ideasIdea
Ambient AI note-taking to give oncologists back a day a week
Oncologists spend hours a day typing notes. Software that listens to the consultation and drafts the note, the letter and the orders could return that time to seeing patients.
Ambient documentation tools are being adopted in primary care with reported reductions in documentation time. Oncology notes are longer and more structured (staging, regimen, cycle, toxicity grading, response), which makes them both harder and more valuable to automate. An oncology-tuned tool that also populates structured fields (mCODE-style) would improve data quality and cut clinic time, if it can be shown not to introduce clinically significant errors.
Hypothesis
Oncologists using an oncology-tuned ambient scribe will reduce documentation time per patient by at least 40% and increase weekly patient capacity by at least 10%, with a documented error rate no higher than manual notes on blinded audit.
Rationale
Documentation burden is a top driver of oncologist burnout and early retirement; recovering time is the fastest way to add capacity without new training.
What would test it
A randomised crossover study across 60 oncologists measuring documentation time, patient volume, burnout scores, and independent note-accuracy audits.
Maturity
early clinical
Who has to act
engineering
Cost to try
Medium ($1M to $50M)
Years to first evidence
2
Bottlenecks it attacks
- Not enough oncologists, nurses, pathologists, physicists · The number of people with cancer is rising faster than the workforce trained to treat them.
- Data silos · Records, scans, genomes and outcomes sit in separate systems that cannot talk. Every patient's experience is lost to the next.