This study examined the use of potentially inappropriate medicines that may affect cognition (PIMcog) in people with dementia and its associated factors. Medical records of all outpatients with dementia attending a tertiary hospital in Vietnam between January 1, 2015, and December 31, 2016, were examined. Medicine use was assessed against a list of PIMcog. Variables associated with having a PIMcog were assessed using a multiple logistic regression. Of the 128 patients, 41% used a PIMcog, 39.1% used cholinesterase inhibitors (CEIs) concomitantly with anticholinergics, and 18% used antipsychotics. The number of hospital visits (adjusted odds ratio [OR]: 1.08; 95% confidence interval [CI]: 1.02-1.16) and number of treating specialists (adjusted OR: 0.61; 95% CI: 0.45-0.83) were associated with PIMcog use. This study highlights a high-level use of medicines that can further impair cognition or reduce the effectiveness of CEIs in people with dementia. Efforts to improve quality use of medicines for this population are warranted.
Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary care physicians (PCPs), particularly in low-resource settings. Here, to bridge the gaps, we developed an integrated image-language system (DeepDR-LLM), combining a large language model (LLM module) and image-based deep learning (DeepDR-Transformer), to provide individualized diabetes management recommendations to PCPs. In a retrospective evaluation, the LLM module demonstrated comparable performance to PCPs and endocrinology residents when tested in English and outperformed PCPs and had comparable performance to endocrinology residents in Chinese. For identifying referable DR, the average PCP's accuracy was 81.0% unassisted and 92.3% assisted by DeepDR-Transformer. Furthermore, we performed a single-center real-world prospective study, deploying DeepDR-LLM. We compared diabetes management adherence of patients under the unassisted PCP arm (n = 397) with those under the PCP+DeepDR-LLM arm (n = 372). Patients with newly diagnosed diabetes in the PCP+DeepDR-LLM arm showed better self-management behaviors throughout follow-up (P