Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches
PurposeThis study aimed to develop prediction models for chronic postsurgical pain (CPSP) after breast cancer surgery using machine learning approaches and evaluate their performance.MethodsThe study was a secondary analysis based on a high-quality dataset from a randomized controlled trial (NCT0041...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.1096468/full |
| _version_ | 1797894262643228672 |
|---|---|
| author | Chen Sun Mohan Li Ling Lan Lijian Pei Lijian Pei Yuelun Zhang Gang Tan Zhiyong Zhang Yuguang Huang |
| author_facet | Chen Sun Mohan Li Ling Lan Lijian Pei Lijian Pei Yuelun Zhang Gang Tan Zhiyong Zhang Yuguang Huang |
| author_sort | Chen Sun |
| collection | DOAJ |
| description | PurposeThis study aimed to develop prediction models for chronic postsurgical pain (CPSP) after breast cancer surgery using machine learning approaches and evaluate their performance.MethodsThe study was a secondary analysis based on a high-quality dataset from a randomized controlled trial (NCT00418457), including patients with primary breast cancer undergoing mastectomy. The primary outcome was CPSP at 12 months after surgery, defined as modified Brief Pain Inventory > 0. The dataset was randomly split into a training dataset (90%) and a testing dataset (10%). Variables were selected using recursive feature elimination combined with clinical experience, and potential predictors were then incorporated into three machine learning models, including random forest, gradient boosting decision tree and extreme gradient boosting models for outcome prediction, as well as logistic regression. The performances of these four models were tested and compared.Results1152 patients were finally included, of which 22.1% developed CPSP at 12 months after breast cancer surgery. The 6 leading predictors were higher numerical rating scale within 2 days after surgery, post-menopausal status, urban medical insurance, history of at least one operation, under fentanyl with sevoflurane general anesthesia, and received axillary lymph node dissection. Compared with the multivariable logistic regression model, machine learning models showed better specificity, positive likelihood ratio and positive predictive value, helping to identify high-risk patients more accurately and create opportunities for early clinical intervention.ConclusionsOur study developed prediction models for CPSP after breast cancer surgery based on machine learning approaches, which may help to identify high-risk patients and improve patients’ management after breast cancer. |
| first_indexed | 2024-04-10T07:07:16Z |
| format | Article |
| id | doaj.art-6f10bcbaf1404439b2d7fe31dae163d7 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-10T07:07:16Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-6f10bcbaf1404439b2d7fe31dae163d72023-02-27T06:55:45ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-02-011310.3389/fonc.2023.10964681096468Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approachesChen Sun0Mohan Li1Ling Lan2Lijian Pei3Lijian Pei4Yuelun Zhang5Gang Tan6Zhiyong Zhang7Yuguang Huang8Department of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaOutcomes Research Consortium, Cleveland, OH, United StatesMedical Research Center, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaDepartment of Anesthesiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, ChinaPurposeThis study aimed to develop prediction models for chronic postsurgical pain (CPSP) after breast cancer surgery using machine learning approaches and evaluate their performance.MethodsThe study was a secondary analysis based on a high-quality dataset from a randomized controlled trial (NCT00418457), including patients with primary breast cancer undergoing mastectomy. The primary outcome was CPSP at 12 months after surgery, defined as modified Brief Pain Inventory > 0. The dataset was randomly split into a training dataset (90%) and a testing dataset (10%). Variables were selected using recursive feature elimination combined with clinical experience, and potential predictors were then incorporated into three machine learning models, including random forest, gradient boosting decision tree and extreme gradient boosting models for outcome prediction, as well as logistic regression. The performances of these four models were tested and compared.Results1152 patients were finally included, of which 22.1% developed CPSP at 12 months after breast cancer surgery. The 6 leading predictors were higher numerical rating scale within 2 days after surgery, post-menopausal status, urban medical insurance, history of at least one operation, under fentanyl with sevoflurane general anesthesia, and received axillary lymph node dissection. Compared with the multivariable logistic regression model, machine learning models showed better specificity, positive likelihood ratio and positive predictive value, helping to identify high-risk patients more accurately and create opportunities for early clinical intervention.ConclusionsOur study developed prediction models for CPSP after breast cancer surgery based on machine learning approaches, which may help to identify high-risk patients and improve patients’ management after breast cancer.https://www.frontiersin.org/articles/10.3389/fonc.2023.1096468/fullchronic postsurgical pain (CPSP)breast cancerprediction modelmachine learninghigh-risk identification |
| spellingShingle | Chen Sun Mohan Li Ling Lan Lijian Pei Lijian Pei Yuelun Zhang Gang Tan Zhiyong Zhang Yuguang Huang Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches Frontiers in Oncology chronic postsurgical pain (CPSP) breast cancer prediction model machine learning high-risk identification |
| title | Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| title_full | Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| title_fullStr | Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| title_full_unstemmed | Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| title_short | Prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| title_sort | prediction models for chronic postsurgical pain in patients with breast cancer based on machine learning approaches |
| topic | chronic postsurgical pain (CPSP) breast cancer prediction model machine learning high-risk identification |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.1096468/full |
| work_keys_str_mv | AT chensun predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT mohanli predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT linglan predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT lijianpei predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT lijianpei predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT yuelunzhang predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT gangtan predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT zhiyongzhang predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches AT yuguanghuang predictionmodelsforchronicpostsurgicalpaininpatientswithbreastcancerbasedonmachinelearningapproaches |