Sökning: WFRF:(Kluger G) > Risk prediction for...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 04231naa a2200985 4500 | |
001 | oai:prod.swepub.kib.ki.se:145243906 | |
003 | SwePub | |
008 | 240811s2020 | |||||||||||000 ||eng| | |
024 | 7 | a http://kipublications.ki.se/Default.aspx?queryparsed=id:1452439062 URI |
024 | 7 | a https://doi.org/10.1038/s41598-020-76974-72 DOI |
040 | a (SwePub)ki | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Kang, JS4 aut |
245 | 1 0 | a Risk prediction for malignant intraductal papillary mucinous neoplasm of the pancreas: logistic regression versus machine learning |
264 | c 2020-11-18 | |
264 | 1 | b Springer Science and Business Media LLC,c 2020 |
520 | a 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. | |
700 | 1 | a Lee, C4 aut |
700 | 1 | a Song, W4 aut |
700 | 1 | a Choo, W4 aut |
700 | 1 | a Lee, S4 aut |
700 | 1 | a Lee, S4 aut |
700 | 1 | a Han, YM4 aut |
700 | 1 | a Bassi, C4 aut |
700 | 1 | a Salvia, R4 aut |
700 | 1 | a Marchegiani, G4 aut |
700 | 1 | a Wolfgang, CL4 aut |
700 | 1 | a He, J4 aut |
700 | 1 | a Blair, AB4 aut |
700 | 1 | a Kluger, MD4 aut |
700 | 1 | a Su, GH4 aut |
700 | 1 | a Kim, SC4 aut |
700 | 1 | a Song, KB4 aut |
700 | 1 | a Yamamoto, M4 aut |
700 | 1 | a Higuchi, R4 aut |
700 | 1 | a Hatori, T4 aut |
700 | 1 | a Yang, CY4 aut |
700 | 1 | a Yamaue, H4 aut |
700 | 1 | a Hirono, S4 aut |
700 | 1 | a Satoi, S4 aut |
700 | 1 | a Fujii, T4 aut |
700 | 1 | a Hirano, S4 aut |
700 | 1 | a Lou, WH4 aut |
700 | 1 | a Hashimoto, Y4 aut |
700 | 1 | a Shimizu, Y4 aut |
700 | 1 | a Del Chiaro, M4 aut |
700 | 1 | a Valente, R4 aut |
700 | 1 | a Lohr, Mu Karolinska Institutet4 aut |
700 | 1 | a Choi, DW4 aut |
700 | 1 | a Choi, SH4 aut |
700 | 1 | a Heo, JS4 aut |
700 | 1 | a Motoi, F4 aut |
700 | 1 | a Matsumoto, I4 aut |
700 | 1 | a Lee, WJ4 aut |
700 | 1 | a Kang, CM4 aut |
700 | 1 | a Shyr, YM4 aut |
700 | 1 | a Wang, SE4 aut |
700 | 1 | a Han, HS4 aut |
700 | 1 | a Yoon, YS4 aut |
700 | 1 | a Besselink, MG4 aut |
700 | 1 | a van Huijgevoort, NCM4 aut |
700 | 1 | a Sho, M4 aut |
700 | 1 | a Nagano, H4 aut |
700 | 1 | a Kim, SG4 aut |
700 | 1 | a Honda, G4 aut |
700 | 1 | a Yang, YM4 aut |
700 | 1 | a Yu, HC4 aut |
700 | 1 | a Do Yang, J4 aut |
700 | 1 | a Chung, JC4 aut |
700 | 1 | a Nagakawa, Y4 aut |
700 | 1 | a Il Seo, H4 aut |
700 | 1 | a Choi, YJ4 aut |
700 | 1 | a Byun, Y4 aut |
700 | 1 | a Kim, H4 aut |
700 | 1 | a Kwon, W4 aut |
700 | 1 | a Park, T4 aut |
700 | 1 | a Jang, JY4 aut |
710 | 2 | a Karolinska Institutet4 org |
773 | 0 | t Scientific reportsd : Springer Science and Business Media LLCg 10:1, s. 20140-q 10:1<20140-x 2045-2322 |
856 | 4 | u https://www.nature.com/articles/s41598-020-76974-7.pdf |
856 | 4 8 | u http://kipublications.ki.se/Default.aspx?queryparsed=id:145243906 |
856 | 4 8 | u https://doi.org/10.1038/s41598-020-76974-7 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy