1
|
Li S, Nair R, Naqvi SM. Acoustic and Text Features Analysis for Adult ADHD Screening: A Data-Driven Approach Utilizing DIVA Interview. IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE 2024; 12:359-370. [PMID: 38606391 PMCID: PMC11008805 DOI: 10.1109/jtehm.2024.3369764] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/18/2023] [Revised: 01/09/2024] [Accepted: 02/15/2024] [Indexed: 04/13/2024]
Abstract
Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder commonly seen in childhood that leads to behavioural changes in social development and communication patterns, often continues into undiagnosed adulthood due to a global shortage of psychiatrists, resulting in delayed diagnoses with lasting consequences on individual's well-being and the societal impact. Recently, machine learning methodologies have been incorporated into healthcare systems to facilitate the diagnosis and enhance the potential prediction of treatment outcomes for mental health conditions. In ADHD detection, the previous research focused on utilizing functional magnetic resonance imaging (fMRI) or Electroencephalography (EEG) signals, which require costly equipment and trained personnel for data collection. In recent years, speech and text modalities have garnered increasing attention due to their cost-effectiveness and non-wearable sensing in data collection. In this research, conducted in collaboration with the Cumbria, Northumberland, Tyne and Wear NHS Foundation Trust, we gathered audio data from both ADHD patients and normal controls based on the clinically popular Diagnostic Interview for ADHD in adults (DIVA). Subsequently, we transformed the speech data into text modalities through the utilization of the Google Cloud Speech API. We extracted both acoustic and text features from the data, encompassing traditional acoustic features (e.g., MFCC), specialized feature sets (e.g., eGeMAPS), as well as deep-learned linguistic and semantic features derived from pre-trained deep learning models. These features are employed in conjunction with a support vector machine for ADHD classification, yielding promising outcomes in the utilization of audio and text data for effective adult ADHD screening. Clinical impact: This research introduces a transformative approach in ADHD diagnosis, employing speech and text analysis to facilitate early and more accessible detection, particularly beneficial in areas with limited psychiatric resources. Clinical and Translational Impact Statement: The successful application of machine learning techniques in analyzing audio and text data for ADHD screening represents a significant advancement in mental health diagnostics, paving the way for its integration into clinical settings and potentially improving patient outcomes on a broader scale.
Collapse
Affiliation(s)
- Shuanglin Li
- Intelligent Sensing and Communications Group, School of EngineeringNewcastle UniversityNE1 7RUNewcastle Upon TyneU.K
| | - Rajesh Nair
- Adult ADHD Services, Cumbria, Northumberland, Tyne and Wear NHS Foundation TrustNE3 3XTNewcastle Upon TyneU.K
| | - Syed Mohsen Naqvi
- Intelligent Sensing and Communications Group, School of EngineeringNewcastle UniversityNE1 7RUNewcastle Upon TyneU.K
| |
Collapse
|
2
|
Olah J, Spencer T, Cummins N, Diederen K. Automated analysis of speech as a marker of sub-clinical psychotic experiences. Front Psychiatry 2024; 14:1265880. [PMID: 38361830 PMCID: PMC10867252 DOI: 10.3389/fpsyt.2023.1265880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Accepted: 12/22/2023] [Indexed: 02/17/2024] Open
Abstract
Automated speech analysis techniques, when combined with artificial intelligence and machine learning, show potential in capturing and predicting a wide range of psychosis symptoms, garnering attention from researchers. These techniques hold promise in predicting the transition to clinical psychosis from at-risk states, as well as relapse or treatment response in individuals with clinical-level psychosis. However, challenges in scientific validation hinder the translation of these techniques into practical applications. Although sub-clinical research could aid to tackle most of these challenges, there have been only few studies conducted in speech and psychosis research in non-clinical populations. This work aims to facilitate this work by summarizing automated speech analytical concepts and the intersection of this field with psychosis research. We review psychosis continuum and sub-clinical psychotic experiences, and the benefits of researching them. Then, we discuss the connection between speech and psychotic symptoms. Thirdly, we overview current and state-of-the art approaches to the automated analysis of speech both in terms of language use (text-based analysis) and vocal features (audio-based analysis). Then, we review techniques applied in subclinical population and findings in these samples. Finally, we discuss research challenges in the field, recommend future research endeavors and outline how research in subclinical populations can tackle the listed challenges.
Collapse
Affiliation(s)
- Julianna Olah
- Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom
| | - Thomas Spencer
- Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom
| | - Nicholas Cummins
- Department of Biostatistics & Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom
| | - Kelly Diederen
- Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United Kingdom
| |
Collapse
|
3
|
Lucarini V, Alouit A, Yeh D, Le Coq J, Savatte R, Charre M, Louveau C, Houamri MB, Penaud S, Gaston-Bellegarde A, Rio S, Drouet L, Elbaz M, Becchio J, Pourchet S, Pruvost-Robieux E, Marchi A, Moyal M, Lefebvre A, Chaumette B, Grice M, Lindberg PG, Dupin L, Piolino P, Lemogne C, Léger D, Gavaret M, Krebs MO, Iftimovici A. Neurophysiological explorations across the spectrum of psychosis, autism, and depression, during wakefulness and sleep: protocol of a prospective case-control transdiagnostic multimodal study (DEMETER). BMC Psychiatry 2023; 23:860. [PMID: 37990173 PMCID: PMC10662684 DOI: 10.1186/s12888-023-05347-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Accepted: 11/03/2023] [Indexed: 11/23/2023] Open
Abstract
BACKGROUND Quantitative electroencephalography (EEG) analysis offers the opportunity to study high-level cognitive processes across psychiatric disorders. In particular, EEG microstates translate the temporal dynamics of neuronal networks throughout the brain. Their alteration may reflect transdiagnostic anomalies in neurophysiological functions that are impaired in mood, psychosis, and autism spectrum disorders, such as sensorimotor integration, speech, sleep, and sense of self. The main questions this study aims to answer are as follows: 1) Are EEG microstate anomalies associated with clinical and functional prognosis, both in resting conditions and during sleep, across psychiatric disorders? 2) Are EEG microstate anomalies associated with differences in sensorimotor integration, speech, sense of self, and sleep? 3) Can the dynamic of EEG microstates be modulated by a non-drug intervention such as light hypnosis? METHODS This prospective cohort will include a population of adolescents and young adults, aged 15 to 30 years old, with ultra-high-risk of psychosis (UHR), first-episode psychosis (FEP), schizophrenia (SCZ), autism spectrum disorder (ASD), and major depressive disorder (MDD), as well as healthy controls (CTRL) (N = 21 × 6), who will be assessed at baseline and after one year of follow-up. Participants will undergo deep phenotyping based on psychopathology, neuropsychological assessments, 64-channel EEG recordings, and biological sampling at the two timepoints. At baseline, the EEG recording will also be coupled to a sensorimotor task and a recording of the characteristics of their speech (prosody and turn-taking), a one-night polysomnography, a self-reference effect task in virtual reality (only in UHR, FEP, and CTRL). An interventional ancillary study will involve only healthy controls, in order to assess whether light hypnosis can modify the EEG microstate architecture in a direction opposite to what is seen in disease. DISCUSSION This transdiagnostic longitudinal case-control study will provide a multimodal neurophysiological assessment of clinical dimensions (sensorimotor integration, speech, sleep, and sense of self) that are disrupted across mood, psychosis, and autism spectrum disorders. It will further test the relevance of EEG microstates as dimensional functional biomarkers. TRIAL REGISTRATION ClinicalTrials.gov Identifier NCT06045897.
Collapse
Affiliation(s)
- Valeria Lucarini
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Pathophysiology of psychiatric disorders", GDR 3557-Institut de Psychiatrie, 102-108 Rue de la Santé, Paris, 75014, France
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Anaëlle Alouit
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Stroke: from prognostic determinants and translational research to personalized interventions", Paris, 75014, France
| | - Delphine Yeh
- Laboratoire Mémoire, Cerveau et Cognition, UR7536, Université Paris Cité, Boulogne-Billancourt, F-92100, France
| | - Jeanne Le Coq
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Romane Savatte
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Mylène Charre
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Cécile Louveau
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Meryem Benlaifa Houamri
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Sylvain Penaud
- Laboratoire Mémoire, Cerveau et Cognition, UR7536, Université Paris Cité, Boulogne-Billancourt, F-92100, France
| | - Alexandre Gaston-Bellegarde
- Laboratoire Mémoire, Cerveau et Cognition, UR7536, Université Paris Cité, Boulogne-Billancourt, F-92100, France
| | - Stéphane Rio
- Centre du Sommeil et de la Vigilance, AP-HP, Hôtel-Dieu, Paris, France
| | - Laurent Drouet
- Centre du Sommeil et de la Vigilance, AP-HP, Hôtel-Dieu, Paris, France
| | - Maxime Elbaz
- Centre du Sommeil et de la Vigilance, AP-HP, Hôtel-Dieu, Paris, France
| | - Jean Becchio
- Collège International de Thérapies d'orientation de l'Attention et de la Conscience (CITAC), Paris, France
| | - Sylvain Pourchet
- Collège International de Thérapies d'orientation de l'Attention et de la Conscience (CITAC), Paris, France
| | - Estelle Pruvost-Robieux
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Stroke: from prognostic determinants and translational research to personalized interventions", Paris, 75014, France
- Service de Neurophysiologie Clinique, GHU Paris Psychiatrie et Neurosciences, Paris, France
| | - Angela Marchi
- Epileptology and Cerebral Rhythmology, APHM, Timone Hospital, Marseille, France
| | - Mylène Moyal
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Pathophysiology of psychiatric disorders", GDR 3557-Institut de Psychiatrie, 102-108 Rue de la Santé, Paris, 75014, France
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Aline Lefebvre
- Department of Child and Adolescent Psychiatry, Fondation Vallee, UNIACT Neurospin CEA - INSERM UMR 1129, Universite Paris Saclay, Gentilly, France
| | - Boris Chaumette
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Pathophysiology of psychiatric disorders", GDR 3557-Institut de Psychiatrie, 102-108 Rue de la Santé, Paris, 75014, France
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Martine Grice
- IfL-Phonetics, University of Cologne, Cologne, Germany
| | - Påvel G Lindberg
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Stroke: from prognostic determinants and translational research to personalized interventions", Paris, 75014, France
| | - Lucile Dupin
- INCC UMR 8002, CNRS, Université Paris Cité, Paris, F-75006, France
| | - Pascale Piolino
- Laboratoire Mémoire, Cerveau et Cognition, UR7536, Université Paris Cité, Boulogne-Billancourt, F-92100, France
| | - Cédric Lemogne
- Inserm, INRAE, Center for Research in Epidemiology and StatisticS (CRESS), Service de Psychiatrie de l'adulte, AP-HP, Hôpital Hôtel-Dieu, Université Paris Cité and Université Sorbonne Paris Nord, Paris, France
| | - Damien Léger
- Centre du Sommeil et de la Vigilance, AP-HP, Hôtel-Dieu, Paris, France
- VIFASOM, ERC 7330, Université Paris Cité, Paris, France
| | - Martine Gavaret
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Stroke: from prognostic determinants and translational research to personalized interventions", Paris, 75014, France
- Service de Neurophysiologie Clinique, GHU Paris Psychiatrie et Neurosciences, Paris, France
| | - Marie-Odile Krebs
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Pathophysiology of psychiatric disorders", GDR 3557-Institut de Psychiatrie, 102-108 Rue de la Santé, Paris, 75014, France
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France
| | - Anton Iftimovici
- Université Paris Cité, Institute of Psychiatry and Neuroscience of Paris (IPNP), INSERM U1266, Team "Pathophysiology of psychiatric disorders", GDR 3557-Institut de Psychiatrie, 102-108 Rue de la Santé, Paris, 75014, France.
- GHU Paris Psychiatrie et Neurosciences, Pôle Hospitalo-Universitaire d'évaluation, Prévention, et Innovation Thérapeutique (PEPIT), Paris, France.
| |
Collapse
|
4
|
Duey AH, Rana A, Siddi F, Hussein H, Onnela JP, Smith TR. Daily Pain Prediction Using Smartphone Speech Recordings of Patients With Spine Disease. Neurosurgery 2023; 93:670-677. [PMID: 36995101 DOI: 10.1227/neu.0000000000002474] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2022] [Accepted: 02/02/2023] [Indexed: 03/31/2023] Open
Abstract
BACKGROUND Pain evaluation remains largely subjective in neurosurgical practice, but machine learning provides the potential for objective pain assessment tools. OBJECTIVE To predict daily pain levels using speech recordings from personal smartphones of a cohort of patients with diagnosed neurological spine disease. METHODS Patients with spine disease were enrolled through a general neurosurgical clinic with approval from the institutional ethics committee. At-home pain surveys and speech recordings were administered at regular intervals through the Beiwe smartphone application. Praat audio features were extracted from the speech recordings to be used as input to a K-nearest neighbors (KNN) machine learning model. The pain scores were transformed from a 0 to 10 scale to low and high pain for better discriminative capacity. RESULTS A total of 60 patients were enrolled, and 384 observations were used to train and test the prediction model. Using the KNN prediction model, an accuracy of 71% with a positive predictive value of 0.71 was achieved in classifying pain intensity into high and low. The model showed 0.71 precision for high pain and 0.70 precision for low pain. Recall of high pain was 0.74, and recall of low pain was 0.67. The overall F1 score was 0.73. CONCLUSION Our study uses a KNN to model the relationship between speech features and pain levels collected from personal smartphones of patients with spine disease. The proposed model is a stepping stone for the development of objective pain assessment in neurosurgery clinical practice.
Collapse
Affiliation(s)
- Akiro H Duey
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Icahn School of Medicine at Mount Sinai, New York , New York , USA
| | - Aakanksha Rana
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge , Massachusetts , USA
| | - Francesca Siddi
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Departments of Neurosurgery, Leiden University Medical Center, Leiden , The Netherlands
| | - Helweh Hussein
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
| | - Jukka-Pekka Onnela
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston , Massachusetts , USA
| | - Timothy R Smith
- Department of Neurosurgery, Computational Neuroscience Outcomes Center, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston , Massachusetts , USA
| |
Collapse
|
5
|
Parola A, Simonsen A, Lin JM, Zhou Y, Wang H, Ubukata S, Koelkebeck K, Bliksted V, Fusaroli R. Voice Patterns as Markers of Schizophrenia: Building a Cumulative Generalizable Approach Via a Cross-Linguistic and Meta-analysis Based Investigation. Schizophr Bull 2023; 49:S125-S141. [PMID: 36946527 PMCID: PMC10031745 DOI: 10.1093/schbul/sbac128] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/23/2023]
Abstract
BACKGROUND AND HYPOTHESIS Voice atypicalities are potential markers of clinical features of schizophrenia (eg, negative symptoms). A recent meta-analysis identified an acoustic profile associated with schizophrenia (reduced pitch variability and increased pauses), but also highlighted shortcomings in the field: small sample sizes, little attention to the heterogeneity of the disorder, and to generalizing findings to diverse samples and languages. STUDY DESIGN We provide a critical cumulative approach to vocal atypicalities in schizophrenia, where we conceptually and statistically build on previous studies. We aim at identifying a cross-linguistically reliable acoustic profile of schizophrenia and assessing sources of heterogeneity (symptomatology, pharmacotherapy, clinical and social characteristics). We relied on previous meta-analysis to build and analyze a large cross-linguistic dataset of audio recordings of 231 patients with schizophrenia and 238 matched controls (>4000 recordings in Danish, German, Mandarin and Japanese). We used multilevel Bayesian modeling, contrasting meta-analytically informed and skeptical inferences. STUDY RESULTS We found only a minimal generalizable acoustic profile of schizophrenia (reduced pitch variability), while duration atypicalities replicated only in some languages. We identified reliable associations between acoustic profile and individual differences in clinical ratings of negative symptoms, medication, age and gender. However, these associations vary across languages. CONCLUSIONS The findings indicate that a strong cross-linguistically reliable acoustic profile of schizophrenia is unlikely. Rather, if we are to devise effective clinical applications able to target different ranges of patients, we need first to establish larger and more diverse cross-linguistic datasets, focus on individual differences, and build self-critical cumulative approaches.
Collapse
Affiliation(s)
- Alberto Parola
- Department of Linguistics, Cognitive Science and Semiotics, Aarhus University, Aarhus, Denmark
- The Interacting Minds Center, Institute of Culture and Society, Aarhus University, Aarhus, Denmark
- Department of Psychology, University of Turin, Turin, Italy
| | - Arndis Simonsen
- The Interacting Minds Center, Institute of Culture and Society, Aarhus University, Aarhus, Denmark
- Psychosis Research Unit, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
| | - Jessica Mary Lin
- Department of Linguistics, Cognitive Science and Semiotics, Aarhus University, Aarhus, Denmark
- The Interacting Minds Center, Institute of Culture and Society, Aarhus University, Aarhus, Denmark
| | - Yuan Zhou
- Institute of Psychology, Chinese Academy of Sciences, Beijing, China
| | - Huiling Wang
- Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan, China
| | - Shiho Ubukata
- Department of Psychiatry, Kyoto University, Kyoto, Japan
| | - Katja Koelkebeck
- LVR-Hospital Essen, Department of Psychiatry and Psychotherapy, Hospital and Institute of the University of Duisburg-Essen, Essen, Germany
- Center for Translational Neuro- and Behavioral Sciences (C-TNBS), University Duisburg-Essen, Germany
| | - Vibeke Bliksted
- The Interacting Minds Center, Institute of Culture and Society, Aarhus University, Aarhus, Denmark
- Psychosis Research Unit, Department of Clinical Medicine, Aarhus University, Aarhus, Denmark
| | - Riccardo Fusaroli
- Department of Linguistics, Cognitive Science and Semiotics, Aarhus University, Aarhus, Denmark
- The Interacting Minds Center, Institute of Culture and Society, Aarhus University, Aarhus, Denmark
- Linguistic Data Consortium, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
6
|
Tang SX, Hänsel K, Cong Y, Nikzad AH, Mehta A, Cho S, Berretta S, Behbehani L, Pradhan S, John M, Liberman MY. Latent Factors of Language Disturbance and Relationships to Quantitative Speech Features. Schizophr Bull 2023; 49:S93-S103. [PMID: 36946530 PMCID: PMC10031730 DOI: 10.1093/schbul/sbac145] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/23/2023]
Abstract
BACKGROUND AND HYPOTHESIS Quantitative acoustic and textual measures derived from speech ("speech features") may provide valuable biomarkers for psychiatric disorders, particularly schizophrenia spectrum disorders (SSD). We sought to identify cross-diagnostic latent factors for speech disturbance with relevance for SSD and computational modeling. STUDY DESIGN Clinical ratings for speech disturbance were generated across 14 items for a cross-diagnostic sample (N = 334), including SSD (n = 90). Speech features were quantified using an automated pipeline for brief recorded samples of free speech. Factor models for the clinical ratings were generated using exploratory factor analysis, then tested with confirmatory factor analysis in the cross-diagnostic and SSD groups. The relationships between factor scores and computational speech features were examined for 202 of the participants. STUDY RESULTS We found a 3-factor model with a good fit in the cross-diagnostic group and an acceptable fit for the SSD subsample. The model identifies an impaired expressivity factor and 2 interrelated disorganized factors for inefficient and incoherent speech. Incoherent speech was specific to psychosis groups, while inefficient speech and impaired expressivity showed intermediate effects in people with nonpsychotic disorders. Each of the 3 factors had significant and distinct relationships with speech features, which differed for the cross-diagnostic vs SSD groups. CONCLUSIONS We report a cross-diagnostic 3-factor model for speech disturbance which is supported by good statistical measures, intuitive, applicable to SSD, and relatable to linguistic theories. It provides a valuable framework for understanding speech disturbance and appropriate targets for modeling with quantitative speech features.
Collapse
Affiliation(s)
- Sunny X Tang
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Katrin Hänsel
- Department of Laboratory Medicine, Yale University, New Haven, USA
| | - Yan Cong
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Amir H Nikzad
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Aarush Mehta
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Sunghye Cho
- Linguistic Data Consortium, University of Pennsylvania, Philadelphia, USA
| | - Sarah Berretta
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Leily Behbehani
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Sameer Pradhan
- Linguistic Data Consortium, University of Pennsylvania, Philadelphia, USA
| | - Majnu John
- Institute of Behavioral Science, Feinstein Institutes for Medical Research, Glen Oaks, USA
| | - Mark Y Liberman
- Linguistic Data Consortium, University of Pennsylvania, Philadelphia, USA
| |
Collapse
|
7
|
Ferrara M, Franchini G, Funaro M, Cutroni M, Valier B, Toffanin T, Palagini L, Zerbinati L, Folesani F, Murri MB, Caruso R, Grassi L. Machine Learning and Non-Affective Psychosis: Identification, Differential Diagnosis, and Treatment. Curr Psychiatry Rep 2022; 24:925-936. [PMID: 36399236 PMCID: PMC9780131 DOI: 10.1007/s11920-022-01399-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 10/12/2022] [Indexed: 11/19/2022]
Abstract
PURPOSE OF REVIEW This review will cover the most relevant findings on the use of machine learning (ML) techniques in the field of non-affective psychosis, by summarizing the studies published in the last three years focusing on illness detection and treatment. RECENT FINDINGS Multiple ML tools that include mostly supervised approaches such as support vector machine, gradient boosting, and random forest showed promising results by applying these algorithms to various sources of data: socio-demographic information, EEG, language, digital content, blood biomarkers, neuroimaging, and electronic health records. However, the overall performance, in the binary classification case, varied from 0.49, which is to be considered very low (i.e., noise), to over 0.90. These results are fully justified by different factors, some of which may be attributable to the preprocessing of the data, the wide variety of the data, and the a-priori setting of hyperparameters. One of the main limitations of the field is the lack of stratification of results based on biological sex, given that psychosis presents differently in men and women; hence, the necessity to tailor identification tools and data analytic strategies. Timely identification and appropriate treatment are key factors in reducing the consequences of psychotic disorders. In recent years, the emergence of new analytical tools based on artificial intelligence such as supervised ML approaches showed promises as a potential breakthrough in this field. However, ML applications in everyday practice are still in its infancy.
Collapse
Affiliation(s)
- Maria Ferrara
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy.
- Department of Psychiatry, Yale School of Medicine, 34 Park Street, New Haven, CT, USA.
| | - Giorgia Franchini
- Department of Physics, Informatics and Mathematics, University of Modena and Reggio Emilia, Via Campi 213/B, Modena, Italy
- Department of Mathematics and Computer Science, University of Ferrara, Via Macchiavelli 33, Ferrara, Italy
| | - Melissa Funaro
- Harvey Cushing/John Hay Whitney Medical Library, Yale University, 333 Cedar St., New Haven, CT, USA
| | - Marcello Cutroni
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Beatrice Valier
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Tommaso Toffanin
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Laura Palagini
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Luigi Zerbinati
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Federica Folesani
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Martino Belvederi Murri
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Rosangela Caruso
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| | - Luigi Grassi
- Department of Neuroscience and Rehabilitation, Institute of Psychiatry, University of Ferrara, via Fossato di Mortara 64/A, Ferrara, Italy
| |
Collapse
|