1
|
Sun J, Dong QX, Wang SW, Zheng YB, Liu XX, Lu TS, Yuan K, Shi J, Hu B, Lu L, Han Y. Artificial intelligence in psychiatry research, diagnosis, and therapy. Asian J Psychiatr 2023; 87:103705. [PMID: 37506575 DOI: 10.1016/j.ajp.2023.103705] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 07/16/2023] [Accepted: 07/20/2023] [Indexed: 07/30/2023]
Abstract
Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.
Collapse
Affiliation(s)
- Jie Sun
- Pain Medicine Center, Peking University Third Hospital, Beijing 100191, China; Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China
| | - Qun-Xi Dong
- School of Medical Technology, Beijing Institute of Technology, Beijing 100081, China
| | - San-Wang Wang
- Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China; Department of Psychiatry, Renmin Hospital of Wuhan University, Wuhan 430060, China
| | - Yong-Bo Zheng
- Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China; Peking-Tsinghua Center for Life Sciences and PKU-IDG/McGovern Institute for Brain Research, Peking University, Beijing 100871, China
| | - Xiao-Xing Liu
- Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China
| | - Tang-Sheng Lu
- National Institute on Drug Dependence and Beijing Key Laboratory of Drug Dependence Research, Peking University, Beijing 100191, China
| | - Kai Yuan
- Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China
| | - Jie Shi
- National Institute on Drug Dependence and Beijing Key Laboratory of Drug Dependence Research, Peking University, Beijing 100191, China
| | - Bin Hu
- School of Medical Technology, Beijing Institute of Technology, Beijing 100081, China.
| | - Lin Lu
- Peking University Sixth Hospital, Peking University Institute of Mental Health, NHC Key Laboratory of Mental Health (Peking University), National Clinical Research Center for Mental Disorders (Peking University Sixth Hospital), Beijing 100191, China; Peking-Tsinghua Center for Life Sciences and PKU-IDG/McGovern Institute for Brain Research, Peking University, Beijing 100871, China.
| | - Ying Han
- National Institute on Drug Dependence and Beijing Key Laboratory of Drug Dependence Research, Peking University, Beijing 100191, China.
| |
Collapse
|
2
|
Swann Z, Daliri A, Honeycutt CF. Impact of Startling Acoustic Stimuli on Word Repetition in Individuals With Aphasia and Apraxia of Speech Following Stroke. JOURNAL OF SPEECH, LANGUAGE, AND HEARING RESEARCH : JSLHR 2022; 65:1671-1685. [PMID: 35377739 DOI: 10.1044/2022_jslhr-21-00486] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
PURPOSE The StartReact effect, whereby movements are elicited by loud, startling acoustic stimuli (SAS), allows the evaluation of movements when initiated through involuntary circuitry, before auditory feedback. When StartReact is applied during poststroke upper extremity movements, individuals exhibit increased muscle recruitment, reaction times, and reaching distances. StartReact releases unimpaired speech with similar increases in muscle recruitment and reaction time. However, as poststroke communication disorders have divergent neural circuitry from upper extremity tasks, it is unclear if StartReact will enhance speech poststroke. Our objective is to determine if (a) StartReact is present in individuals with poststroke aphasia and apraxia and (b) SAS exposure enhances speech intelligibility. METHOD We remotely delivered startling, 105-dB white noise bursts (SAS) and quiet, non-SAS cues to 15 individuals with poststroke aphasia and apraxia during repetition of six words. We evaluated average word intensity, pitch, pitch trajectories, vowel formants F1 and F2 (first and second formants), phonemic error rate, and percent incidence of each SAS versus non-SAS-elicited phoneme produced under each cue type. RESULTS For SAS trials compared to non-SAS, speech intensity increased (∆ + 0.6 dB), speech pitch increased (∆ + 22.7 Hz), and formants (F1 and F2) changed, resulting in a smaller vowel space after SAS. SAS affected pitch trajectories for some, but not all, words. Non-SAS trials had more stops (∆ + 4.7 utterances) while SAS trials had more sustained phonemes (fricatives, glides, affricates, liquids; ∆ + 5.4 utterances). SAS trials had fewer distortion errors but no change in substitution errors or overall error rate compared to non-SAS trials. CONCLUSIONS We show that stroke-impaired speech is susceptible to StartReact, evidenced by decreased intelligibility due to altered formants, pitch trajectories, and articulation, including increased incidence of sounds that could not be produced without SAS. Future studies should examine the impact of SAS on voluntary speech intelligibility and clinical measures of aphasia and apraxia.
Collapse
Affiliation(s)
- Zoe Swann
- School of Life Sciences, Arizona State University, Tempe
| | - Ayoub Daliri
- College of Health Solutions, Arizona State University, Tempe
| | - Claire F Honeycutt
- School of Biological and Health Science Engineering, Arizona State University, Tempe
| |
Collapse
|
3
|
Ćosić K, Popović S, Šarlija M, Kesedžić I, Gambiraža M, Dropuljić B, Mijić I, Henigsberg N, Jovanovic T. AI-Based Prediction and Prevention of Psychological and Behavioral Changes in Ex-COVID-19 Patients. Front Psychol 2021; 12:782866. [PMID: 35027902 PMCID: PMC8751545 DOI: 10.3389/fpsyg.2021.782866] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 12/02/2021] [Indexed: 12/30/2022] Open
Abstract
The COVID-19 pandemic has adverse consequences on human psychology and behavior long after initial recovery from the virus. These COVID-19 health sequelae, if undetected and left untreated, may lead to more enduring mental health problems, and put vulnerable individuals at risk of developing more serious psychopathologies. Therefore, an early distinction of such vulnerable individuals from those who are more resilient is important to undertake timely preventive interventions. The main aim of this article is to present a comprehensive multimodal conceptual approach for addressing these potential psychological and behavioral mental health changes using state-of-the-art tools and means of artificial intelligence (AI). Mental health COVID-19 recovery programs at post-COVID clinics based on AI prediction and prevention strategies may significantly improve the global mental health of ex-COVID-19 patients. Most COVID-19 recovery programs currently involve specialists such as pulmonologists, cardiologists, and neurologists, but there is a lack of psychiatrist care. The focus of this article is on new tools which can enhance the current limited psychiatrist resources and capabilities in coping with the upcoming challenges related to widespread mental health disorders. Patients affected by COVID-19 are more vulnerable to psychological and behavioral changes than non-COVID populations and therefore they deserve careful clinical psychological screening in post-COVID clinics. However, despite significant advances in research, the pace of progress in prevention of psychiatric disorders in these patients is still insufficient. Current approaches for the diagnosis of psychiatric disorders largely rely on clinical rating scales, as well as self-rating questionnaires that are inadequate for comprehensive assessment of ex-COVID-19 patients' susceptibility to mental health deterioration. These limitations can presumably be overcome by applying state-of-the-art AI-based tools in diagnosis, prevention, and treatment of psychiatric disorders in acute phase of disease to prevent more chronic psychiatric consequences.
Collapse
Affiliation(s)
- Krešimir Ćosić
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Siniša Popović
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Marko Šarlija
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Ivan Kesedžić
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Mate Gambiraža
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Branimir Dropuljić
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Igor Mijić
- Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
| | - Neven Henigsberg
- Croatian Institute for Brain Research, University of Zagreb School of Medicine, Zagreb, Croatia
| | - Tanja Jovanovic
- Department of Psychiatry and Behavioral Neurosciences, Wayne State University School of Medicine, Detroit, MI, United States
| |
Collapse
|
4
|
Sarlija M, Popovic S, Jagodic M, Jovanovic T, Ivkovic V, Zhang Q, Strangman G, Cosic K. Prediction of Task Performance From Physiological Features of Stress Resilience. IEEE J Biomed Health Inform 2021; 25:2150-2161. [PMID: 33253118 DOI: 10.1109/jbhi.2020.3041315] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
In this paper, we investigate the potential of generic physiological features of stress resilience in predicting air traffic control (ATC) candidates' performance in a highly-stressful low-fidelity ATC simulator scenario. Stress resilience is highlighted as an important occupational factor that influences the performance and well-being of air traffic control officers (ATCO). Poor stress management, besides the lack of skills, can be a direct cause of poor performance under stress, both in the selection process of ATCOs and later in the workplace. 40 ATC candidates, within the final stages of their selection process, underwent a stimulation paradigm for elicitation and assessment of various generic task-unrelated physiological features, related to resting heart rate variability (HRV) and respiratory sinus arrhythmia (RSA), acoustic startle response (ASR) and the physiological allostatic response, which are all recognized as relevant psychophysiological markers of stress resilience. The multimodal approach included analysis of electrocardiography, electromyography, electrodermal activity and respiration. We make advances in computational methodology for assessment of physiological features of stress resilience, and investigate the predictive power of the obtained feature space in a binary classification problem: prediction of high- vs. low-performance on the developed ATC simulator. Our novel approach yields a relatively high 78.16% classification accuracy. These results are discussed in the context of prior work, while considering study limitations and proposing directions for future work.
Collapse
|
5
|
Pantoni MM, Herrera GM, Van Alstyne KR, Anagnostaras SG. Quantifying the Acoustic Startle Response in Mice Using Standard Digital Video. Front Behav Neurosci 2020; 14:83. [PMID: 32595460 PMCID: PMC7289120 DOI: 10.3389/fnbeh.2020.00083] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2020] [Accepted: 05/04/2020] [Indexed: 11/13/2022] Open
Abstract
The startle response is an unconditional reflex, characterized by the rapid contraction of facial and skeletal muscles, to a sudden and intense startling stimulus. It is an especially useful tool in translational research for its consistency across species, simple neural circuitry, and sensitivity to a variety of experimental manipulations. The rodent acoustic startle response is commonly used to study fundamental properties of the central nervous system, including habituation, sensitization, classical conditioning, fear and anxiety, sensorimotor gating, and drug effects. The rodent startle response is typically assessed in stabilimeter chambers, and while these systems are excellent at measuring startle, they are designed only for this sole purpose. In the present study, we used the VideoFreeze system-a widely used tool for studying Pavlovian fear conditioning-to assess the acoustic startle response in freely moving mice. We validated the use of this system to quantify startle response amplitude and prepulse inhibition of startle. This is the first demonstration to date of using standard video in the automated assessment of the acoustic startle response in rodents. We believe that researchers already using the VideoFreeze system will benefit from the additional ability to assess startle without the purchase of new equipment.
Collapse
Affiliation(s)
- Madeline M Pantoni
- Molecular Cognition Laboratory, Department of Psychology, University of California, San Diego, La Jolla, CA, United States
| | - Gerald M Herrera
- Med-Associates Inc., Catamount Research & Development Inc., St. Albans, VT, United States.,Department of Pharmacology, University of Vermont, Burlington, VT, United States
| | - Kaitlin R Van Alstyne
- Molecular Cognition Laboratory, Department of Psychology, University of California, San Diego, La Jolla, CA, United States
| | - Stephan G Anagnostaras
- Molecular Cognition Laboratory, Department of Psychology, University of California, San Diego, La Jolla, CA, United States.,Program in Neurosciences, University of California, San Diego, La Jolla, CA, United States
| |
Collapse
|
6
|
A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors. SENSORS 2019; 19:s19071659. [PMID: 30959956 PMCID: PMC6479880 DOI: 10.3390/s19071659] [Citation(s) in RCA: 33] [Impact Index Per Article: 6.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/14/2019] [Revised: 03/31/2019] [Accepted: 04/03/2019] [Indexed: 11/16/2022]
Abstract
One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept’s performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals.
Collapse
|
7
|
Characterization of Volume-Based Changes in Cortical Auditory Evoked Potentials and Prepulse Inhibition. Sci Rep 2017; 7:11098. [PMID: 28894145 PMCID: PMC5593922 DOI: 10.1038/s41598-017-11191-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2017] [Accepted: 08/21/2017] [Indexed: 12/11/2022] Open
Abstract
The auditory evoked startle reflex is a conserved response resulting in neurological and motor activity. The presence of a mild prepulse immediately before the main pulse inhibits startle responses, though the mechanism for this remains unknown. In this study, the electroencephalography (EEG) data recorded from 15 subjects was analyzed to study the N1 and P2 components of cortical auditory evoked potentials (CAEPs) evoked by 70, 80, 90, 100, and 110 dB stimuli both in the presence and absence of 70 dB prepulses. Results without a prepulse showed an evolution of N1 amplitudes, increasing with stimulus intensity and showing largely significant differences. Results from prepulse trials only showed noteworthy changes in peak-to-peak amplitude in the 100 dB condition. Prepulse and non-prepulse conditions were then compared using peak amplitudes and theta power. Prepulse conditions significantly decreased the amplitude for both components in the 110 dB condition, i.e., pre-pulse inhibition, but significantly increased the N1 amplitude in the 70 dB condition, i.e., pre-pulse facilitation. Similarly theta band power significantly increased in the 70 dB prepulse condition and significantly decreased in the 110 dB prepulse condition. These results expand the basis of knowledge regarding how CAEPs change and elaborate on their neural function and representation.
Collapse
|