Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis
Anwendung von KI in der mehrstufigen Schmerzerfassung anhand von Gesichtsaufnahmen: systematische Übersichtsarbeit und Metaanalyse
Journal of Medical Internet Research · 12.04.2024 · 26 · e51250
DOI: 10.2196/51250 ↗Auf einen Blick
Die Übersichtsarbeit untersuchte, wie gut KI-Modelle Schmerzen aus Gesichtsaufnahmen in mehreren Stufen erkennen. In der Metaanalyse zeigten die Modelle sehr hohe Sensitivität und Spezifität.
Fragestellung
Wie gut ist die diagnostische Leistung von KI-Modellen zur mehrstufigen Schmerzerfassung aus Gesichtsaufnahmen?
Methode
Systematische Übersichtsarbeit und Metaanalyse; Suche in PubMed, Embase, IEEE, Web of Science und Cochrane Library bis 30. September 2023; Qualitätsbewertung mit QUADAS-2.
Ergebnisse
45 Berichte in der systematischen Übersicht, 6 Studien in der Metaanalyse. Kombinierte Sensitivität 98 % (95 %-KI 96 %-99 %), Spezifität 98 % (95 %-KI 97 %-99 %), LDOR 7,99 (95 %-KI 6,73-9,31), AUC 0,99 (95 %-KI 0,99-1).
Einschränkungen
Alle Studien hatten mindestens einen Bereich mit hohem Verzerrungsrisiko; bei 20 % der Studien bestanden keine Anwendbarkeitsprobleme. Unbalancierte Daten wurden als Hauptproblem hervorgehoben.
Schlussfolgerung der Autor:innen
Die aktuellen CV-Algorithmen zeigten eine vielversprechende Leistung für die Schmerzerfassung aus Gesichtsaufnahmen. Genannt wurden als Schwächen kleine Datenbanken und geeignete Metriken für Multiklassen-Performance.
Kernaussagen
- 45 Berichte in der Übersicht, 6 Studien in der Metaanalyse
- Sensitivität und Spezifität jeweils 98 %
- Unbalancierte Daten waren ein zentrales Problem
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Metaanalyse in der Zeitschrift Journal of Medical Internet Research, online erschienen am 12.04.2024. Verfasst von Jian Huo und 4 weiteren Autor:innen. Beteiligte Einrichtung: Boston Intelligent Medical Research Center, Shenzhen United Scheme Technology Company Limited, Boston, MA, United States. Hauptthemen laut MEDLINE: Artificial Intelligence, Algorithms. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Schmerzmanagement
Abstract (Originalsprache)
Background
The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps.
Objective
The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images.
Methods
The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots.
Results
A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns.
Conclusions
This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. Trial Registration PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Boston Intelligent Medical Research Center, Shenzhen United Scheme Technology Company Limited, Boston, MA, United States.
- Department of Anesthesia, Shenzhen People's Hospital, The First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Key Medical Discipline, Shenzhen, China.
- Shenzhen United Scheme Technology Company Limited, Shenzhen, China.
- The Second Clinical Medical College, Jinan University, Shenzhen, China.
ORCID-Profile: Jian Huo, Yan Yu, Wei Lin, Anmin Hu, Chaoran Wu
Zitieren
APA
Huo, J., Yu, Y., Lin, W., Hu, A., & Wu, C. (2024). Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 26, e51250. https://doi.org/10.2196/51250
Vancouver
Huo J, Yu Y, Lin W, Hu A, Wu C. Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2024;26:e51250. doi:10.2196/51250
BibTeX
@article{Huo2024,
author = {Huo, Jian and Yu, Yan and Lin, Wei and Hu, Anmin and Wu, Chaoran},
title = {Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis},
journal = {Journal of Medical Internet Research},
year = {2024},
volume = {26},
pages = {e51250},
doi = {10.2196/51250}
}
EUVIMED