EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access

Speech- and Text-Based Emotion Recognition in Anesthesiology Residents During Critical Incident Simulation Training: Exploratory Observational Study

Sprach- und textbasierte Emotionserkennung bei Anästhesie-Assistenzärzt:innen während einer Simulation kritischer Zwischenfälle: explorative Beobachtungsstudie

Sapir Gershov, Itay Bentov, Fadi Mahameed, Aeyal Raz, Shlomi Laufer

JMIR Medical Education · 21.08.2026 · 12 · e96628-e96628

DOI: 10.2196/96628 ↗

Auf einen Blick

In 164 Simulationsszenarien von 90 Anästhesie-Assistenzärzt:innen zeigten sich Unterschiede der Emotionssignale je nach Leistungsgruppe und Simulationsphase. Sprachbasierte Merkmale waren konsistenter mit der Expertenbewertung verbunden.

Fragestellung

Variieren automatisch ermittelte sprach- und textbasierte Emotionssignale in Phasen kritischer Simulationsszenarien und hängen sie mit der von Expert:innen bewerteten Leistung zusammen?

Methode

Explorative Beobachtungsstudie mit 164 Simulationsszenarien von 90 Anästhesie-Assistenzärzt:innen aus 17 Kliniken; SER- und TER-Analyse, Expertenrating 1-5, ANOVA und Mixed-Effects-Sensitivitätsanalysen.

Ergebnisse

65 Szenarien wurden als schlechte, 72 als mittlere und 27 als exzellente Leistung eingestuft. SER unterschied sich zwischen den Gruppen; schlechte Leistung zeigte mehr fear/surprise, exzellente mehr calm/happiness/neutrality. TER war nur Richtung ähnlich, aber nicht signifikant.

Einschränkungen

7 Aufnahmen wurden wegen technischer Probleme ausgeschlossen.

Schlussfolgerung der Autor:innen

Automatisierte Sprach- und Textemotionserkennung erfasste phasenabhängige affektive Kommunikationsmuster in kritischen Simulationen. Sprachbasierte Merkmale waren konsistenter mit der Expertenbewertung verbunden.

Kernaussagen

  • SER unterschied sich signifikant zwischen den Leistungsgruppen.
  • Schlechte Leistung war mit mehr fear und surprise verbunden.
  • TER zeigte nur explorative, emotionsspezifische Zusammenhänge.

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

Kurz gefasst

Beobachtungsstudie in der Zeitschrift JMIR Medical Education, online erschienen am 21.08.2026. Verfasst von Sapir Gershov und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, NYU Grossman School of Medicine, 1 Park Ave., 8th Floor, New York, NY, 10016, United States, 1 646-934-4738. Hauptthemen laut MEDLINE: Internship and Residency, Anesthesiology, Simulation Training, Emotions. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Communication during crisis management involves not only the exchange of clinical information but also the expression and regulation of emotional tone and sentiment, which may reflect clinician performance during a critical incident. In simulation-based medical education, these emotional dynamics are rarely measured objectively, limiting the ability to capture aspects of performance relevant to competency assessment.

Objective

This study aimed to examine whether automatically extracted speech- and text-based emotion signals varied across predefined phases of critical incident simulation training and whether these signals were associated with expert-rated performance among anesthesiology residents.

Methods

In this exploratory observational study, we analyzed 164 simulated crisis scenarios performed by 90 anesthesiology residents from 17 hospitals during a national board preparation workshop. Each high-fidelity simulation comprised 4 predefined phases: initial condition, extreme deterioration, advanced cardiovascular life support (ACLS) management, and recovery. Resident speech was isolated and analyzed using a speech-based emotion recognition (SER) model that estimated 8 emotion categories per utterance. Speech was also automatically transcribed and analyzed using text-based emotion recognition (TER), which estimated 9 emotion categories. Expert anesthesiologists rated performance on a 1-5 scale. ANOVA tested associations between emotion categories and performance, as well as variation across simulation phases. Exploratory mixed-effects sensitivity analyses accounted for repeated simulations and scenario-level clustering.

Results

After 7 recordings were excluded because of technical issues, 65 of 164 (39.6%) simulations were classified as poor performance (score ≤2), 72 (43.9%) as intermediate, and 27 (16.5%) as excellent (score=5). SER categories differed across performance groups ( F 2,161 =4.61; P =.02): poor performance showed more fear and surprise, whereas excellent performance showed more calm, happiness, and neutrality. In mixed-effects analyses, performance group remained associated with happy, angry, fearful, surprise, calm, and neutral speech-emotion proportions after false discovery rate correction. The largest excellent vs poor differences were observed for neutral (+4.24 percentage points), happy (+4.11), and surprise (−3.17) speech affect. TER showed a directionally similar but nonsignificant omnibus association ( F 2,161 =2.57; P =.08); mixed-effects analyses identified associations with happy and sad text-emotion proportions after correction. During extreme deterioration and ACLS management, fear and surprise together accounted for 64.1% and 64.6% of classified speech emotions, respectively, among poor performances. During ACLS management, neutral and calm emotions accounted for 49.1% and 37.7%, respectively, among excellent performances.

Conclusions

Automated speech- and text-based emotion recognition captured phase-dependent affective communication patterns during critical incident simulations. Speech-derived features were more consistently associated with expert-rated performance, whereas text-derived findings were more exploratory and emotion-specific. These markers may complement simulation debriefing and formative feedback, but validation using multirater outcomes, preregistered adjusted models, and larger multicenter datasets is needed before they inform competency assessment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Internship and ResidencyAnesthesiologySimulation TrainingEmotionsSpeechHumansClinical CompetenceMaleFemale

Stichwörter der Autor:innen

affective communicationanesthesiology residentscritical incident simulationformative feedbacksimulation-based medical educationspeech-based emotion recognitiontext-based emotion recognition

Autor:innen und Institutionen

  • Department of Psychiatry, NYU Grossman School of Medicine, 1 Park Ave., 8th Floor, New York, NY, 10016, United States, 1 646-934-4738.
  • Technion Autonomous Systems Program, Technion - Israel Institute of Technology, Haifa, Israel.
  • Department of Anesthesiology and Pain Medicine, Harborview Medical Center, Seattle, WA, United States.
  • Department of Anesthesiology, Rambam Health Care Campus, Haifa, Israel.
  • Faculty of Data and Decision Sciences, Technion - Israel Institute of Technology, Haifa, Israel.
  • Rappaport Faculty of Medicine, Technion - Israel Institute of Technology, Haifa, Israel.

Zitieren

APA

Gershov, S., Bentov, I., Mahameed, F., Raz, A., & Laufer, S. (2026). Speech- and Text-Based Emotion Recognition in Anesthesiology Residents During Critical Incident Simulation Training: Exploratory Observational Study. JMIR Medical Education, 12, e96628-e96628. https://doi.org/10.2196/96628

Vancouver

Gershov S, Bentov I, Mahameed F, Raz A, Laufer S. Speech- and Text-Based Emotion Recognition in Anesthesiology Residents During Critical Incident Simulation Training: Exploratory Observational Study. JMIR Medical Education. 2026;12:e96628-e96628. doi:10.2196/96628

BibTeX
@article{Gershov2026,
  author = {Gershov, Sapir and Bentov, Itay and Mahameed, Fadi and Raz, Aeyal and Laufer, Shlomi},
  title = {Speech- and Text-Based Emotion Recognition in Anesthesiology Residents During Critical Incident Simulation Training: Exploratory Observational Study},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e96628--e96628},
  doi = {10.2196/96628}
}
Kostenlos starten →