Predicting Therapeutic Response to Hypoglossal Nerve Stimulation Using Deep Learning.

OBJECTIVES: To develop and validate machine learning (ML) and deep learning (DL) models using drug-induced sleep endoscopy (DISE) images to predict the therapeutic efficacy of hypoglossal nerve stimulator (HGNS) implantation. METHODS: Patients who underwent DISE and subsequent HGNS implantation at a tertiary care referral center were included. Six DL models and five ML algorithms were trained on images from the base of tongue (BOT) and velopharynx (VP) from patients classified as responders or non-responders as defined by Sher's criteria (50% reduction in apnea-hypopnea index (AHI) and AHI < 15 events/h). Precision, recall, F1 score, and overall accuracy were evaluated as measures of performance. RESULTS: In total, 25,040 images from 127 patients were included, of which 16,515 (69.3%) were from responders and 8,262 (30.7%) from non-responders. Models trained on the VP dataset had greater overall accuracy when compared to BOT alone and combined VP and BOT image sets, suggesting that VP images contain discriminative features for identifying therapeutic efficacy. The VCG-16 DL model had the best overall performance on the VP image set with high training accuracy (0.833), F1 score (0.78), and recall (0.883). Among ML models, the logistic regression model had the greatest accuracy (0.685) and F1 score (0.813). CONCLUSION: Deep neural networks have potential to predict HGNS therapeutic efficacy using images from DISE, facilitating better patient selection for implantation. Development of multi-institutional data and image sets will allow for development of generalizable predictive models. LEVEL OF EVIDENCE: N/A Laryngoscope, 2024.

Effect of Sugar Replacement with Stevia-Based Tabletop Sweetener on Weight and Cardiometabolic Health among Indian Adults.

Added sugars contribute to caloric intake in the diet, which may lead to conditions like obesity. Replacing added sugar with a natural sugar substitute like zero-calorie stevia may help in reducing sugar and caloric intake. METHODS: An open-label, single-arm pilot study was conducted to evaluate the efficacy and safety of a stevia-based tabletop sweetener among overweight subjects with normal blood sugar levels (n = 24) and overweight prediabetic subjects (n = 21). Subjects were instructed to replace added sugar in their daily diet with the test product over a study period of 90 days. Primary outcomes included change in body weight and waist circumference, while the secondary outcomes included change in blood glucose (PPBG), body mass index (BMI), and lipid parameters evaluated at baseline, 30 days, 60 days, and 90 days. Glycated hemoglobin (HbA1c) was evaluated at baseline and 90 days. RESULTS: When compared with the baseline, a significant reduction in weight (p < 0.001) and waist circumference (p < 0.001) was observed at Day 90 in overweight subjects. Similarly, in overweight prediabetic subjects, a significant reduction in weight (p < 0.001) and waist circumference (p < 0.05) with non-significant change in HbA1c was observed at Day 90 from baseline. In a subgroup analysis, among the subjects who lost weight, 2.12 kg (n = 35) weight loss and 4.78 cm (n = 32) reduction in waist circumference were observed at 90 days. No adverse outcomes were reported throughout the study period. The consumption of steviol glycosides was within the acceptable daily intake (ADI). CONCLUSIONS: Replacing added sugar in the daily diet with stevia-based tabletop sweetener, along with a physical activity regimen, promotes weight loss and reduction in waist circumference in overweight subjects with normal blood sugar levels and prediabetic subjects (CTRI/2019/12/022470).

Formulation and pharmacokinetic evaluation of hard gelatin capsule encapsulating lyophilized Vasa Swaras for improved stability and oral bioavailability of vasicine.

The oral bioavailability of vasicine (1) was investigated in hard gelatin capsules of lyophilized Vasa Swaras (aqueous extract of Adhatoda vasica Nees.,Fam.: Acanthaceae) The rat pharmacokinetic profile of lyophilized Vasa Swaras, Vasa Swaras, vasicine (1) (chief marker compounds of A. vasica) and a marketed capsule formulation of A. vasica were compared. Vasicine (1) was found to be more orally bioavailable from lyophilized Vasa Swaras, with an overall minor conversion to vasicinone (2).