Diagnostic accuracy of deep learning using speech samples in depression: a systematic review and meta-analysis
Diagnostische Genauigkeit von Deep Learning mit Sprachproben bei Depression: systematische Übersicht und Metaanalyse
Journal of the American Medical Informatics Association · 01.10.2024 · 31 (10) · 2394-2404
DOI: 10.1093/jamia/ocae189 ↗Auf einen Blick
Eine systematische Übersicht und Metaanalyse untersuchte die diagnostische Genauigkeit von Deep Learning mit Sprachproben bei Depression. Gepoolt lagen Genauigkeit, Spezifität und Sensitivität bei 0,87, 0,85 und 0,82.
Fragestellung
Wie genau erkennen Deep-Learning-Modelle Depression anhand von Sprachproben?
Methode
Systematische Übersicht und Metaanalyse; Datenbanken PubMed, Medline, Embase, PsycINFO, Scopus, IEEE und Web of Science bis 31. Januar 2024; Risiko für Bias mit QUADAS-2 bewertet.
Ergebnisse
25 Studien erfüllten die Kriterien, 8 gingen in die Metaanalyse ein. Gepoolte Genauigkeit 0,87 (95 %-KI 0,81–0,93), Spezifität 0,85 (95 %-KI 0,78–0,91), Sensitivität 0,82 (95 %-KI 0,71–0,94). Handcrafted-Gruppe: 0,89 (95 %-KI 0,81–0,97).
Einschränkungen
Alle Studien der Metaanalyse nutzten CNN-Modelle; dadurch sind andere DL-Algorithmen schwer beurteilbar.
Schlussfolgerung der Autor:innen
Die Anwendung von Deep Learning in Sprache war ein nützliches Instrument zur Depressionsdetektion. CNN-Modelle mit handgefertigten akustischen Merkmalen könnten die diagnostische Leistung verbessern.
Kernaussagen
- Gepoolte Genauigkeit: 0,87
- Spezifität 0,85; Sensitivität 0,82
- Handcrafted-Gruppe mit höchster Genauigkeit: 0,89
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 16.07.2024. Verfasst von Lidan Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London, …. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King's College London-China Scholarship Council, King’s College London—China Scholarship Council.
Themen: Depression
Abstract (Originalsprache)
Objective
This study aims to conduct a systematic review and meta-analysis of the diagnostic accuracy of deep learning (DL) using speech samples in depression. Materials and Methods This review included studies reporting diagnostic results of DL algorithms in depression using speech data, published from inception to January 31, 2024, on PubMed, Medline, Embase, PsycINFO, Scopus, IEEE, and Web of Science databases. Pooled accuracy, sensitivity, and specificity were obtained by random-effect models. The diagnostic Precision Study Quality Assessment Tool (QUADAS-2) was used to assess the risk of bias.
Results
A total of 25 studies met the inclusion criteria and 8 of them were used in the meta-analysis. The pooled estimates of accuracy, specificity, and sensitivity for depression detection models were 0.87 (95% CI, 0.81-0.93), 0.85 (95% CI, 0.78-0.91), and 0.82 (95% CI, 0.71-0.94), respectively. When stratified by model structure, the highest pooled diagnostic accuracy was 0.89 (95% CI, 0.81-0.97) in the handcrafted group.
Discussion
To our knowledge, our study is the first meta-analysis on the diagnostic performance of DL for depression detection from speech samples. All studies included in the meta-analysis used convolutional neural network (CNN) models, posing problems in deciphering the performance of other DL algorithms. The handcrafted model performed better than the end-to-end model in speech depression detection.
Conclusions
The application of DL in speech provided a useful tool for depression detection. CNN models with handcrafted acoustic features could help to improve the diagnostic performance. Protocol registration The study protocol was registered on PROSPERO (CRD42023423603).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Population Health Sciences, School of Life Course and Population Sciences, Faculty of Life Sciences & Medicine, King's College London, London, SE1 1UL, United Kingdom.
- Department of Intelligent Medical Engineering, School of Biomedical Engineering, Anhui Medical University, Hefei, 230032, China.
- Department of Psychology, School of Mental Health and Psychological Sciences, Anhui Medical University, Hefei, 230032, China.
- Beth Israel Deaconess Medical Center, Harvard Medical School, Harvard University, Boston, MA, 02115, United States.
ORCID-Profile: Yanzhong Wang
Förderung
- King's College London-China Scholarship Council
- King’s College London—China Scholarship Council
Zitieren
APA
Liu, L., Liu, L., Wafa, H. A., Tydeman, F., Xie, W., & Wang, Y. (2024). Diagnostic accuracy of deep learning using speech samples in depression: a systematic review and meta-analysis. Journal of the American Medical Informatics Association, 31(10), 2394-2404. https://doi.org/10.1093/jamia/ocae189
Vancouver
Liu L, Liu L, Wafa HA, Tydeman F, Xie W, Wang Y. Diagnostic accuracy of deep learning using speech samples in depression: a systematic review and meta-analysis. Journal of the American Medical Informatics Association. 2024;31(10):2394-2404. doi:10.1093/jamia/ocae189
BibTeX
@article{Liu2024,
author = {Liu, Lidan and Liu, Lu and Wafa, Hatem A and Tydeman, Florence and Xie, Wanqing and Wang, Yanzhong},
title = {Diagnostic accuracy of deep learning using speech samples in depression: a systematic review and meta-analysis},
journal = {Journal of the American Medical Informatics Association},
year = {2024},
volume = {31},
number = {10},
pages = {2394--2404},
doi = {10.1093/jamia/ocae189}
}
EUVIMED