Can a recording help a model tell apart people who report asthma and people selected as healthy controls? The new Colive Voice analysis gives a model several kinds of information at once. To see what the voice contributes, compare the full model with versions that use just the audio or just the structured information.

THE SHORT READ
  • The journal abstract reports an AUROC of 0.83 and a Brier score of 0.18 in a matched sample of 1,218 people.
  • In the author manuscript, the two voice tasks together scored 0.71 AUROC. Structured health and demographic data alone scored 0.75.
  • The comparison uses self-reported asthma and selected healthy controls. A clinic evaluation would need its own recruitment and reference diagnosis.
THE STUDY AT A GLANCEVoice and clinical information in the Colive Voice study · Despotovic et al.
Paper date
22 November 2026
Matched sample
1,218 Colive Voice participants
Journal abstract AUROC
0.83
Journal abstract Brier score
0.18

Original publication: 22 Nov 2026 · The date above refers to this brief.

THE NUMBERS, IN CONTEXT

How the model inputs changed ranking performance

AUROC

Two voice tasks0.71
Structured information0.75
All three inputs0.83
01
Point estimates from Table 2 in the author manuscript. The full-model value agrees with the journal abstract.
THE EXPERIMENT, EXPLAINED

What the next validation would check

  1. Define the label

    Record whether the outcome is self-reported or clinically assessed.

  2. Compare the inputs

    Check how performance differs with audio, structured information and both.

  3. Recruit a separate test group

    Check ranking and probability errors where the tool would be evaluated.

Press-News guide to reading the model evaluation and a possible follow-up.

Look for the comparison that isolates the input

The author manuscript describes two recordings, a sustained vowel and a reading task, alongside structured health and demographic information. In Table 2, the audio-only combination had an AUROC of 0.71, the structured-information model scored 0.75 and the full model scored 0.83. The full score is 0.12 higher than the audio-only score and 0.08 higher than the structured-information score. Those are differences between reported point estimates in the same table.

Source 1 ↗Source 2 ↗

Ranking and probability error can favour different versions

AUROC asks whether the model tends to rank a person labelled as a case above a person labelled as a control across possible cutoffs. The Brier score averages squared differences between predicted probabilities and the observed binary labels. Lower scores indicate smaller errors by that measure. In the author manuscript, the full model had higher AUROC than the XGBoost comparator using all three inputs, 0.83 versus 0.81. The comparator had the lower Brier score, 0.17 versus 0.18. The two differences are descriptive and depend on the evaluation data.

Source 1 ↗Source 2 ↗

The reference labels and the sample determine the question

The author manuscript lists 609 self-reported cases and 609 matched controls. Each group makes up half of the analysis by design. That can help compare scores across groups. It also means that the observed case proportion and the measured probability error belong to this sample. In a group of patients with similar respiratory symptoms and different diagnoses, a model would face a different set of examples.

Source 1 ↗Source 2 ↗

A clinical validation would change the comparison again

An independent study could recruit people for whom the diagnosis is still uncertain and compare predictions with a prespecified clinical assessment. It could report how many people cross a fixed cutoff, how probabilities agree with observed outcomes and how results vary by language or recording conditions. The new report evaluates a candidate research measure. Its matched-sample results give that next study a comparison to work from.

Source 1 ↗Source 2 ↗
TRACE THE EVIDENCE

Read the inputs, labels and scores together

Publisher’s abstract and publication record for the accepted article. Checked the sample size, self-reported reference label and headline performance. The author manuscript provides the detailed comparison.

01What did the journal report for the full model?

What was observed
AUROC 0.83 and Brier score 0.18.
Where the conclusion stops
These metrics describe performance against the labels in the matched sample.

Source 1 · Published abstract

02Was the highest-ranking model also best by probability error?

What was observed
The full model had higher AUROC than XGBoost, while XGBoost had the lower Brier score.
Where the conclusion stops
The distinction is between the reported point estimates in this analysis.

Source 2 · Author manuscript, Table 2

Numbers you can inspect

MeasureValue & unitOrigin & method
Matched evaluation sample1218 peopleReported Study cases and controls together.
Source 1 · Published abstract
Full model ranking0.83 AUROCReported Combined voice, health and demographic inputs.
Source 1 · Published abstract
Full model probability error0.18 Brier scoreReported Reported mean squared probability error.
Source 1 · Published abstract
Self-reported cases609 peopleReported Matched case group in the author manuscript.
Source 2 · Author manuscript, Table 1
Matched controls609 peopleReported Control group in the author manuscript.
Source 2 · Author manuscript, Table 1
Two voice tasks only0.71 AUROCReported Sustained vowel and reading input.
Source 2 · Author manuscript, Table 2
Structured information only0.75 AUROCReported Health and demographic inputs.
Source 2 · Author manuscript, Table 2
Full model minus audio-only estimate0.12 AUROC unitsCalculated Subtract the audio-only score of 0.71 from 0.83.
Source 2 · Author manuscript, Table 2
Full model minus structured-only estimate0.08 AUROC unitsCalculated Subtract the structured-only score of 0.75 from 0.83.
Source 2 · Author manuscript, Table 2
XGBoost ranking using all inputs0.81 AUROCReported Different algorithm using all three input sets.
Source 2 · Author manuscript, Table 2
XGBoost probability error using all inputs0.17 Brier scoreReported Same comparator and its probability error.
Source 2 · Author manuscript, Table 2

Compare the actual experiments

These studies answer different questions. Read the unit and endpoint before comparing results.

StudyUnit & settingReadoutInterpretation boundary
Combined inputs and a voice-only model

Source 2 · Author manuscript, Table 2

Same matched sampleAUROC changes with available inputsRead what was measured before crediting one input for the full result.
Ranking and threshold decisions

Source 1 · Published abstract and author manuscript

Matched participants and possible decision cutoffsAUROC and threshold-specific error ratesA threshold for a new population requires separate validation.
Download evidence table (CSV)

The export includes claims, available numbers, methods and source locations. It contains our reading notes and published summaries; it is not raw participant data or an independent reanalysis.

Evidence update · 22 Nov 2026
First publication. Any calculations in this brief use reported figures. The reading notes identify possible follow-up questions. AI source check; no human editorial or clinical review.

CONNECT THE EVIDENCE

Model inputs and two different performance measures

Inputs and modelRanking measureProbability error
Two voice tasksAUROC 0.71Brier score 0.23.
Structured information onlyAUROC 0.75Brier score 0.20.
All three inputs, full modelAUROC 0.83Brier score 0.18.
All three inputs, XGBoost comparatorAUROC 0.81Brier score 0.17.

Author manuscript, Table 2. Values refer to the same matched-sample analysis.

READER QUESTIONS

Your questions, answered

Were the headline results obtained from voice alone?

The journal reports the combined model. The separate voice-only comparison in the author manuscript gives a lower AUROC of 0.71.

Does 0.83 AUROC mean the test got 83% of decisions right?

AUROC measures ranking across decision cutoffs. To read proportions of correct decisions, look for a stated cutoff and the associated test counts.

Why can a model rank better but have a higher Brier score?

A model can order cases well while the probabilities it assigns are still farther from the observed outcomes. Ranking and squared probability errors are different checks.

What does the half-and-half split mean?

The authors matched cases and controls for the study. Their equal numbers describe the research sample.

LIMITATIONS

Limits of this interpretation

  • The journal abstract supports the selected sample and headline results. Input comparisons are separately attributed to Table 2 of the author manuscript.
  • The reported labels and balanced sample limit what the scores say about evaluation in a clinic.
  • Changes in the collection setting, equipment, language or mix of respiratory symptoms could affect model performance.
SOURCE NOTES

Sources & transparency

  1. Despotovic et al. (2026) — Multimodal digital biomarker for asthma: complementary roles of vocal, clinical and demographic factors

    Publisher’s abstract and publication record for the accepted article. Checked the sample size, self-reported reference label and headline performance. The author manuscript provides the detailed comparison. · Accessed 22 Nov 2026

    DOI: 10.1038/s41746-026-03465-w
  2. Despotovic et al. (2026) — Author manuscript on arXiv

    Author manuscript, Tables 1 and 2 and Methods. The full-model values in Table 2 match the journal abstract. The earlier preprint summary lists different values, so detailed comparisons here identify their table. · Accessed 22 Nov 2026

    DOI: 10.48550/arXiv.2607.08714

Prepared and source-checked with AI for Press-news Team. The source notes identify the material available during preparation. The article received no human editorial or clinical review. The source list supports the reported results and the calculations shown.

Source check: AI source check — primary research and stated source limits

Clinical review: Not applicable to this educational guide

Suggest a correction