Prevalence, risk-factors and early prediction of impaired kidney function among indigenous adults in Odisha, India: A secondary analysis.
6 affiliations
- 1ICMR-National Institute of Health Research, Bhubaneswar, Odisha, India.
- 2Model Rural Health Research Unit, Sheragada, Ganjam, Odisha, India.
- 3Care and Public Health Research Institute (CAPHRI), Maastricht University, Maastricht, The Netherlands.
- 4ICMR-National Institute for Research in Digital Health, New Delhi, India.
- 5The George Institute for Global Health, New Delhi, India.
- 6Indian Council of Medical Research, New Delhi, India.
Abstract
Background and objectives Native and indigenous communities have a high burden of chronic kidney disease (CKD). The burden of this condition amongst the indigenous populations of India is poorly documented. We estimated the prevalence and determinants of impaired kidney function among indigenous adults in Odisha, using large scale sample survey data, employing machine learning models. Methods We analysed data from 19,703 adults across 53 indigenous communities enrolled in the Odisha Tribal Family Health Survey (OTFHS, 2022-23). Data were collected with serum creatinine, from which estimated glomerular filtration rate (eGFR) was derived using chronic kidney disease epidemiology collaboration equation (CKD-EPI). Impaired kidney function (IKF) was defined as eGFR <90 mL/min/1.73m2 and classified into mild, moderate, severe, and failure categories. Deep neural network (DNN) and eXtreme gradient boosting (XGBoost) models were developed for early prediction for IKF. Results Overall, 24.8% [95% confidence interval (CI): 23.8-25.9] of participants had IKF: 16.6% mild, 6.4% moderate, 1.5% severe, and 0.3% kidney failure. The prevalence increased with age (5.6% in 18-30 y vs. 79.4% in >70 y) and was higher among men, those with lower education, tobacco or alcohol use, and individuals with hypertension, diabetes, or underweight. The DNN model showed good predictive performance (accuracy 0.78; recall 0.69), with improved recall (0.78) at a threshold of 0.4. Decision curve analysis suggested a potential benefit of machine learning (ML) based targeted screening. Shapley Additive explanations (SHAP) analysis identified age, hypertension, diabetes, tobacco use, alcohol use, and low dietary diversity as key predictors. Interpretations and conclusions Nearly one in four adults from indigenous communities in Odisha had IKF, highlighting a substantial and inequitable kidney disease burden. Machine learning models using routine data offer a feasible strategy for early detection and targeted interventions in resource-limited indigenous settings.
Related
- Early Life Programming of Impaired Neurocognitive Function—What Does It Mean for Public Health?
- Impaired Left Atrial Function in Patients with Embolic Stroke of Undetermined Source
- Genetic Aspects of Reproductive Function Disorders in Men with Impaired Semen Parameters
- Developmental myelination deficits and impaired fine motor function in a mouse model of pediatric obstructive sleep apnea
- Incidence of left ventricular thrombus and subclinical cerebral infarction by magnetic resonance imaging 2 weeks after anterior ST-elevation myocardial infarction with impaired left ventricular function and apical akinesis
BibTeX
@article{kshatri2026prevalence,
title = {{Prevalence, risk-factors and early prediction of impaired kidney function among indigenous adults in Odisha, India: A secondary analysis.}},
author = {Jaya Singh Kshatri and Vishal Deo and Kavitha A K and Tanveer Rehman and Vivekananda Jha and Sanghamitra Pati},
journal = {The Indian journal of medical research},
year = {2026},
month = aug,
doi = {10.25259/ijmr_491_2026},
url = {https://europepmc.org/article/MED/42851230},
note = {CC BY-NC-SA},
}
RIS
TY - JOUR
TI - Prevalence, risk-factors and early prediction of impaired kidney function among indigenous adults in Odisha, India: A secondary analysis.
AU - Jaya Singh Kshatri
AU - Vishal Deo
AU - Kavitha A K
AU - Tanveer Rehman
AU - Vivekananda Jha
AU - Sanghamitra Pati
PY - 2026
DA - 2026/08/01
JO - The Indian journal of medical research
DO - 10.25259/ijmr_491_2026
UR - https://europepmc.org/article/MED/42851230
AB - Background and objectives Native and indigenous communities have a high burden of chronic kidney disease (CKD). The burden of this condition amongst the indigenous populations of India is poorly documented. We estimated the prevalence and determinants of impaired kidney function among indigenous adults in Odisha, using large scale sample survey data, employing machine learning models. Methods We analysed data from 19,703 adults across 53 indigenous communities enrolled in the Odisha Tribal Family Health Survey (OTFHS, 2022-23). Data were collected with serum creatinine, from which estimated glomerular filtration rate (eGFR) was derived using chronic kidney disease epidemiology collaboration equation (CKD-EPI). Impaired kidney function (IKF) was defined as eGFR <90 mL/min/1.73m2 and classified into mild, moderate, severe, and failure categories. Deep neural network (DNN) and eXtreme gradient boosting (XGBoost) models were developed for early prediction for IKF. Results Overall, 24.8% [95% confidence interval (CI): 23.8-25.9] of participants had IKF: 16.6% mild, 6.4% moderate, 1.5% severe, and 0.3% kidney failure. The prevalence increased with age (5.6% in 18-30 y vs. 79.4% in >70 y) and was higher among men, those with lower education, tobacco or alcohol use, and individuals with hypertension, diabetes, or underweight. The DNN model showed good predictive performance (accuracy 0.78; recall 0.69), with improved recall (0.78) at a threshold of 0.4. Decision curve analysis suggested a potential benefit of machine learning (ML) based targeted screening. Shapley Additive explanations (SHAP) analysis identified age, hypertension, diabetes, tobacco use, alcohol use, and low dietary diversity as key predictors. Interpretations and conclusions Nearly one in four adults from indigenous communities in Odisha had IKF, highlighting a substantial and inequitable kidney disease burden. Machine learning models using routine data offer a feasible strategy for early detection and targeted interventions in resource-limited indigenous settings.
SN - 0971-5916
ER -