OHDSI / OHDSI/FeatureExtraction

EHR-based electronic frailty index

Open
#172 1 comment 0 reactions 0 assignees View on GitHub

@cyanover is already working on this.

Since Jul 31, 2022.

  • #173 by @cyanover — open
Dominant language
R
Stars
74
Forks
63
PR merge metrics
No merged PRs in 30d

Description

The electronic frailty index (eFI) was developed and validated using primary care data of over 900,000 people aged $\geq$65 years in England (Clegg et el, 2016). It cosiders 36 deficits (comorbidities, symptoms, disabilities, abnormal lab values, and polupharmacy), calculcuted directly from EHRs. NHS England anticipate eFI “being used frequently as it: (1) has been externally validated using routine primary care data and its use is recommended in NICE Guideline 56 on Multimorbidity; (2) is available in all GP practices and therefore promotes consistency; (3) uses existing GP data and therefore requires no additional resource” (link).

eFI seems a valuable feature in studies concerning the elderly, alongside the hospital frailty risk score (HFRS), which Seng Chan You implemented back in 2018 (OHDSI Forum post).

@anthonysena

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing linked pull request #173 and the existing hospital frailty risk score implementation referenced in the issue and OHDSI Forum post. Done means FeatureExtraction supports the 36-deficit electronic frailty index for EHR-based studies, with the requested approach validated against the cited eFI definition.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
data
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.