Randomised trial of an AI management platform for breast cancer patients on home CDK4/6 inhibitor therapy
In a three-arm randomised trial across hospitals in Tianjin, 189 breast cancer patients taking CDK4/6 inhibitors at home were assigned to an AI management platform, a tailored active follow-up service by phone and text, or standard care; a preprint reports that both active arms kept anxiety and depression scores better than standard care, without reporting a comparison between the AI and the human follow-up.
- Model
- Zhiliao Doctor AI management platform
- Field
- Medicine
- Date
- 2026-11-03
- Human collaborators
- Li Zhang
What was found
The registration describes the platform as a 24-hour service added to routine follow-up, offering emotional companionship, medication reminders and adverse-reaction assessment against CTCAE standards. The second arm received personalised phone calls and text messages from a follow-up centre, and the third routine advice and education. Primary outcomes were the Self-Rating Anxiety and Depression Scales at 24 weeks, with EORTC QLQ-C30 quality of life and patient-reported adverse events (PRO-CTCAE) secondary. Of 189 randomised, 161 were analysed (53 AI, 54 follow-up, 54 standard care). Both intervention arms did better than standard care on anxiety and depression (both ) and on cognitive, emotional and social functioning and global health, while scores in the standard-care arm worsened, with depression peaking at week 16. The authors also report that the AI arm captured more patient-reported adverse events.
Novelty check
Europe PMC, 2026-11-05: (TITLE:"CDK4/6" OR TITLE:"CDK4/6i") AND ("artificial intelligence" OR "AI-driven" OR chatbot) AND (randomized OR randomised OR trial) returned 44 records; this preprint is the only randomised trial of an AI platform for patients on CDK4/6 inhibitors, the others being drug trials, reviews and prognostic models. ClinicalTrials.gov holds the registration, NCT07409298.
Caveats and known objections
A Research Square preprint, not peer-reviewed, so capped at claimed. The comparison that matters for the AI is with the human follow-up arm, and the abstract reports none on the primary outcome: both active arms beat standard care, which is what an attention control would also be expected to do. Endpoints are self-rated scales, surrogates rather than hard outcomes, in an open-label trial (the registration lists no masking) where patients knew their arm. 28 of 189 randomised patients (15%) were not analysed. The registration was first posted on 2026-02-13, after its stated start of 2025-07-05, with an estimated enrolment of 300, and the abstract dates randomisation to 2024 and 2025, which does not match the registered start. The trial is academic, led by Tianjin Medical University Cancer Institute and Hospital with seven Tianjin hospitals as collaborators; who built the platform and whether its maker had any role is not stated in the abstract or the registration. Autonomy is ai-assisted, the weaker reading: the platform ran alongside routine follow-up and the abstract does not say which decisions, if any, it made without a clinician.
Trial registration
NCT07409298
That a study was registered, with the outcomes it declared and the date it declared them, so a published endpoint can be checked against the one planned. It does not certify the results, their analysis, or any clinical benefit; registry records are submitted by the sponsor and are not peer reviewed.
No independent check is recorded on this entry yet.
Reading the primary source closely enough to say whether it supports the claim counts as a check, and you are credited on the entry.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
Entry history (1 event)
- AddedEntered the registry graded Claimed and AI-assisted.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Graded claimed for verification and ai-assisted for autonomy. What these mean.
Cite this entry
whataifound.org. (2026). Randomised trial of an AI management platform for breast cancer patients on home CDK4/6 inhibitor therapy. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2026-11-03-cdk46-home-therapy-ai-rctBibTeX
@misc{whataifound-tianjinmedicaluniversitycancerinstituteandhospital-2026-rct,
title = {Randomised trial of an AI management platform for breast cancer patients on home CDK4/6 inhibitor therapy},
author = {{whataifound.org}},
year = {2026},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by Tianjin Medical University Cancer Institute and Hospital. Verification: Claimed. Autonomy: AI-assisted.},
url = {https://whataifound.org/finding/2026-11-03-cdk46-home-therapy-ai-rct}
}