DiaHealth: A Bangladeshi Dataset for Type 2 Diabetes Prediction
Donated on 11-06-2024
A complete diabetes dataset has been gathered from CMED Health Ltd. and the Palli Karma-Sahayak Foundation (PKSF) in Bangladesh. This dataset includes 14 independent attributes, encompassing demographics, clinical parameters, patient medical history, and conditions. The classification target is to determine whether a patient has diabetes. It consists of 5437 patient samples, representing both males and females between the ages of 21 and 80, with each sample labeled as either diabetic or non-diabetic.
Dataset Characteristics
Tabular
Subject Area
Computer Science, Health And Medicine
Associated Tasks
Classification
Feature Type
Real, Categorical, Integer
# Instances
5437
# Features
14
The purpose of the dataset:
To create a comprehensive diabetes dataset with all the important attributes needed to predict Type 2 Diabetes.
What do the instances in this dataset represent?
Each row represents a person participating in this study.
The dataset creation was funded by:
United Trust
Value of the data:
This data is crucial because it includes comprehensive information on all diabetes symptoms, aiding the development of more effective preventative and therapeutic measures. It is also valuable for health informatics researchers to develop algorithms for early identification and detection of diabetes and its complications. Machine learning algorithms can be trained on this dataset to identify patterns indicative of diabetes and its consequences. Additionally, the dataset can assess the feasibility of various diabetes treatments and improve healthcare management for diabetic patients.
Attributes:
1. Age
2. Gender
3. Pulse Rate
4. Systolic BP
5. Diastolic BP
6. Hypertension
7. Family Hypertension
8. Family Diabetes
9. Glucose
10. Body Mass Index (BMI)
11. Height
12. Weight
13. Stroke
14. Cardiovascular Disease (CVD)
Class Labels:
● Diabetes
● Non-diabetes
Advanced Intelligent Multidisciplinary Systems (AIMS) Lab
United International University