Title

Use of machine learning to predict hypertension based on BMI and routine lab data

Authors

Amisha Sood¹*, Sangeeta Gupta², Shweta Ramnarayan Borkar³, Amrit Podder⁴ & Parth Jani⁵

Affiliation

¹Department of Psychiatry, Wrexham Maelor Hospital, Wrexham; ²Department of Physiology, AIIMS Gorakhpur, Uttar Pradesh, India; ³Department of Internal Medicine, Datta Meghe Medical College, Datta Meghe Institute of Higher Education and Research, Nagpur, India; ⁴Department of Physiology, Teerthanker Mahaveer Medical College & Research Centre, Teerthanker Mahaveer University, Moradabad, Uttar Pradesh, India; ⁵Department of General Medicine, All India Institute of Medical Sciences, Rajkot, Gujarat, India; *Corresponding author

Email

Amisha Sood - E-mail: amishasoodo612@gmail.com
Sangeeta Gupta - E-mail: drsangeeta77.65@rediffmail.com
Shweta Ramnarayan Borkar - E-mail: drshwetaborkar@gmail.com
Amrit Podder - E-mail: amritpodder0@gmail.com
Parth Jani - E-mail: parthjani13@gmail.com

Article Type

Research Article

Date

Received October 1, 2025; Revised October 31, 2025; Accepted October 31, 2025, Published October 31, 2025

Abstract

Random Forest machine learning model could be used to classify hypertension using BMI and regular laboratory characteristics. The overall number of participants included in the analysis was 150 and multiple models were trained on key clinical variables including fasting glucose, LDL and BMI. The Random Forest model revealed the best predictive accuracy of 88.0%. Thus, we show the possibility of applying non-invasive poor data to early detection of hypertension. According to the study, machine learning could increase the effectiveness of screening and patient outcomes.

Keywords

BMI, fasting glucose, hypertension, LDL, machine learning

Citation

Sood et al. Bioinformation 21(10): 3645-3648 (2025)

Edited by

Ritik Kashwani

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.