FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3214030735> ?p ?o ?g. }

• W3214030735 endingPage "37" @default.
• W3214030735 startingPage "29" @default.
• W3214030735 abstract "Background and AimsRadiofrequency ablation (RFA) is a widely accepted, minimally invasive treatment for hepatocellular carcinoma (HCC). This study aimed to develop a machine learning (ML) model to predict the risk of HCC recurrence after RFA treatment for individual patients.MethodsWe included a total of 1778 patients with treatment-naïve HCC who underwent RFA. The cumulative probability of overall recurrence after the initial RFA treatment was 78.9% and 88.0% at 5 and 10 years, respectively. We developed a conventional Cox proportional hazard model and 6 ML models—including the deep learning–based DeepSurv model. Model performance was evaluated using Harrel’s c-index and was validated externally using the split-sample method.ResultsThe gradient boosting decision tree (GBDT) model achieved the best performance with a c-index of 0.67 from external validation, and it showed a high discriminative ability in stratifying the external validation sample into 2, 3, and 4 different risk groups (P < .001 among all risk groups). The c-index of DeepSurv was 0.64. In order of significance, the tumor number, serum albumin level, and des-gamma-carboxyprothrombin level were the most important variables for the prediction of HCC recurrence in the GBDT model. Also, the current GBDT model enabled the output of a personalized cumulative recurrence prediction curve for each patient.ConclusionWe developed a novel ML model for the personalized risk prediction of HCC recurrence after RFA treatment. The current model may lead to the personalization of effective follow-up strategies after RFA treatment according to the risk stratification of HCC recurrence. Radiofrequency ablation (RFA) is a widely accepted, minimally invasive treatment for hepatocellular carcinoma (HCC). This study aimed to develop a machine learning (ML) model to predict the risk of HCC recurrence after RFA treatment for individual patients. We included a total of 1778 patients with treatment-naïve HCC who underwent RFA. The cumulative probability of overall recurrence after the initial RFA treatment was 78.9% and 88.0% at 5 and 10 years, respectively. We developed a conventional Cox proportional hazard model and 6 ML models—including the deep learning–based DeepSurv model. Model performance was evaluated using Harrel’s c-index and was validated externally using the split-sample method. The gradient boosting decision tree (GBDT) model achieved the best performance with a c-index of 0.67 from external validation, and it showed a high discriminative ability in stratifying the external validation sample into 2, 3, and 4 different risk groups (P < .001 among all risk groups). The c-index of DeepSurv was 0.64. In order of significance, the tumor number, serum albumin level, and des-gamma-carboxyprothrombin level were the most important variables for the prediction of HCC recurrence in the GBDT model. Also, the current GBDT model enabled the output of a personalized cumulative recurrence prediction curve for each patient. We developed a novel ML model for the personalized risk prediction of HCC recurrence after RFA treatment. The current model may lead to the personalization of effective follow-up strategies after RFA treatment according to the risk stratification of HCC recurrence." @default.
• W3214030735 created "2021-11-22" @default.
• W3214030735 creator A5008751771 @default.
• W3214030735 creator A5009985299 @default.
• W3214030735 creator A5019510139 @default.
• W3214030735 creator A5024035182 @default.
• W3214030735 creator A5046522736 @default.
• W3214030735 creator A5048851902 @default.
• W3214030735 creator A5051161148 @default.
• W3214030735 creator A5059201555 @default.
• W3214030735 creator A5060462446 @default.
• W3214030735 creator A5065906991 @default.
• W3214030735 creator A5066658224 @default.
• W3214030735 creator A5073692464 @default.
• W3214030735 creator A5074549541 @default.
• W3214030735 creator A5075991149 @default.
• W3214030735 creator A5076296211 @default.
• W3214030735 creator A5079837821 @default.
• W3214030735 creator A5085971196 @default.
• W3214030735 date "2022-01-01" @default.
• W3214030735 modified "2023-10-11" @default.
• W3214030735 title "Machine Learning–Based Personalized Prediction of Hepatocellular Carcinoma Recurrence After Radiofrequency Ablation" @default.
• W3214030735 cites W1563869372 @default.
• W3214030735 cites W1902475470 @default.
• W3214030735 cites W1964829819 @default.
• W3214030735 cites W1985299015 @default.
• W3214030735 cites W1990996253 @default.
• W3214030735 cites W1992125785 @default.
• W3214030735 cites W1995656887 @default.
• W3214030735 cites W1997033640 @default.
• W3214030735 cites W2000249913 @default.
• W3214030735 cites W2008056655 @default.
• W3214030735 cites W2037480346 @default.
• W3214030735 cites W2039553081 @default.
• W3214030735 cites W2040263621 @default.
• W3214030735 cites W2044644368 @default.
• W3214030735 cites W2047554241 @default.
• W3214030735 cites W2048697945 @default.
• W3214030735 cites W2088794999 @default.
• W3214030735 cites W2100876416 @default.
• W3214030735 cites W2102636708 @default.
• W3214030735 cites W2103723243 @default.
• W3214030735 cites W2109202667 @default.
• W3214030735 cites W2122825543 @default.
• W3214030735 cites W2127313936 @default.
• W3214030735 cites W2129925362 @default.
• W3214030735 cites W2130191588 @default.
• W3214030735 cites W2146502722 @default.
• W3214030735 cites W2155868778 @default.
• W3214030735 cites W2163403599 @default.
• W3214030735 cites W2163486683 @default.
• W3214030735 cites W2481243666 @default.
• W3214030735 cites W2556851635 @default.
• W3214030735 cites W2566079294 @default.
• W3214030735 cites W2612400171 @default.
• W3214030735 cites W2753919178 @default.
• W3214030735 cites W2919115771 @default.
• W3214030735 cites W2934399013 @default.
• W3214030735 cites W2947814151 @default.
• W3214030735 cites W3011923175 @default.
• W3214030735 cites W3039117614 @default.
• W3214030735 cites W3120001138 @default.
• W3214030735 cites W3123085760 @default.
• W3214030735 cites W3125776321 @default.
• W3214030735 cites W3128180004 @default.
• W3214030735 cites W3177746593 @default.
• W3214030735 cites W4245784696 @default.
• W3214030735 cites W4251580432 @default.
• W3214030735 doi "https://doi.org/10.1016/j.gastha.2021.09.003" @default.
• W3214030735 hasPublicationYear "2022" @default.
• W3214030735 type Work @default.
• W3214030735 sameAs 3214030735 @default.
• W3214030735 citedByCount "4" @default.
• W3214030735 countsByYear W32140307352023 @default.
• W3214030735 crossrefType "journal-article" @default.
• W3214030735 hasAuthorship W3214030735A5008751771 @default.
• W3214030735 hasAuthorship W3214030735A5009985299 @default.
• W3214030735 hasAuthorship W3214030735A5019510139 @default.
• W3214030735 hasAuthorship W3214030735A5024035182 @default.
• W3214030735 hasAuthorship W3214030735A5046522736 @default.
• W3214030735 hasAuthorship W3214030735A5048851902 @default.
• W3214030735 hasAuthorship W3214030735A5051161148 @default.
• W3214030735 hasAuthorship W3214030735A5059201555 @default.
• W3214030735 hasAuthorship W3214030735A5060462446 @default.
• W3214030735 hasAuthorship W3214030735A5065906991 @default.
• W3214030735 hasAuthorship W3214030735A5066658224 @default.
• W3214030735 hasAuthorship W3214030735A5073692464 @default.
• W3214030735 hasAuthorship W3214030735A5074549541 @default.
• W3214030735 hasAuthorship W3214030735A5075991149 @default.
• W3214030735 hasAuthorship W3214030735A5076296211 @default.
• W3214030735 hasAuthorship W3214030735A5079837821 @default.
• W3214030735 hasAuthorship W3214030735A5085971196 @default.
• W3214030735 hasBestOaLocation W32140307351 @default.
• W3214030735 hasConcept C126322002 @default.
• W3214030735 hasConcept C143998085 @default.
• W3214030735 hasConcept C151956035 @default.
• W3214030735 hasConcept C154945302 @default.
• W3214030735 hasConcept C207103383 @default.

• next