583 patient records collected from North East Andhra Pradesh, India, for liver disease prediction. The dataset includes 416 liver patient records and 167 non liver patient records, with 441 male and 142 female entries. It was downloaded from the UCI ML Repository and preprocessed by filling missing values with column averages.
Use Cases
- Predict liver disease based on patient demographic and biochemical features like Age and Gender.
- Analyze the relationship between liver disease and biochemical markers such as Total Bilirubin and Albumin.
- Train and validate classification models using the provided 5 stratified K-Folds to handle data imbalance.
- Study potential biases or patterns in liver disease prevalence within a specific Indian regional population.
Strengths
- Contains 583 patient records with a clear target label for liver disease.
- Data has been preprocessed by filling missing values with column averages.
- Includes 5 stratified K-Folds splits to aid model validation on an imbalanced dataset.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Data may reflect geographic bias inherent to collection from a single region in India.
- Last update date is unknown; freshness unverified.
Provenance
- Source
- UCI ML Repository
- Collection Method
- Patient records collected from North East Andhra Pradesh, India.
- Geography
- North East Andhra Pradesh, India