Objective: The aim of this study was to systematically assess the application and potential benefits of natural language processing (NLP) in surgical outcomes research. Summary Background Data: Widespread implementation of electronic health records (EHRs) has generated a massive patient data source. Traditional methods of data capture, such as billing codes and/or manual review of free-text narratives in EHRs, are highly labor-intensive, costly, subjective, and potentially prone to bias. Methods: A literature search of PubMed, MEDLINE, Web of Science, and Embase identified all articles published starting in 2000 that used NLP models to assess perioperative surgical outcomes. Evaluation metrics of NLP systems were assessed by means of pooled analysis and meta-analysis. Qualitative synthesis was carried out to assess the results and risk of bias on outcomes. Results: The present study included 29 articles, with over half (n = 15) published after 2018. The most common outcome identified using NLP was postoperative complications (n = 14). Compared to traditional non-NLP models, NLP models identified postoperative complications with higher sensitivity [0.92 (0.87–0.95) vs 0.58 (0.33–0.79), P < 0.001]. The specificities were comparable at 0.99 (0.96–1.00) and 0.98 (0.95–0.99), respectively. Using summary of likelihood ratio matrices, traditional non-NLP models have clinical utility for confirming documentation of outcomes/diagnoses, whereas NLP models may be reliably utilized for both confirming and ruling out documentation of outcomes/diagnoses. Conclusions: NLP usage to extract a range of surgical outcomes, particularly postoperative complications, is accelerating across disciplines and areas of clinical outcomes research. NLP and traditional non-NLP approaches demonstrate similar performance measures, but NLP is superior in ruling out documentation of surgical outcomes.

Background Postmastectomy radiation therapy (PMRT) is an important component in the treatment of locally advanced breast cancer. Optimal timing of therapy in relation to autologous breast reconstruction (ABR) remains clinically debated. Herein, we comparatively analyze short- and long-term outcomes between immediate ABR (I-ABR) and delayed-immediate ABR (DI-ABR) in the setting of PMRT. Methods Adult patients undergoing ABR with PMRT were separated into cohorts based on reconstructive timeline: I-ABR or DI-ABR. The groups were propensity matched 1:1 by age, body mass index, and comorbidities. Surgical site events and long-term clinical outcomes (readmissions, reoperations, and revision procedures) were collected. Univariate analyses were completed using Pearson's chi-squared tests and Fisher's exact tests, and statistical significance was set at p < 0.05. Results One hundred and thirty-two flaps (66 in each cohort) were identified for inclusion. Patients with I-ABR were more likely to experience fat necrosis (p = 0.034) and skin necrosis (p < 0.001), require additional office visits (p < 0.001) and outpatient surgeries (p = 0.015) to manage complications, and undergo revision surgery after reconstruction (p < 0.001). DI-ABR patients, however, had a 42.4% incidence of complications following tissue expander placement prior to reconstruction, with 16.7% of patients requiring reoperation during this time. Only one patient (I-ABR) experienced flap loss due to a vascular complication. Conclusion The complications encountered in both of these groups were not prohibitive to offering either treatment. Patients should be made aware of the specific and unique risks of these reconstruction timelines and involved throughout the entire decision-making process. Plastic surgeons should continue to strive to elucidate innovative approaches that facilitate enhanced quality of life without compromising oncologic therapy.

No abstract

Purpose Posterior component separation with transversus abdominis release (TAR) enables medial myofascial flap advancement in complex abdominal wall reconstruction. Here, we add to a growing body of literature on TAR by assessing longitudinal clinical and patient-reported outcomes (PROs) after complex ventral hernia repair (VHR) with TAR. Methods Adult patients undergoing VHR with TAR between 10/15/2015 and 1/15/2020 were retrospectively identified. Patients with parastomal hernias and <12 months of follow-up were excluded. Clinical outcomes and PROs were assessed. Results Fifty-six patients were included with a median age and body mass index of 60 and 30.8 kg/m2, respectively. The average hernia defect was 384 cm2 [IQR 205-471], and all patients had retromuscular mesh placed. The most common complications were delayed healing (19.6%) and seroma (14.3%). There were no cases of mesh infection or explantation. Previous hernia repair and concurrent panniculectomy were risk factors for developing complications ( P < .05). One patient (1.8%) recurred at a median follow-up of 25.2 months [IQR 18.2-42.4]. Significant improvement in disease-specific PROs was maintained throughout the follow-up period (before to after P < .05). Conclusion Transversus abdominis release is a safe and efficacious technique to achieve fascial closure and retromuscular mesh in the repair of complex hernia defects.

espite years of surgical research, advancements in biomaterial science, and improvement in techniques, ideal mesh selection for ventral hernia repair in the setting of contamination remains controversial. Mesh reinforcement is an integral component of modern hernia surgery, shown to reduce recurrence rates when compared to primary suture repair alone. [1][2][3] With mesh placement, however, comes an increased risk for mesh-related complications. 2 These risks are augmented in patients undergoing contaminated hernia repair, 4,5 and it is "off label" to use mesh in clean-contaminated, contaminated, and infected wounds. 6,7