An automated diabetes prevention app did as well as human coaches

In a 368-person Johns Hopkins trial, the Sweetch AI-led diabetes prevention program met the risk-reduction goal as often as human coaching (31.7% vs 31.9%).

2
Benefit status
Reported
Evidence
Independently studied
Source information as of
Sources
1 publication
Download data CiteSuggest a correction

Benefits

Benefit

31.7% of the AI group and 31.9% of the human-coaching group met the combined goal

Awaiting review

Outcome identifiers

Unresolved

Not reviewedUnresolved

Category

Increased Scalability

Awaiting review

Status

Reported benefit

Awaiting review

Beneficiary groups

People. Society.

Awaiting review

Beneficiaries

Unresolved

Not reviewedUnresolved

Reach

Unresolved

Not reviewedUnresolved

Distribution and access

Unresolved

Not reviewedUnresolved

Duration

Unresolved

Not reviewedUnresolved

Expected?

Yes

Awaiting review

Costs and harms

Unresolved

Not reviewedUnresolved

AI system

System

Sweetch AI-led Diabetes Prevention Program app

Awaiting review

Model

This is an explicit unresolved assignment: the sources on record do not settle this question.

Not reviewedUnresolved

Release

Unresolved

Not reviewedUnresolved

Provider

Unresolved

Not reviewedUnresolved

Role

Unresolved

Not reviewedUnresolved

Configuration

Unresolved

Not reviewedUnresolved

Inputs and outputs

Unresolved

Not reviewedUnresolved

Autonomy

Unresolved

Not reviewedUnresolved

Workflow

Participants received a Bluetooth scale and the app within 8 to 12 days of referral. A reinforcement learning algorithm chose the timing and content of messages from logged and passive data. No human coach took part in the AI arm.

Awaiting review

Human oversight

Unresolved

Not reviewedUnresolved

Relation to AI

Participants were randomized to the AI-led program or to human-led programs. The comparison isolates the automated program against human delivery. It does not separate the learning algorithm from the app's other features.

Awaiting review

AI contribution

Participants were randomized to the AI-led program or to human-led programs. The comparison isolates the automated program against human delivery. It does not separate the learning algorithm from the app's other features.

Awaiting review

Measurement

Studies

Randomized. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Study design

Randomized. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Measurement

Composite of at least 5% weight loss, at least 4% weight loss with 150 minutes of weekly activity by actigraphy, or HbA1c drop of 0.2 points at 12 months. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Setting and sample

368 adults with prediabetes and overweight or obesity at two US sites. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Measures

Share meeting the composite outcome; program initiation and completion. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Comparison

Human-led CDC-recognized diabetes prevention programs. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Results

31.7% against 31.9% (noninferior); initiation 93.4% against 82.7%; completion 63.9% against 50.3%. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Additional value from AI

Equal outcome to human coaching with higher uptake. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Limitations

Unmasked; surrogate outcomes; human programs delivered remotely; app updates during the trial. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Denominators

12 months. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Materials for replication

ClinicalTrials.gov NCT05056376; protocol in supplements. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Money

Kind of value

The kind of monetary value is unclear.

Not reviewedUnresolved

Amount

The monetary value is not established.

Not reviewedUnresolved

Currency and prices

The currency and price basis are unclear.

Not reviewedUnresolved

Period and unit

The period and unit of the monetary estimate are unclear.

Not reviewedUnresolved

Realization

Whether the monetary value was realized is unclear.

Not reviewedUnresolved

Recipients and payers

The recipients and payers are unclear.

Not reviewedUnresolved

Gross or net

Whether the monetary figure includes costs is unclear.

Not reviewedUnresolved

Included costs

The costs included in the estimate are unclear.

Not reviewedUnresolved

Comparison

The financial comparison is not established.

Not reviewedUnresolved

Method

The method used to calculate monetary value is unclear.

Not reviewedUnresolved

Return and payback

The return on investment or payback period is not established.

Not reviewedUnresolved

People and places

Participants

Developer: Sweetch Health, Ltd. Operator: Johns Hopkins Medicine AI-DPP study (sites in Baltimore and at Reading Hospital, Tower Health).

Awaiting review

Jurisdictions

Benefit: Baltimore, Maryland, and Reading, Pennsylvania, United States. Developer: Israel. Operator: United States.

Awaiting review

Ownership and control

Unresolved

Not reviewedUnresolved

Dependencies

Unresolved

Not reviewedUnresolved

Cross-border connections

Unresolved

Not reviewedUnresolved

Geopolitical implications

The geopolitical implications are unclear.

Not reviewedUnresolved

Follow-up

Conditions for replication

Participants own a smartphone and keep using the app for months. Clinicians refer adults with prediabetes to the program.

Awaiting review

Replication attempts

Unresolved

Not reviewedUnresolved

Later findings

Unresolved

Not reviewedUnresolved

Availability

Unresolved

Not reviewedUnresolved

Institutional decision

A relevant institutional decision has not been established.

Not reviewedUnresolved

Grounds

The grounds for an institutional decision are unclear.

Not reviewedUnresolved

Action and result

The result of an institutional decision is not established.

Not reviewedUnresolved

Success criterion

The criterion for a successful institutional decision is unclear.

Not reviewedUnresolved

Evidence

Source numbers

AIBD-0640-source-0001

Awaiting review

Citations

Numbered references below.

Awaiting review

Language

Unresolved

Not reviewedUnresolved

Source relationships

Independent

Awaiting review

Original evidence

Unresolved

Not reviewedUnresolved

Access and versions

Unresolved

Not reviewedUnresolved

Supported findings

Unresolved

Not reviewedUnresolved

Evidence strength

Independently studied. Sources: one independent peer-reviewed study. The cited evidence includes no finding by a regulator or court. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Missing evidence

Unresolved

Not reviewedUnresolved

Grades

Assessed benefits

People. Society.

Awaiting review

Depth

People: 2. Society: Not assessed.

Awaiting review

Reasons

People: 31.7% of people referred to the AI program reached the weight, activity or HbA1c goal, the same share as with human coaching. Society: The higher start rate was measured among the 368 trial participants, and no source documents a change in reach beyond the trial.

Awaiting review

Observed or intended

Unresolved

Not reviewedUnresolved

Rubric

Unresolved

Not reviewedUnresolved

Assessor and date

Unresolved

Not reviewedUnresolved

Alternative assessments

Unresolved

Not reviewedUnresolved

Fill

Independently studied

Awaiting review

Entry details

Kind

The case describes an evaluation or a study. A phase 3 randomized noninferiority trial. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Field

Healthcare.

Awaiting review

Purpose

The Sweetch program was built to deliver the Diabetes Prevention Program lifestyle intervention without human coaches. The measured benefit is that purpose.

Awaiting review

Dates

Source information as of: 16 December 2024. Updated: 29 October 2026.

Awaiting review

Stage

The system was in routine use. A commercial program delivered to trial participants by the company. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Version

SHA-256: 231bfa9ec0bb…

Awaiting review

SHA-256 of the public case, its assessments, and its displayed answers and notes, excluding its own identifier and the derived coverage summary.

References

Other identifiers

Unresolved

Not reviewedUnresolved

Category mappings

Unresolved

Not reviewedUnresolved

Citable summary

Unresolved

Not reviewedUnresolved

Revisions

2 revisions. Latest: 29 October 2026.

Awaiting review

Sources

  1. Peer-reviewed study Independent author

    Mathioudakis N, Lalani B, Abusamaan MS, et al. An AI-Powered Lifestyle Intervention vs Human Coaching in the Diabetes Prevention Program: A Randomized Clinical Trial. JAMA 2025;334(23):2079-2089. doi:10.1001/jama.2025.19563.

Collections: Cross-border cases.

Cite this case

BibTeX Download BibTeX

Version 231bfa9ec0bb, archived in the edition of 29 October 2026

Benefit marks

Depth

The number and color show the depth of a benefit.

  1. A convenience, or time or money saved.
  2. A measurable improvement in a result or ability.
  3. A lasting change, an ability restored, or a risk removed.
  4. A serious harm averted or a serious condition resolved in time.
  5. A life or livelihood preserved, or a change documented across a population.

Beneficiary

  • Circle: a person
  • Square: an organization
  • Triangle: society

Evidence

  • Solid. A court or regulator found a benefit, or researchers independently studied it.

  • Hatched. Independent reporting.

  • Outline. Claimed by the parties. Only the people or organizations involved, or sources whose independence has not been assessed, support the benefit.

The fill changes with the evidence. The depth color stays the same.

How benefits are assessed