client logo
Version: 1.0.0 | Published: 9 Jun 2026 | Updated: 13 days ago

University College London Hospitals, DataTools4Heart: federated patient data analysis for research

Dataset

Documentation

Description:
In heart failure, the patient’s heart is not able to pump blood around sufficiently, leading to symptoms such as shortness of breath and fluid retention. Patients with heart failure often also have chronic kidney disease. In this situation, it is difficult to find the best dose of medication to use, as patients are at risk of complications. It is also difficult to know which patients can be safely treated at home and which patients need to be admitted to hospital for closer monitoring. In this study, we aim to use real word clinical data to evaluate the prescription of medication in patients with chronic kidney disease who are hospitalized with heart failure. This will lead to improved knowledge of the current implementation of clinical treatment guidelines. Secondly, we aim to develop a risk score for patients admitted with heart failure. This may help clinicians may help the clinician to decide if a patient should be admitted or managed at home, and what level of monitoring is required. The risk score could also help to predict and optimise the use of health care resources. For these aims, we will analyse clinical data extracted from the UCLH electronic health record. Findings from these data will be combined with findings from patient data at other European hospitals, under the DataTools4Haert project (https://www.datatools4heart.eu/). This will be carried out using a federated learning approach, in which data is analysed within each hospital and the results are combined without any data leaving the individual hospital. This will allow research questions to be answered robustly using data from a large, diverse patient population whilst maintaining the security and privacy of patient data.
Is Part Of:
null

Coverage

Spatial:
United Kingdom
Typical Age Range:
22-90
Follow Up:
0 - 6 Months

Provenance

Origin

Sources:
EPR

Temporal

Accrual Periodicity:
Continuous
Start Date:
01 April 2019
End Date:
31 December 2024
Time Lag:
Not applicable

Accessibility

Access

Access Rights:
In Progress

Usage

Data Use Limitations:
Research use only

Format and Standards

Vocabulary Encoding Schemes:
  • SNOMED CT
  • LOINC
  • OPCS4
  • RXNORM
  • RXNORM EXTENSION
Conforms To:
OMOP
Languages:
en
Formats:
application/parquet

Observations

Statistical Population
Population Description
Population Size
Measured Property
Observation Date
Persons
1128
Count
31 December 2024