JMIR Publications

ABSTRACT

Background:

Diabetes Mellitus is a major non-communicable disease with significant increase in prevalence, especially in low middle-income countries. The latest IDF Diabetes Atlas (2025) reports that 11.1% of the adult population (20-79 years old) is living with diabetes, with over 4 in 10 unaware that they have the condition. Early diagnosis and treatment of Diabetes reduce the risk and slows the progression of debilitating complications such as amputation, vision loss, and renal failure, cardiovascular disease, dementia, some cancers, and infections such as tuberculosis and severe COVID-19. Current screening methods for diabetes are invasive and costly. This has limited its utilisation especially in a high-density population, low-middle income country such as Indonesia. Blood Glucose Evaluation and Monitoring (BGEM) is a machine learning (ML) algorithm developed by Actxa to analyse Photoplethysmography (PPG) data from wearable devices for diabetic risk assessment. It is non-invasive and user-friendly nature makes it a strong candidate for fulfilling the need for a diabetes screening or monitoring tool.

Objective:

The aim of this study is to collect a larger and more diverse dataset, with particular attention to glycaemic and demographic variability, for the training of BGEM ML models. This dataset is intended to improve model generalizability and to evaluate performance across different racial groups and skin types, with the goal of enhancing accuracy and robustness for diabetes risk assessment.

Methods:

Adult participants aged 18 years old and above, either with a diabetic or non-diabetic history that resides in Greater Jakarta Area, Indonesia were approached for recruitment. Blood glucose was assessed using laboratory blood analysis from capillary or plasma samples at after fasting, 1 hour, 2 hour and 3 hours after meal. BGEM data was also collected at each of these time points. Anthropological measurement, a standardize questionnaire on physical activity, demographic information, respondent’s diabetic status and current medications taken were also collected.

Results:

Between June and October 2024, 885 participants were enrolled. Eight PPG recordings per participant were collected across four meal-time points using two wearable devices in addition to collection of clinical measurements, blood sampling and related questionnaires.

Conclusions:

This protocol paper outlines the methodology designed for assessing and interpreting participants’ blood sugar profiles especially on demographic and glycaemic variability in order to evaluate BGEM, a PPG-based AI model designed to estimate blood glucose levels and diabetic risk. The clinical trial was conducted on both diabetic (DM) and non-diabetic (non-DM) Indonesian subjects, while considering various influencing factors. This dataset is designed to enable assessment of the model’s performance across diverse racial, risk factors and skin-type groups, with the aim at making the model more valid and reliable. Clinical Trial: Clinical trial registration NCT06642467 Institutional Review Board of Ukrida faculty of medicine & health sciences ethical committee 1779/SLKE/IM/UKKW /FKIK/KEPK /VII/2024 approved on 15th of July 2024