Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach.
<h4>Background</h4>Non-small-cell lung cancer (NSCLC) and its surgery significantly increase the venous thromboembolism (VTE) risk. This study explored the VTE risk factors and established a machine-learning model to predict a failure of postoperative thromboprophylaxis.<h4>Methods...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0320674 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850152440373968896 |
|---|---|
| author | Ligang Hao Junjie Zhang Yonghui Di Zheng Qi Peng Zhang |
| author_facet | Ligang Hao Junjie Zhang Yonghui Di Zheng Qi Peng Zhang |
| author_sort | Ligang Hao |
| collection | DOAJ |
| description | <h4>Background</h4>Non-small-cell lung cancer (NSCLC) and its surgery significantly increase the venous thromboembolism (VTE) risk. This study explored the VTE risk factors and established a machine-learning model to predict a failure of postoperative thromboprophylaxis.<h4>Methods</h4>This retrospective study included patients with NSCLC who underwent surgery between January 2018 and November 2022. The patients were randomized 7:3 to the training and test sets. Nine machine learning models were constructed. The three most predictive machine-learning classifiers were chosen as the first layer of the stacking machine-learning model, and logistic regression was the second layer of the meta-learning model.<h4>Results</h4>This study included 362 patients, including 58 (16.0%) with VTE. Based on the multivariable logistic regression analysis, age, platelets, D-dimers, albumin, smoking history, and epidermal growth factor receptor (EGFR) exon 21 mutation were used to develop the nine machine-learning models. LGBM Classifier, RandomForest Classifier, and GNB were chosen for the first layer of the stacking machine learning model. The area under the received operating characteristics curve (ROC-AUC), accuracy, sensitivity, and specificity of the stacking machine learning model in the training/test set were 0.984/0.979, 0.949/0.954, 0.935/1.000, and 0.958/0.887, respectively. In the validation set, the final stacking machine learning model demonstrated an ROC AUC of 0.983, accuracy of 0.937, sensitivity of 0.978, and specificity of 0.947. The decision curve analyses revealed high benefits.<h4>Conclusion</h4>The stacking machine learning model based on EGFR mutation and clinical characteristics had a predictive value for postoperative VTE in patients with NSCLC. |
| format | Article |
| id | doaj-art-e9f8e54842374509b81f5bfc2a7146bd |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-e9f8e54842374509b81f5bfc2a7146bd2025-08-20T02:25:59ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e032067410.1371/journal.pone.0320674Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach.Ligang HaoJunjie ZhangYonghui DiZheng QiPeng Zhang<h4>Background</h4>Non-small-cell lung cancer (NSCLC) and its surgery significantly increase the venous thromboembolism (VTE) risk. This study explored the VTE risk factors and established a machine-learning model to predict a failure of postoperative thromboprophylaxis.<h4>Methods</h4>This retrospective study included patients with NSCLC who underwent surgery between January 2018 and November 2022. The patients were randomized 7:3 to the training and test sets. Nine machine learning models were constructed. The three most predictive machine-learning classifiers were chosen as the first layer of the stacking machine-learning model, and logistic regression was the second layer of the meta-learning model.<h4>Results</h4>This study included 362 patients, including 58 (16.0%) with VTE. Based on the multivariable logistic regression analysis, age, platelets, D-dimers, albumin, smoking history, and epidermal growth factor receptor (EGFR) exon 21 mutation were used to develop the nine machine-learning models. LGBM Classifier, RandomForest Classifier, and GNB were chosen for the first layer of the stacking machine learning model. The area under the received operating characteristics curve (ROC-AUC), accuracy, sensitivity, and specificity of the stacking machine learning model in the training/test set were 0.984/0.979, 0.949/0.954, 0.935/1.000, and 0.958/0.887, respectively. In the validation set, the final stacking machine learning model demonstrated an ROC AUC of 0.983, accuracy of 0.937, sensitivity of 0.978, and specificity of 0.947. The decision curve analyses revealed high benefits.<h4>Conclusion</h4>The stacking machine learning model based on EGFR mutation and clinical characteristics had a predictive value for postoperative VTE in patients with NSCLC.https://doi.org/10.1371/journal.pone.0320674 |
| spellingShingle | Ligang Hao Junjie Zhang Yonghui Di Zheng Qi Peng Zhang Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. PLoS ONE |
| title | Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. |
| title_full | Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. |
| title_fullStr | Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. |
| title_full_unstemmed | Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. |
| title_short | Predicting a failure of postoperative thromboprophylaxis in non-small cell lung cancer: A stacking machine learning approach. |
| title_sort | predicting a failure of postoperative thromboprophylaxis in non small cell lung cancer a stacking machine learning approach |
| url | https://doi.org/10.1371/journal.pone.0320674 |
| work_keys_str_mv | AT liganghao predictingafailureofpostoperativethromboprophylaxisinnonsmallcelllungcancerastackingmachinelearningapproach AT junjiezhang predictingafailureofpostoperativethromboprophylaxisinnonsmallcelllungcancerastackingmachinelearningapproach AT yonghuidi predictingafailureofpostoperativethromboprophylaxisinnonsmallcelllungcancerastackingmachinelearningapproach AT zhengqi predictingafailureofpostoperativethromboprophylaxisinnonsmallcelllungcancerastackingmachinelearningapproach AT pengzhang predictingafailureofpostoperativethromboprophylaxisinnonsmallcelllungcancerastackingmachinelearningapproach |