Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bridging the Gap in Bangla Healthcare: Machine Learning Based Disease Prediction Using a Symptoms-Disease Dataset

Rowzatul Zannat, Abdullah Al Shafi, Abdul Muntakim

TL;DR

This paper addresses the scarcity of Bangla-language resources for disease prediction by constructing a public Bangla symptoms-disease dataset with 758 symptom-disease relationships across 85 diseases. It preprocesses the data with one-hot encoding, label encoding, scaling, and PCA, and evaluates eight classifiers, followed by soft and hard voting ensembles. Ensemble methods achieve up to 98% accuracy on a held-out test set, demonstrating strong generalization for Bangla symptom inputs. The dataset and methods advance localized health informatics and have potential to improve equitable access to early disease screening for Bangla-speaking communities.

Abstract

Increased access to reliable health information is essential for non-English-speaking populations, yet resources in Bangla for disease prediction remain limited. This study addresses this gap by developing a comprehensive Bangla symptoms-disease dataset containing 758 unique symptom-disease relationships spanning 85 diseases. To ensure transparency and reproducibility, we also make our dataset publicly available. The dataset enables the prediction of diseases based on Bangla symptom inputs, supporting healthcare accessibility for Bengali-speaking populations. Using this dataset, we evaluated multiple machine learning models to predict diseases based on symptoms provided in Bangla and analyzed their performance on our dataset. Both soft and hard voting ensemble approaches combining top-performing models achieved 98\% accuracy, demonstrating superior robustness and generalization. Our work establishes a foundational resource for disease prediction in Bangla, paving the way for future advancements in localized health informatics and diagnostic tools. This contribution aims to enhance equitable access to health information for Bangla-speaking communities, particularly for early disease detection and healthcare interventions.

Bridging the Gap in Bangla Healthcare: Machine Learning Based Disease Prediction Using a Symptoms-Disease Dataset

TL;DR

This paper addresses the scarcity of Bangla-language resources for disease prediction by constructing a public Bangla symptoms-disease dataset with 758 symptom-disease relationships across 85 diseases. It preprocesses the data with one-hot encoding, label encoding, scaling, and PCA, and evaluates eight classifiers, followed by soft and hard voting ensembles. Ensemble methods achieve up to 98% accuracy on a held-out test set, demonstrating strong generalization for Bangla symptom inputs. The dataset and methods advance localized health informatics and have potential to improve equitable access to early disease screening for Bangla-speaking communities.

Abstract

Increased access to reliable health information is essential for non-English-speaking populations, yet resources in Bangla for disease prediction remain limited. This study addresses this gap by developing a comprehensive Bangla symptoms-disease dataset containing 758 unique symptom-disease relationships spanning 85 diseases. To ensure transparency and reproducibility, we also make our dataset publicly available. The dataset enables the prediction of diseases based on Bangla symptom inputs, supporting healthcare accessibility for Bengali-speaking populations. Using this dataset, we evaluated multiple machine learning models to predict diseases based on symptoms provided in Bangla and analyzed their performance on our dataset. Both soft and hard voting ensemble approaches combining top-performing models achieved 98\% accuracy, demonstrating superior robustness and generalization. Our work establishes a foundational resource for disease prediction in Bangla, paving the way for future advancements in localized health informatics and diagnostic tools. This contribution aims to enhance equitable access to health information for Bangla-speaking communities, particularly for early disease detection and healthcare interventions.
Paper Structure (29 sections, 4 equations, 3 figures, 6 tables)

This paper contains 29 sections, 4 equations, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. A Bangla Symptoms-Disease Dataset
  4. Proposed Methodology
  5. Data Cleaning
  6. Preprocessing
  7. Feature Encoding
  8. Target Encoding
  9. Feature Scaling
  10. Dimensionality Reduction
  11. Classification Algorithms
  12. Perceptron
  13. Logistic Regression
  14. Naive Bayes
  15. Decision Tree
  16. ...and 14 more sections

Figures (3)

  • Figure 1: Word Cloud of Symptoms in our dataset
  • Figure 2: The proposed methodology in brief
  • Figure 3: Learning curve of K-Nearest Neighbors. The convergence pattern demonstrates a healthy learning behavior for KNN and shows a well-fitted model that is neither underfitting nor overfitting.