METHODS: In this prospective observational study, we measured BCAAs in fasting serum samples collected at inception from 2139 T2D patients free of cardiovascular-renal diseases. The study outcome was the first hospitalization for HF.
RESULTS: During 29 103 person-years of follow-up, 115 primary events occurred (age: 54.8 ± 11.2 years, 48.2% men, median [interquartile range] diabetes duration: 5 years [1-10]). Patients with incident HF had 5.6% higher serum BCAAs than those without HF (median 639.3 [561.3-756.3] vs 605.2 [524.8-708.7] μmol/L; P = .01). Serum BCAAs had a positive linear association with incident HF (per-SD increase in logarithmically transformed BCAAs: hazard ratio [HR] 1.22 [95% CI 1.07-1.39]), adjusting for age, sex, and diabetes duration. The HR remained significant after sequential adjustment of risk factors including incident coronary heart disease (1.24, 1.09-1.41); blood pressure, low-density lipoprotein cholesterol, and baseline use of related medications (1.31, 1.14-1.50); HbA1c , waist circumference, triglyceride, and baseline use of related medications (1.28, 1.11-1.48); albuminuria and estimated glomerular filtration rate (1.28, 1.11-1.48). The competing risk of death analyses showed similar results.
CONCLUSIONS: Circulating levels of BCAAs are independently associated with incident HF in patients with T2D. Prospective cohort analysis and randomized trials are needed to evaluate the long-term safety and efficacy of using different interventions to optimize BCAAs levels in these patients.
METHODS: Two blinded reviewers searched PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases, then selected and graded the risk of bias of observational studies of adults (≥ 18 years) comparing the diagnostic performance of AI algorithms using craniofacial photographs, versus conventional OSA diagnostic criteria (i.e. apnea-hypopnea index [AHI]). Studies were excluded if they detected apneic events without diagnosing OSA. AI models evaluated with a random split test set or k-fold cross-validation were included in a Bayesian bivariate meta-analysis.
RESULTS: From 5,147 records, 6 studies were included, containing 10 AI models trained/tested on 1,417/983 participants. The risk of bias was low. AI trained on craniofacial photographs achieved a pooled 84.9% sensitivity (95% credible interval [95% CrI]: 77.1-90.7%) and 71.2% specificity (95% CrI: 60.7-81.4%). Bayesian meta-regression identified deep learning (convolutional neural networks) as the most accurate AI algorithm (91.1% sensitivity, 79.2% specificity) comparable to home sleep apnea tests. AHI cutoffs, OSA prevalence, feature engineering, input data, camera type and informativeness of Bayesian prior did not alter diagnostic accuracy. There was no substantial publication bias.
CONCLUSION: AI trained on craniofacial photographs have high diagnostic accuracy and should be considered as a low-cost OSA screening tool. Future work focused on deep learning using smartphone images could improve the feasibility of this approach in primary care.