34K+ Longitudinal EHR Records Dataset
Patient Health Records & Digital Health
Tags and Keywords
£38,800
About
34K+ Longitudinal EHR Records Dataset
Description
The 34K+ Longitudinal EHR Records Dataset is a healthcare dataset containing 34K+ longitudinal Electronic Health Record (EHR) records of 34K+ anonymized patients designed for artificial intelligence (AI), machine learning, healthcare analytics, clinical research, and medical data science applications. The dataset provides longitudinal patient information across healthcare encounters, enabling analysis of patient histories, clinical events, diagnoses, treatments, investigations, and healthcare utilization over time.
By connecting healthcare information across multiple time points, the dataset can support longitudinal patient analysis, clinical data mining, predictive modeling, healthcare AI, clinical NLP, disease progression research, and healthcare analytics. It is intended for researchers, data scientists, AI developers, healthcare technology organizations, and academic institutions working with structured clinical and patient-level healthcare data.
Note: Pricing varies depending on several factors, including the number of prescription records, data volume, metadata availability, data fields, level of detail, file format, licensing terms, and customization needs. The final price will be determined based on the specific dataset requirements.
Data Product Features
| Feature | Description |
|---|---|
| Longitudinal EHR Records | Electronic health records representing patient information and healthcare events across multiple time points. |
| Patient Information | Available demographic and patient-related information associated with healthcare records. |
| Medical History | Previous or existing medical conditions and relevant clinical history. |
| Diagnosis | Diagnoses and clinical conditions documented during healthcare encounters. |
| Visit Information | Information associated with patient healthcare visits and encounters. |
| Medications | Medicines and treatment information associated with patient encounters. |
| Investigations | Diagnostic tests, examinations, or investigations associated with healthcare encounters. |
| Temporal Information | Dates, years, or other time-related information supporting longitudinal analysis. |
Distribution
The dataset is provided as a collection of 34K+ longitudinal EHR records containing structured healthcare information and associated clinical attributes.
- Data Volume: 34K+ Longitudinal EHR Records
- Data Type: Electronic Health Records / Healthcare Data
- Format: PDF
- Structure: Patient and healthcare encounter records containing clinical, diagnostic, medication, investigation, and temporal information where available.
- Dataset Size: Dataset size may vary depending on the selected dataset package, number of records, available fields, metadata, and specific dataset requirements.
Usage
This data product is ideal for a variety of applications:
- Longitudinal Patient Analysis: Analyze patient healthcare histories and events across multiple time points.
- Healthcare AI: Develop and evaluate AI models using structured clinical and longitudinal healthcare data.
- Clinical Research: Support research into patient histories, diagnoses, treatments, and healthcare outcomes.
- Predictive Modeling: Develop models for healthcare analytics and prediction tasks using historical patient information.
- Clinical NLP: Analyze medical notes and other clinical text where available.
- Disease Progression Research: Study changes in diagnoses, treatments, and clinical events over time.
- Healthcare Analytics: Analyze patient visits, treatments, investigations, and healthcare utilization.
- Medical Data Mining: Identify patterns and relationships within longitudinal EHR data.
- Machine Learning: Train, fine-tune, and evaluate healthcare-focused machine learning models.
Coverage
-
Geographic Coverage: Uganda
-
Data Domain: Electronic health records, clinical history, diagnoses, medications and healthcare encounters.
License
CC BY 4.0 (Creative Commons Attribution 4.0 International)
AI Training Rights
InfoBay.AI ensures that all datasets are sourced, curated, and managed with proper ownership verification, licensing documentation, and data provenance records. We hold the necessary rights to license and sublicense the datasets we provide through formal agreements with our data vendors, which grant us the required permissions for commercial licensing and AI training use cases. To ensure transparency and compliance, we maintain relevant documentation and have previously shared redacted agreements for selected datasets as evidence of our data rights and licensing authority.
Data Dictionary
| Column Name | Data Type | Description | Possible Values/Notes |
|---|---|---|---|
patient_id | STRING | Identifier associated with the patient. | Anonymized |
visit_date | DATE | Date of the healthcare encounter. | Date value |
visit_year | INTEGER | Year in which the healthcare encounter occurred. | Four-digit year |
age | INTEGER | Patient age associated with the encounter. | Age in years, where available |
gender | STRING | Patient gender, where available. | Dataset-specific values |
medical_history | STRING | Previous or existing medical conditions and relevant clinical history. | Dataset-specific |
diagnosis | STRING | Diagnosis or clinical condition recorded during the encounter. | Dataset-specific |
medical_note | STRING | Clinical notes or observations documented by the healthcare provider. | Free-text clinical information, where available |
medication | STRING | Medicine or medicines associated with the patient's treatment. | Drug/medicine names |
dosage | STRING | Prescribed or recorded medication dosage. | Dataset-specific |
frequency | STRING | Medication administration frequency. | Dataset-specific |
duration | STRING | Treatment or medication duration. | Dataset-specific |
Considerations
This dataset is provided for research and educational purposes only. It contains only sample data.
TRUSTLoading...
£38,800
Download Dataset in PDF Format
Recommended Datasets
Loading recommendations...