Skip to main content
Tessa NewsLink
Paste a health news link, or browse
Latest checks

Source study found

Story checked

Can an AI chatbot help women recognize heart disease? (opens in a new tab)

medicalxpress.com · 2026-10-28

Short answerEvidenceSource

Short answer

Mixed

Mixed.

One claim goes further than the study. One other point was not covered by the paper.

  • 3 supported
  • 1 overstated
  • 1 not covered

Checked against the study summary. The full text wasn't available, so some details couldn't be settled either way.

Share this check

Follow the evidence trail
1
2

NewsLink checks it

Mixed

One claim overstates the study. Three of five check out. One claim the study doesn't address.

  • 3 supported
  • 1 overstated
  • 1 not covered
Open claim evidence
3
Then inspect each claim

Evidence layer

Claim by claim

Each claim gets a verdict. Expand it to see the evidence directly below.

5 claims in this story

Showing all 5 claimsChoose a verdict to focus the list.

Claim 1 of 5OverstatedThe current HeartBot II study is a six-month randomized controlled trial with 201 female UCSF Health patients, with half getting immediate access and half serving as a delayed-access control group.View evidenceHide evidence

As stated201 female UCSF Health patients; six months; half immediate access

Why this verdict

The RCT and delayed-access/waitlist-control structure are supported, but the story’s details do not match the abstract-level paper profile: the protocol specifies 200 women aged 25 or older, 1:1 randomization, a 12-week intervention/primary endpoint, and 86 enrolled at submission. The profile does not support 201 female UCSF Health patients or a six-month primary trial as stated.

1

Study evidence

This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.

“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
Claim 2 of 5Not coveredHeartBot, created by a team of UC researchers, regularly answers questions from women seeking information on heart disease.View evidenceHide evidence

Why this verdict

The abstract-level profile supports that AI HeartBot II is a chatbot-based educational mobile app for women, but it does not verify that it was created by UC researchers or that it already regularly answers questions from women seeking heart-disease information.

1

Study evidence

This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.

“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
Claim 3 of 5SupportedThe goal was to study whether having a heart-health chatbot on participants' phones would increase awareness of heart disease risks and recognition of heart attack symptoms so they would seek medical help when necessary.View evidenceHide evidence

Why this verdict

The paper profile states that the trial is designed to evaluate whether the AI HeartBot II chatbot intervention improves women’s awareness/knowledge of heart attack symptoms and intended care-seeking behaviors, which matches the story’s framing as the study goal rather than as a proven result.

1

Study evidence

This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.

“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
Claim 4 of 5SupportedResearchers will compare changes in the women's retention of heart disease information over time.View evidenceHide evidence

Why this verdict

The protocol specifies comparison of change from baseline to 12 weeks in a heart attack response preparedness score, analyzed longitudinally. The story’s wording about comparing changes over time is broadly consistent, although the paper’s stated primary outcome is preparedness/awareness and intended care-seeking rather than generic retention of heart-disease information.

1

Study evidence

This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.

“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
Claim 5 of 5SupportedThe study question is whether a conversation with AI can help women recognize the warning signs of a heart attack and know what to do when minutes matter.View evidenceHide evidence

Why this verdict

The paper’s stated objective is to evaluate whether the chatbot-based intervention improves women’s recognition/awareness of heart attack symptoms and intended care-seeking. The story frames this as a study question, not as an established efficacy result, so it is supported.

1

Study evidence

This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.

“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
Then look for missing context

Context layer

What the story left out

Important study details the story did not include.

  • The planned trial design in the paper is 200 women aged 25 or older randomized 1:1, with a 12-week intervention and primary endpoint; the waitlist group receives the intervention at 12 weeks.

    The story reflects the broad randomized/delayed-access design, but it gives materially different specifics: 201 female UCSF Health patients and a six-month trial. Those details are not supported by the abstract-level profile.

    From randomized controlled trial (waitlist control)

  • A key limitation is that the primary outcome is self-reported and may be subject to reporting or response bias.

    The story caveats mention no results yet and safety/efficacy not established, but they do not mention the self-reported nature of the primary outcome or its bias implications.

    From randomized controlled trial (waitlist control)

  • The primary endpoint assesses short-term change from baseline to 12 weeks; longer-term effects are not assessed in the primary endpoint.

    The story instead describes a six-month study and changes over time, which could give an impression of longer-term assessment than the abstract-level profile supports for the primary endpoint.

    From randomized controlled trial (waitlist control)

  • Enrollment was ongoing at manuscript submission, with 86 participants enrolled out of the planned 200.

    The story presentation notes that the trial is ongoing, but it does not reflect the profile’s enrollment status and instead frames the study as involving 201 participants.

    From randomized controlled trial (waitlist control)

2 things the story did carry across
  • The paper is a trial protocol for an RCT of AI HeartBot II versus a waitlist control, not a report of completed efficacy results.
  • The primary outcome is a self-reported 4-item heart attack response preparedness score assessing confidence in recognizing symptoms, distinguishing them, calling 911, and reaching an ER within 60 minutes.
Then read the study layer

Study layer

Study at a glance

Scan the study first. Expand only the parts you want to inspect.

Pieces of work

1

Evidence read

study summary

Lead result

human in vivo

1Lead resulthuman in vivoEvaluate the short-term efficacy of the AI HeartBot II chatbot-based educational intervention, versus a waitlist control, for improving women’s awareness/knowledge of heart attack symptoms and intended care-seeking behaviors (primary outcome: 4-item preparedness score from baseline to 12 weeks).randomized controlled trial (waitlist control)Expand

In plain English

Protocol for a randomized controlled trial (waitlist control) evaluating the short-term efficacy of the AI HeartBot II chatbot-based mobile app to improve women's awareness and intended care-seeking for heart attack. The trial will randomize 200 women aged ≥25 (1:1) to receive a 12-week, 4-module app intervention or to a waitlist control that receives the same intervention after 12 weeks. The prespecified primary outcome is the change from baseline to 12 weeks in a 4-item heart attack response preparedness score (mean of four self-reported items assessing confidence recognizing symptoms, distinguishing from other problems, calling 911, and reaching an ER within 60 minutes). The primary analysis will use constrained longitudinal data analysis via linear mixed models with a time-by-treatment interaction; sensitivity analyses for individual ordinal items will use ordinal logistic mixed-effects models. IRB approval and trial registration were completed prior to enrollment; recruitment began April 2026 and 86 participants were enrolled at the time of manuscript submission. No trial outcome data are reported in this protocol.

Key findings

  • This protocol specifies a randomized trial to evaluate whether the AI HeartBot II chatbot increases short-term (12-week) heart attack preparedness among women, measured by a 4-item self-reported preparedness score; no efficacy data are reported in this protocol.
“This randomized controlled clinical trial (RCT) with a waitlist control will enroll 200 women aged 25 or older, who will be randomized using a 1:1 allocation ratio.”
What this piece can’t prove
  • This document is a trial protocol and does not report efficacy results.
  • Primary outcome is based on self-reported preparedness items (potential for reporting bias).
  • Primary follow-up period is short-term (baseline to 12 weeks); longer-term effects are not assessed in the primary endpoint.
Finally, the search trail

Method layer

NewsLink found the paper. Tessa takes you deeper.

NewsLink checks the story. Tessa is where you inspect the paper, authors, evidence, and research context.

Open the paper in Tessa

Short-Term Efficacy of the Artificial Intelligence HeartBot II in Increasing Awareness and Knowledge of Heart Attack in Women: Protocol for a Randomized Controlled Trial With a Waitlist Control

JMIR Research Protocols · 2026

Deep dive in Tessa (opens in a new tab)Source record (opens in a new tab)

Why this one

Confident

NewsLink found the paper. Tessa is where you inspect it deeply.

Papers considered

The selected paper, plus nearby candidates.

Europe PMC, Crossref, PubMed · 15 candidate papers

SelectedOpen access

Short-Term Efficacy of the Artificial Intelligence HeartBot II in Increasing Awareness and Knowledge of Heart Attack in Women: Protocol for a Randomized Controlled Trial With a Waitlist Control

JMIR Research Protocols · 2026 · Europe PMC, Crossref

Tessa (opens in a new tab)Source (opens in a new tab)
Candidate

Abstract 4144376: Applying artificial intelligence chatbot to increase heart disease awareness and knowledge in women

Circulation · 2024 · Crossref

Source (opens in a new tab)
Candidate

Medical Chatbot for Disease Prediction Using Machine Learning and Symptom Analysis

Proceedings of the 20Th International Conference on Evaluation of Novel Approaches to Software Engineering · 2025 · Crossref

Source (opens in a new tab)
Candidate

Randomized Trial of Estrogen Plus Progestin for Secondary Prevention of Coronary Heart Disease in Postmenopausal Women

Journal of Cardiopulmonary Rehabilitation · 1999 · Crossref

Source (opens in a new tab)

And 9 more candidates considered.