Cargando…
Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy
Tumor metastasis is a common event in patients with gastric cancer (GC) who previously underwent curative gastrectomy. It is meaningful to employ high-volume clinical data for predicting the survival of metastatic GC patients. We aim to establish an improved machine learning (ML) classifier for pred...
Autores principales: | , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9751187/ https://www.ncbi.nlm.nih.gov/pubmed/36533072 http://dx.doi.org/10.3389/fmolb.2022.937242 |
_version_ | 1784850417337761792 |
---|---|
author | Zhang, Cheng Zhang, Yi Yang, Ya-Hui Xu, Hui Zhang, Xiao-Peng Wu, Zhi-Jun Xie, Min-Min Feng, Ying Feng, Chong Ma, Tai |
author_facet | Zhang, Cheng Zhang, Yi Yang, Ya-Hui Xu, Hui Zhang, Xiao-Peng Wu, Zhi-Jun Xie, Min-Min Feng, Ying Feng, Chong Ma, Tai |
author_sort | Zhang, Cheng |
collection | PubMed |
description | Tumor metastasis is a common event in patients with gastric cancer (GC) who previously underwent curative gastrectomy. It is meaningful to employ high-volume clinical data for predicting the survival of metastatic GC patients. We aim to establish an improved machine learning (ML) classifier for predicting if a patient with metastatic GC would die within 12 months. Eligible patients were enrolled from a Chinese GC cohort, and the complete detailed information from medical records was extracted to generate a high-dimensional dataset. Appropriate feature engineering and feature filter were conducted before modeling with eight algorithms. A 10-fold cross validation (CV) nested in a holdout CV (8:2) was employed for hyperparameter tuning and model evaluation. Model selection was based on the area under the receiver operating characteristic (AUROC) curve, recall, and precision. The selected model was globally explained using interpretable surrogate models. Of the total 399 cases (median survival of 8.2 months), 242 patients survived less than 12 months. The linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) model had the highest AUROC (0.78 ± 0.021), recall (0.93 ± 0.031), and precision (0.80 ± 0.026), respectively. The LDA model created a new function that generally separated the two classes. The predicted probability of the SVM model was interpreted using a linear regression model visualized by a nomogram. The predicted class of the RF model was explained using a decision tree model. In summary, analyzing high-volume medical data by ML is helpful to produce an improved model for predicting the survival in patients with metastatic GC. The algorithm should be carefully selected in different practical scenarios. |
format | Online Article Text |
id | pubmed-9751187 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-97511872022-12-16 Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy Zhang, Cheng Zhang, Yi Yang, Ya-Hui Xu, Hui Zhang, Xiao-Peng Wu, Zhi-Jun Xie, Min-Min Feng, Ying Feng, Chong Ma, Tai Front Mol Biosci Molecular Biosciences Tumor metastasis is a common event in patients with gastric cancer (GC) who previously underwent curative gastrectomy. It is meaningful to employ high-volume clinical data for predicting the survival of metastatic GC patients. We aim to establish an improved machine learning (ML) classifier for predicting if a patient with metastatic GC would die within 12 months. Eligible patients were enrolled from a Chinese GC cohort, and the complete detailed information from medical records was extracted to generate a high-dimensional dataset. Appropriate feature engineering and feature filter were conducted before modeling with eight algorithms. A 10-fold cross validation (CV) nested in a holdout CV (8:2) was employed for hyperparameter tuning and model evaluation. Model selection was based on the area under the receiver operating characteristic (AUROC) curve, recall, and precision. The selected model was globally explained using interpretable surrogate models. Of the total 399 cases (median survival of 8.2 months), 242 patients survived less than 12 months. The linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) model had the highest AUROC (0.78 ± 0.021), recall (0.93 ± 0.031), and precision (0.80 ± 0.026), respectively. The LDA model created a new function that generally separated the two classes. The predicted probability of the SVM model was interpreted using a linear regression model visualized by a nomogram. The predicted class of the RF model was explained using a decision tree model. In summary, analyzing high-volume medical data by ML is helpful to produce an improved model for predicting the survival in patients with metastatic GC. The algorithm should be carefully selected in different practical scenarios. Frontiers Media S.A. 2022-12-01 /pmc/articles/PMC9751187/ /pubmed/36533072 http://dx.doi.org/10.3389/fmolb.2022.937242 Text en Copyright © 2022 Zhang, Zhang, Yang, Xu, Zhang, Wu, Xie, Feng, Feng and Ma. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Molecular Biosciences Zhang, Cheng Zhang, Yi Yang, Ya-Hui Xu, Hui Zhang, Xiao-Peng Wu, Zhi-Jun Xie, Min-Min Feng, Ying Feng, Chong Ma, Tai Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title | Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title_full | Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title_fullStr | Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title_full_unstemmed | Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title_short | Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
title_sort | machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy |
topic | Molecular Biosciences |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9751187/ https://www.ncbi.nlm.nih.gov/pubmed/36533072 http://dx.doi.org/10.3389/fmolb.2022.937242 |
work_keys_str_mv | AT zhangcheng machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT zhangyi machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT yangyahui machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT xuhui machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT zhangxiaopeng machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT wuzhijun machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT xieminmin machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT fengying machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT fengchong machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy AT matai machinelearningmodelsforpredictingoneyearsurvivalinpatientswithmetastaticgastriccancerwhoexperiencedupfrontradicalgastrectomy |