Dark Mode
Liver Cirrhosis Patient Data
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset focuses on liver cirrhosis, a condition resulting from prolonged liver damage and extensive scarring, often caused by conditions such as hepatitis or chronic alcohol consumption. It provides patient data for classifying the stages of cirrhosis and is derived from a Mayo Clinic study on primary biliary cirrhosis (PBC) conducted between 1974 and 1984. The original dataset has been manually cleaned, and synthetic data has been incorporated to increase the sample size, making it suitable for analysis and model development.
Columns
- N_Days: Number of days elapsed between patient registration and the earliest of death, liver transplantation, or the study analysis time in 1986.
- Status: Patient's status, indicating whether they were censored (C), censored due to liver transplantation (CL), or deceased (D).
- Drug: The type of drug administered to the patient, either D-penicillamine or a placebo.
- Age: Patient's age, recorded in days.
- Sex: Patient's biological sex, indicated as Male (M) or Female (F).
- Ascites: Denotes the presence of ascites, with 'N' for No and 'Y' for Yes.
- Hepatomegaly: Indicates the presence of hepatomegaly, with 'N' for No and 'Y' for Yes.
- Spiders: Records the presence of spider angiomata, with 'N' for No and 'Y' for Yes.
- Edema: Describes the presence and management of edema: 'N' for no edema and no diuretic therapy, 'S' for edema present without diuretics or resolved by diuretics, and 'Y' for edema persisting despite diuretic therapy.
- Bilirubin: Serum bilirubin levels, measured in milligrams per decilitre (mg/dl).
- Cholesterol: Serum cholesterol levels, measured in milligrams per decilitre (mg/dl).
- Albumin: Albumin levels, measured in grams per decilitre (gm/dl).
- Copper: Urine copper concentration, measured in micrograms per day (ug/day).
- Alk_Phos: Alkaline phosphatase levels, measured in Units per litre (U/liter).
- SGOT: Serum glutamic oxaloacetic transaminase levels, measured in Units per millilitre (U/ml).
- Tryglicerides: Triglycerides levels, measured in milligrams per decilitre (mg/dl).
- Platelets: Platelet count, expressed as platelets per cubic millilitre (ml/1000).
- Prothrombin: Prothrombin time, measured in seconds (s).
- Stage: The histologic stage of the disease, categorised as 1, 2, or 3.
Distribution
The dataset is provided in a CSV format and is approximately 2.35 MB in size. It comprises 25,000 records across 19 columns. The data structure includes integer, float, and object (string/categorical) data types for various attributes.
Usage
This dataset is ideal for disease stage classification, patient survival prediction, and general healthcare analytics. It can be used for building and evaluating machine learning models, conducting statistical analyses to understand cirrhosis progression, and data visualization to explore patterns within patient health conditions.
Coverage
The data originates from a Mayo Clinic study conducted from 1974 to 1984, with patient follow-up data extending up to 1986. Demographically, the dataset includes patient age (ranging from approximately 26 to 78 years) and sex, with females constituting about 89% and males 11% of the patient cohort.
License
CC0: Public Domain
Who Can Use It
This dataset is suitable for data scientists and machine learning engineers interested in developing predictive models for medical outcomes, healthcare researchers studying liver diseases, and students or beginners in data science looking for real-world medical datasets. Its applications include studying disease progression, treatment efficacy, and patient survival rates.
Dataset Name Suggestions
- Liver Cirrhosis Patient Data
- PBC Stage Classification Dataset
- Mayo Clinic Cirrhosis Registry
- Cirrhosis Patient Outcomes Data
- Liver Disease Progression Data
Attributes
Original Data Source:Liver Cirrhosis Patient Data
QUALITY