Machine Learning for Automatic Detection of Velopharyngeal Dysfunction: A Preliminary Report.

BACKGROUND: Even after palatoplasty, the incidence of velopharyngeal dysfunction (VPD) can reach 30%; however, these estimates arise from high-income countries (HICs) where speech-language pathologists (SLP) are part of standardized cleft teams. The VPD burden in low- and middle-income countries (LMICs) is unknown. This study aims to develop a machine-learning model that can detect the presence of VPD using audio samples alone. METHODS: Case and control audio samples were obtained from institutional and publicly available sources. A machine-learning model was built using Python software. RESULTS: The initial 110 audio samples used to test and train the model were retested after format conversion and file deidentification. Each sample was tested 5 times yielding a precision of 100%. Sensitivity was 92.73% (95% CI: 82.41%-97.98%) and specificity was 98.18% (95% CI: 90.28%-99.95%). One hundred thirteen prospective samples, which had not yet interacted with the model, were then tested. Precision was again 100% with a sensitivity of 88.89% (95% CI: 78.44%-95.41%) and a specificity of 66% (95% CI: 51.23%-78.79%). DISCUSSION: VPD affects nearly 100% of patients with unrepaired overt soft palatal clefts and up to 30% of patients who have undergone palatoplasty. VPD can render patients unintelligible, thereby accruing significant psychosocial morbidity. The true burden of VPD in LMICs is unknown, and likely exceeds estimates from HICs. The ability to access a phone-based screening machine-learning model could expand access to diagnostic, and potentially therapeutic modalities for an innumerable amount of patients worldwide who suffer from VPD.

Reducing the incidence of surgical site infection after ventral hernia repair: Outcomes from the RINSE randomized control trial.

BACKGROUND: The clinical and financial impact of surgical site infection after ventral hernia repair is significant. Here we investigate the impact of dual antibiotic irrigation on SSI after VHR. METHODS: This was a multicenter, prospective randomized control trial of open retromuscular VHR with mesh. Patients were randomized to gentamicin â€‹+ â€‹clindamycin (G â€‹+ â€‹C) (n â€‹= â€‹125) vs saline (n â€‹= â€‹125) irrigation at time of mesh placement. Primary outcome was 30-day SSI. RESULTS: No significant difference was seen in SSI between control and antibiotic irrigation (9.91 vs 9.09 â€‹%; p â€‹= â€‹0.836). No differences were seen in secondary outcomes: SSO (11.71 vs 13.64 â€‹%; p â€‹= â€‹0.667); 90-day SSO (11.1 vs 13.9 â€‹%; p â€‹= â€‹0.603); 90-day SSI (6.9 vs 3.8 â€‹%; p â€‹= â€‹0.389); SSIPI (7.21 vs 7.27 â€‹%, p â€‹= â€‹0.985); SSOPI (3.6 vs 3.64 â€‹%; p â€‹= â€‹0.990); 30-day readmission (9.91 vs 6.36 â€‹%; p â€‹= â€‹0.335); reoperation (5.41 vs 0.91 â€‹%; p â€‹= â€‹0.056). CONCLUSION: Dual antibiotic irrigation with G â€‹+ â€‹C did not reduce the risk of surgical site infection during open retromuscular ventral hernia repair.

Savi Scout Radar Localization Versus Wire Localization for Breast Biopsy Regarding Positive Margin, Complication, and Reoperation Rates.

BACKGROUND: Breast cancer is the most commonly diagnosed noncutaneous malignancy and remains the second leading cause of cancer deaths in women. The Savi Scout (Cianna Medical, Merit Medical Systems, Inc. South Jordan, UT) is a wireless, nonradioactive, wave reflection implant system that enables surgeons to remove targeted breast lesions. Our study aims to be the largest comparison of wire and Savi Scout localization techniques for positive margin, complication, and reoperation rates. METHODS: Single-institution retrospective review of 512 patients that had Savi Scout Surgical Guidance System breast lesion biopsy or wire localized breast biopsy from May 2017 to December 2018. A RedCaps database was created and reviewed for outcomes. RESULTS: For 320 Savi scout patients, margins were positive or less than 1 mm in 18 cases (5.6%). 17 (5.3%) patients required reoperation. Surgical site occurrence was found in 7 (2.1%) patients, and 2 patients required intervention (0.6%). For 175 wire localization patients, margins were positive or less than 1 mm in 24 patients, and all required reoperation (13.7%). A surgical site occurrence was found in 13 (7.4%) patients and 5 patients required intervention (2.8%). DISCUSSION: In our series, the Savi Scout localization system resulted in a lower rate of positive margins, reoperation, and surgical site occurrence. These data suggest that Savi Scout localization is a reasonable replacement to wire localization for breast lesions and might produce superior results.