Affiliations: [a] CoBTeK (Cognition-Behaviour-Technology) Lab, Memory Center CHU, Université Côte d’Azur, Nice, France
| [b] INRIA Stars Team, Sophia Antipolis, Valbonne, France
| [c]
German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany
Correspondence:
[*]
Correspondence to: Dr. Alexandra König, CoBTeK (Cognition, Behaviour, Technology) Lab Université Cøote d’Azur, France; Centre Mémoire de Ressources et de Recherche, CHU de Nice, Institut Claude Pompidou, 10 rue Molière 06100, Nice, France. Tel.: +33 (0) 492 034 760; Fax: +33 (0) 4 93 52 92 57; E-mail: [email protected].
Abstract: Background:Apathy is present in several psychiatric and neurological conditions and has been found to have a severe negative effect on disease progression. In older people, it can be a predictor of increased dementia risk. Current assessment methods lack objectivity and sensitivity, thus new diagnostic tools and broad-scale screening technologies are needed. Objective:This study is the first of its kind aiming to investigate whether automatic speech analysis could be used for characterization and detection of apathy. Methods:A group of apathetic and non-apathetic patients (n = 60) with mild to moderate neurocognitive disorder were recorded while performing two short narrative speech tasks. Paralinguistic markers relating to prosodic, formant, source, and temporal qualities of speech were automatically extracted, examined between the groups and compared to baseline assessments. Machine learning experiments were carried out to validate the diagnostic power of extracted markers. Results:Correlations between apathy sub-scales and features revealed a relation between temporal aspects of speech and the subdomains of reduction in interest and initiative, as well as between prosody features and the affective domain. Group differences were found to vary for males and females, depending on the task. Differences in temporal aspects of speech were found to be the most consistent difference between apathetic and non-apathetic patients. Machine learning models trained on speech features achieved top performances of AUC = 0.88 for males and AUC = 0.77 for females. Conclusions:These findings reinforce the usability of speech as a reliable biomarker in the detection and assessment of apathy.
