Bookmarks

Machine Learning Frailty Index estimates with routine test results in acute care

Population Size

6,808

People

Population Size statistic card

Years

2020 - 2021

Years statistic card

Associated BioSamples

None/not available

Associated BioSamples statistic card

Geographic coverage

United Kingdom

England

Geographic coverage statistic card

Lead time

Not applicable

Lead time statistic card

Summary

Electronic Frailty Index from routinely collected test results in EHR’s. Granular condition, ethnicity, multi-morbidity. Deeply phenotyped. Serial physiology, blood biomarkers, interventions, longitudinal, pre/post admission healthcare use.

Documentation

Background.

Frailty is a critical measure in health care for evidence-based clinical decision making and an accurate electronic Frailty Index (eFI) at admission will be beneficial to both patients and medical service for prompt and appropriate assessment and management in acute care.

An accurate and valid eFI will be beneficial to both patients and emergency care services for prompt and appropriate assessment and management.

Since 2020, Clinical Frailty Scale (CFS) was introduced to QE as a way to screen and quantify frailty and fitness of individual patients with Covid 19 at admission. Essentially, CFS is a value derived from 92 baseline variables (also referred to as deficits) using a cumulative model, although studies have shown feasibility of reducing the number of variables without loss of predictive ability. In addition, CFS is judgement-based and requires specially trained clinicians to perform a series of measurements and determine the presence or absence of each deficit.

An eFI that was derived from 31 routinely collected test results showed that it has promising identification power for high risk frailty patients in aged cohort (>65), indicating the potential of having a simpler and more efficient model for frailty estimation.

PIONEER geography The West Midlands (WM) has a population of 5.9 million & includes a diverse ethnic & socio-economic mix.

EHR. UHB is one of the largest NHS Trusts in England, providing direct acute services & specialist care across four hospital sites, with 2.2 million patient episodes per year, 2750 beds & an expanded 250 ITU bed capacity during COVID. UHB runs a fully electronic healthcare record (EHR) (PICS; Birmingham Systems), a shared primary & secondary care record (Your Care Connected) & a patient portal “My Health”.

Scope: All hospitalised patients admitted to UHB during the COVID-19 pandemic, curated to focus on patients with frailty score. Longitudinal & individually linked, so that the preceding & subsequent health journey can be mapped & healthcare utilisation prior to & after admission understood. The dataset includes highly granular patient demographics & co-morbidities taken from ICD-10 & SNOMED-CT codes. Serial, structured data pertaining to acute care process (timings, discharge locations), presenting complaint, all physiology readings (Clinical Frailty Scale, pulse, blood pressure, respiratory rate, oxygen saturations), blood results (albumin, glucose, platelets, sodium, c-reactive protein, urea and others) and all outcomes.

Available supplementary data: Matched controls; ambulance, OMOP data, synthetic data.

Available supplementary support: Analytics, Model build, validation & refinement; A.I.; Data partner support for ETL (extract, transform & load) process, Clinical expertise, Patient & end-user access, Purchaser access, Regulatory requirements, Data-driven trials, “fast screen” services.

Dataset type

Health and disease, Measurements/Tests

Dataset sub-type

Not applicable

Dataset population size

6808

Keywords

Observations

Observed Node

Disambiguating Description

Measured Value

Measured Property

Observation Date

Persons

6,808 emergency admissions with Clinical Frailty Score between 01/01/2020 and 01/01/2021

6808

Count

25 Apr 2022

Provenance

Purpose of dataset collection

Care

Source of data extraction

EPR

Collection source setting

Secondary care - Accident and Emergency

Patient pathway description

Data is representative of the multi-ethnicity population within the West Midlands (42% non white). Data includes all patients admitted during this timeframe, with National data Opt Outs applied, and therefore is representative of admissions to secondary care. Data focuses on in-patient stay in hospital during the acute episode but can be supplemented on request to include previous and subsequent hospital contacts (including outpatient appointments) and ambulance, 111, 999 data.

Image contrast

Not stated

Biological sample availability

None/not available

Structural Metadata

Details

Publishing frequency

Quarterly

Version

1.0.0

Modified

08/10/2024

Distribution release date

12/10/2023

Citation Requirements

This publication uses data from PIONEER, an ethically approved database and analytical environment (East Midlands Derby Research Ethics 20/EM/0158)

Coverage

Start date

01/01/2020

End date

01/01/2021

Time lag

Other

Geographic coverage

United Kingdom, England, West Midlands

Minimum age range

18

Maximum age range

96

Follow-up

1 - 10 Years

Accessibility

Language

en

Alignment with standardised data models

LOCAL

Controlled vocabulary

SNOMED CT, ICD10

Format

SQL

Data Access Request

Dataset pipeline status

Available

Time to dataset access

Not applicable

Access request cost

www.pioneerdatahub.co.uk/data/data-services-costs/

Access method category

TRE/SDE

Access service description

Trusted Research Environments (TRE) are built using Microsoft Azure services and hosted in the UK to provide research teams a safe, secure and agile environment which allows users to quickly analyse, interpret and form an enriched view of primary care information through a range of integrated datasets.

Health data collated from multiple sources is ingested into a secure data lake which will then allow subsets of data to be made available to research teams on approval of a data request. Once approved a customer specific TRE is made available with a standard set of leading analytical tools from Microsoft including Azure Databricks, Azure Machine Learning, Azure SQL and Azure Synapse (for large-scale data warehouses). Specific tools can be provided at an additional cost over the standard platform data access charge and the PIONEER team will work with you to determine your exact needs.

Access to the TRE is managed using the latest virtual desktop technology to provide a safe and secure end-user experience. By utilising leading edge design PIONEER are able to create TREs rapidly to enable us to service any customer requirement.

Jurisdiction

GB-ENG

Data use limitation

General research use

Data use requirements

Project-specific restrictions

Data Controller

University Hospitals Birmingham NHS Foundation Trust

Dataset Types: Health and disease, Measurements/Tests


Collection Sources: Secondary care - Accident and Emergency

end of page