{"resourceId":"lmic-prehospital-ai-scoping-review-2025","versions":[{"version":"external-8c4fe0edad458d732fda1b52f15c0e7bb2b3e58dab0b9377ccef87cd89eeb6d8","resource":{"id":"lmic-prehospital-ai-scoping-review-2025","title":"Prehospital AI review finds uneven evidence and no low-income-country studies","organization":"Mallon and colleagues; Maastricht University and international collaborators","sector":"EMS dispatch, coordination and prehospital decision support","geography":"Middle-income-country evidence; U.S. transfer requires local validation","publishedAt":"June 20, 2025","publicationDate":"2025-06-20","eventDate":null,"sourceName":"Frontiers in Public Health","sourceLabel":"Peer-reviewed scoping review","sourceUrl":"https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2025.1604231/full","evidenceClass":"academic-research","outcomeClass":"mixed","topics":["knowledge-work","infrastructure","data-security","governance-procurement","accessibility-workforce","operating-model"],"finding":"The review maps promising EMS uses but does not establish general clinical benefit or universal model superiority.","sledRelevance":"Interpretation: Helps U.S. agencies question transferability and evidence gaps without equating their systems with the reviewed settings.","evidence":"Five databases and reference searches through July 23, 2024 yielded 16 studies: 15 retrospective and one prospective; none used low-income-country data. Table 2 includes a maritime-demand case favoring a statistical comparator and a prospective stroke-delay study with negligible AUC difference against logistic regression. There is no common baseline or pooled effect estimate.","architectureImplications":"Interpretation: Validate the data pipeline before adding model complexity. Compare with simple statistical and current operational baselines. Cloud, on-premises and hybrid fit depend on local data availability and continuity; this review is not a hosting benchmark. Agentic capability has limited direct evidence here.","governanceImplications":"Interpretation: Require intended-population validation and independent appraisal before procurement; descriptive literature coverage cannot substitute for that appraisal.","securityPrivacyImplications":"Interpretation: Establish data minimization, controlled linkage and retention rules for dispatch and patient records, including vendors and research partners.","caveats":"English-only search, initial single screening, heterogeneous reporting and no methodological critical appraisal. Search cutoff predates this edition. Authors disclose employment at Falck and Rescue.co. Individual cited studies and supplementary search files were not independently re-evaluated.","streamIds":["emergency-services"],"roles":{"sales":"Interpretation — EMS leaders and dispatch planners need evidence that a proposed tool fits their population and service constraints. Ask about the existing baseline, missing records, rural coverage, language mix and who can independently assess a vendor's study. A bounded engagement could build an evidence inventory and identify the smallest locally testable use case. The value hypothesis is avoiding unsupported scope while finding a measurable operational problem. Include clinical leadership, analysts, frontline staff and procurement. This review does not support a uniform savings estimate or a claim that AI always beats simpler methods. International findings should inform questions, with explicit limits on transfer to U.S. agencies.","engineering":"Interpretation — Select one task, such as demand forecasting or record classification, and create a reproducible baseline before integrating a new model. Prerequisites include trustworthy timestamps, defined missing-data handling, lawful access and a representative temporal holdout. Compare model performance with the existing process and an appropriate simpler method using identical inputs. Audit data leakage, calibration and subgroup errors; report excluded cases and system outages. Avoid pooling incompatible accuracy measures into a product score. A proof of value should establish whether the complete local workflow improves its prespecified endpoint under realistic staffing and connectivity constraints. Secure the evaluation dataset and document what remains untested before any operational integration.","delivery":"Interpretation — Appoint an evaluation lead alongside the operational EMS owner and a data steward. Inventory data sources, resolve definitions, train staff in consistent recording and agree on baseline and stopping rules. Dependencies include outcome linkage, access approvals and sufficient analyst time. Review representativeness and methodological quality before a pilot, then review adoption and unintended workload during it. Proposed acceptance requires a reproducible comparison, explicit missingness counts, results for agreed population groups and a documented disposition for every material limitation. Thresholds should be agreed locally rather than borrowed from the review. Maintain the existing service when evidence is inconclusive; improvement work may appropriately end with better data rather than a deployed model."},"retrievedAt":"2026-09-14T03:01:57Z","enrichedAt":"2026-09-14T03:05:02Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Interpretation: Include local languages, rural workflows and affected staff in testing; lack of representation is an evidence gap rather than proof of poor performance.","procurementImplications":"Interpretation: Require task-specific comparisons and subgroup reporting. Do not extrapolate a favorable published metric into local response-time savings.","operatingModelImplications":"Interpretation: Pair a dispatch or clinical owner with an evaluation lead and data steward; maintain current protocols until a bounded local study supports change.","updateExplanation":"Newly catalogued historical review; full-archive DOI search found no match. Adds international representativeness and non-AI comparator evidence to the EMS collection. Not presented as a September announcement.","sourceVerification":{"openedUrl":"https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2025.1604231/full","referenceExcerpt":"there was no methodological critical appraisal of the individual studies","promptVersion":"sled-research-v3.2","model":null,"basis":"agent-reported inspection"}}}]}