Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer
ObjectiveTo develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.MethodsClinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically con...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Endocrinology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fendo.2022.1019037/full |
| _version_ | 1811194697537814528 |
|---|---|
| author | Sheng-wei Lai Yun-long Fan Yu-hua Zhu Fei Zhang Zheng Guo Bing Wang Zheng Wan Pei-lin Liu Ning Yu Han-dai Qin |
| author_facet | Sheng-wei Lai Yun-long Fan Yu-hua Zhu Fei Zhang Zheng Guo Bing Wang Zheng Wan Pei-lin Liu Ning Yu Han-dai Qin |
| author_sort | Sheng-wei Lai |
| collection | DOAJ |
| description | ObjectiveTo develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.MethodsClinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians.ResultsA total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/.ConclusionThe results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level. |
| first_indexed | 2024-04-12T00:31:03Z |
| format | Article |
| id | doaj.art-807cafb9582549208e9dc1fe6153acd6 |
| institution | Directory Open Access Journal |
| issn | 1664-2392 |
| language | English |
| last_indexed | 2024-04-12T00:31:03Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Endocrinology |
| spelling | doaj.art-807cafb9582549208e9dc1fe6153acd62022-12-22T03:55:20ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922022-10-011310.3389/fendo.2022.10190371019037Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancerSheng-wei Lai0Yun-long Fan1Yu-hua Zhu2Fei Zhang3Zheng Guo4Bing Wang5Zheng Wan6Pei-lin Liu7Ning Yu8Han-dai Qin9Medical School of Chinese PLA, Beijing, ChinaMedical School of Chinese PLA, Beijing, ChinaDepartment of Otolaryngology Head and Neck Surgery, The First Medical Centre of Chinese PLA General Hospital, Beijing, ChinaMedical School of Chinese PLA, Beijing, ChinaMedical School of Chinese PLA, Beijing, ChinaDepartment of General Surgery, The First Medical Centre of Chinese PLA General Hospital, Beijing, ChinaDepartment of General Surgery, The First Medical Centre of Chinese PLA General Hospital, Beijing, ChinaThe Third Team, Academy of Basic Medicine, The Fourth Military Medical University, Xi’an, ChinaDepartment of Otolaryngology Head and Neck Surgery, The First Medical Centre of Chinese PLA General Hospital, Beijing, ChinaMedical School of Chinese PLA, Beijing, ChinaObjectiveTo develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.MethodsClinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians.ResultsA total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/.ConclusionThe results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level.https://www.frontiersin.org/articles/10.3389/fendo.2022.1019037/fullmachine learningcentral lymph node metastasispapillary thyroid cancerfeature selectionmodel interpretationdynamic prediction |
| spellingShingle | Sheng-wei Lai Yun-long Fan Yu-hua Zhu Fei Zhang Zheng Guo Bing Wang Zheng Wan Pei-lin Liu Ning Yu Han-dai Qin Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer Frontiers in Endocrinology machine learning central lymph node metastasis papillary thyroid cancer feature selection model interpretation dynamic prediction |
| title | Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| title_full | Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| title_fullStr | Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| title_full_unstemmed | Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| title_short | Machine learning-based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| title_sort | machine learning based dynamic prediction of lateral lymph node metastasis in patients with papillary thyroid cancer |
| topic | machine learning central lymph node metastasis papillary thyroid cancer feature selection model interpretation dynamic prediction |
| url | https://www.frontiersin.org/articles/10.3389/fendo.2022.1019037/full |
| work_keys_str_mv | AT shengweilai machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT yunlongfan machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT yuhuazhu machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT feizhang machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT zhengguo machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT bingwang machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT zhengwan machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT peilinliu machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT ningyu machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer AT handaiqin machinelearningbaseddynamicpredictionoflaterallymphnodemetastasisinpatientswithpapillarythyroidcancer |