A dataset of demographic and lifestyle risk factors for assessing chronic kidney disease development in diabetic patients

TL;DR

This paper introduces a dataset of 400 diabetic patients in Bangladesh to study risk factors for chronic kidney disease over a decade.

Contribution

The novel contribution is a longitudinal dataset capturing demographic and lifestyle factors for CKD prediction in diabetic patients.

Findings

The dataset includes 20 variables tracking health trajectories over ten years.

185 out of 400 diabetic patients were diagnosed with CKD.

The dataset offers a non-invasive alternative for CKD risk prediction in resource-limited settings.

Abstract

Chronic Kidney Disease (CKD) is a significant comorbidity in diabetic populations, particularly in low- and middle-income countries, where early diagnosis and timely intervention remain critical healthcare challenges. This article presents a curated dataset comprising 400 diabetic patients from BIRDEM General Hospital, Dhaka, Bangladesh, with the aim of supporting early CKD detection, and healthcare planning. Among the 400 patients, 185 were diagnosed with CKD, and 215 were non-CKD cases. All individuals had been leaving with diabetes for at least ten years, enduring a consistent CKD progressing window. The dataset contains 20 variables focused on demographic and lifestyle-related risk factors, including age, gender, occupation type, BMI, family history of diabetes, hypertension, heart disease, physical activity, sleep quality, smoking, water intake, and detailed daily calorie consumption. The unique strength of this dataset lies in its longitudinal structure, which captures the health trajectories of patients over a decade. This temporal data is essential for predicting CKD progression, as it allows for the modelling of risk factors over time, a critical aspect often missed in datasets relying on single-year data. In resource-limited settings, where access to laboratory diagnostics is restricted, this dataset provides a valuable non-invasive alternative for CKD risk prediction. Given the growing global burden of CKD, especially among diabetic populations, this dataset serves as a valuable resource for researchers, healthcare providers, and policymakers seeking cost-effective, scalable strategies for early intervention and prevention.

Figures