Anas Belouali1, Samir Gupta2, Vaibhav Sourirajan2, Jiawei Yu2, Nathaniel Allen3, Adil Alaoui2, Mary Ann Dutton4, Matthew J Reinhard3,4. 1. Innovation Center for Biomedical Informatics, Georgetown University Medical Center, Washington, DC, USA. ab873@georgetown.edu. 2. Innovation Center for Biomedical Informatics, Georgetown University Medical Center, Washington, DC, USA. 3. War Related Illness and Injury Study Center, Veterans Affairs Medical Center, Washington, DC, USA. 4. Department of Psychiatry, Georgetown University Medical Center, Washington, DC, USA.
Abstract
BACKGROUND: Screening for suicidal ideation in high-risk groups such as U.S. veterans is crucial for early detection and suicide prevention. Currently, screening is based on clinical interviews or self-report measures. Both approaches rely on subjects to disclose their suicidal thoughts. Innovative approaches are necessary to develop objective and clinically applicable assessments. Speech has been investigated as an objective marker to understand various mental states including suicidal ideation. In this work, we developed a machine learning and natural language processing classifier based on speech markers to screen for suicidal ideation in US veterans. METHODOLOGY: Veterans submitted 588 narrative audio recordings via a mobile app in a real-life setting. In addition, participants completed self-report psychiatric scales and questionnaires. Recordings were analyzed to extract voice characteristics including prosodic, phonation, and glottal. The audios were also transcribed to extract textual features for linguistic analysis. We evaluated the acoustic and linguistic features using both statistical significance and ensemble feature selection. We also examined the performance of different machine learning algorithms on multiple combinations of features to classify suicidal and non-suicidal audios. RESULTS: A combined set of 15 acoustic and linguistic features of speech were identified by the ensemble feature selection. Random Forest classifier, using the selected set of features, correctly identified suicidal ideation in veterans with 86% sensitivity, 70% specificity, and an area under the receiver operating characteristic curve (AUC) of 80%. CONCLUSIONS: Speech analysis of audios collected from veterans in everyday life settings using smartphones offers a promising approach for suicidal ideation detection. A machine learning classifier may eventually help clinicians identify and monitor high-risk veterans.
BACKGROUND: Screening for suicidal ideation in high-risk groups such as U.S. veterans is crucial for early detection and suicide prevention. Currently, screening is based on clinical interviews or self-report measures. Both approaches rely on subjects to disclose their suicidal thoughts. Innovative approaches are necessary to develop objective and clinically applicable assessments. Speech has been investigated as an objective marker to understand various mental states including suicidal ideation. In this work, we developed a machine learning and natural language processing classifier based on speech markers to screen for suicidal ideation in US veterans. METHODOLOGY: Veterans submitted 588 narrative audio recordings via a mobile app in a real-life setting. In addition, participants completed self-report psychiatric scales and questionnaires. Recordings were analyzed to extract voice characteristics including prosodic, phonation, and glottal. The audios were also transcribed to extract textual features for linguistic analysis. We evaluated the acoustic and linguistic features using both statistical significance and ensemble feature selection. We also examined the performance of different machine learning algorithms on multiple combinations of features to classify suicidal and non-suicidal audios. RESULTS: A combined set of 15 acoustic and linguistic features of speech were identified by the ensemble feature selection. Random Forest classifier, using the selected set of features, correctly identified suicidal ideation in veterans with 86% sensitivity, 70% specificity, and an area under the receiver operating characteristic curve (AUC) of 80%. CONCLUSIONS: Speech analysis of audios collected from veterans in everyday life settings using smartphones offers a promising approach for suicidal ideation detection. A machine learning classifier may eventually help clinicians identify and monitor high-risk veterans.
Authors: John P Pestian; Jacqueline Grupp-Phelan; Kevin Bretonnel Cohen; Gabriel Meyers; Linda A Richey; Pawel Matykiewicz; Michael T Sorter Journal: Suicide Life Threat Behav Date: 2015-08-07
Authors: John P Pestian; Michael Sorter; Brian Connolly; Kevin Bretonnel Cohen; Cheryl McCullumsmith; Jeffry T Gee; Louis-Philippe Morency; Stefan Scherer; Lesley Rohlfs Journal: Suicide Life Threat Behav Date: 2016-11-03
Authors: Charles R Marmar; Adam D Brown; Meng Qian; Eugene Laska; Carole Siegel; Meng Li; Duna Abu-Amara; Andreas Tsiartas; Colleen Richey; Jennifer Smith; Bruce Knoth; Dimitra Vergyri Journal: Depress Anxiety Date: 2019-04-22 Impact factor: 6.505
Authors: Pratik Shah; Francis Kendall; Sean Khozin; Ryan Goosen; Jianying Hu; Jason Laramie; Michael Ringel; Nicholas Schork Journal: NPJ Digit Med Date: 2019-07-26
Authors: Joshua Cohen; Jennifer Wright-Berryman; Lesley Rohlfs; Douglas Trocinski; LaMonica Daniel; Thomas W Klatt Journal: Front Digit Health Date: 2022-02-02