Computer-read chest X-rays speed TB treatment at a Malawi clinic

In the PROSPECT trial at a Blantyre clinic, TB patients offered HIV testing plus chest X-rays read by CAD4TB started treatment a median of 1 day after the visit, against 11 days under standard care.

2
Benefit status
Reported
Evidence
Independently studied
Observed
Sources
1 publication
Download data CiteSuggest a correction

Benefits

Benefit

Median time to treatment was 1 day in the X-ray arm and 11 days under standard care

Awaiting review

Outcome identifiers

Unresolved

Not reviewedUnresolved

Category

Improved Physical Health

Awaiting review

Status

Reported benefit

Awaiting review

Beneficiary groups

People.

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

CAD4TB computer-aided detection software reading digital chest X-rays

Awaiting review

Model

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

Not reviewedUnresolved

Reported configuration

CAD4TB v5

Awaiting review

Provider

Unresolved

Not reviewedUnresolved

Role

Unresolved

Not reviewedUnresolved

Configuration

Unresolved

Not reviewedUnresolved

Inputs and outputs

Unresolved

Not reviewedUnresolved

Autonomy

Unresolved

Not reviewedUnresolved

Workflow

Adults with cough at an urban primary clinic were offered a digital chest X-ray during the same visit. A CAD4TB score of 45 or higher led to an on-site Xpert sputum test. The clinic TB officer started treatment when the Xpert test was positive.

Awaiting review

Human oversight

Unresolved

Not reviewedUnresolved

Relation to AI

The trial compares HIV testing with and without the combined X-ray and CAD4TB package. It does not separate the software from the X-ray or compare it with a human reader.

Awaiting review

AI contribution

Unresolved

Not reviewedUnresolved

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

Time to TB treatment and same-day treatment from clinic and study records over 56 days; intention-to-treat analysis. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Setting and sample

Bangwe Health Centre, Blantyre, Malawi; 1,462 adults with cough randomized 1:1:1 between 15 November 2018 and 27 November 2019. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Measures

Time to TB treatment; proportion treated the same day. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Comparison

Standard care; HIV testing alone. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Results

Median 1 day to treatment against 11 days under standard care; hazard ratio 2.86 (1.04 to 7.87); same-day treatment 6/15 against 0/5. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Additional value from AI

Not isolated; the X-ray and software were delivered as one package. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Limitations

Few TB cases (15, 8 and 5 by arm), a difference in the number treated that was not statistically significant, 56-day follow-up, an open-label design, and a 0% probability of cost-effectiveness at US$1,200 per QALY. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Denominators

497 adults allocated to HIV testing plus digital X-ray with CAD4TB v5. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Materials for replication

Trial registered as NCT03519425. [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: Delft Imaging. Operator: PROSPECT trial team of the Malawi-Liverpool-Wellcome Trust Clinical Research Programme at Bangwe Health Centre.

Awaiting review

Jurisdictions

Benefit: Bangwe Health Centre, Blantyre, Malawi. Developer: Netherlands. Operator: Malawi.

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

X-ray equipment, Xpert testing and trained staff must be available during the visit. The score threshold must suit the local population.

Awaiting review

Replication attempts

1 follow-up entry. Outcome unresolved: 1.

Awaiting review

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-0634-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.

Awaiting review

Depth

People: 2.

Awaiting review

Reasons

People: Median time to TB treatment fell from 11 days under standard care to 1 day in the X-ray arm, and 6 of 15 TB patients in that arm started treatment on the day of the visit.

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 three-arm randomized trial with a cost-effectiveness analysis. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Field

Healthcare.

Awaiting review

Purpose

CAD4TB was built to score chest X-rays for signs of pulmonary TB so that staff can decide who needs a confirmatory test. Faster diagnosis and treatment of TB was the purpose of its use in this trial.

Awaiting review

Dates

Observed: 27 November 2019. Updated: 29 October 2026.

Awaiting review

Stage

The system was used in a pilot. The X-ray and CAD4TB package ran inside a randomized trial at one clinic. [1]

Fully reviewed

Review date: 29 October 2026.

Sources: [1]

Version

SHA-256: 2291fa09b561…

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

AI Incident Database: 81.

Awaiting review

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

    MacPherson P, Webb EL, Kamchedzera W, et al. Computer-aided X-ray screening for tuberculosis and HIV testing among adults with cough in Malawi (the PROSPECT study): a randomised trial and cost-effectiveness analysis. PLoS Med. 2021;18(9):e1003752. doi:10.1371/journal.pmed.1003752

Collections: Cross-border cases.

Cite this case

BibTeX Download BibTeX

Version 2291fa09b561, 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