[Paper Review] Prevalence and Major Risk Factors of Non-communicable Diseases: A Machine Learning based Cross-Sectional Study

Mrinmoy Roy, Anica Tasnim Protity+2 more|arXiv (Cornell University)|Mar 3, 2023

Global Public Health Policies and EpidemiologyBusiness, Management and Accounting3 citations

TL;DR

This machine learning-based cross-sectional study investigates the prevalence and risk factors of non-communicable diseases (NCDs) among adult patients in Dhaka, Bangladesh. Using statistical tests and data analysis on a cohort, it reveals that cardiovascular disease (CVD) is the most prevalent NCD (83.56%), with strong associations between CVD, diabetes, obesity, and multiple comorbidities—particularly in males and middle-aged individuals.

ABSTRACT

Objective: The study aimed to determine the prevalence of several non-communicable diseases (NCD) and analyze risk factors among adult patients seeking nutritional guidance in Dhaka, Bangladesh. Result: Our study observed the relationships between gender, age groups, obesity, and NCDs (DM, CKD, IBS, CVD, CRD, thyroid). The most frequently reported NCD was cardiovascular issues (CVD), which was present in 83.56% of all participants. CVD was more common in male participants. Consequently, male participants had a higher blood pressure distribution than females. Diabetes mellitus (DM), on the other hand, did not have a gender-based inclination. Both CVD and DM had an age-based progression. Our study showed that chronic respiratory illness was more frequent in middle-aged participants than in younger or elderly individuals. Based on the data, every one in five hospitalized patients was obese. We analyzed the co-morbidities and found that 31.5% of the population has only one NCD, 30.1% has two NCDs, and 38.3% has more than two NCDs. Besides, 86.25% of all diabetic patients had cardiovascular issues. All thyroid patients in our study had CVD. Using a t-test, we found a relationship between CKD and thyroid (p-value 0.061). Males under 35 years have a statistically significant relationship between thyroid and chronic respiratory diseases (p-value 0.018). We also found an association between DM and CKD among patients over 65 (p-value 0.038). Moreover, there has been a statistically significant relationship between CKD and Thyroid (P < 0.05) for those below 35 and 35-65. We used a two-way ANOVA test to find the statistically significant interaction of heart issues and chronic respiratory illness, in combination with diabetes. The combination of DM and RTI also affected CKD in male patients over 65 years old.

Motivation & Objective

• To assess the prevalence of non-communicable diseases (NCDs) such as diabetes mellitus (DM), chronic kidney disease (CKD), cardiovascular disease (CVD), and others among adult patients in Dhaka, Bangladesh.
• To identify major demographic and clinical risk factors associated with NCDs using statistical and machine learning-informed analysis.
• To examine comorbidity patterns and interrelationships among NCDs, especially focusing on gender, age, and obesity.
• To evaluate the statistical significance of associations between specific NCDs, such as CVD with thyroid disorders or DM with CKD.
• To provide evidence-based insights for public health interventions targeting high-risk populations in low-resource urban settings.

Proposed method

• Conducted a cross-sectional study using anonymized patient data from individuals seeking nutritional guidance in Dhaka, Bangladesh.
• Applied inferential statistical methods including t-tests, two-way ANOVA, and p-value analysis to assess associations between NCDs and demographic/clinical variables.
• Used prevalence estimation to determine the frequency of individual and co-occurring NCDs across age groups and genders.
• Employed machine learning-informed data analysis to detect patterns and interactions among multiple NCDs and risk factors.
• Classified participants by age groups (under 35, 35–65, over 65), gender, and BMI status to evaluate subgroup-specific disease patterns.
• Calculated comorbidity rates and assessed statistical significance of observed associations using p-values and confidence thresholds (p < 0.05).

Experimental results

Research questions

• RQ1 What is the prevalence of major non-communicable diseases (NCDs) such as CVD, DM, CKD, and thyroid disorders among adult patients in Dhaka, Bangladesh?
• RQ2 How do gender and age group influence the risk and distribution of specific NCDs, particularly CVD and DM?
• RQ3 What is the extent of comorbidity among NCDs, and which combinations are most prevalent in the study population?
• RQ4 Are there statistically significant associations between specific NCDs (e.g., CVD with thyroid disease or CKD with DM) across different age and gender subgroups?
• RQ5 How do obesity and age interact with the risk of developing multiple NCDs in this population?

Key findings

• Cardiovascular disease (CVD) was the most prevalent NCD, affecting 83.56% of all participants, with a higher prevalence in males compared to females.
• Diabetes mellitus (DM) showed no significant gender-based difference but exhibited age-related progression, with a statistically significant association with CKD among patients over 65 years (p-value 0.038).
• Among hospitalized patients, 20% were obese, and 38.3% had more than two NCDs, indicating a high burden of multimorbidity.
• 86.25% of diabetic patients also had cardiovascular issues, and all thyroid patients in the study had comorbid CVD, suggesting a strong link between thyroid disorders and CVD.
• A statistically significant relationship was found between CKD and thyroid disorders in individuals under 35 and in the 35–65 age group (p < 0.05), and between thyroid and chronic respiratory disease in males under 35 (p-value 0.018).
• The combination of DM and respiratory tract infections (RTI) significantly affected CKD risk in male patients over 65, as revealed by two-way ANOVA (p-value 0.038).