CTAD 2026 · Boston · 16–19 November · Poster P446
Do your speech measures shift when phones change mid‑trial?
Noise cancellation and other phone or software changes can shift speech measures in Alzheimer’s disease trials. Find us at poster P446, or book 20 minutes about your own trial.
The speaker stays the same. The phone does not.
Over a long Alzheimer’s trial, phones update, noise cancellation changes and phones get replaced. Speech measures can move with them, and a standard analysis can read that as decline or improvement.
Noise cancellation varies
Phones and apps clean up speech in different ways, and an update can change the cleaning in the middle of a study.
Updates on their own schedule
Operating system and app updates arrive when the phone installs them, not at a visit, so a change can fall anywhere in the trial.
What the FDA asks
The FDA guidance on digital health technologies asks sponsors to record each update, compare data before and after it, and say how differences are handled before unblinding.
Recalibrated from the audio
Separate from the poster: Cephalgo readings stay stable across phone and software changes, recalibrated from the recordings themselves, blind to arm, so readings before and after a change sit on one scale.
Poster P446, Gloucester Ballroom and Atrium
We stand by the poster during the coffee breaks. To talk outside the breaks, or away from the poster hall, book a time that suits you.
- Conference
- CTAD 2026, Clinical Trials on Alzheimer’s Disease, in person and online
- Dates
- 16–19 November 2026
- Venue
- Boston Marriott Copley Place, 110 Huntington Avenue, Boston
- Poster
- P446, Gloucester Ballroom and Atrium, level 3
- Online
- In the virtual poster hall of the CTAD app once the conference opens
- Afterwards
- The abstract will be published in a Journal of Prevention of Alzheimer’s Disease supplement
Bring your study, leave with a plan
Twenty minutes is enough to go through one of these for your own program. Each one can start as a fixed scope with a fixed fee.
Audio from a trial you already ran
You leave with the outline of a re-analysis pilot: readings on your trial’s own scale from recordings you already hold. Re‑analysis pilot ›
Your device plan
Study phones or BYOD: we go through where phone or software changes can enter your study, and what a stability audit would check. Stability audit ›
Recorded CDR or NPI interviews
You see how each interview would be checked against the rater’s own usual range, with flags per rater and per site. Trial QC ›
Your own or your vendor’s speech measures
Recalibration works on measures you already use, with their definitions unchanged, so you see how they hold up when phones change. Already using a vendor ›
From Copenhagen to Boston
Five posters in 2026, from explainable screening in Copenhagen to phone and software changes in Basel, Philadelphia and Boston.
- March 2026
AD/PD™ 2026, Copenhagen · two ePosters
Validation of fully explainable speech biomarkers for AD/MCI screening, and for PD/HC screening
More about these ePosters › - June 2026
Digital Biomarkers in Clinical Trials Summit, Basel
When the device changes mid‑trial: evaluating speech‑based digital endpoint robustness to on‑device preprocessing variability in longitudinal remote monitoring
More about this poster › - September 2026
ISCTM Autumn Conference, Philadelphia
When the device changes mid‑trial: speech‑based digital endpoint robustness to on‑device preprocessing variability
More about this poster › - November 2026
CTAD 2026, Boston · P446
Noise‑cancellation variability as a source of longitudinal drift in speech‑based digital endpoints for Alzheimer’s disease trials
Request the poster ›
