2022
DOI: 10.3389/fonc.2022.986867
|View full text |Cite|
|
Sign up to set email alerts
|

Machine learning prediction model for post- hepatectomy liver failure in hepatocellular carcinoma: A multicenter study

Abstract: IntroductionPost-hepatectomy liver failure (PHLF) is one of the most serious complications and causes of death in patients with hepatocellular carcinoma (HCC) after hepatectomy. This study aimed to develop a novel machine learning (ML) model based on the light gradient boosting machines (LightGBM) algorithm for predicting PHLF.MethodsA total of 875 patients with HCC who underwent hepatectomy were randomized into a training cohort (n=612), a validation cohort (n=88), and a testing cohort (n=175). Shapley additi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(13 citation statements)
references
References 43 publications
0
13
0
Order By: Relevance
“…In hepatobiliary surgery, different groups have successfully developed models to improve perioperative management of patients with hepatocellular carcinoma and predict both complications and recurrence patterns [ 17 ]. For example, to predict the risk of posthepatectomy liver failure, several artificial neural network models to help surgeons identify those patients at intermediate and high risk have been described [ 18 ]. Our group defined a risk-scoring model useful to estimate the patients’ level of risk based on the initial presentation and bile duct injury type and detailed how the patient’s risk category may be used to determine the appropriate management [ 19 ].…”
Section: Discussionmentioning
confidence: 99%
“…In hepatobiliary surgery, different groups have successfully developed models to improve perioperative management of patients with hepatocellular carcinoma and predict both complications and recurrence patterns [ 17 ]. For example, to predict the risk of posthepatectomy liver failure, several artificial neural network models to help surgeons identify those patients at intermediate and high risk have been described [ 18 ]. Our group defined a risk-scoring model useful to estimate the patients’ level of risk based on the initial presentation and bile duct injury type and detailed how the patient’s risk category may be used to determine the appropriate management [ 19 ].…”
Section: Discussionmentioning
confidence: 99%
“…Wang et al constructed a machine learning clinical model using laboratory values, tumor characteristics, and surgical variables (e.g., surgical approach, extent of resection, intraoperative blood loss) to predict the risk of PHLF. The model outperformed traditional models such as MELD, Child-Turcotte-Pugh, or albumin-bilirubin grade when predicting PHLF [52]. AI-derived algorithms have successfully predicted other surgical complications.…”
Section: Surgical Complicationsmentioning
confidence: 96%
“…recently reported a multicenter study showing that the AUC of LightGBM was 0.944, 0.870, and 0.822 for predicting PHLF on training set, validation set, and test set, respectively, and the AUCs were higher than those of traditional clinical prediction models [15] . However, they included only one ML model and did not uniformly compare other models, and the best model for patients with PHLF has not been reported.…”
Section: Introductionmentioning
confidence: 94%