ideasIdea
An automatic electronic frailty index inside the oncology record
Frailty is the strongest predictor of who will be harmed by treatment, but it is rarely measured. Software can estimate it automatically from existing records and flag patients who need a closer look.
Electronic frailty indices derived from coded diagnoses, prescriptions, and utilisation are used in primary care in England and predict outcomes well. An oncology version, computed automatically at referral and displayed with the staging information, would identify patients who should have a full geriatric assessment and would allow frailty-stratified outcome reporting. It requires validation against clinical frailty scales and treatment outcomes.
Hypothesis
An automated frailty index will predict grade 3 or higher toxicity and 90-day mortality after systemic therapy with discrimination at least as good as clinician judgement, and will increase geriatric assessment referrals among flagged patients.
Rationale
Automated indices remove the workload barrier that limits formal screening and enable population-level monitoring of undertreatment and overtreatment.
What would test it
Derive and validate the index in two health systems against toxicity and survival, then a pragmatic trial of displaying it versus not on assessment referrals and outcomes.
Maturity
early clinical
Who has to act
data
Cost to try
Small (under $1M)
Years to first evidence
2
Bottlenecks it attacks
- Older and multimorbid patients are excluded and undertreated · Most people with cancer are over 65 but most trial patients are younger and fitter. We guess how to treat the majority.
- Data silos · Records, scans, genomes and outcomes sit in separate systems that cannot talk. Every patient's experience is lost to the next.