المؤلفون: Alexandra, König, Johannes, Tröger, Elisa, Mallick, Mario, Mina, Nicklas, Linz, Carole, Wagnon, Julia, Karbach, Caroline, Kuhn, Jessica, Peter

المصدر: BMC psychiatry. 22(1)

مصطلحات موضوعية: Adult, Male, Young Adult, Depressive Disorder, Major, Depression, Surveys and Questionnaires, Humans, Speech, Female, Longitudinal Studies

الوصف: Automated speech analysis has gained increasing attention to help diagnosing depression. Most previous studies, however, focused on comparing speech in patients with major depressive disorder to that in healthy volunteers. An alternative may be to associate speech with depressive symptoms in a non-clinical sample as this may help to find early and sensitive markers in those at risk of depression.We included n = 118 healthy young adults (mean age: 23.5 ± 3.7 years; 77% women) and asked them to talk about a positive and a negative event in their life. Then, we assessed the level of depressive symptoms with a self-report questionnaire, with scores ranging from 0-60. We transcribed speech data and extracted acoustic as well as linguistic features. Then, we tested whether individuals below or above the cut-off of clinically relevant depressive symptoms differed in speech features. Next, we predicted whether someone would be below or above that cut-off as well as the individual scores on the depression questionnaire. Since depression is associated with cognitive slowing or attentional deficits, we finally correlated depression scores with performance in the Trail Making Test.In our sample, n = 93 individuals scored below and n = 25 scored above cut-off for clinically relevant depressive symptoms. Most speech features did not differ significantly between both groups, but individuals above cut-off spoke more than those below that cut-off in the positive and the negative story. In addition, higher depression scores in that group were associated with slower completion time of the Trail Making Test. We were able to predict with 93% accuracy who would be below or above cut-off. In addition, we were able to predict the individual depression scores with low mean absolute error (3.90), with best performance achieved by a support vector machine.Our results indicate that even in a sample without a clinical diagnosis of depression, changes in speech relate to higher depression scores. This should be investigated in more detail in the future. In a longitudinal study, it may be tested whether speech features found in our study represent early and sensitive markers for subsequent depression in individuals at risk.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=pmid________::3e6ace8f78688c41e4856af38a2962ddTest
https://pubmed.ncbi.nlm.nih.gov/36575442Test

المؤلفون: Jan Alexandersson, Johannes Tröger, Jutta Kray, Philippe Robert, Alexandra König, Nicklas Linz, Jessica Peter

المساهمون: Deutsches Forschungszentrum für Künstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (DFKI), Cognition Behaviour Technology (CobTek), Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre Hospitalier Universitaire de Nice (CHU Nice)-Institut Claude Pompidou [Nice] (ICP - Nice), Spatio-Temporal Activity Recognition Systems (STARS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Psychiatric University Clinic [Bern] (UPD), Faculty of Medicine [Bern], University of Bern-University of Bern, Saarland University [Saarbrücken], This research was partially funded by the EIT Digital WellbeingActivity 17074, ELEMENT. The data was partially collected during theEU FP7 Dem@Care project, grant agreement 288199. The authors liketo thank Hali Lindsay and Katja Häuser for helpful feedback on anearlier version of the manuscript., Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre Hospitalier Universitaire de Nice (CHU Nice)-Institut Claude Pompidou [Nice] (ICP - Nice)-Université Côte d'Azur (UCA)

المصدر: Neuropsychologia
Neuropsychologia, Elsevier, 2019, 131, pp.53-61. ⟨10.1016/j.neuropsychologia.2019.05.007⟩
Neuropsychologia, 2019, 131, pp.53-61. ⟨10.1016/j.neuropsychologia.2019.05.007⟩

مصطلحات موضوعية: Male, Cognitive Neuroscience, Semantic analysis (machine learning), Experimental and Cognitive Psychology, Disease, Semantic speech analysis, Neuropsychological Tests, MCI (mild cognitive impairment), 050105 experimental psychology, Speech Disorders, 03 medical and health sciences, Behavioral Neuroscience, [SCCO]Cognitive science, 0302 clinical medicine, Qualitative analysis, Alzheimer Disease, medicine, Semantic memory, Dementia, Verbal fluency test, Humans, Speech, 0501 psychology and cognitive sciences, Control (linguistics), Aged, Aged, 80 and over, 05 social sciences, Alzheimer's disease, Temporal analysis, medicine.disease, Clinical Practice, Female, Psychology, 030217 neurology & neurosurgery, Cognitive psychology

الوصف: International audience; Contents lists available atScienceDirectNeuropsychologiajournal homepage:www.elsevier.com/locate/neuropsychologiaExploitation vs. exploration—computational temporal and semantic analysisexplains semantic verbalfluency impairment in Alzheimer's diseaseJohannes Trögera,∗, Nicklas Linza, Alexandra Königb, Philippe Robertb, Jan Alexanderssona,Jessica Peterc, Jutta KraydaGerman Research Center for Artificial Intelligence (DFKI), GermanybMemory Center, CoBTeK, IA CHU Université Côte d’Azur, FrancecUniversity Hospital of Old Age Psychiatry and Psychotherapy, University of Bern, SwitzerlanddChair for Development of Language, Learning & Action, University of Saarland, GermanyARTICLE INFOKeywords:Alzheimer's diseaseMCI (mild cognitive impairment)Semantic speech analysisTemporal analysisABSTRACTImpaired Semantic Verbal Fluency (SVF) in dementia due to Alzheimer's Disease (AD) and its precursor MildCognitive Impairment (MCI) is well known. Yet, it remains open whether this impairment mirrors the break-down of semantic memory retrieval processes or executive control processes. Therefore, qualitative analysis ofthe SVF has been proposed but is limited in terms of methodology and feasibility in clinical practice.Consequently, research draws no conclusive picture which of these afore-mentioned processes drives the SVFimpairment in AD and MCI. This study uses a qualitative computational approach—combining temporal andsemantic information—to investigate exploitation and exploration patterns as indicators for semantic memoryretrieval and executive control processes. Audio SVF recordings of 20 controls (C, 66–81 years), 55 MCI (57–94years) and 20 AD subjects (66–82 years) were assessed while groups were matched according to age and edu-cation. All groups produced, on average, the same amount of semantically related items in rapid successionwithin word clusters. Conversely, towards AD, there was a clear decline in semantic as well as temporal ex-ploration patterns between clusters. Results strongly point towards preserved exploitation—semantic memoryretrieval processes—and hampered exploration—executive control processes—in AD and potentially in MCI.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b94614d2fe916c6cf12bab8784723924Test

المؤلفون: Hali Lindsay, Philippe Robert, Nicklas Linz, Julia Elbaum, Kevin Riviere, Alexandre Derreumaux, Roxane Fabre, Alexandra König

المساهمون: Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria), Spatio-Temporal Activity Recognition Systems (STARS), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre Hospitalier Universitaire de Nice (CHU Nice), ki:elements [Saarbrücken], Deutsches Forschungszentrum für Künstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (DFKI), Cognition Behaviour Technology (CobTek), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre Hospitalier Universitaire de Nice (CHU Nice)-Institut Claude Pompidou [Nice] (ICP - Nice)-Université Côte d'Azur (UCA)

المصدر: Journal of Medical Internet Research, Vol 23, Iss 4, p e24191 (2021)
Journal of Medical Internet Research
Journal of Medical Internet Research, 2021, 23 (4), pp.e24191. ⟨10.2196/24191⟩
Journal of Medical Internet Research, JMIR Publications, 2021, 23 (4), pp.e24191. ⟨10.2196/24191⟩

مصطلحات موضوعية: Adult, Male, Health Personnel, speech, Computer applications to medicine. Medical informatics, 0206 medical engineering, R858-859.7, Pilot Projects, Health Informatics, 02 engineering and technology, Anxiety, Speech Acoustics, Voice analysis, phone monitoring, [SCCO]Cognitive science, 03 medical and health sciences, 0302 clinical medicine, Phone, Surveys and Questionnaires, Health care, medicine, Humans, Stress measures, Burnout, Professional, Pandemics, Original Paper, computer linguistics, SARS-CoV-2, business.industry, COVID-19, 020601 biomedical engineering, Telephone, 3. Good health, voice analysis, Female, Observational study, Public aspects of medicine, RA1-1270, medicine.symptom, business, Psychology, Psychosocial, 030217 neurology & neurosurgery, stress detection, Clinical psychology

الوصف: BackgroundDuring the COVID-19 pandemic, health professionals have been directly confronted with the suffering of patients and their families. By making them main actors in the management of this health crisis, they have been exposed to various psychosocial risks (stress, trauma, fatigue, etc). Paradoxically, stress-related symptoms are often underreported in this vulnerable population but are potentially detectable through passive monitoring of changes in speech behavior.ObjectiveThis study aims to investigate the use of rapid and remote measures of stress levels in health professionals working during the COVID-19 outbreak. This was done through the analysis of participants’ speech behavior during a short phone call conversation and, in particular, via positive, negative, and neutral storytelling tasks.MethodsSpeech samples from 89 health care professionals were collected over the phone during positive, negative, and neutral storytelling tasks; various voice features were extracted and compared with classical stress measures via standard questionnaires. Additionally, a regression analysis was performed.ResultsCertain speech characteristics correlated with stress levels in both genders; mainly, spectral (ie, formant) features, such as the mel-frequency cepstral coefficient, and prosodic characteristics, such as the fundamental frequency, appeared to be sensitive to stress. Overall, for both male and female participants, using vocal features from the positive tasks for regression yielded the most accurate prediction results of stress scores (mean absolute error 5.31).ConclusionsAutomatic speech analysis could help with early detection of subtle signs of stress in vulnerable populations over the phone. By combining the use of this technology with timely intervention strategies, it could contribute to the prevention of burnout and the development of comorbidities, such as depression or anxiety.

الوصول الحر: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2dca6c3a053b0e42769a679c9562ebeTest
https://doi.org/10.2196/24191Test