Modern Approaches to Abdominal-Based Breast Reconstruction

Applying unsupervised machine learning approaches to characterize autologous breast reconstruction patient subgroups: an NSQIP analysis of 14,274 patients

BACKGROUND

Autologous breast reconstruction is composed of diverse techniques and results in a variety of outcome trajectories. We propose employing an unsupervised machine learning method to characterize such heterogeneous patterns in large-scale datasets.

METHODS

A retrospective cohort study of autologous breast reconstruction patients was conducted through the National Surgical Quality Improvement Program database. Patient characteristics, intraoperative variables, and occurrences of acute postoperative complications were collected. The cohort was classified into patient subgroups via the K-means clustering algorithm, a similarity-based unsupervised learning approach. The characteristics of each cluster were compared for differences from the complementary sample (p < 2 ×10-4) and validated with a test set.

RESULTS

A total of 14,274 female patients were included in the final study cohort. Clustering identified seven optimal subgroups, ordered by increasing rate of postoperative complication. Cluster 1 (2027 patients) featured breast reconstruction with free flaps (50%) and latissimus dorsi flaps (40%). In addition to its low rate of complications (14%, p < 2 ×10-4), its patient population was younger and with lower comorbidities when compared with the whole cohort. In the other extreme, cluster 7 (1112 patients) almost exclusively featured breast reconstruction with free flaps (94%) and possessed the highest rates of unplanned reoperations, readmissions, and dehiscence (p < 2 ×10-4). The reoperation profile of cluster 3 was also significantly different from the general cohort and featured lower proportions of vascular repair procedures (p < 8 ×10-4).

CONCLUSIONS

This study presents a novel, generalizable application of an unsupervised learning model to organize patient subgroups with associations between comorbidities, modality of breast reconstruction, and postoperative outcomes.

Reconstruction of a lateral thigh defect with a transverse rectus abdominis myocutaneous (TRAM) free flap: A case report

INTRODUCTION

Despite advancements in reconstructive surgery, the repair of large thigh deformities remains challenging. When other options are not feasible, distant flaps become necessary. Successful repairs have been achieved using a transverse rectus abdominis myocutaneous (TRAM) flap for the chest wall, groin, abdominal wall, sternum, and breast.

CASE PRESENTATION

This study presents the case of a 40-year-old man who experienced a large deformity, measuring 20 cm ∗ 10 cm in his left lateral thigh resulting from a road accident that occurred a decade ago. Additionally, he developed osteomyelitis due to exposed bone based on MRI and clinical signs. To address this large defect, a free TRAM flap was utilized, effectively covering the area with a well-vascularized skin graft. This approach eliminated the need for a latissimus flap with a skin graft.

DISCUSSION

In cases of covering large thigh defects, a variety of flaps can also be considered. The latissimus dorsi muscle is mainly used as a free flap, but surgeons should be cautious regarding the use of the latissimus dorsi flap while this flap is an attractive option in many other parts of the body, it's functional loss must be carefully weighed in lower extremity patients who are often crutch- and/or wheelchair-dependent.

CONCLUSION

Based on this experience, the free-TRAM flap has proven to be a highly resilient option for similar defects and ranks among our top choices. It is important to note that in cases of infected and traumatic wounds where fatty tissue is undesirable, the flap may not be the best solution.