Publications by authors named "T L Joon"
Article Synopsis
- The study focused on developing a machine-learning model to help health systems in Alberta, Canada, identify older adults (aged 65 and older) at risk for falls and related hospital admissions, using 2018-2019 administrative health data.
- The CatBoost model showed promising results with a c-statistic of 0.70, indicating moderate accuracy, and predicted fall-related events among a large group of participants (224,445).
- The findings suggest that targeting interventions for the highest risk groups could lead to significant cost savings in the healthcare system, with potential savings of up to $C16 million by focusing on the top 25-50% of predicted risk.
Objective: To develop a machine-learning (ML) model using administrative data to estimate risk of adverse outcomes within 30-days of a benzodiazepine (BZRA) dispensation in older adults for use by health departments/regulators.
Design, Setting And Participants: This study was conducted in Alberta, Canada during 2018-2019 in Albertans 65 years of age and older. Those with any history of malignancy or palliative care were excluded.
Purpose: The contributions of hypertension and diabetes to microvascular dysfunction in the kidney and eye were investigated. Two indices of microvascular dysfunction, urinary albumin excretion rate (AER) and albumin vascular clearance (AVC) in the eye, were studied in control and streptozocin diabetic Wistar Kyoto (WKY) and spontaneously hypertensive rats (SHR).
Methods: Studies were performed on four groups of untreated rats--nondiabetic and diabetic WKY and nondiabetic and diabetic SHR--and on three groups of diabetic SHR treated with a converting enzyme inhibitor (perindopril), a calcium-channel blocker (lacidipine), or triple therapy (hydrochlorothiazide, reserpine, and hydralazine).