Dark Mode
Patient Health Indicators Dataset
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset reveals the intricate relationship between patients and diseases across over 100 different medical conditions. It offers a wealth of information, illustrating the fascinating connections between symptoms, patient demographics, and various health indicators. You can delve into the detailed tapestry of symptoms such as fever, cough, fatigue, and difficulty breathing, all intertwined with patient age, gender, blood pressure, and cholesterol levels. Whether you are a medical researcher, a healthcare professional, or a data enthusiast, this dataset provides key insights to unlock profound patterns, uncover unique symptom profiles, and embark on a captivating journey through the world of medical conditions, helping to revolutionise healthcare understanding.
Columns
- Disease: The name of the specific disease or medical condition. This column contains 116 unique disease names, with Asthma appearing as the most common.
- Fever: Indicates whether a patient presents with a fever. Data suggests an even split, with approximately 50% of patients having a fever and 50% not.
- Cough: Denotes whether a patient experiences a cough. About 48% of patients in the dataset have a cough, while 52% do not.
- Fatigue: Specifies if a patient experiences fatigue. Roughly 69% of patients in the dataset report fatigue, compared to 31% who do not.
- Difficulty Breathing: Indicates whether a patient has difficulty breathing. Approximately 25% of patients experience this symptom, while 75% do not.
- Age: The age of the patient in years. Patient ages range from 19 to 90, with an average age of 46.3 years.
- Gender: The gender of the patient, categorised as Male or Female. The dataset shows an equal distribution of 50% Female and 50% Male patients.
- Blood Pressure: The blood pressure level of the patient. Categories include Normal and High, with High blood pressure being slightly more common.
- Cholesterol Level: The cholesterol level of the patient. Categories include Normal and High, with High cholesterol being more frequently observed.
- Outcome Variable: This variable indicates the result of the diagnosis or assessment for the specific disease, with categories being Positive or Negative. Positive outcomes are slightly more frequent. All listed columns contain 349 valid records.
Distribution
The dataset is provided in CSV format and is 20.51 kB in size. It comprises 10 distinct columns and a total of 349 records or rows.
Usage
This dataset offers a variety of applications for different stakeholders. Healthcare professionals, including medical practitioners and doctors, can utilise it for clinical analysis, research studies, and epidemiological investigations concerning various diseases. It can significantly aid in understanding the prevalence and patterns of symptoms among patients with specific medical conditions. Medical researchers can explore relationships between symptoms, age, gender, and other variables to contribute to new insights, treatment strategies, and preventative measures. Furthermore, healthcare technology companies can find this dataset valuable for training and validating their models, assisting in the development of predictive tools for disease diagnosis or monitoring based on patient symptoms and characteristics.
Coverage
The dataset covers over 100 different diseases. Demographically, it includes patient ages ranging from 19 to 90 years, with an even split of 50% male and 50% female patients. Specific geographic coverage and a precise time range for the data collection are not detailed within the provided materials.
License
CC0: Public Domain
Who Can Use It
- Healthcare Professionals: For analysing clinical data, conducting research, and epidemiological studies to understand symptom prevalence.
- Medical Researchers: To investigate correlations between symptoms, age, and gender, aiding in the development of new treatments and preventative approaches.
- Healthcare Technology Companies: For training and validating machine learning models to build diagnostic tools or monitoring applications.
- Data Enthusiasts: To explore hidden patterns and unique symptom profiles within a medical context.
Dataset Name Suggestions
- Disease Symptom and Patient Profile
- Medical Condition Symptom Data
- Patient Health Indicators Dataset
- Clinical Symptom & Demographics
- Disease Manifestation Records
Attributes
Original Data Source: Patient Health Indicators Dataset
QUALITY