John Torous, MD, MBI

The last year has seen an unprecedented shift in the medical landscape, and mental health care is no exception. Experts look at the evidence and risks of digital tools, apps, telehealth, and other technologies for the treatment of serious mental illness. 

In this video, John Torous, MD, and Sherin Khan, LCSW, briefly talk about their presentation at the 

American Psychiatric Association Annual Meeting

Three New Tools to Augment Care for People With Serious Mental Illness

. Speakers are Sherin Khan, LCSW; John Torous, MD, MBI; Amy Cohen, PhD; Tristan Gorrindo, MD, and Moderator, John Luo, MD. 

Dr Torous is director of the Digital Psychiatry Division, Department of Psychiatry at Beth Israel Deaconess Medical Center, Boston; editor in chief of 

​. Sherin Khan, LCSW, is the Senior Director of Workforce and Organizational Development at 

, Illinois' oldest and largest provider of community mental health services; and Social Work Expert for 

Videos

The last year has seen an unprecedented shift in the medical landscape, and mental health care is no exception. Experts look at the evidence and risks of digital tools, apps, telehealth, and other technologies for the treatment of serious mental illness.

New Digital Psychiatry Tools to Improve Care

Slideshows

Against a sea change in real-world practice of technology in psychiatry, John Torous, MD, MBI, shares what clinicians can expect next.

6 Predictions for Digital Psychiatry in 2021

Experts discuss the latest in digital mental health smartphone apps, digital clinics, and online therapies and telehealth, topics that are especially relevant as we are experiencing a radical transformation of health care.

Most people have access to both the internet and devices that can connect to providers, but do patients have tools to make digital health work for them? We are in a pivotal time now with COVID-19 where we have seen wider access being provided at least in highly populated areas. We are still at the beginning stages as we strive to provide wide access to a lot of different people. 

, is Director of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, and Chair, American Psychiatric Association, Health Information Technology Committee. He is the Digital Psychiatry Section Editor for 

, is Clinical Director of the Division of Digital Psychiatry at Beth Israel Deaconess Medical Center, Boston, MA.

 can be properly converted to a new platform in the form of digital technology apps. Additionally, some interventions might be a easier than others. Cognitive behavioral therapy and dialectical behavior therapy are more formulaic and provide homework for patients. Psychodynamic approaches may be more nuanced than some of the shorter term interventions that we are seeing. 

For some patients, it may be unclear exactly what happens in that translation. One useful analogy is comparing a book with a movie. Sometimes, the book is better than the movie; sometimes vice versa. But there is still a lot that we don't know as to why in-person therapy works for some and not for others. The principles are there but we are still learning about the evidence.

Sometimes, the book is better than the movie; sometimes vice versa. But there is a lot we don't know as to why in-person therapy works for some and why digital works for others. In this video, experts discuss the evidence.


Digital Technologies in Mental Health Care

There is a massive effort in the US to curb the spread of 

. But the US has been behind other countries in part because of lack of testing capacity. As testing capacity accelerates, the number of confirmed cases has grown. Singapore and South Korea have flattened the curve more quickly through efficiently identifying cases and exposures and promoting quarantine. This public health strategy, contact tracing, is old but their method is novel. They use phones.

Countries are using Bluetooth or mobility data (eg, Global Positioning System [GPS], cell tower) collected by the phone for contact tracing. One method of contact tracing involves scanning and recording Bluetooth signals from other nearby phones, usually within a 30 feet diameter. The real time data offer a novel means to track proximity and potential interaction with others. Another method for contact tracing involves use of mobility data (often GPS) collected by the phone that allows a digital trail of timestamped locations visited to be easily recreated.

Public health officials can leverage either approach, Bluetooth or mobility, to determine who an infected person may have been in close contact with—and then notify those exposed of possible risk. Countries have taken different approaches in what information they share with individuals identified as being at risk.

, where the age, gender, and location history of those infected are disclosed to those who may have been exposed. On the other end of the spectrum is Singapore, where people are only informed that they may have been exposed. Both South Korea and 

 have been successful in flattening the cure and their use of phone-based contact tracing offers clear potential to better understand how COVID-19 spreads and can be stopped. With increasing interest in using contact tracing in other countries, it is important to understand the potential risks and benefits of use in the US.


During these unprecedented times it is necessary to consider the benefits of disclosure to exposed third parties against the risks of not respecting individual privacy—everyone’s right to control their health information. People are reluctant to share their health information for various reasons, such us harm to one’s reputation, employment problems, and access to insurance.

In the US, health care professionals do not break confidentiality to disclose a patient’s disease status even for communicable diseases like COVID-19 that present a risk to others. One exception is HIV where many state laws encourage or mandate disclosure to public health identities and/or sexual partners. This HIV status disclosure is justified because public health benefits are thought to outweigh the risks to the individual, though this is not without controversy. For COVID-19, one’s personal data (such as age, gender, location, and health status) is shared with others in a public fashion. Yet a discussion about COVID-19 status disclosure does not appear to be happening in many countries where phone-based contract tracing is deployed. In other words, personal data is being shared without the input of people whose information is being shared—in this case those infected.

The current pandemic-related disclosed data can be very sensitive, especially if linked to GPS mobility data collected by phones. Intimate details like where a person sleeps, shops, and even eats can be easily inferred. Later secondary uses of this data can have numerous unintended consequences around employment, social standing, and health insurance coverage. People have already been assaulted because of suspected or confirmed COVID-19—now imagine their home address being shared too. While efforts to deidentify data can be undertaken, history seems to always show that in the near future reidentification is possible. It is assumed that the data are encrypted and secure. But is it? We do not know, key details are lacking.


The legal implications cannot be ignored either; will there be criminal consequences for spreading coronavirus? It may sound fantastical, but in the US there are criminal laws against certain high-risk behaviors that could spread HIV. In Singapore, refusal to share COVID-19 related data requested by the Ministry of Health can lead to prosecution. These consequences have likely led to people avoiding testing or care.

Ethically based solutions offer a path forward. One pathway is to simply ask for 

 to collect data. This could be done in multiple ways including an opt-in system (Singapore) or even opt-out in some circumstances. Although Iranian officials used an opt-in system, the consent was displayed in a non-native language or not at all for many users. Regardless of the system, to respect privacy, it is important that the data collected, shared, and where data are stored is clearly explained to users. Alternatively, it could be an opt-out consent, which may be more coercive because people are less likely to change from the default. If an infected person’s consent is required before his or her data are shared, an opt-in system could be more palatable. Another solution is to aggregate data at the community level to examine trends rather than an individual’s data. This does not necessarily preclude obtaining consent. Although less advantageous for contact tracing, storing contact data on the phone of an infected person rather than a centralized database lets that individual decide whether he or she want to share the data with public health officials.


COVID-19 has spurred many changes leading to wider adoption of various technologies to support public health efforts. But even data collected for the greater good such as phone-based contact tracing can have unintended negative or punitive consequences. There is always a risk when sensitive information is collected. Ultimately, US public health officials must weigh these risks against potential benefits in an informed fashion.

is a Child and Adolescent Psychiatry Fellow, University of California Los Angeles Semel Institute for Neuroscience and Human Behavior, Los Angeles, CA.

is Director, Digital Psychiatry Division, Department of Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA. He is Digital Psychiatry Section Editor for 

Articles

COVID-19 has spurred many changes leading to wider adoption of various technologies to support public health efforts. But even data collected for the greater good can have unintended negative or punitive consequences.

A Novel Approach to Contact Tracing

We have all been there. In an idle moment, you instinctively reach for your smartphone to browse your social media feed. The goal is simple: an easy distraction. But the effect is sometimes complicated. Many of us enjoy social media to stay connected with friends, family, colleagues, or groups of individuals with similar interests, but there is inherently an ugly side too. That side where you see something-the perfect family photo, the vacation picture, the promotion of a work accomplishment-and think, “I wish that were me,” can have negative mental health effects.

These double-sided reactions to social media are critical to understand given the high rates of exposure so many people around the globe have to social media each day. In 2018, 

 social media use among internet users worldwide was 2 hours and 16 minutes.

 And, while user retention for most apps over the first 90 days is 

between 10% and 30%, many social media apps have retention rates ranging from 60% to 98%.

 But are they good for us or are they just addictive? Perhaps they are the social-emotional equivalent of eating fast food every day for lunch.

Several lines of research may be relevant in answering this question. For example, 

 would have us speculate that when we are offered highly curated pictures of other people’s lives, we tend to feel worse about our own.

 Similarly, mindfulness, or focusing on the present moment on purpose without judgement, has been found time and time again to be linked to emotional wellbeing. To the extent that social medial calls for a focus on documenting our most precious moments rather than living them, we might expect that users focused on posting pictures or videos of these moments may be a little less present in those moments.

The difficulty in answering this question is that most of the studies evaluating the social and emotional impact of social media have been cross-sectional. They only look at one point rather than how engaging with social media affects users over time. From cross sectional studies, we know some things. For example, more than 1 hour of 

 daily has been associated with worse psychological well-being (

of young adult social media users indicates that those who used a large number of platforms (7 to 11 different social media platforms) were 3 times more likely to have symptoms consistent with a mood or anxiety disorder.

The challenge of these studies is that they do not tell us whether use of social media makes people unhappy. Cross-sectional studies focus on describing patterns observed (for example, that individuals with high amounts of screen time or who use more platforms are more often unhappy), but not why those patterns are observed. From these findings two different scenarios are entirely possible. First, it may be that people who are more depressed use social media more often in an attempt to feel better. Second, it may be that people who use social media more often become more depressed because they are less mindful in their day-to-day lives or are more engaged in destructive social comparison practices. Either explanation, and may others, could be true. A 2019 study analyzed cross sectional data from over 350,000 youths about their well-being and digital technology use. The researchers concluded that the actual negative effects could be much smaller than projected (0.4%).

A study from 2018 looked beyond cross-sectional data.

 The researchers recruited 200 students: 100 were assigned to an app-based intervention intended to reduce use of social networking apps; the other 100 were not assigned an intervention. The app included education on the use of social networking and allowed students to create limits on how often they could use smartphone social networking platforms. The results showed that among students who received the intervention, use of online social networking platforms as well as symptoms of depression and anxiety decreased. Conversely, the group that did not receive the intervention showed no difference in the use of online social networking platforms or in symptoms of depression or anxiety.

The tentative conclusion from this study: less social media use improved emotional health. As scientists, we have to point out that this study was far from perfect. Most notably, there was no comparison between the intervention and control group-which is a key aspect of establishing what caused the observed changes. Also, while the authors reported that the only criteria for participation was being a student at the host university, they imply that the study recruited participants who perceived their use of online social networking to be an addiction. If participation was skewed toward people who viewed their use of online social media negatively, that alone could certainly explain results. The bottom line is that we will need replication of these kinds of longitudinal studies to draw any firm conclusions. Nonetheless this study represents a promising step toward understanding the impact of social media.

So, is social media your best bet for a relaxing way to pass time between meetings or on your morning bus ride? Should parents allow their impressionable teenagers to use social media? We will certainly need more studies to answer this. But it is looking more and more like the answer may be that social media is not particularly beneficial for most of us.

 is Associate Director, Brigham and Women’s Hospital Digital Behavioral Health and Informatics Research Program, Boston, MA. 

 is Director of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, and Chair, American Psychiatric Association, Health Information Technology Committee.

This articles was originally posted on February 7, 2020, and has since been updated. -Ed

Daily Time Spent on Social Nerworking by Internet Users Worldwide From 2012 to 2018

Which Apps Retain Their Users-And Which Ones Don’t

3. Chen A. New data show losing 80% of mobile users is normal, and why the best apps do better. 2018.

Associations between screen time and lower psychological well-being among children and adolescents: evidence from a population-based study

6. Primack BA, Shensa A, Escobar-Viera CG, et al. 

Use of multiple social media platforms and symptoms of depression and anxiety: a nationally-representative study among US young adults

7. Orben A, Przybylski AK. The association between adolescent well-being and digital technology use. 

8. Rad ME, Ahmadi F. A new method to measure and decrease the online social networking addiction. 

Based on recent data, it is looking more and more like the answer may be that social media is not particularly beneficial for most of us.

Why You May Want to Swipe Left on Social Media

It has been a busy year for digital mental health. While no one knows what 2020 will bring, some themes are sure to continue to shape the field.

7 Trends in Digital Mental Health for 2020

Across all mental illnesses, especially in schizophrenia, the goal is to optimize cognitive functioning. But in the online world, how are our digital environments changing the brain and the way we think?

The 'online brain': how the Internet may be changing our cognition

  explores how the internet may be changing three brain domains: attention, memory, and social cognition.

Understanding the potential influences of the digital world can help us both design new tools to assist those with cognitive impairment in illness like schizophrenia, and also work to ensure we use technology towards recovery and to optimizing cognition.

Dr Torous is Director of the Digital Psychiatry Division, Department of Psychiatry at Beth Israel Deaconess Medical Center, Boston; Editor in Chief of 

1. Firth J, Torous J, Stubbs B, et al. The "online brain": how the Internet may be changing our cognition. 

Across all mental illnesses, especially in schizophrenia, the goal is to optimize cognitive functioning. Digital Psychiatry Section Editor John Torous, MD, MDI, sheds light on new advances.

Negative and Positive Consequences of Internet Use

John Torous, MD, MBI offers insights about a randomized clinical trial by 

 that offers high-quality evidence for helping patients reduce symptoms related to technology addiction.

Applying principles of cognitive behavioral therapy (CBT), the study authors created a new therapy which they randomized patients with gaming disorder too. Results of remission in 69% of patients receiving the therapy versus 23% in the waitlist group highlight the potential of this novel therapy.

Dr Torous is Director of the Digital Psychiatry Division, Department of Psychiatry at Beth Israel Deaconess Medical Center, Boston; Editor in Chief of 

Dr Torous reports receiving unrelated research support from Otsuka.

1. WÃ¶lfling K, MÃ¼ller KW, Dreier M, et al. 

Efficacy of Short-term Treatment of Internet and Computer Game Addiction: A Randomized Clinical Trial.

Technology addiction and screen time are topics of increased concern, but often the discussion does not focus on solutions. In this video, John Torous, MD discusses a new randomized clinical trial that explores the efficacy of CBT to guide patients in their recovery.

Therapy for Gaming Disorder: New Applications of Old Solutions

Apple’s Siri, Amazon’s Alexa, and Google’s Assistant are taking over your smartphones and smart-homes. You’ve no doubt heard, seen, or used one, and likely, so have your patients. They’re great for checking the weather, asking niche trivia questions, trying out new cooking recipes, shopping online, and . . . virtual therapy? While conversational agent technology is growing rapidly, the various technologies (chatbots) might not yet be fully equipped to help patients with clinical needs related to their mental health.

Chatbots for patients with mental health conditions

Among studies conducted so far, educating patients and helping them stay adherent to their treatment plan were the most studied benefits of talking to a chatbot. This finding makes sense as chatbots can easily pull up mental health-related information and offer alarms and reminders. But can they do even more like delivering psychotherapy or making a diagnosis?

In July 2018, we performed a systematic search of the literature in the PubMed, EmBase, PsycINFO, Cochrane, Web of Science, and IEEE Xplore databases and isolated 12 studies that used a chatbot in a mental health setting with individuals at risk for or with depression, anxiety, schizophrenia, bipolar disorder, or substance abuse disorder. The review was published in the 

Although interest in deploying chatbots in clinical contexts is expanding, most studies are not reporting metrics for outcomes or efficacy in a standardized way but rather employing custom scales or unique outcomes, which makes it challenging to compare chatbot functionality. Some studies conducted just a few years ago are unreproducible today because the rate of technological advancement has outpaced that of research.

Empathy and relatability are crucial yet seldom considered cornerstones for patients interacting with chatbots and matching and cooperating with the way humans communicate is paramount in the quest for humanoid chatbots. Most people use conversation fillers like “umm” and “ah” when talking naturally, and the simple omission of these filler words and pauses negatively impacts the perception of an already robotic-sounding chatbot.

 Aside from using variations on common phrases, this might be what chatbots need to build more rapport with patients and, in general, any user. Chatbots also don’t really understand tone of voice or the emotional subtext of language. Because they’re programmed to handle conversational cases specifically, they are typically not very good at answering open-ended “why” or “how” questions, which might lead down a tangent of irrelevance instead of an actual therapeutic conversation.

Unexpected duality of patient interaction

We found evidence that some patients prefer the anonymity of talking to a chatbot instead of to a therapist. When interacting with a chatbot, these patients shared sensitive and traumatic experiences, private information that they may not have revealed during an in-person clinical encounter.

 In a different study, however, patients using a chatbot became more open about their emotional states when they learned that a human being was reading the script; for these patients the human element was essential in fostering trust and enabling patients to open up about their internal life and emotional challenges.

 Today, it remains difficult to predict which patients will engage more effectively with a chatbot and which patients will prefer the traditional model of face-to-face clinical care.

Conveying the right amount of empathy is surprisingly difficult; too much and it may come across as fake and disingenuous, but too little and the chatbot may fail to build rapport with the patient. It is definitely hard for anyone to take a robot seriously when it tries to tell you, “I too have also struggled with depression.”

 Of the patients who do open up to a chatbot, some might develop a view of chatbots as emotional creatures. This view of chatbots could lead to an unhealthy attachment that impedes the patient’s ability to have a real-life connection with humans.

 Because there are so few data regarding the therapeutic alliance between patients and clinical tools in the digital age, we have yet to determine best practices for use of these digital tools, especially in vulnerable populations.

Possibility of diagnosis and intervention?

Our review also suggests that chatbots are not yet able to understand complex medical inquiries or make diagnoses. When asked about-or directly informed of-suicidal ideation, built-in smartphone chatbots we reviewed either did not provide an actionable intervention or offered inappropriate responses such as “Maybe the weather is affecting you.”

 Some chatbots have developed the capability to detect words like “suicide” and may suggest that the user contact crisis hotlines such as the National Suicide Prevention line. While there is potential for chatbots to help patients in distress, currently there isn’t a strong evidence-base showing that chatbots can effectively intervene when patients are in crisis.

Flaws aside, there is a growing abundance of ongoing research on chatbots in various roles within the mental health space. The field of psychiatry must quickly determine standards of reporting, evaluation, transparency, and replication before we can make any firm clinical decisions around the use of chatbots. The field should champion new legislature to ensure the confidentiality, privacy, security, liability, competency, and even the licensure of overseeing clinicians. Even if these chatbots aren’t the virtual therapists of tomorrow, you may soon see them in clinical decision support, data processing or entry, and even in managing the clinic’s schedule.

Dr Torous is Director and Ms Vaidyam is Technology Lead, Division of Digital Psychiatry, Beth Israel Deaconess Medical Center, Boston, MA. Dr Touros is also Digital Section Editor of Psychiatric Times. The authors report no conflicts of interest concerning the subject matter of this article.

 Vaidyam AN, Wisniewski H, Halamka JD, et al. Chatbots and conversational agents in mental health: a review of the psychiatric landscape. 

Gardiner PM, McCue KD, Negash LM, et al. Engaging women with an embodied conversational agent to deliver mindfulness and lifestyle recommendations: a feasibility randomized control trial. 

Tielman ML, Neerincx MA, Bidarra R, et al. A therapy for post-traumatic stress disorder using a virtual agent and virtual storytelling to reconstruct traumatic memories. 

 Bickmore T, Mitchell S, Jack B, et al. Response to a relational agent by hospital patients with depressive symptoms. 

 Bickmore TW, Puskar K, Schlenk EA, et al. Maintaining reality: relational agents for antipsychotic medication adherence. 

Tielman ML, Neerincx MA, Van MM, et al. How should a virtual agent present psychoeducation? Influence of verbal and textual presentation on adherence. 

 Miner AS, Milstein A, Schueller S, et al. Smartphone-based conversational agents and responses to questions about mental health, interpersonal violence, and physical health. 

While conversational agent technology is growing rapidly, the various technologies (chatbots) might not yet be fully equipped to help patients with clinical needs.

Chatbots: What Are They and Why Care?

2019 American Psychiatric Association (APA) Annual Meeting

 was digital mental health. In this two-part series, we asked presenters at the session “Revitalizing Psychiatry Through Engaging with Innovation to Increase Access and Inclusion with Care” to share some in-depth comments and thoughts with 

 covered social media use for youth, and app privacy and efficacy claims. In this article, the presenters discuss voice analytics for detecting and monitoring mood, and smartphone and web-based passive data as a digital biomarker for mental health disorders.

Professor Julien Epps addresses “Can We Diagnose Mental Illnesses Using Voice Data Collected From Phones?”

Speech production is not only the most complex coordination of neuromuscular activity in the entire body, but is sensitive to a vast range of influencing factors, including cognitive function, affective state, motor function, fatigue, and social context. Speech can also be conveniently collected non-invasively and non-intrusively at low cost via smartphone and has attracted research attention as a behavioral signal that is indicative of many psychiatric disorders.

Speech comprises two main components: linguistic-what is said-and acoustic-how it is said. To date, most research has focused on acoustic approaches. For example, insights about depressed speech include reductions in prosodic variation, spectral variability, vowel space area and speech rate, and increases in phone duration and motor incoordination. However, even features as simple as the duration of speech detected by a smartphone over a fixed period, as a proxy for social interaction, have been shown to be indicative of depression level.

Automatic speech-based assessment systems are likely to be applied to screening of the general population or to the monitoring of mental state within an individual (eg, in response to treatment), rather than to diagnosis. Because of the richness of information conveyed by speech, it contains many forms of unwanted variability: due to speaker identity, spoken content, and other factors unrelated to the disorder. Mitigation of these sources of variability is an active research area.

Many speech feature extraction approaches can run in a fraction of real time on a smartphone processor, or extracted features can be efficiently sent via network to a server to process. Similarly, many machine learning approaches are computationally feasible for smartphone platforms. Smartphones offer a unique opportunity to either elicit speech (via app) or process speech passively during everyday use. Elicitation methods include sustained vowels, read speech, diadochokinetic stimuli (eg, “pa-ta-ka”), interview, virtual human interview, and mood induction. However, tasks controlled for affect, articulatory effort, and linguistic complexity have been shown to help discriminate disorders more effectively based on speech.

Opportunities abound, including the possibility for regular minimal-cost assessment, longitudinal within-individual analysis, and integration with smartphone-based interventions or automatically cued therapy (eg, social rhythm therapy). Smartphones also offer the opportunity to crowdsource very large databases and hence develop a stronger evidence base. For more information, please contact 

“Can the Digital Data From Smartphone and Online Web Searches Indicate Early Signs of Severe Mental Health Issues, Including Suicide?” >>

Abhishek Pratap addresses “Can the Digital Data From Smartphone and Online Web Searches Indicate Early Signs of Severe Mental Health Issues, Including Suicide?”

The large-scale adoption of smartphones and online search engines (>5 billion queries a day) offers a unique opportunity for researchers to engage, assess, and monitor social, emotional, and behavioral states at the population level, in real time, with limited user burden, and at low cost. 

 show that adults in the US are spending more than 150 minutes on their phones daily, with more than 2500 average screen touches. There is 

 for utilizing this high-volume, high-velocity smartphone usage data (

) to assess mood disorders at the population level and on an 

Continuous passive data streams (eg, GPS) could offer the means to assess, contextualize, and trigger need-based survey assessments objectively without requiring the user to share sensitive location data. Geospatial contextual analysis pipeline (

) is a recent effort that is piloting ways to process and generate geospatial contextual features (eg, visiting a park, having coffee, spending time at home) onboard the user’s device without knowing the exact location.

Online information-seeking behavior (web searches) is another rich source of passively collected data that can potentially uncover health-related behavior based on the proximity and type of information sought by the user. In an on-going pilot study as part of 

 at the University of Washington, Seattle, search data with true labels (prior suicide attempts) show distinct trends before and after a confirmed suicide attempt event. This could offer an unparalleled opportunity to understand proximal risk factors for adults who are severely distressed or thinking of killing themselves and potentially provide an early intervention opportunity. You can find more work by Abhishek Pratap at: 

https://scholar.google.com/citations?user=qt2AE_4AAAAJ&hl=en

Dr Torous is Director of the Digital Psychiatry Division, Department of Psychiatry at 

. Dr Epps is Professor in Signal Processing and Deputy Head of School (Education), School of Electrical Engineering and Telecommunications, at 

 (University of New South Wales) in Australia. Abhishek Pratap is Principal Scientist, Digital Health, at 

Among the innovations presented at the 2019 APA meeting: voice analytics for detecting and monitoring mood, and smartphone and web-based passive data as a digital biomarker for mental health disorders.