Machine Learning Model to Predict Postmastectomy Breast Reconstruction Complications

Can a machine learning (ML) model trained with both structured data and curated information from clinical notes accurately predict major postoperative complications in patients undergoing postmastectomy breast reconstruction (PMBR)?This prognostic study including 411 patients found that a trained extreme gradient boosting model predicted major complications after PMBR with an area under the receiver operating characteristic curve of 0.83, area under the precision-recall curve of 0.62, and accuracy of 80.59%. Model performance was consistent across both autologous and implant reconstruction.These findings demonstrate the feasibility of using an ML model trained with combined structured and unstructured clinical data to support patient risk assessment and decision-making across implant and autologous reconstruction.

Corresponding Authors: Ping-Han Tsai, MD, Division of Rheumatology, Allergy and Immunology, Chang Gung Memorial Hospital, No. 15 Wenhua Rd, Guishan District, Taoyuan City, Taiwan (a9232@cgmh.org.tw); Kevin C. Chung, MD, MS, Section of Plastic Surgery, Michigan Medicine, 1500 E Medical Center Dr, 2130 Taubman Center, SPC 5340, Ann Arbor, MI 48109-5340 (kecchung@med.umich.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.