From the Emergency Services edition of October 23, 2026
Research Square preprint: in 90 Swedish cardiac arrest calls missed by one side, ML caught 52 dispatchers missed and dispatchers caught 38 ML missed
Swedish OHCA dispatch research team (Research Square preprint) · Emergency medical dispatch · Sweden
- Publisher
- Research Square
- Original publication
- 2026-10-18
- Source retrieved
- 2026-10-24
What happened
Using a nationwide 2018 Swedish OHCA cohort in which the ML model recognized 729 of 851 cardiac arrest calls and dispatchers 715, the authors audited the 90 discordant 112 calls with CARES criteria. ML recognized arrest that dispatchers missed in 58% (52/90); dispatchers recognized arrest the ML missed in 42% (38/90). ML did better when the caller knew the patient, was a layperson, was alone, the arrest was at home, or the call was in the evening; dispatchers did better when CPR was already under way or the caller was not alone. The authors conclude the two show different failure patterns and that ML support may complement dispatchers.
Why it matters
Directly relevant to 911 and EMS dispatch centers considering AI cardiac arrest recognition: it shows where machines and call-takers each fail, which matters for alert design.
Evidence and measured results
Observational secondary analysis of 2018 audio; preprint, not peer reviewed; small discordant sample; odds ratios have wide confidence intervals.
Limitations and uncertainty
Data from 2018; Swedish language and protocols; only 90 calls; association analysis, not a trial of live alerting.
Put this evidence to work
Lighthouse Advisory interpretation, grounded in this source. Enriched 2026-10-23; this does not change the original publication date. Each role follows the same checklist so takeaways compare across sources.
Sales
Role takeaway
- Customer problem
- Dispatchers miss some out-of-hospital cardiac arrests on calls, delaying CPR instructions.
- Stakeholders
- 911/PSAP director
- EMS medical director
- Quality assurance lead
- CAD vendor
- Discovery questions
- What share of your confirmed arrests were recognized on the call?
- Do you audit missed-arrest calls by caller type?
- How would call-takers be told to handle an AI alert they disagree with?
- Value hypothesis
- An ML second listener may catch some arrests dispatchers miss, mainly with lone lay callers (interpretation).
- Potential engagement
- A bounded retrospective audit of local cardiac arrest call recordings against an ML model.
- Unsupported claims
- Lives saved or faster CPR
- That dispatchers will act on alerts
- Performance in English-language U.S. centers
Pre-sales engineering
Role takeaway
- Fit
- Fits PSAPs with recorded call audio and EMD protocols for cardiac arrest.
- Architecture and integration
- Real-time speech model on call audio producing alerts in the call-taker's screen or CAD.
- Prerequisites
- Access to call audio streams
- Local labeled cardiac arrest calls
- CAD or call-handling integration
- Constraints
- 2018 Swedish data
- Small discordant sample
- Preprint status
- Language and protocol differences
- Security
- Live caller audio needs secure processing and retention limits matching recording policy.
- Proof of value
- Retrospective recognition comparison on local calls
- Error breakdown by CPR-in-progress and multi-caller calls
- Time-to-recognition measurement
Delivery
Role takeaway
- Work
- Audit local calls, set alert handling protocols, then trial silent-mode alerts before live use.
- Dependencies
- Call recording access
- Medical director protocol
- QA reviewers
- Ownership
- PSAP director with the EMS medical director.
- Skills and adoption
- Call-takers learn how to treat and document AI alerts.
- Governance checkpoints
- Medical protocol approval
- Silent-mode review before live alerts
- Quarterly missed-arrest audit
- Acceptance criteria
- Proposed: higher combined recognition than dispatcher baseline in silent mode
- Proposed: no added call time
- Risks
- Alert fatigue
- Dispatchers ignoring alerts
- Weaker accuracy in other languages
Implementation considerations
Lighthouse Advisory interpretation across the operating dimensions a public-sector buyer must settle before this evidence becomes a design. Each note answers the question under its heading for this specific source.
Architecture and integration
What must connect, and where does the AI sit in the workflow?
Real-time ML listening on emergency call audio with alerts to the call-taker; the study does not test live alerting.
Governance
Who approves, reviews and stays accountable for outcomes?
Because each side misses different calls, policy should treat ML as a second listener with protocols for when its alert conflicts with the dispatcher's judgement.
Security and privacy
What data, permissions and controls need testing?
Requires processing live caller audio; retention and access rules for recordings apply.
Accessibility and workforce
Who is affected, and what skills or accommodations follow?
Dispatchers outperform ML in multi-caller and CPR-in-progress calls, so the human role remains central.
Procurement
What should contracts, pricing and exit terms secure?
Buyers should ask vendors for failure-mode analysis by call type, not only overall sensitivity.
Operating model
Which teams own the service once it runs?
Supports a complementary model with ML as a second listener rather than a replacement.
Publication history
- 2026-10-23Emergency Services · Issue 475 resources
Stable resource ID: researchsquare-sweden-ohca-ml-vs-dispatchers-discordant-90-calls-20261018