Sage Journals: Discover world-class research

Abstract

Background:

COVID-19 has a profound impact on people with existing mental disorders, augmenting the prevailing inequalities in mental health.

Methods:

In order to understand the status of telepsychiatry in India and the role of artificial intelligence (AI) in mental health and its potential applications, a scoping review was done between March 2020 and May 2020. The literature review revealed 253 papers, which were used to derive the primary framework for analysis. The information was then reviewed for ideas and concepts, which were integrated with evidence from gray literature and categorized under broader themes based on the insights derived. Finally, a thematic framework was developed for discussion to tailor scientific information for decision-makers’ needs.

Results:

Review findings are summarized under the following headings: changing patterns of health-seeking behavior, origin and evolution of telepsychiatry, possible applications of telepsychiatry and AI, technological features, and AI models in mental health.

Conclusions:

Though there are several potential opportunities, the time is not yet ripe for telepsychiatry and AI to be adopted fully in the field of mental health care. But it is time that we develop indigenous proprietary technology and test and validate it. With many solutions offered by telepsychiatry and AI, psychiatrists must choose an appropriate tool based on their requirements, availability of resources, and feasibility of deployment. Harmony between conventional care and technology-based care must be reached gradually.

Keywords

Telepsychiatry e-mental health artificial intelligence in mental health review India COVID-19

Key Messages:

Telepsychiatry equipped with artificial intelligence can be effectively deployed to address the shortage of psychiatrists and the urban–rural gap in providing mental health services. The technology must be indigenous and validated for use in India.

Mental health is one of the priority areas of global health policies and is an important agenda of sustainable development goals.¹ The prevalence of mental health disorders in India has doubled in the period between 1990 and 2017, with one in seven Indians affected by psychiatric disorders of varying severity.² This burden is further worsened by the average national deficit of psychiatrists, of 77%.³

COVID-19 has a profound impact on people with existing mental disorders, augmenting the prevailing inequalities in mental health.⁴ Studies show that pandemics cause stress disorders, as seen in SARS.⁵ COVID-19 is, therefore, expected to cause an increased incidence of mental disorders of varying severities in the future.⁶ Isolation and quarantine for longer periods, due to COVID-19, are known to precipitate depression and anxiety.^{7, 8} Also, social distancing leading to an alteration in routine and livelihood results in frustration, stress, boredom, low mood, and depression, while fear of contagion leads to anxiety.^{9, 10} There might also be a cancelation of psychiatry services, deeming them as nonessential.¹¹ All these factors related to COVID-19 may exacerbate the existing barriers and challenges posed by stigma, traditional and religious beliefs, sociocultural factors, low literacy, unavailability of services, and discrimination associated with mental illness.^{12, 13} These factors can aggravate the existing mental illness and also increase the incidence of mental disorders. There is a possibility of a higher incidence of post-traumatic stress disorder (PTSD) during and after the pandemic.^14–16 The voluminous burden of mental health issues makes it practically difficult to address this singularly at the level of psychiatrists alone or to use the traditional approaches.¹⁷

These challenges pose several questions; how can these issues be handled with the existing infrastructure and mental health care spending? Can we look forward to any technology to help bridge the supply–demand gap? Will technology help in enhancing psychiatry clinical practice, ensuring the standards of clinical care and social distancing? Can we experiment with artificial intelligence (AI) enabled telepsychiatry when social distancing, isolation, lockdown, and quarantine are in place? If the model is successful, can it be used for future interventions? What is the common ground where psychiatrists collaborate with technology experts? What is the information that a psychiatrist needs in order to collaborate with a technology expert and vice versa?

We may be already having the answers to these questions. Most of the time, the necessary technology is present in a form unfamiliar to a psychiatrist, one of the reasons being the lack of an interdisciplinary approach to problem-solving in medicine. Technology experts too find it hard to understand the gaps from a psychiatrist’s perspective. They find it hard to identify the issues (to create solutions), whereas psychiatrists find it hard to understand what type of technology exists.^18–22 Another potential challenge is that technology-related information is mostly present in gray literature and nonmedical academic literature more than the medical academic sources, which further increases the information gap.²³ Any psychiatrist who wants to use technology to address problems in psychiatry must rely on nonacademic sources of knowledge. Therefore, a traditional systematic review of literature cannot be attempted.

An alternate approach to synthesize evidence for policy and practice is to perform a scoping review.²⁴ In order to synthesize knowledge on telepsychiatry in India, the role of AI in mental health, and its potential applications in psychiatry clinical practice, the following scoping review was done.

Materials and Methods

Between March 2020 and May 2020, a scoping review, using the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) guidelines, was done by the two authors in the published literature (Medline, PsycINFO, and Web of Science; for academic knowledge) and gray literature (for nonacademic knowledge and evidence).^25–27 Many research questions were framed for the study (Box 1), and the following search terms were used: “telepsychiatry in India,” “telemedicine and mental health,” “e-mental health,” “telemental health care,” and “AI and mental health.” Box 1.
Research Questions That Were Used to Guide the Review

How has technology in telepsychiatry evolved in India in the last two decades?

What are the various ways to use artificial intelligence (AI) in psychiatry?

What are the various technological features that can be used in telepsychiatry with AI?

What are the possible applications of AI-enabled telepsychiatry in India?

How can AI be integrated with telepsychiatry?

What is the must-have knowledge for a psychiatrist who wishes to use technology to address problems in psychiatry or to collaborate with technology experts?

What are the solutions that can be developed indigenously for having AI-enabled telepsychiatry in India?

How does the current pandemic offer a situational advantage to design, develop, and deploy such technology? (situational perspective)

Initially, two reviewers independently identified peer-reviewed articles published in English between 2000 and 2020. Articles on telepsychiatry were chosen only from Indian studies, which primarily discussed the design of the telepsychiatry model. On the other hand, peer-reviewed articles on AI in mental health were chosen primarily from western literature, to understand the growth and potential of the technology. Articles that did not give any new insight were removed for the sake of conciseness.

After the removal of duplicates, 253 papers were analyzed using the grounded theory approach and the constant comparative method.²⁸ Knowledge was retrieved from these articles as concepts. The concepts were categorized under different preexisting themes (origin and evolution of telepsychiatry in India from a design perspective, possible applications of telepsychiatry and AI, and technological features of AI-enabled telepsychiatry). Secondary qualitative analysis of the retrieved information yielded new themes (changing patterns of health-seeking behavior and AI/machine learning/deep learning models in mental health). A thematic framework was developed, which was used to integrate evidence and knowledge from gray literature.²⁹ The final synthesis of knowledge from the themes was done. Figure 1 shows the methodology used for conducting the review.

Figure 1.
PRISMA-ScR: Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews.

Results

The review showed that the health-seeking behavior of patients is evolving due to the advancement of technology in health care. More people are turning online to seek help from professionals and peers. The telepsychiatry models have also evolved from simple teleconsultation to tele-enabling models. The automated evaluation has increased the need for AI-enabled psychiatry with innovations in machine learning and deep learning models. The findings are elaborated under discussion. Table 1 shows the themes and concepts derived from the qualitative analysis of the peer-reviewed articles.
Table 1.
Themes and Categories from the Scoping Review on Telepsychiatry and Artificial Intelligence

S. No. Themes Concepts

1 Changing patterns of health-seeking behavior
General health-seeking behaviour34–39
Mental health-seeking behaviour40

2 Origin and evolution of telepsychiatry in India (design perspective)
Synchronous or asynchronous interactions^42–44

Using AI in various models

(tele-enabling model)^{45, 46}

3 Possible applications of AI-enabled telepsychiatry Automated evaluation
Imaging and behavior analysis⁴⁷

Evaluating biosignals⁴⁸

Language use in mental disorders⁴⁹

Acoustic analysis⁵⁰

Knowledge-based methods⁵¹

Retinal examination^52–56

Online information exchange and support services⁵⁷

Psychiatric consultation in primary care and emergency rooms⁵⁸

Asynchronous psychotherapy⁵⁹

Home care and related interventions⁶⁰

4 Technological features of AI-enabled telepsychiatry
Videoconference, telephone, and messaging systems^{61, 62}

Web-based interactions^{63, 64}

Mobile phone technologies⁶⁵

Networking via social media and group discussions⁶⁶

Simulated people and places⁶⁷

Internet game^s68

5 AI/machine learning/deep learning models in mental health
Clinical decisions^{69, 70}

EHRs (electronic health records)⁶⁹

Diagnosis^{69, 71}

Personalized medicine^{69, 72}

Health care system management⁶⁹

Medical robots⁶⁹

Discussion

The pandemic COVID-19 has put an extraordinary burden on the existing health care resources.³⁰ For psychiatry, this has widened the already existing gap between the mental health seekers and providers.³¹ Considering the fact that it will take a while for the pandemic to reduce or a cure to be found, we must find alternate strategies for providing mental health care.³² AI-enabled telepsychiatry, therefore, may be an option at present and in the future.³³

The technology used in telepsychiatry in India has evolved from a simple synchronous teleconsultation model using video conferencing, telephone, online chatrooms, etc., to the deployment of asynchronous models using AI-enabled telepsychiatry. AI in mental health has enabled automated evaluation of various clinical parameters. There are several ways the potential of AI can be leveraged in telepsychiatry, ranging from web-based interactions to internet games. The following section explains the must-have knowledge for a psychiatrist to work with a technology expert and vice versa. The current pandemic is the best time to collaborate, design, develop, deploy, and validate AI-based telepsychiatry models. These models can be used during the COVID-19 situation as well as repurposed for routine primary care post COVID-19. Therefore, the following section discusses the key findings with potential applications in COVID-19 times and beyond.

Changing Patterns of Health-Seeking Behavior

Initially found as a secondary insight from the review, changing patterns of health-seeking behavior is an important factor that determines the uptake and scaling of telemental health: Studies show that people are increasingly using the internet for seeking help for various health-related issues, which enable the users to gain more knowledge on any health condition.^34–36 There are several benefits, like being free of cost,³⁷ better privacy,³⁸ and the potential for anonymity.³⁹ This is especially true for mental health-seeking behavior where people are turning to online social platforms and other resources for mental health and are more comfortable seeking mental health-related information online than in person.⁴⁰ The present generation is increasingly seeking online help for health issues than the previous generation, though disparities exist in the quality of care sought.⁴¹ The current generation of millennials, which will be the youth of the next decade, is known to be digitally active and friendly. The uptake of online services will, therefore, increase in the coming decades, thereby leading to a large number of people turning to e-mental health than conventional care. In the extraordinary times of the pandemic, where social distancing and no contact interactions are encouraged, this behavior should be understood and encouraged by the practicing psychiatrists. At present, urban people are favorably positioned to access this type of service than the rural population. But considering the increasing digital and technology penetration, the percentage of people using online mental health services will increase substantially even in rural areas. Developing countries like India would benefit more from such initiatives than the developed nations that already have a good doctor to patient ratio. Therefore, a practicing psychiatrist should look for ways to accommodate this online health-seeking behavior of their patients in their regular practice, beginning from the current pandemic, into the future.

Origin and Evolution of Telepsychiatry (Design Perspective)

In India, along with the changing patterns of health-seeking behavior, the technology associated with health has also gradually evolved from being a simple teleconsultation model using video conferencing, telephone, online chatrooms, etc., to the deployment of asynchronous models using AI.⁴² Synchronous telepsychiatry models were successfully implemented in India during the tsunami of 2004 from fixed establishments, which later evolved into mobile telepsychiatry units.^{27, 28} Asynchronous models were known to have limited feasibility,⁴³ but with improved access, lower costs, and as a supplement to the existing care.⁴⁴ Studies globally show that digital technology coupled with AI, known as the “tele-enabling model,” can be used to leverage the potential of medical informatics in conventional telepsychiatry.⁴⁵ AI is being effectively utilized for patient monitoring, health care information technology, intelligent assistance diagnosis, and information analysis collaboration.⁴⁶ With the current growth trajectory, the technology associated with telemedicine is bound to increase and also service uptake will improve with better penetration of technology. The current model will evolve to become stable enough for large-scale deployment. Therefore, it is essential to develop a model that is based on telepsychiatry integrated with features of AI with better ease of use. Psychiatrists must become familiar with such models. During COVID-19, psychiatrists, with the help of technology experts, can try developing such models for communicating with their existing and new clientele. In the future, the models might migrate toward augmented reality/virtual reality (AR/VR). There are also various telepsychiatry services for academic purposes in India, which is beyond the scope of this article.

Possible Applications of Telepsychiatry and AI

Studies show that telepsychiatry and AI can be effectively deployed for automated evaluation, namely imaging and behavior analysis,⁴⁷ evaluating biosignals,⁴⁸ assessing language use in mental disorders,⁴⁹ acoustic analysis,⁵⁰ knowledge-based methods,⁵¹ and retinal examination.^52–56 Other potential uses include online information exchange and support services using social media and networking,⁵⁷ psychiatric consultation in primary care and emergency rooms,⁵⁸ and asynchronous psychotherapy.⁵⁹ Home care and related interventions for the geriatric population are also possible using technology.⁶⁰ All these possible applications help in collecting as much data as possible for making effective clinical decisions by the psychiatrist. The availability of temporal data that has been effectively summarized using AI can be a potential tool for psychiatrists in clinical decision making. Any psychiatrist relies on data for making clinical decisions. This type of big data with temporal characteristics analyzed using AI will be an effective tool for diagnosis, follow-up, and monitoring of patients. Psychiatrists will have meaningful data to enhance their clinical decisions. But, with no uniform data collection pattern, this type of automated evaluation is not possible immediately or in the near future. Yet, it is time that ethical guidelines on alternate data collection practices are encouraged in psychiatry.

Technological Attributes of Telepsychiatry and AI

Technological features include videoconference, telephone, and messaging systems,^{61, 62} web-based interactions,^{63, 64} mobile phone technologies,⁶⁵ networking via social media and group discussions,⁶⁶ simulated people and places,⁶⁷ and internet games.⁶⁸ The technology aspect of telepsychiatry has been experimented on a small scale in different cultural settings.^{63, 64, 67, 68} Any large-scale implementation requires more validation studies. Institutions that focus on mental health should encourage experimenting with these technologies during this pandemic. Personal interactions with patients revealed that patients are also willing to experiment with telepsychiatry, due to the social distancing norms during this pandemic. The learning from these experiments should inform future decisions in AI-enabled telepsychiatry.

Specific AI/Machine Learning/Deep Learning Models in Mental Health⁶⁹

Specific models of AI in mental health can be used for clinical decisions, electronic health records (EHR), diagnosis, personalized medicine, health care system management, and medical robots. These models can help reduce the need for human resources, reduce costs, and improve the efficiency of time. A large number of patients can be seen in a shorter duration. In addition, a single psychiatrist can consult a large number of patients by using triaging models for prioritizing patients and effectively reduce the time needed for history taking. This will enable the psychiatrist to spend more time talking to the patient than collecting data. However, the models have to be robust enough with high sensitivity and specificity.

Machine learning models using natural language processing techniques can read and review EHRs in addition to comparing the EHR with the published literature. With the ever-increasing medical literature, this will be an effective tool in the hands of a psychiatrist. A chatbot built to specifically review published literature will be effective for senior practitioners who have less time for updating themselves. Advanced algorithms can help make clinical decisions through their clinical decision support systems (CDSS).⁷⁰ Studies show that AI can improve the quality of medical diagnosis.⁷¹ Also, precision medicine models are completely dependent on AI for accuracy where an individual patient is considered as one unit and is evaluated from different perspectives of genetics, lifestyle, sociobehavior, environment, ethnicity, etc.⁷² Technology experts, in collaboration with psychiatrists, can develop specific AI-models focusing on the mental illness during COVID-19. Since technology people do not completely understand how clinical decision making in psychiatry works, psychiatrists and psychiatric institutions must take initiatives to give specific requirements to technology experts for developing such products. This will be resource-efficient than the technology experts trying to figure out themselves what needs to be done.

Challenges in Implementing Technology in Mental Health Care^73–75

Along with the many opportunities that technology offers, there are also unique challenges. The challenges in implementing technology in providing mental health care are many and beyond the scope of this article. However, it is essential to understand that there are issues related to validation, privacy, security, biases, urban/rural gaps, language barriers, financial constraints, technical issues, training and professional issues, professionalism issues, and problems related to patient–provider relationships.

Conclusion

Though there are many potential opportunities, the time is not yet ripe for telepsychiatry and AI to be adopted fully in the field of mental health care. But it is time that we develop indigenous proprietary technology and test and validate it. With many solutions offered by telepsychiatry and AI, psychiatrists must choose an appropriate tool based on their requirements, availability of resources, and feasibility of deployment. Any institution, public or private, that pioneer this process must establish a clinical and technology research and development team that continuously fuels the process of innovation at the grassroots level. A platform should be developed and validated with robust clinical trials. The final platform and technology can be deployed and scaled up in India in a decade or two, to reach the WHO goal of universal health coverage for mental health. Simultaneously, awareness among the public regarding the importance of mental health care should be done along with the training of mental health care professionals to handle the technology. Harmony between conventional care and technology-based care must be reached gradually.

Footnotes
Declaration of Conflicting Interests
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Funding
The authors received no financial support for the research, authorship, and/or publication of this article.
References
1.
World Health Organization. Mental health action plan 2013–2020 . Geneva: WHO, 2013.
2.
Sagar R Dandona R Gururaj G . The burden of mental disorders across the states of India: the Global Burden of Disease Study 1990–2017. Lancet Psychiatry 2020 February; 7(2): 148–161.
3.
Thirunavukarasu M Thirunavukarasu P. Training and national deficit of psychiatrists in India–a critical analysis. Indian J Psychiatry 2010 January; 52(suppl 1): S83–S88.
4.
Yao H Chen JH Xu YF. Patients with mental health disorders in the COVID-19 epidemic. Lancet Psychiatry 2020 April; 7(4): e21.
5.
Cheng SK Wong CW Tsang J . Psychological distress and negative appraisals in survivors of severe acute respiratory syndrome (SARS). Psychol Med 2004 October; 34(7): 1187.
6.
Duan L Zhu G. Psychological interventions for people affected by the COVID-19 epidemic. Lancet Psychiatry 2020 April; 7(4): 300–302.
7.
Hawryluck L Gold WL Robinson S . SARS control and psychological effects of quarantine, Toronto, Canada. Emerg Infect Dis 2004 July; 10(7): 1206.
8.
Jeong H Yim HW Song YJ . Mental health status of people isolated due to Middle East Respiratory Syndrome. Epidemiol Health 2016; 38: e2016048.
9.
Bai Y Lin CC Lin CY . Survey of stress reactions among health care workers involved with the SARS outbreak. Psychiatr Serv 2004 September; 55(9): 1055–1057.
10.
Brooks SK Webster RK Smith LE . The psychological impact of quarantine and how to reduce it: rapid review of the evidence [published online February 26, 2020]. Lancet DOI:10.1016/S0140-6736(20)30460-8
11.
Venkatesh A Edirappuli S. Social distancing in COVID-19: what are the mental health implications? BMJ 2020 April; 369: m1379.
12.
Raguram RD Weiss MG Channabasavanna SM . Stigma, depression, and somatization in South India. Am J Psychiatry 1996 August; 153(8): 1043–1049.
13.
Kumar A. Mental health services in rural India: challenges and prospects. Health 2011; 3(12): 757–761.
14.
Dutheil F Mondillon L Navel V. PTSD as the second tsunami of the SARS-Cov-2 pandemic [published online April 24, 2020]. Psychol Med DOI:10.1017/S0033291720001336.
15.
Huang JZ Han MF Luo TD . Mental health survey of 230 medical staff in a tertiary infectious disease hospital for COVID-19. Zhonghua Lao Dong Wei Sheng Zhi Ye Bing Za Zhi 2020 March; 38(3): E001.
16.
Liang L Ren H Cao R . The effect of COVID-19 on youth mental health [published online April 21, 2020]. Psychiatr Q. DOI:10.1007/s11126-020-09744-3.
17.
Magnabosco JL. Innovations in mental health services implementation: a report on state-level data from the US evidence-based practices project [published online May 30, 2006]. Implement Sci. DOI:10.1186/1748-5908-1-13.
18.
Parikh SV Bostwick JR Taubman DS. Videoconferencing technology to facilitate a pilot training course in advanced psychopharmacology for psychiatrists. Acad Psychiatry 2019 August; 43(4): 411–416.
19.
Bernstein CA Bhugra D. Next generation of psychiatrists: what is needed in training? Asian J Psychiatry 2011 June; 4(2): 88–91.
20.
Shore J. The evolution and history of telepsychiatry and its impact on psychiatric care: current implications for psychiatrists and psychiatric organizations. Int Rev Psychiatry 2015 November; 27(6): 469–475.
21.
Siotia R Simpson C. Applying telecare in dementia: what psychiatrists need to know. Adv Psychiatr Treat 2008 September; 14(5): 382–388.
22.
Zhang MW Ho R. Enabling psychiatrists to explore the full potential of e-health. Front Psychiatry 2015 December; 6: 177.
23.
Rothstein HR Hopewell S. Grey literature. In: Cooper H Hedges LV Valentine JC , eds. The handbook of research synthesis and meta-analysis . New York: Russell Sage Foundation, 2009: 103–125.
24.
Munn Z Peters MD Stern C . Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Med Res Methodol 2018 December; 18(1): 143.
25.
Tricco AC Lillie E Zarin W . A scoping review on the conduct and reporting of scoping reviews. BMC Med Res Methodol 2016 December; 16(1): 15.
26.
Tricco AC Lillie E Zarin W . PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med 2018 October; 169(7): 467–473.
27.
McGowan J Straus S Moher D . Reporting scoping reviews—PRISMA ScR extension. J Clin Epidemiol 2020 July; 123: 177–179.
28.
Kelle U. The development of categories: different approaches in grounded theory. In: Bryant A Charmaz K eds. The Sage handbook of grounded theory . Thousand Oaks, CA: SAGE, 2007: 191–213.
29.
Thomas J Harden A. Methods for the thematic synthesis of qualitative research in systematic reviews. BMC Med Res Methodol 2008 December; 8(1): 45.
30.
Ji Y Ma Z Peppelenbosch MP . Potential association between COVID-19 mortality and health-care resource availability. Lancet Global Health 2020 April; 8(4): e480.
31.
Holmes EA O’Connor RC Perry VH . Multidisciplinary research priorities for the COVID-19 pandemic: a call for action for mental health science. Lancet Psychiatry 2020 June; 7(6): 547–560.
32.
Li W Yang Y Liu ZH . Progression of mental health services during the COVID-19 outbreak in China. Int J Biol Sci 2020; 16(10): 1732.
33.
Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019 January; 25(1): 44–56.
34.
Cline RJ Haynes KM. Consumer health information seeking on the internet: the state of the art. Health Educ Res 2001 December; 16(6): 671–692.
35.
Atkinson N Saperstein S Pleis J. Using the internet for health-related activities: findings from a national probability sample. J Med Internet Res 2009; 11(1): e4.
36.
Koch-Weser S Bradshaw YS Gualtieri L . The Internet as a health information source: findings from the 2007 Health Information National Trends Survey and implications for health communication. J Health Commun 2010 December; 15(suppl 3): 279–293.
37.
Wang Z Walther JB Pingree S . Health information, credibility, homophily, and influence via the internet: web sites versus discussion groups. Health Commun 2008 August; 23(4): 358–368.
38.
DuBois KN. Deep medicine: how artificial intelligence can make healthcare human again. Perspect Sci Christ Faith 2019 September; 71(3): 199–201.
39.
Zhao S. Parental education and children’s online health information seeking: beyond the digital divide debate. Soc Sci Med 2009 November; 69(10): 1501–1505.
40.
Naskar S Victor R Das H . Telepsychiatry in India—where do we stand? A comparative review between global and Indian telepsychiatry programs. Indian J Psychol Med 2017 May; 39(3): 223.
41.
Thara R Sujit J Rao K. Telepsychiatry in Chennai, India: the SCARF experience. Behav Sci Law 2008 May; 26(3): 315–322.
42.
Thara R Sujit J. Mobile telepsychiatry in India. World Psychiatry 2013 February; 12(1): 84.
43.
Balasinorwala VP Shah NB Chatterjee SD . Asynchronous telepsychiatry in Maharashtra, India: study of feasibility and referral pattern. Indian J Psychol Med 2014 July; 36(3): 299.
44.
Hilty DM Parish M Chan S . A comparison of in-person, synchronous and asynchronous telepsychiatry: skills/competencies, teamwork, and administrative workflow. J Tech Behav Sci. 2020; 5: 273–288.
45.
Malhotra S Shah R. Telepsychiatry and digital mental health care in child and adolescent psychiatry: implications for service delivery in low-and middle-income countries. In: Hodes M Shur-Fen Gau S De Vries PJ , eds. Understanding uniqueness and diversity in child and adolescent mental health . Cambridge, MA: Academic Press, 2018 January: 263–287.
46.
Pacis DM Subido Jr ED Bugtai NT. Trends in telemedicine utilizing artificial intelligence. AIP Conf Proc 2018 February; 1933(1): 040009.
47.
Valstar MF Pantic M. Fully automatic recognition of the temporal phases of facial actions. IEEE Trans Syst Man Cybern Part B (Cybern) 2011 September; 42(1): 28–43.
48.
Luneski A Bamidis PD Hitoglou-Antoniadou M. Affective computing and medical informatics: state of the art in emotion-aware medical applications. Stud Health Technol Inform 2008 January; 136: 517–522.
49.
Elvevaag B Foltz PW Rosenstein M . An automated method to analyze language use in patients with schizophrenia and their first-degree relatives. J Neurol 2010 May; 23(3): 270–284.
50.
Goh TJ Diederich J Song I . Using diagnostic information to develop a machine learning application for the effective screening of autism spectrum disorders. In: Mental health informatics. Berlin, Heidelberg: Springer, 2014: 229–245.
51.
Panagiotakopoulos TC Lyras DP Livaditis M . A contextual data mining approach toward assisting the treatment of anxiety disorders. IEEE Trans Inform Technol Biomed 2010 January; 14(3): 567–581.
52.
Appaji A Nagendra B Chako DM . Retinal vascular abnormalities in schizophrenia and bipolar disorder: a window to the brain. Bipolar Disord 2019 November; 21(7): 634–641.
53.
Appaji A Nagendra B Chako DM . Examination of retinal vascular trajectory in schizophrenia and bipolar disorder. Psychiatry Clin Neurosci 2019 December; 73(12): 738–744.
54.
Appaji A Nagendra B Chako DM . Retinal vascular tortuosity in schizophrenia and bipolar disorder. Schizophr Res 2019 October; 212: 26–32.
55.
Appaji A Nagendra B Chako DM . Relation between retinal vascular abnormalities and working memory impairment in patients with schizophrenia and bipolar disorder. Asian J Psychiatry 2020 March; 49: 101942.
56.
Appaji A Nagendra B Chako DM . Retinal vascular fractal dimension in bipolar disorder and schizophrenia. J Affect Disord 2019 December; 259: 98–103.
57.
McKay E Martin J. Mental health and wellbeing: converging HCI with human informatics in higher education. Issues Informing Sci Inf Technol 2010 January; 7(3): 339–351.
58.
Hilty DM Ferrer DC Parish MB . The effectiveness of telemental health: a 2013 review. Telemed J E Health 2013 June; 19(6): 444–454.
59.
Yellowlees PM Odor A Parish MB . A feasibility study of the use of asynchronous telepsychiatry for psychiatric consultations. Psychiatr Serv 2010 August; 61(8): 838–840.
60.
Langarizadeh M Tabatabaei MS Tavakol K . Telemental health care, an effective alternative to conventional mental care: a systematic review. Acta Inform Med 2017 December; 25(4): 240.
61.
Kazdin AE. Evidence-based treatment research: advances, limitations, and next steps. Am Psychol 2011 November; 66(8): 685.
62.
Richardson LK Christopher Frueh B Grubaugh AL . Current directions in videoconferencing tele-mental health research. Clin Psychol: Sci Pract 2009 September; 16(3): 323–338.
63.
Ritterband LM Thorndike FP Cox DJ . A behavior change model for internet interventions. Ann Behav Med 2009 August; 38(1): 18–27.
64.
Vernon ML. A review of computer-based alcohol problem services designed for the general public. J Subst Abuse Treat 2010 April; 38(3): 203–211.
65.
Høybye MT Dalton SO Deltour I . Effect of Internet peer-support groups on psychosocial adjustment to cancer: a randomised study. Br J Cancer 2010 April; 102(9): 1348–1354.
66.
Beard L Wilson K Morra D . A survey of health-related activities on second life. J Med Internet Res 2009; 11(2): e17.
67.
Bickmore T Gruber A Picard R. Establishing the computer–patient working alliance in automated health behavior change interventions. Patient Educ Couns 2005 October; 59(1): 21–30.
68.
Wilkinson N Ang RP Goh DH. Online video game therapy for mental health concerns: a review. Int J Soc Psychiatry 2008 July; 54(4): 370–382.
69.
Guo J Li B. The application of medical artificial intelligence technology in rural areas of developing countries. Health Equity 2018 August; 2(1): 174–181.
70.
Berner ES. Clinical decision support systems: state of the art . Rockville, Maryland: Agency for Healthcare Research and Quality, 2009.
71.
Dawes TJ de Marvao A Shi W . Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac MR imaging study. Radiology 2017 May; 283(2): 381–390.
72.
Mesko B. The role of artificial intelligence in precision medicine. Expert Rev Precis Med Drug Dev 2017; 2(5): 1–3.
73.
Christensen H Hickie IB. Using e-health applications to deliver new mental health services. Med J Aust 2010 June; 192: S53–S56.
74.
Emmelkamp PM. Technological innovations in clinical assessment and psychotherapy. Psychother Psychosom 2005; 74(6): 336–343.
75.
Ybarra ML Eaton WW. Internet-based mental health interventions. Ment Health Serv Res 2005 June; 7(2): 75–87.

S. No.	Themes	Concepts
1	Changing patterns of health-seeking behavior	General health-seeking behaviour34–39 Mental health-seeking behaviour40
2	Origin and evolution of telepsychiatry in India (design perspective)	Synchronous or asynchronous interactions^42–44 Using AI in various models (tele-enabling model)^{45, 46}
3	Possible applications of AI-enabled telepsychiatry	Automated evaluation Imaging and behavior analysis⁴⁷ Evaluating biosignals⁴⁸ Language use in mental disorders⁴⁹ Acoustic analysis⁵⁰ Knowledge-based methods⁵¹ Retinal examination^52–56 Online information exchange and support services⁵⁷ Psychiatric consultation in primary care and emergency rooms⁵⁸ Asynchronous psychotherapy⁵⁹ Home care and related interventions⁶⁰
4	Technological features of AI-enabled telepsychiatry	Videoconference, telephone, and messaging systems^{61, 62} Web-based interactions^{63, 64} Mobile phone technologies⁶⁵ Networking via social media and group discussions⁶⁶ Simulated people and places⁶⁷ Internet game^s68
5	AI/machine learning/deep learning models in mental health	Clinical decisions^{69, 70} EHRs (electronic health records)⁶⁹ Diagnosis^{69, 71} Personalized medicine^{69, 72} Health care system management⁶⁹ Medical robots⁶⁹

Telepsychiatry and the Role of Artificial Intelligence in Mental Health in Post-COVID-19 India: A Scoping Review on Opportunities

Abstract

Background:

Methods:

Results:

Conclusions:

Keywords

Key Messages:

Materials and Methods

Research Questions That Were Used to Guide the Review

Results

Themes and Categories from the Scoping Review on Telepsychiatry and Artificial Intelligence

Discussion

Changing Patterns of Health-Seeking Behavior

Origin and Evolution of Telepsychiatry (Design Perspective)

Possible Applications of Telepsychiatry and AI

Technological Attributes of Telepsychiatry and AI

Specific AI/Machine Learning/Deep Learning Models in Mental Health 69

Challenges in Implementing Technology in Mental Health Care73–75

Conclusion

Footnotes

Declaration of Conflicting Interests

Funding

References

Specific AI/Machine Learning/Deep Learning Models in Mental Health⁶⁹

Challenges in Implementing Technology in Mental Health Care^73–75