Synthetic EMR and Hospital Admissions Dataset

Dataset Features

• Age: Age of the patient.
• Gender: Gender of the patient (Male/Female).
• Rural: Whether the patient resides in a rural area (Yes/No).
• Type of Admission: Emergency or Outpatient Department (OPD) admission.
• Month/Year: Date of admission.
• Duration of Stay: Length of hospitalization in days.
• Duration of Intensive Unit Stay: Time spent in intensive care.
• Outcome: Discharge status (e.g., Discharge, DAMA - Discharge Against Medical Advice).
• Smoking & Alcohol: Patient’s history of smoking and alcohol consumption.
• Comorbidities:
  • DM: Diabetes Mellitus
  • HTN: Hypertension
  • CAD: Coronary Artery Disease
  • Prior CMP: History of cardiomyopathy
  • CKD: Chronic Kidney Disease
• Laboratory Results:
  • HB: Hemoglobin level
  • TLC: Total Leukocyte Count
  • Platelets: Platelet count
  • Glucose, Urea, Creatinine: Key metabolic and kidney function indicators
  • BNP: B-type Natriuretic Peptide (heart failure marker)
  • Raised Cardiac Enzymes: Presence of elevated enzymes indicating cardiac stress
• Cardiac Conditions:
  • EF: Ejection Fraction (heart function measure)
  • Severe Anemia, Anemia
  • Stable Angina, Acute Coronary Syndrome (ACS), STEMI
  • Atypical Chest Pain, Heart Failure (HFrEF, HFpEF)
  • Valvular Disease, Complete Heart Block (CHB)
  • Sick Sinus Syndrome (SSS), Arrhythmias (AF, VT, PSVT)
• Other Conditions:
  • Acute Kidney Injury (AKI), Stroke (CVA Infarct, CVA Bleed)
  • Congenital Conditions, Urinary Tract Infection (UTI)
  • Neurocardiogenic Syncope, Orthostatic Hypotension
  • Infective Endocarditis, Deep Vein Thrombosis (DVT)
  • Cardiogenic Shock, Other Types of Shock, Pulmonary Embolism
  • Chest Infections

Distribution

Usage

• Healthcare Analytics: Identify patterns in hospital admissions and patient outcomes.
• Predictive Modeling: Develop machine learning models to predict patient risks and treatment outcomes.
• Clinical Research: Investigate associations between comorbidities and hospitalization duration.
• Educational Purposes: Provide a dataset for medical, data science, and public health students to analyze real-world hospital data trends.

Coverage

License

Who Can Use It

• Healthcare Researchers: To explore hospitalization trends and risk factors.
• Clinicians and Medical Practitioners: To analyze patterns in hospital admissions and treatment outcomes.
• Data Scientists and Machine Learning Practitioners: To build predictive models for healthcare risk assessment.
• Educators and Students: As a resource for medical and healthcare analytics training.