Risk prediction for malignant intraductal papillary mucinous neoplasm of the pancreas: logistic regression versus machine learning
| Autor: | Youngmin Han, Sohei Satoi, Masakazu Yamamoto, Yoo Seok Yoon, C.L. Wolfgang, Hongbeom Kim, Alex B. Blair, Satoshi Hirano, Yuichi Nagakawa, Yi Ming Shyr, Taesung Park, Marc G. Besselink, Hyung Il Seo, Yasuhiro Shimizu, Jin-Young Jang, Michael D. Kluger, Jun Chul Chung, Takashi Hatori, Ippei Matsumoto, Goro Honda, Wooil Kwon, Ki Byung Song, Ho-Seong Han, Sungyoung Lee, Wenhui Lou, Roberto Valente, Yoonhyeong Byun, Ryota Higuchi, Seiko Hirono, Hiroki Yamaue, Fuyuhiko Motoi, Matthias Löhr, Shin E. Wang, Wookyeong Song, Wonho Choo, Jae Seung Kang, Gloria H. Su, Jin Seok Heo, Hiroaki Nagano, Nadine C.M. van Huijgevoort, Giovanni Marchegiani, Chanhee Lee, Ching-Yao Yang, Sang Geol Kim, Claudio Bassi, Seungyeoun Lee, Roberto Salvia, Marco Del Chiaro, Jin He, Dong Wook Choi, Seong Ho Choi, Chang Moo Kang, Hee Chul Yu, Yinmo Yang, Yasushi Hashimoto, Tsutomu Fujii, Song Cheol Kim, Yoo Jin Choi, Jae Do Yang, Woo Jung Lee, Masayuki Sho |
|---|---|
| Přispěvatelé: | Surgery, CCA - Imaging and biomarkers, Amsterdam Gastroenterology Endocrinology Metabolism, Graduate School |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0301 basic medicine
Male Pancreatic Intraductal Neoplasms lcsh:Medicine computer.software_genre Logistic regression Main duct Machine Learning 0302 clinical medicine malignant Risk Factors IPMN malignant regression Diagnosis Computer-Assisted lcsh:Science Mathematics Interpretability Multidisciplinary Gastroenterology Middle Aged Prognosis medicine.anatomical_structure Oncology 030220 oncology & carcinogenesis Female regression Pancreas Algorithms Machine learning Cross-validation Article 03 medical and health sciences IPMN medicine Humans Model development Aged Retrospective Studies Intraductal papillary mucinous neoplasm business.industry lcsh:R medicine.disease 030104 developmental biology Logistic Models Test set lcsh:Q Artificial intelligence Pancreatic Cyst business computer |
| Zdroj: | Scientific reports, 10(1):20140. Nature Publishing Group Scientific Reports Scientific Reports, Vol 10, Iss 1, Pp 1-8 (2020) |
| Popis: | Most models for predicting malignant pancreatic intraductal papillary mucinous neoplasms were developed based on logistic regression (LR) analysis. Our study aimed to develop risk prediction models using machine learning (ML) and LR techniques and compare their performances. This was a multinational, multi-institutional, retrospective study. Clinical variables including age, sex, main duct diameter, cyst size, mural nodule, and tumour location were factors considered for model development (MD). After the division into a MD set and a test set (2:1), the best ML and LR models were developed by training with the MD set using a tenfold cross validation. The test area under the receiver operating curves (AUCs) of the two models were calculated using an independent test set. A total of 3,708 patients were included. The stacked ensemble algorithm in the ML model and variable combinations containing all variables in the LR model were the most chosen during 200 repetitions. After 200 repetitions, the mean AUCs of the ML and LR models were comparable (0.725 vs. 0.725). The performances of the ML and LR models were comparable. The LR model was more practical than ML counterpart, because of its convenience in clinical use and simple interpretability. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|