Dark Mode
Heart Attack Prediction Zheen Hospital
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This medical dataset provides crucial information for identifying and predicting heart attacks. Collected from January 2019 to May 2019 at Zheen hospital in Erbil, Iraq, it contains anonymised patient attributes such as age, gender, heart rate, blood pressure, blood sugar, and specific cardiac enzyme levels (Ck-mb and Troponin), along with an outcome label indicating a heart attack or none. The dataset has been prepared for machine learning applications, with gender, blood sugar, and the outcome normalised into numerical formats. It is suitable for building highly accurate predictive models and performing in-depth exploratory data analysis (EDA).
Columns
- Age: The patient's age, ranging from 14 to 103 years, with a mean of 56.2.
- Gender: The biological sex of the patient, where 1 represents male and 0 represents female. There are 870 male entries and 449 female entries.
- Heart Rate: The number of heartbeats per minute, typically between 20 and 1111, with an average of 78.3.
- Systolic Blood Pressure: The pressure in arteries when the heart contracts, observed between 42 and 223, averaging 127.
- Diastolic Blood Pressure: The pressure in arteries between heartbeats, with values from 38 to 154, and a mean of 72.3.
- Blood Sugar: The patient's blood glucose level. Normalised to 1 if above 120, otherwise 0. Actual values range from 35 to 541, with a mean of 147.
- Ck-mb: A cardiac enzyme released during heart muscle damage. Values range from 0.32 to 300, with a mean of 15.3.
- Troponin: A highly specific protein biomarker for heart muscle injury. Values range from 0 to 10.3, with a mean of 0.36.
- Result: The outcome label indicating whether or not the patient experienced a heart attack. Positive is set to 1 and negative to 0. 61% of records are positive for a heart attack, while 39% are negative.
Distribution
The dataset is typically provided as a CSV file, named
Medicaldataset.csv, with a file size of 52.36 kB. It contains 9 columns and 1319 valid records for all attributes. The data is structured as a single, flat table. Key categorical features like gender, blood sugar, and the final result are encoded numerically for ease of analysis and model training.Usage
This dataset is ideal for:
- Developing and evaluating machine learning models for heart attack prediction, capable of achieving high accuracy (e.g., 99%).
- Conducting exploratory data analysis (EDA) to uncover correlations between various physiological parameters and heart attack incidence.
- Performing feature engineering to derive new insights and improve predictive model performance.
- Supporting medical research into cardiac conditions and patient risk factors.
Coverage
The dataset's coverage is geographically specific to Zheen hospital in Erbil, Iraq. The time range for data collection was from January 2019 to May 2019. It includes patient demographics based on age (14-103 years) and gender (male/female), representing a diverse patient group from the hospital during the collection period. All columns have 100% data validity, with no missing or mismatched entries.
License
Attribution 4.0 International (CC BY 4.0)
Who Can Use It
This dataset is valuable for:
- Data scientists and machine learning engineers focused on building predictive healthcare models.
- Medical researchers and public health professionals studying cardiac diseases and patient outcomes.
- Students and academics for educational purposes, coursework, and research projects in health informatics or data science.
- Healthcare data analysts seeking to understand patterns and risk factors associated with heart attacks.
Dataset Name Suggestions
- Heart Attack Prediction Zheen Hospital
- Erbil Cardiac Patient Records 2019
- Heart Attack Diagnosis Dataset Iraq
- Zheen Hospital Heart Disease Outcomes
Attributes
Original Data Source: Heart Attack Prediction Zheen Hospital
QUALITY