSP, Universidade de São Paulo, São Paulo, Brazil.; Herman P; Serviço de Cirurgia do Fígado, Divisão de Cirurgia do Aparelho Digestivo, Departamento de Gastroenterologia, Faculdade de Medicina, Hospital das Clínicas HCFMUSP, Universidade de São Paulo, São Paulo, Brazil.; Cerezuela A; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Brusadin R; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Kaizu T; Department of General, Pediatric and Hepatobiliary-Pancreatic Surgery, Kitasato University School of Medicine, Sagamihara, Japan.; Lujan J; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Department of General Surgery, School of Medicine, Clínica Universidad de Navarra, University of Navarra, Pamplona, Spain.; Rotellar F; Department of General Surgery, School of Medicine, Clínica Universidad de Navarra, University of Navarra, Pamplona, Spain.; Monden K; Department of Surgery, Fukuyama City Hospital, Hiroshima, Japan.; Dalmau M; Department of HPB Surgery and Transplants, Vall d'Hebron University Hospital, Barcelona Autonomic University, Barcelona, Spain.; Gotohda N; Department of Surgery, National Cancer Center Hospital East, Kashiwa, Japan.; Kudo M; Department of Surgery, National Cancer Center Hospital East, Kashiwa, Japan.; Kanazawa A; Department of Hepato-Biliary-Pancreatic Surgery, Osaka City General Hospital, Osaka, Japan.; Kato Y; Department of Surgery, Fujita Health University, Toyoake, Japan.; Nitta H; Department of Surgery, Iwate Medical University, Iwate, Japan.; Amano S; Department of Surgery, Iwate Medical University, Iwate, Japan.; Valle RD; General Surgery Unit, Parma University Hospital, Parma, Italy.; Giuffrida M; General Surgery Unit, Parma University Hospital, Parma, Italy.; Ueno M; Second Department of Surgery, Wakayama Medical University, 811-1 Kimiidera, Wakayama City, Wakayama, Japan.; Otsuka Y; Department of Surgery, Toho University, Tokyo, Japan.; Asano D; Department of Hepatobiliary and Pancreatic Surgery, Graduate School of Medicine, Tokyo Medical and Dental University, Tokyo, Japan.; Tanabe M; Department of Hepatobiliary and Pancreatic Surgery, Graduate School of Medicine, Tokyo Medical and Dental University, Tokyo, Japan.; Itano O; Department of Hepato-Biliary-Pancreatic and Gastrointestinal Surgery, School of Medicine, International University of Health and Welfare, Chiba, Japan.; Minagawa T; Department of Hepato-Biliary-Pancreatic and Gastrointestinal Surgery, School of Medicine, International University of Health and Welfare, Chiba, Japan.; Eshmuminov D; Department of Surgery and Transplantation, University Hospital Zurich and University of Zurich, Zurich, Switzerland.; Herrero I; Department of Surgery, Getafe University Hospital, Madrid, Spain.; Ramírez P; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Ruipérez-Valiente JA; Department of Information and Communication Engineering, Murcia University, Murcia, Spain. jruiperez@um.es.; Robles-Campos R; Department of General, Visceral and Transplantation Surgery, Clinic and University Hospital Virgen de La Arrixaca, IMIB-ARRIXACA, El Palmar, Murcia, Spain.; Wakabayashi G; Department of Surgery, Ageo Central General Hospital, Ageo, Japan.
Source
Publisher: Springer Country of Publication: Germany NLM ID: 8806653 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1432-2218 (Electronic) Linking ISSN: 09302794 NLM ISO Abbreviation: Surg Endosc Subsets: MEDLINE
Subject
Language
English
Abstract
Background: Artificial intelligence (AI) is becoming more useful as a decision-making and outcomes predictor tool. We have developed AI models to predict surgical complexity and the postoperative course in laparoscopic liver surgery for segments 7 and 8.
Methods: We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open.
Results: Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time."
Conclusion: We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8.
(© 2024. The Author(s).)
Methods: We included patients with lesions located in segments 7 and 8 operated by minimally invasive liver surgery from an international multi-institutional database. We have employed AI models to predict surgical complexity and postoperative outcomes. Furthermore, we have applied SHapley Additive exPlanations (SHAP) to make the AI models interpretable. Finally, we analyzed the surgeries not converted to open versus those converted to open.
Results: Overall, 585 patients and 22 variables were included. Multi-layer Perceptron (MLP) showed the highest performance for predicting surgery complexity and Random Forest (RF) for predicting postoperative outcomes. SHAP detected that MLP and RF gave the highest relevance to the variables "resection type" and "largest tumor size" for predicting surgery complexity and postoperative outcomes. In addition, we explored between surgeries converted to open and non-converted, finding statistically significant differences in the variables "tumor location," "blood loss," "complications," and "operation time."
Conclusion: We have observed how the application of SHAP allows us to understand the predictions of AI models in surgical complexity and the postoperative outcomes of laparoscopic liver surgery in segments 7 and 8.
(© 2024. The Author(s).)