A novel electronic health record-based, machine-learning model to predict severe hypoglycemia leading to hospitalizations in older adults with diabetes: A territory-wide cohort and modeling study.

BACKGROUND: Older adults with diabetes are at high risk of severe hypoglycemia (SH). Many machine-learning (ML) models predict short-term hypoglycemia are not specific for older adults and show poor precision-recall. We aimed to develop a multidimensional, electronic health record (EHR)-based ML model to predict one-year risk of SH requiring hospitalization in older adults with diabetes. METHODS AND FINDINGS: We adopted a case-control design for a retrospective territory-wide cohort of 1,456,618 records from 364,863 unique older adults (age ≥65 years) with diabetes and at least 1 Hong Kong Hospital Authority attendance from 2013 to 2018. We used 258 predictors including demographics, admissions, diagnoses, medications, and routine laboratory tests in a one-year period to predict SH events requiring hospitalization in the following 12 months. The cohort was randomly split into training, testing, and internal validation sets in a 7:2:1 ratio. Six ML algorithms were evaluated including logistic-regression, random forest, gradient boost machine, deep neural network (DNN), XGBoost, and Rulefit. We tested our model in a temporal validation cohort in the Hong Kong Diabetes Register with predictors defined in 2018 and outcome events defined in 2019. Predictive performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC) statistics, and positive predictive value (PPV). We identified 11,128 SH events requiring hospitalization during the observation periods. The XGBoost model yielded the best performance (AUROC = 0.978 [95% CI 0.972 to 0.984]; AUPRC = 0.670 [95% CI 0.652 to 0.688]; PPV = 0.721 [95% CI 0.703 to 0.739]). This was superior to an 11-variable conventional logistic-regression model comprised of age, sex, history of SH, hypertension, blood glucose, kidney function measurements, and use of oral glucose-lowering drugs (GLDs) (AUROC = 0.906; AUPRC = 0.085; PPV = 0.468). Top impactful predictors included non-use of lipid-regulating drugs, in-patient admission, urgent emergency triage, insulin use, and history of SH. External validation in the HKDR cohort yielded AUROC of 0.856 [95% CI 0.838 to 0.873]. Main limitations of this study included limited transportability of the model and lack of geographically independent validation. CONCLUSIONS: Our novel-ML model demonstrated good discrimination and high precision in predicting one-year risk of SH requiring hospitalization. This may be integrated into EHR decision support systems for preemptive intervention in older adults at highest risk.

Pharmacokinetic properties of single-dose lamivudine/adefovir dipivoxil fixed-dose combination in healthy Chinese male volunteers.

BACKGROUND: Both lamivudine and adefovir dipivoxil are approved for the treatment of chronic hepatitis B (CHB) and have established safety profiles. A fixed-dose combination (FDC) formulation of lamivudine/adefovir dipivoxil for the treatment of CHB may provide dosing convenience and improve adherence. OBJECTIVE: This study compared the pharmacokinetic profiles of an FDC capsule containing lamivudine/adefovir dipivoxil 100/10 mg and conventional lamivudine 100-mg + adefovir dipivoxil 10-mg tablets to determine bioequivalence. METHODS: This randomized, open-label, single-dose, 2-period crossover study was conducted in healthy male Chinese subjects. The study included a screening visit, 2 treatment sessions, and a follow-up visit. Subjects who met the inclusion/exclusion criteria were assigned to receive, in randomized order, 1 FDC capsule or 1 tablet each of lamivudine and adefovir dipivoxil. After a 7- to 10-day washout period, alternate treatment was given to the subjects during the second treatment session. Blood samples were collected immediately before and after dosing for 48 hours for plasma drug concentration measurement. Data on adverse events (AEs) were collected from the start of dosing until the follow-up visit. Tolerability assessments included physical examinations with vital sign measurements and clinical laboratory evaluations throughout the study. RESULTS: Forty subjects were enrolled into the study (mean age, 22.4 years [range, 19-28 years]; weight, 63.8 kg [range, 54-78 kg]). The pharmacokinetic profiles of lamivudine and adefovir were similar between the FDC and reference formulations. The geometric mean ratios (GMRs) for lamivudine C(max) and AUC(0-last) were 1.02 (90% CI, 0.92-1.12) and 0.99 (90% CI, 0.95-1.04), respectively; adefovir, 0.94 (90% CI, 0.89-0.99) and 0.95 (90% CI, 0.91-1.00). A limited number of mild AEs were reported, with no clinically significant changes in vital signs or laboratory results. CONCLUSIONS: The FDC capsule was bioequivalent to the concurrent administration of lamivudine + adefovir dipivoxil tablets based on the 90% CIs of the GMRs for C(max), AUC(0-∞), AUC(0-last), and t12 (all were between 0.80 and 1.25). Both treatments were well-tolerated.