Population Health-Based Machine Learning Reveals Associations Between Psychosocial Factors and Chronic Kidney Disease

arXiv cs.LG Papers

Summary

The paper presents a two-part study using machine learning on large-scale telehealth data to classify self-reported chronic kidney disease status and identify key psychosocial and medical predictors, achieving balanced accuracy around 72-76% with SHAP analysis for interpretability.

arXiv:2608.17174v1 Announce Type: new Abstract: Chronic kidney disease (CKD) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes. We present a two-part study that combines large-scale telehealth data with advanced machine learning to both classify self-reported CKD status and identify key drivers of disease. Using selected features from the Behavioral Risk Factor Surveillance System (BRFSS 2021: 438,693 samples; BRFSS 2019: 418,268 samples) and the National Health Interview Survey (NHIS 2021: 29,482 samples; NHIS 2020: 31,568 samples), we addressed missing data with nine state-of-the-art imputation methods and mitigated class imbalance via sampling strategies. Our customized stacked ensemble model achieved balanced accuracy of 72.56-76.12%, with corresponding AUROC scores of 79.59-82.29%. SHapley Additive exPlanations (SHAP) analysis, followed by clinical review, highlighted critical predictors, including regular medical check-ups, age, blood pressure, and indicators of mental health stress. These findings deliver a robust and interpretable framework for CKD risk stratification and provide actionable insights into its associated factors.
Original Article
View Cached Full Text

Cached at: 08/19/26, 10:23 AM

# Population Health-Based Machine Learning Reveals Associations Between Psychosocial Factors and Chronic Kidney Disease
Source: [https://arxiv.org/abs/2608.17174](https://arxiv.org/abs/2608.17174)
Authors:[Md\. Atik Shams](https://arxiv.org/search/cs?searchtype=author&query=Shams,+M+A),[David Eisenberg](https://arxiv.org/search/cs?searchtype=author&query=Eisenberg,+D),[Sumaiya Fatema](https://arxiv.org/search/cs?searchtype=author&query=Fatema,+S),[Asma Sultana](https://arxiv.org/search/cs?searchtype=author&query=Sultana,+A),[D\. M Hasibul Islam](https://arxiv.org/search/cs?searchtype=author&query=Islam,+D+M+H),[Junnatul Mawa](https://arxiv.org/search/cs?searchtype=author&query=Mawa,+J),[Anindita Datta](https://arxiv.org/search/cs?searchtype=author&query=Datta,+A),[Nafiya Ahmed](https://arxiv.org/search/cs?searchtype=author&query=Ahmed,+N),[Danastan Tasaouf Mridula](https://arxiv.org/search/cs?searchtype=author&query=Mridula,+D+T),[SK\. Sazid Mahmud](https://arxiv.org/search/cs?searchtype=author&query=Mahmud,+S+S),[Simon Bin Akter](https://arxiv.org/search/cs?searchtype=author&query=Akter,+S+B),[Tanjila Helaly](https://arxiv.org/search/cs?searchtype=author&query=Helaly,+T),[Jorge Fresneda Fernandez](https://arxiv.org/search/cs?searchtype=author&query=Fernandez,+J+F),[Humayera Islam](https://arxiv.org/search/cs?searchtype=author&query=Islam,+H),[Tanmoy Sarkar Pias](https://arxiv.org/search/cs?searchtype=author&query=Pias,+T+S)

[View PDF](https://arxiv.org/pdf/2608.17174)

> Abstract:Chronic kidney disease \(CKD\) progresses silently and severely undermines quality of life, making early detection critical for improving patient outcomes\. We present a two\-part study that combines large\-scale telehealth data with advanced machine learning to both classify self\-reported CKD status and identify key drivers of disease\. Using selected features from the Behavioral Risk Factor Surveillance System \(BRFSS 2021: 438,693 samples; BRFSS 2019: 418,268 samples\) and the National Health Interview Survey \(NHIS 2021: 29,482 samples; NHIS 2020: 31,568 samples\), we addressed missing data with nine state\-of\-the\-art imputation methods and mitigated class imbalance via sampling strategies\. Our customized stacked ensemble model achieved balanced accuracy of 72\.56\-76\.12%, with corresponding AUROC scores of 79\.59\-82\.29%\. SHapley Additive exPlanations \(SHAP\) analysis, followed by clinical review, highlighted critical predictors, including regular medical check\-ups, age, blood pressure, and indicators of mental health stress\. These findings deliver a robust and interpretable framework for CKD risk stratification and provide actionable insights into its associated factors\.

## Submission history

From: Tanmoy Sarkar Pias \[[view email](https://arxiv.org/show-email/120e3cb1/2608.17174)\] **\[v1\]**Mon, 17 Aug 2026 22:22:13 UTC \(4,074 KB\)

Similar Articles