Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction
Background: Two-stage breast reconstruction is a common technique used to restore preoperative appearance in patients undergoing mastectomy. However, capsular contracture may develop and lead to implant failure and significant morbidity. The objective of this study is to build a machine-learning mod...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | JPRAS Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352587823000402 |
| _version_ | 1827596369216405504 |
|---|---|
| author | Yunchan Chen Marcos Lu Wang Grant G. Black Nancy Qin George Zhou Jaime L. Bernstein Malini Chinta David M. Otterburn |
| author_facet | Yunchan Chen Marcos Lu Wang Grant G. Black Nancy Qin George Zhou Jaime L. Bernstein Malini Chinta David M. Otterburn |
| author_sort | Yunchan Chen |
| collection | DOAJ |
| description | Background: Two-stage breast reconstruction is a common technique used to restore preoperative appearance in patients undergoing mastectomy. However, capsular contracture may develop and lead to implant failure and significant morbidity. The objective of this study is to build a machine-learning model that can determine the risk of developing contracture formation after two-stage breast reconstruction. Methods: A total of 209 women (406 samples) were included in the study cohort. Patient characteristics that were readily accessible at the preoperative visit and details pertaining to the surgical approach were used as input data for the machine-learning model. Supervised learning models were assessed using 5-fold cross validation. A neural network model is also evaluated using a 0.8/0.1/0.1 train/validate/test split. Results: Among the subjects, 144 (35.47%) developed capsular contracture. Older age, smaller nipple-inframammary fold distance, retropectoral implant placement, synthetic mesh usage, and postoperative radiation increased the odds of capsular contracture (p < 0.05). The neural network achieved the best performance metrics among the models tested, with a test accuracy of 0.82 and area under receiver operative curve of 0.79. Conclusion: To our knowledge, this is the first study that uses a neural network to predict the development of capsular contraction after two-stage implant-based reconstruction. At the preoperative visit, surgeons may counsel high-risk patients on the potential need for further revisions or guide them toward autologous reconstruction. |
| first_indexed | 2024-03-09T03:09:35Z |
| format | Article |
| id | doaj.art-07eb1668cb064f118bd5b9285d1cdb88 |
| institution | Directory Open Access Journal |
| issn | 2352-5878 |
| language | English |
| last_indexed | 2024-03-09T03:09:35Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | JPRAS Open |
| spelling | doaj.art-07eb1668cb064f118bd5b9285d1cdb882023-12-04T05:23:05ZengElsevierJPRAS Open2352-58782023-12-0138113Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast ReconstructionYunchan Chen0Marcos Lu Wang1Grant G. Black2Nancy Qin3George Zhou4Jaime L. Bernstein5Malini Chinta6David M. Otterburn7Division of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USADivision of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USADivision of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USADivision of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USADivision of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USANewYork-Presbyterian Hospital, New York, NY, USANewYork-Presbyterian Hospital, New York, NY, USADivision of Plastic and Reconstructive Surgery, Weill Cornell Medicine, New York, NY, USA; Corresponding author: David M. Otterburn MD, Weill Cornell Medicine, 525 E 68th St, Payson 7-708, New York, NY 10065, USA, Tel: (646) 962-4250; Fax: (646) 962-0523Background: Two-stage breast reconstruction is a common technique used to restore preoperative appearance in patients undergoing mastectomy. However, capsular contracture may develop and lead to implant failure and significant morbidity. The objective of this study is to build a machine-learning model that can determine the risk of developing contracture formation after two-stage breast reconstruction. Methods: A total of 209 women (406 samples) were included in the study cohort. Patient characteristics that were readily accessible at the preoperative visit and details pertaining to the surgical approach were used as input data for the machine-learning model. Supervised learning models were assessed using 5-fold cross validation. A neural network model is also evaluated using a 0.8/0.1/0.1 train/validate/test split. Results: Among the subjects, 144 (35.47%) developed capsular contracture. Older age, smaller nipple-inframammary fold distance, retropectoral implant placement, synthetic mesh usage, and postoperative radiation increased the odds of capsular contracture (p < 0.05). The neural network achieved the best performance metrics among the models tested, with a test accuracy of 0.82 and area under receiver operative curve of 0.79. Conclusion: To our knowledge, this is the first study that uses a neural network to predict the development of capsular contraction after two-stage implant-based reconstruction. At the preoperative visit, surgeons may counsel high-risk patients on the potential need for further revisions or guide them toward autologous reconstruction.http://www.sciencedirect.com/science/article/pii/S2352587823000402Capsular contractureMachine learningArtificial intelligenceImplant-based reconstructionPostoperative complicationsAlloplastic reconstruction |
| spellingShingle | Yunchan Chen Marcos Lu Wang Grant G. Black Nancy Qin George Zhou Jaime L. Bernstein Malini Chinta David M. Otterburn Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction JPRAS Open Capsular contracture Machine learning Artificial intelligence Implant-based reconstruction Postoperative complications Alloplastic reconstruction |
| title | Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction |
| title_full | Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction |
| title_fullStr | Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction |
| title_full_unstemmed | Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction |
| title_short | Machine-Learning Prediction of Capsular Contraction after Two-Stage Breast Reconstruction |
| title_sort | machine learning prediction of capsular contraction after two stage breast reconstruction |
| topic | Capsular contracture Machine learning Artificial intelligence Implant-based reconstruction Postoperative complications Alloplastic reconstruction |
| url | http://www.sciencedirect.com/science/article/pii/S2352587823000402 |
| work_keys_str_mv | AT yunchanchen machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT marcosluwang machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT grantgblack machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT nancyqin machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT georgezhou machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT jaimelbernstein machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT malinichinta machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction AT davidmotterburn machinelearningpredictionofcapsularcontractionaftertwostagebreastreconstruction |