Optimal computed tomography-based biomarkers for prediction of incisional hernia formation.

PURPOSE: Unstructured data are an untapped source for surgical prediction. Modern image analysis and machine learning (ML) can harness unstructured data in medical imaging. Incisional hernia (IH) is a pervasive surgical disease, well-suited for prediction using image analysis. Our objective was to identify optimal biomarkers (OBMs) from preoperative abdominopelvic computed tomography (CT) imaging which are most predictive of IH development. METHODS: Two hundred and twelve rigorously matched colorectal surgery patients at our institution were included. Preoperative abdominopelvic CT scans were segmented to derive linear, volumetric, intensity-based, and textural features. These features were analyzed to find a small subset of OBMs, which are maximally predictive of IH. Three ML classifiers (Ensemble Boosting, Random Forest, SVM) trained on these OBMs were used for prediction of IH. RESULTS: Altogether, 279 features were extracted from each CT scan. The most predictive OBMs found were: (1) abdominopelvic visceral adipose tissue (VAT) volume, normalized for height; (2) abdominopelvic skeletal muscle tissue volume, normalized for height; and (3) pelvic VAT volume to pelvic outer aspect of body wall skeletal musculature (OAM) volume ratio. Among ML prediction models, Ensemble Boosting produced the best performance with an AUC of 0.85, accuracy of 0.83, sensitivity of 0.86, and specificity of 0.81. CONCLUSION: These OBMs suggest increased intra-abdominopelvic volume/pressure as the salient pathophysiologic driver and likely mechanism for IH formation. ML models using these OBMs are highly predictive for IH development. The next generation of surgical prediction will maximize the utility of unstructured data using advanced image analysis and ML.

Transversus abdominis release with biosynthetic mesh for large ventral hernia repair: a 5-year analysis of clinical outcomes and quality of life.

INTRODUCTION: Transversus abdominis release (TAR) may provide an optimal plane for mesh placement for large ventral hernias requiring medial myofascial flap advancement. Long-term outcomes of TAR for large ventral hernia repair (VHR) remains under-studied. This study aims to assess longitudinal clinical outcomes and quality of life (QoL) following large VHR with TAR and resorbable biosynthetic mesh. METHODS: Retrospective review of clinical outcomes and prospective QoL was performed for patients undergoing VHR with poly-4-hydroxybutyrate mesh and TAR from 2016 to 2021. Patients with ≤ 24 months of follow-up, defects ≤ 150 cm2, and parastomal hernias were excluded. Cost-related data was collected for each patient's hospital course. QoL was compared using paired Wilcoxon signed-rank tests. RESULTS: Twenty-nine patients met inclusion criteria. Median age and BMI were 61 years (53.2-68.1 years) and 31.4 kg/m2 (26.1-35.3 kg/m2). Average hernia defect was 390cm2 ± 152.9 cm2. All patients underwent previous abdominal surgery and were primarily Ventral Hernia Working Group 2 (58.6%). Two hernia recurrences (6.9%) occurred over the median follow-up period of 63.1 months (IQR 43.7-71.3 months), with no cases of mesh infection or explantation. Delayed healing and seroma occurred in 27 and 10.3% of patients, respectively. QoL analysis identified a significant improvement in postoperative QoL (p < 0.005), that continued throughout the 5-year follow-up period, with a 41% overall improvement. Cost analysis identified the hospital revenue generated was approximately equal to the direct costs of patient care. Higher costs were associated with ASA class and length of stay (p < 0.05). CONCLUSION: Large VHR with resorbable biosynthetic mesh and TAR can be performed safely, with a low recurrence and complication rate, acceptable hospital costs, and significant improvement in disease-specific QoL at long-term follow-up.