File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Article: A machine learning model for colorectal liver metastasis post-hepatectomy prognostications
Title | A machine learning model for colorectal liver metastasis post-hepatectomy prognostications |
---|---|
Authors | |
Issue Date | 1-Aug-2023 |
Publisher | AME Publishing |
Citation | Hepatobiliary Surgery and Nutrition, 2023, v. 12, n. 4, p. 495-506 How to Cite? |
Abstract | Background: Currently, surgical resection is the mainstay for colorectal liver metastases (CRLM) management and the only potentially curative treatment modality. Prognostication tools can support patient selection for surgical resection to maximize therapeutic benefit. This study aimed to develop a survival prediction model using machine learning based on a multicenter patient sample in Hong Kong.Methods: Patients who underwent hepatectomy for CRLM between 1 January 2009 and 31 December 2018 in four hospitals in Hong Kong were included in the study. Survival analysis was performed using Cox proportional hazards (CPH). A stepwise selection on Cox multivariable models with LASSO regression was applied to a multiply-imputed dataset to build a prediction model. The model was validated in the validation set, and its performance was compared with that of Fong Clinical Risk Score (CRS) using concordance index.Results: A total of 572 patients were included with a median follow-up of 3.6 years. The full models for overall survival (OS) and recurrence-free survival (RFS) consist of the same 8 established and novel variables, namely colorectal cancer nodal stage, CRLM neoadjuvant treatment, Charlson Comorbidity Score, pre-hepatectomy bilirubin and CEA levels, CRLM largest tumor diameter, extrahepatic metastasis detected on PET-scan as well as KRAS status. Our CRLM Machine-learning Algorithm Prognostication model (CMAP) demonstrated better ability to predict OS (C-index =0.651), compared with the Fong CRS for 1-year (C-index =0.571) and 5-year OS (C-index =0.574). It also achieved a C-index of 0.651 for RFS.Conclusions: We present a promising machine learning algorithm to individualize prognostications for patients following resection of CRLM with good discriminative ability. |
Persistent Identifier | http://hdl.handle.net/10722/338780 |
ISSN | 2023 Impact Factor: 6.1 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lam, Cynthia Sin Nga | - |
dc.contributor.author | Bharwani, Alina Ashok | - |
dc.contributor.author | Chan, Evelyn Hui Yi | - |
dc.contributor.author | Chan, Vernice Hui Yan | - |
dc.contributor.author | Au, Howard Lai Ho | - |
dc.contributor.author | Ho, Margaret Kay | - |
dc.contributor.author | Rashed, Shireen | - |
dc.contributor.author | Kwong, Bernard Ming Hong | - |
dc.contributor.author | Fang, Wentao | - |
dc.contributor.author | Ma, Ka Wing | - |
dc.contributor.author | Lo, Chung Mau | - |
dc.contributor.author | Cheung, Tan To | - |
dc.date.accessioned | 2024-03-11T10:31:28Z | - |
dc.date.available | 2024-03-11T10:31:28Z | - |
dc.date.issued | 2023-08-01 | - |
dc.identifier.citation | Hepatobiliary Surgery and Nutrition, 2023, v. 12, n. 4, p. 495-506 | - |
dc.identifier.issn | 2304-3881 | - |
dc.identifier.uri | http://hdl.handle.net/10722/338780 | - |
dc.description.abstract | <p> <span>Background: Currently, surgical resection is the mainstay for colorectal liver metastases (CRLM) management and the only potentially curative treatment modality. Prognostication tools can support patient selection for surgical resection to maximize therapeutic benefit. This study aimed to develop a survival prediction model using machine learning based on a multicenter patient sample in Hong Kong.Methods: Patients who underwent hepatectomy for CRLM between 1 January 2009 and 31 December 2018 in four hospitals in Hong Kong were included in the study. Survival analysis was performed using Cox proportional hazards (CPH). A stepwise selection on Cox multivariable models with LASSO regression was applied to a multiply-imputed dataset to build a prediction model. The model was validated in the validation set, and its performance was compared with that of Fong Clinical Risk Score (CRS) using concordance index.Results: A total of 572 patients were included with a median follow-up of 3.6 years. The full models for overall survival (OS) and recurrence-free survival (RFS) consist of the same 8 established and novel variables, namely colorectal cancer nodal stage, CRLM neoadjuvant treatment, Charlson Comorbidity Score, pre-hepatectomy bilirubin and CEA levels, CRLM largest tumor diameter, extrahepatic metastasis detected on PET-scan as well as KRAS status. Our CRLM Machine-learning Algorithm Prognostication model (CMAP) demonstrated better ability to predict OS (C-index =0.651), compared with the Fong CRS for 1-year (C-index =0.571) and 5-year OS (C-index =0.574). It also achieved a C-index of 0.651 for RFS.Conclusions: We present a promising machine learning algorithm to individualize prognostications for patients following resection of CRLM with good discriminative ability.</span> <br></p> | - |
dc.language | eng | - |
dc.publisher | AME Publishing | - |
dc.relation.ispartof | Hepatobiliary Surgery and Nutrition | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.title | A machine learning model for colorectal liver metastasis post-hepatectomy prognostications | - |
dc.type | Article | - |
dc.identifier.doi | 10.21037/hbsn-21-453 | - |
dc.identifier.volume | 12 | - |
dc.identifier.issue | 4 | - |
dc.identifier.spage | 495 | - |
dc.identifier.epage | 506 | - |
dc.identifier.eissn | 2304-389X | - |
dc.identifier.issnl | 2304-3881 | - |