Publications

Research
foundation.

Daibeats is built on research in ECG signal processing, physiological modelling, and machine learning. The work below was carried out by Md Basit Azam with co-author S. I. Singh as part of doctoral research at Tezpur University, research that began before Daibeats was founded in 2026. We list it here because it is the evidence base the company is built on.

July 21, 2025

When Validation Fails: Cross-Institutional Blood Pressure Prediction and the Limits of Electronic Health Record-Based Models

When Validation Fails: Cross-Institutional Blood Pressure Prediction and the Limits of Electronic Health Record-Based Models

External validation remains rare in healthcare machine learning despite being critical for establishing real-world feasibility. We developed an ensemble framework to predict blood pressure from electronic health records, incorporating rigorous data leakage prevention.

Azam, M.B. & Singh, S.I. · 2025

arXiv preprint · Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

DOI: 10.48550/arXiv.2507.19530

April 1, 2026

Re-evaluating heart rate variability biomarkers for glucose sensing: the impact of age normalisation and subject-independent validation

Re-evaluating heart rate variability biomarkers for glucose sensing: the impact of age normalisation and subject-independent validation

Heart rate variability (HRV) derived from electrocardiogram (ECG) signals offers a promising non-invasive window into glycemic status; however, existing studies frequently combine distinct glucose measurements and employ validation strategies susceptible to data leakage. Because HRV declines by approximately 3–5% per decade due to age-related autonomic degeneration, absolute HRV values conflate the effects of aging with diabetes-specific autonomic dysfunction. We hypothesised that normalising HRV features using an age-dependent scaling factor would isolate the diabetes-specific component and improve glycemic status estimation.

Azam, M.B. & Singh, S.I. · 2026

BMC Medical Informatics and Decision Making (peer-reviewed)

DOI: 10.1186/s12911-026-03455-8

October 6, 2026

MIMIC-IV-Ext-ECG-Glucose: Temporally Aligned 12-Lead ECG and Laboratory Blood Glucose Pairs with Quality and Pharmacological Annotations

MIMIC-IV-Ext-ECG-Glucose: Temporally Aligned 12-Lead ECG and Laboratory Blood Glucose Pairs with Quality and Pharmacological Annotations

A PhysioNet dataset providing temporally aligned 12-lead ECG and laboratory blood glucose pairs, with quality and pharmacological annotations, to support research in ECG-based glucose estimation and machine learning. Version 1.0.0.

Azam, Md Basit & Singh, Sarangthem · 2026

PhysioNet

DOI: 10.13026/nts2-vj76