EUVIMEDSkopri EUVIMED
MetaanalyseSystematische ÜbersichtOpen access

Technological Integration in Triage With AI and Machine Learning Compared With Conventional Triage and Narrative Synthesis of Telehealth for Patient Prioritization in Emergency and Acute Care Settings: Systematic Review and Meta-Analysis

Technologische Integration in der Triage mit KI und Machine Learning im Vergleich zur konventionellen Triage und narrative Synthese von Telehealth zur Patient:innenpriorisierung in Notaufnahme und Akutversorgung: systematische Übersichtsarbeit und Metaanalyse

Faii O M Ashour, Waqas Sami, Intima Alrimawi, Moattar Raza Rizvi, Majeda M El-Banna

Journal of Medical Internet Research · 2026-10-19 · 28 · e93931-e93931

DOI: 10.2196/93931 ↗

Auf einen Blick

27 Studien untersuchten KI-/ML-gestützte Triage und Teletriage. Für erwachsene Notaufnahme-Studien mit kritischen Zuständen zeigte sich eine hohe Diskriminierung; Teletriage verbesserte teils Prozessmaße.

Fragestellung

Wie schneiden KI-/ML-gestützte Triage und Teletriage bei der Priorisierung in Notaufnahme und Akutversorgung ab?

Methode

Systematische Übersichtsarbeit mit Metaanalyse und narrativer Synthese; Suche in mehreren Datenbanken, Preprint-Servern, Studienregistern und Konferenzbeiträgen für 2010 bis 2025.

Ergebnisse

27 Studien: 13 quantitative und 14 narrative. Erwachsene ED-Studien: gepoolter AUC 0,874 (95 %-KI 0,845–0,898; I²=94,4 %; 95 %-Prädiktionsintervall 0,803–0,922). Teletriage: 15 %–40 % kürzere Zeit bis zur klinischen Beurteilung und 2–8 Prozentpunkte weniger left-without-being-seen.

Einschränkungen

Hohe Heterogenität, unvollständige Berichte zu Schwellenwerten und Kalibrierung, begrenzte externe Validierung und spärliche pädiatrische Evidenz.

Schlussfolgerung der Autor:innen

KI- und ML-gestützte Triage-Modelle zeigen bei erwachsenen ED-Risiken vielversprechende Diskriminierung, belegen aber weder bessere klinisch relevante Entscheidungen noch verbesserte Patientenergebnisse oder Implementierbarkeit.

Kernaussagen

  • Erwachsene ED-Studien: gepoolter AUC 0,874
  • Teletriage war mit besseren Front-door-Prozessmaßen verbunden
  • Für Routineimplementierung fehlen Validierung, Kalibrierung und Ökonomie-Daten

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Metaanalyse in Journal of Medical Internet Research, published online on 2026-10-19. Written by Faii O M Ashour and 4 co-authors. Institution: College of Nursing, QU-Health Sector, Qatar University, P.O. Box 2713, Doha, Qatar, +974 4403 7433. Major MEDLINE topics: Artificial Intelligence, Telemedicine, Triage. 106 references. The full text is freely available in PubMed Central.

Auf einen BlickAstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Conventional triage relies on clinician judgment and limited information available at first contact. AI and machine learning (ML) may improve early risk stratification, whereas tele-triage and patient-facing tools primarily support remote assessment, access, and care routing.

Objective

This study aimed to evaluate the diagnostic and prognostic performance of AI- and ML-assisted triage systems and summarize evidence on tele-triage, workflow, implementation, economic, and equity outcomes.

Methods

Comparative studies published between January 1, 2010, and December 31, 2025, evaluating AI-, ML-, natural language processing–, telehealth-, or digitally enhanced triage. At first, clinical contacts were included. PubMed/MEDLINE, CINAHL, Web of Science, Scopus, preprint servers, trial registries, and conference proceedings were searched. Screening and data extraction were performed independently in duplicate. Risk of bias was assessed using design-appropriate tools. Clinically comparable area under the receiver operating characteristic curve (AUC) estimates were synthesized using random-effects meta-analysis; heterogeneous diagnostic, operational, implementation, economic, and equity outcomes were summarized narratively. Exploratory scenario modeling projected effects per 10,000 emergency department (ED) visits.

Results

Twenty-seven studies were included, comprising 13 studies in the quantitative evidence stream and 14 in the narrative synthesis. Four adult ED studies evaluating critical care or deterioration outcomes demonstrated high pooled discrimination for AI-assisted triage (AUC 0.874; 95% CI 0.845‐0.898; I ²=94.4%; 95% prediction interval 0.803‐0.922). Four studies reported directly extractable within-study comparisons favoring AI-assisted models (AUC differences of 0.097, 0.120, 0.108, and 0.065), although these could not be pooled because paired variance estimates were unavailable. Admission/disposition studies reported AI-model AUCs ranging from 0.80 to 0.93 and were summarized descriptively because extreme heterogeneity precluded meaningful pooling. Two pediatric studies (AUCs of 0.85‐0.99) were summarized descriptively. Prediction-model studies were primarily limited by deficiencies in model analysis, calibration reporting, and external validation. Narrative evidence suggested improved front-door operational metrics with tele-triage, including reported reductions of 15%‐40% in time to clinical assessment and 2‐8 percentage points in left-without-being-seen rates, whereas patient-facing symptom checkers generally favored sensitivity over specificity. Exploratory scenario modeling illustrated that, under specified prevalence and threshold assumptions, AI-assisted triage could be associated with 12‐38 fewer missed critical illness cases and 45‐120 additional false-positive escalations per 10,000 ED visits. Economic and equity findings were assumption-dependent projections rather than observed clinical, cost-effectiveness, or equity outcomes.

Conclusions

AI- and ML-assisted triage models demonstrate promising discrimination for adult ED risk stratification; however, AUC-based discrimination does not establish superiority at clinically relevant decision thresholds, improved patient outcomes, or readiness for clinical implementation. Interpretation is limited by substantial heterogeneity, incomplete threshold-level performance and calibration reporting, limited external validation, and sparse pediatric evidence. Prospective multicenter validation, workflow assessment, subgroup calibration and equity auditing, and formal economic evaluation are required before routine implementation.

Subjects

MeSH terms (MEDLINE)

Artificial IntelligenceTelemedicineTriageHumansEmergency Service, HospitalMachine Learning

Author keywords

artificial intelligenceemergency department triagehealth equitymachine learningrisk predictiontele-triage

Authors and institutions

  • College of Nursing, QU-Health Sector, Qatar University, P.O. Box 2713, Doha, Qatar, +974 4403 7433.
  • Department of Pre-Clinical Affairs, College of Nursing, QU-Health, Qatar University, Doha, Qatar.
  • Berkley School of Nursing, Georgetown University, Washington, DC, United States.
  • Faculty of Allied Health Sciences, Santosh Deemed to be University, Ghaziabad, Delhi, NCR, 201009, India.

Cite

APA

Ashour, F. O. M., Sami, W., Alrimawi, I., Rizvi, M. R., & El-Banna, M. M. (2026). Technological Integration in Triage With AI and Machine Learning Compared With Conventional Triage and Narrative Synthesis of Telehealth for Patient Prioritization in Emergency and Acute Care Settings: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e93931-e93931. https://doi.org/10.2196/93931

Vancouver

Ashour FOM, Sami W, Alrimawi I, Rizvi MR, El-Banna MM. Technological Integration in Triage With AI and Machine Learning Compared With Conventional Triage and Narrative Synthesis of Telehealth for Patient Prioritization in Emergency and Acute Care Settings: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e93931-e93931. doi:10.2196/93931

BibTeX
@article{Ashour2026,
  author = {Ashour, Faii O M and Sami, Waqas and Alrimawi, Intima and Rizvi, Moattar Raza and El-Banna, Majeda M},
  title = {Technological Integration in Triage With AI and Machine Learning Compared With Conventional Triage and Narrative Synthesis of Telehealth for Patient Prioritization in Emergency and Acute Care Settings: Systematic Review and Meta-Analysis},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e93931--e93931},
  doi = {10.2196/93931}
}
Start for free →