Vocal pattern detection of depression among older adults

Depression is a serious problem for many older adults but is too often undetected by the person, family or providers. Although vocal patterns have been successfully used to detect and predict depression in adults aged 18 to 65 years, no studies to date have included older adults. The study purpose w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of mental health nursing 2020-06, Vol.29 (3), p.440-449
Hauptverfasser: Smith, Marianne, Dietrich, Bryce Jensen, Bai, Er‐wei, Bockholt, Henry Jeremy
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Depression is a serious problem for many older adults but is too often undetected by the person, family or providers. Although vocal patterns have been successfully used to detect and predict depression in adults aged 18 to 65 years, no studies to date have included older adults. The study purpose was to determine whether vocal patterns associated with clinical depression in younger people also signify depression in older adults. An observational, repeated measures design was used to enroll 46 volunteer older adults who completed a semi‐structured interview composed the 9‐item Patient Health Questionnaire or PHQ‐9 depression scale and selected speech measures. Recorded interviews were analysed by machine learning algorithms to evaluate whether vocal patterns may predict presence of depression in older adults. In this study, using the PHQ‐9 and a supervised machine learning algorithm accurately predicted high and low depression scores between 86% and 92% of the time. Change in raw PHQ‐9 scores between interview cycles was predicted within 1.17 points. These results provide strong and promising evidence that vocal patterns can be used effectively to detect clinical depression in adults who are 65 years and older.
ISSN:1445-8330
1447-0349
DOI:10.1111/inm.12678