🔥 Hot topics · ⛔ Can NOT do · ✅ Can do · § The Court · ⚖ Recent inflections · 📈 Timeline · ❓ Ask · ✨ Editorials · 🔥 Hot topics · ⛔ Can NOT do · ✅ Can do · § The Court · ⚖ Recent inflections · 📈 Timeline · ❓ Ask · ✨ Editorials
Stuff AI CAN'T Do

Can AI predict rheumatoid arthritis exacerbations from voice tremors detected in phone calls ?

What do you think?

Could subtle voice tremors picked up during everyday phone calls serve as an early warning system for rheumatoid arthritis flares? Research is probing whether AI-driven analysis of vocal fluctuations—detectable before joint pain intensifies—could enable real-time, non-invasive flare prediction without wearables. How close are such techniques to being clinically actionable?

Background

Inflammation in rheumatoid arthritis can impair vocal cord function, introducing subtle voice fluctuations such as pitch instability or tremolo that may precede overt joint pain. Early studies leveraging smartphone voice recordings and machine-learning models have reported correlations between acoustic features and patient-reported disease activity, suggesting the feasibility of using passive call monitoring for flare prediction. However, these findings remain preliminary, with modest accuracy and unresolved challenges around background noise, emotional stress confounding results, privacy, consent, and regulatory approval. Larger, longitudinal clinical trials are still required before such AI-driven audio analysis could be validated for routine patient care. Source: Nature Medicine, May 12, 2026.

Status last checked on September 25, 2026.

📰

Gallery

In the Court of AI Capability
Summary of Findings
Verdict over time
May 2026May 2026May 2026May 2026May 2026Jun 2026Jun 2026Jun 2026Jun 2026Jun 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Jul 2026Aug 2026Aug 2026Aug 2026Aug 2026Aug 2026Aug 2026Sep 2026Sep 2026Sep 2026Sep 2026Sep 2026
Sitting at the Bench Filed · Sep 25, 2026
— The Question Before the Court —

Can AI predict rheumatoid arthritis exacerbations from voice tremors detected in phone calls?

★ The Court Finds ★
▲ Upgraded from No
⚖
In Research

The jury could not deliver a verdict on the evidence presented.

Jury Tally
0Yes
0Almost
0No
Verdict Confidence
60%
The Court of AI Capability is, of course, not a real court.
But the data is real.
The Case File · Stacked History
Session I · May 2026 No
Session II · May 2026 Almost · 75%
Session III · May 2026 Almost · 75%
Session IV · May 2026 Almost · 68%
Session V · May 2026 Almost · 70%
Session VI · Jun 2026 Almost · 75%
Session VII · Jun 2026 Almost · 73%
Session VIII · Jun 2026 Almost · 70%
Session IX · Jun 2026 In_research · 65%
Session X · Jun 2026 In_research · 60%
Session XI · Jul 2026 In_research · 70%
Session XII · Jul 2026 No · 90%
Session XIII · Jul 2026 In_research · 45%
Session XIV · Jul 2026 In_research · 60%
Session XV · Jul 2026 Almost · 70%
Session XVI · Jul 2026 Almost · 70%
Session XVII · Aug 2026 Almost · 80%
Session XVIII · Aug 2026 In_research · 65%
Session XIX · Aug 2026 In_research · 80%
Session XX · Aug 2026 In_research · 60%
Session 21 · Aug 2026 In_research · 70%
Session 22 · Aug 2026 In_research · 90%
Session 23 · Sep 2026 No · 70%
Session 24 · Sep 2026 In_research · 63%
Session 25 · Sep 2026 No · 85%
Session 26 · Sep 2026 No · 85%
Case № 4B36 · Session 27
In the Court of AI Capability

The Case File

Docket № 4B36 · Session 27 · Vol. 27
I. Particulars of the Case
Question put to the courtCan AI predict rheumatoid arthritis exacerbations from voice tremors detected in phone calls?
Session27 (27 hearing)
Convened25 Sep 2026
Previously ruledNO (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (May '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → ALMOST (Jun '26) → IN_RESEARCH (Jun '26) → IN_RESEARCH (Jun '26) → IN_RESEARCH (Jul '26) → NO (Jul '26) → IN_RESEARCH (Jul '26) → IN_RESEARCH (Jul '26) → ALMOST (Jul '26) → ALMOST (Jul '26) → ALMOST (Aug '26) → IN_RESEARCH (Aug '26) → IN_RESEARCH (Aug '26) → IN_RESEARCH (Aug '26) → IN_RESEARCH (Aug '26) → IN_RESEARCH (Aug '26) → NO (Sep '26) → IN_RESEARCH (Sep '26) → NO (Sep '26) → NO (Sep '26) → IN_RESEARCH (Sep '26)
II. Cumulative Tally Across Sessions

Across 27 sessions, 50 jurors have heard this case. Combined tally: 0 YES · 25 ALMOST · 13 NO · 12 IN RESEARCH.

Note: cumulative includes older juror opinions. The current session tally above is the live verdict.

III. Verdict

By a vote of 0 — 0 — 0, the panel returns a verdict of IN RESEARCH, with verdict confidence of 60%. The court so orders. Verdict upgraded from prior session.

IV. Statements from the Bench
Juror I IN RESEARCH

"Specific longitudinal studies linking voice biomarkers to RA exacerbation predictions are not sufficiently established in public literature."

—
Presiding Judge
M. Lovelace
Clerk of the Court

What the audience thinks

No 61% · Yes 9% · Maybe 30% 23 votes
No · 61%
Maybe · 30%
9 days of activity

Discussion

no comments

Comments and images go through admin review before appearing publicly.

⚖ 27 jury checks · most recent 1 day ago
25 Sep 2026 1 juror · undecided undecided
20 Sep 2026 1 juror · cannot cannot
15 Sep 2026 1 juror · cannot cannot
09 Sep 2026 1 juror · undecided undecided
04 Sep 2026 1 juror · cannot cannot
29 Aug 2026 1 juror · undecided undecided
24 Aug 2026 1 juror · undecided undecided
19 Aug 2026 1 juror · undecided undecided
13 Aug 2026 2 jurors · undecided, cannot undecided
08 Aug 2026 2 jurors · undecided, cannot undecided
02 Aug 2026 1 juror · undecided undecided
28 Jul 2026 1 juror · undecided undecided
23 Jul 2026 1 juror · undecided undecided
17 Jul 2026 1 juror · undecided undecided
12 Jul 2026 2 jurors · undecided, undecided undecided
06 Jul 2026 1 juror · cannot cannot
01 Jul 2026 2 jurors · undecided, undecided undecided
25 Jun 2026 2 jurors · undecided, undecided undecided
20 Jun 2026 2 jurors · undecided, undecided undecided
15 Jun 2026 3 jurors · undecided, undecided, undecided undecided
09 Jun 2026 3 jurors · cannot, undecided, undecided undecided
04 Jun 2026 3 jurors · undecided, cannot, undecided undecided
29 May 2026 4 jurors · undecided, cannot, undecided, undecided undecided
24 May 2026 3 jurors · undecided, undecided, undecided undecided
19 May 2026 3 jurors · cannot, undecided, undecided undecided
15 May 2026 4 jurors · undecided, cannot, undecided, undecided undecided status changed
12 May 2026 2 jurors · cannot, cannot cannot status changed

Each row is a separate jury check. Jurors are AI models (identities kept neutral on purpose). Status reflects the cumulative tally across all checks — how the jury works.

More in health

Got one we missed?

Add a statement to the atlas. We review weekly.