biostudies-literatureUnknown158(2)Famularo S<h4>Importance</h4>Clear indications on how to select retreatments for recurrent hepatocellular carcinoma (HCC) are still lacking.<h4>Objective</h4>To create a machine learning predictive model of survival after HCC recurrence to allocate patients to their best potential treatment.<h4>Design, setting, and participants</h4>Real-life data were obtained from an Italian registry of hepatocellular carcinoma between January 2008 and December 2019 after a median (IQR) follow-up of 27 (12-51) months. External validation was made on data derived by another Italian cohort and a Japanese cohort. Patients who experienced a recurrent HCC after a first surgical approach were included. Patients were profiled, and factors predicting survival after recurrence under different treatments that acted also as tJAMA surgery192-202https://www.ebi.ac.uk/biostudies/studies/S-EPMC9857766biostudies-literatureMachine Learning Predictive Model to Guide Treatment Allocation for Recurrent Hepatocellular Carcinoma After Surgery.PMC9857766Antonucci AMolfino SRussolillo NMontuori MRossi MKawaguchi YCosta GValsecchi MGCosola DGermani PZanello MBraga MConci SDE Peppo VFarinati FDelvecchio AChiarelli MGriseri GAbu Hilal MRomano MArdito FNotte FTarchi PRomano FFazio FDonadon MGiani ARuzzenente ADE Stefano FFrena AMilana FJovine ELa Barba GRatti FBernasconi DPFumagalli LAldrighetti LZago MCipriani FCucchetti AErcolani GGiuffrida MConticchio MFerrari CManzoni AMemeo RPinotti EDalla Valle RMori SFamularo SIaria MDominioni TRazionale FFranceschi AHasegawa KCarissimi FPerri PCorleone PMaestri MFerrero AZimmitti GGrazi GLMarchitelli IPiscaglia FZanus GHE.RC.O.LE.S. GroupLai QLarghi Laurerio ZPatauner SSalvador LTorzilli GBaiocchi GLGiuliante FfalseMachine Learning Predictive Model to Guide Treatment Allocation for Recurrent Hepatocellular Carcinoma After Surgery.<h4>Importance</h4>Clear indications on how to select retreatments for recurrent hepatocellular carcinoma (HCC) are still lacking.<h4>Objective</h4>To create a machine learning predictive model of survival after HCC recurrence to allocate patients to their best potential treatment.<h4>Design, setting, and participants</h4>Real-life data were obtained from an Italian registry of hepatocellular carcinoma between January 2008 and December 2019 after a median (IQR) follow-up of 27 (12-51) months. External validation was made on data derived by another Italian cohort and a Japanese cohort. Patients who experienced a recurrent HCC after a first surgical approach were included. Patients were profiled, and factors predicting survival after recurrence under different treatments that acted also as t2023-01-01T00:00:00Z2023 Feb2026-05-28T02:14:32.255Z2025-04-06T19:18:51.107ZS-EPMC98577663657681310.1001/jamasurg.2022.6697