Using Virtual Reality to Address Serious Mental Illness

OxfordVR Earns FDA’s Breakthrough Device Designation for its gameChange Treatment

Published in Lancet Psychiatry an automated virtual reality therapy program to treat agoraphobic avoidance and distress in patients with psychosis: a multicenter, parallel-group, single-blind, randomized, controlled trial in England was granted FDA’s Breakthrough Device Designation.

Oxford VR develops clinically validated, cost-effective, user-centred cognitive treatments for clinical conditions with significant impact on patients and the healthcare system.

Oxford VR’s developers are drawn from the gaming industry. They apply their animation, illustration and programming skills to help ensure the treatments are not only effective, but also engaging and easy to use. Each VR treatment uses high-quality simulations that promote the best clinical experience.

The Study

The clinical study assessed automated virtual reality therapy to treat agoraphobic avoidance and distress in patients with psychosis. It was a parallel-group, single-blind, randomized, controlled trial across nine National Health Service trusts in England. Eligible patients were aged 16 years or older, with a clinical diagnosis of a schizophrenia spectrum disorder or an affective diagnosis with psychotic symptoms, and had self-reported difficulties going outside due to anxiety. Patients were randomly assigned (1:1) to either gameChange VR therapy plus usual care or usual care alone. gameChange VR therapy was provided in approximately six sessions over 6 weeks. Trial assessors were masked to group allocation. Outcomes were assessed at 0, 6 (primary endpoint), and 26 weeks after randomization. The primary outcome was avoidance of, and distress in, everyday situations, assessed using the self-reported Oxford Agoraphobic Avoidance Scale (O-AS).

Results

A total of 346 were enrolled. 231 (67%) patients were men and 111 (32%) were women, 294 (85%) were White, and the mean age was 37·2 years (SD 12·5). 174 patients were randomly assigned to the gameChange VR therapy group and 172 to the usual care alone group. Compared with the usual care alone group, the gameChange VR therapy group had significant reductions in agoraphobic avoidance at 6 weeks.

Reductions in threat cognitions and within-situation defense behaviors mediated treatment outcomes. The greater the severity of anxious fears and avoidance, the greater the treatment benefits. There was no significant difference in the occurrence of serious adverse events between the gameChange VR therapy group (12 events in nine patients) and the usual care alone group (eight events in seven patients; p=0·37).

Automated VR therapy led to significant reductions in anxious avoidance of, and distress in, everyday situations compared with usual care alone. gameChange VR therapy has the potential to increase the provision of effective psychological therapy for psychosis, particularly for patients who find it difficult to leave their home, visit local amenities, or use public transport.

Sources:

Freeman D, Lambe S, Kabir T, et al. Automated virtual reality therapy to treat agoraphobic avoidance and distress in patients with psychosis (gameChange): a multicentre, parallel-group, single-blind, randomised, controlled trial in England with mediation and moderation analyses. Lancet Psychiatry 2022; 9: 375–88.Published Online. April 5, 2022. https://doi.org/10.1016/ S2215-0366(22)00060-8 

OxfordVR website

GamechangeVR website


AIfred Health Begins North American Clinical Trial of AI-based Clinical Decision Support Tool for MDD

This clinical trial, a world-first in the treatment of mental health using an AI-based clinical decision support tool, was designed with input from US and Canadian regulatory authorities to validate Aifred’s AI platform for use with patients suffering from moderate to severe depression.  

Aifred’s technology was developed using high quality clinical data from clinical trials evaluating therapeutic treatments of depression. Aifred’s software was developed with and for treating physicians (family doctors and psychiatrists) who today have limited tools to personalize the therapeutic choice for patients, leading to what is for many patients a lengthy and painful trial-and-error process. Aifred’s software is intended to support clinical decision making and improve this experience for patients and clinicians alike.

The trial is being conducted at up to 12 U.S. and Canadian centers of excellence for depression treatment including Veterans Affairs (VA) hospitals where Aifred is a VA research partner. Aifred expects to complete enrollment in 2022 and report top-line results in mid 2023. Aifred’s technology placed #1 in North America and #2 in the world in the IBM Watson AI XPRIZE, the goal is to initiate and complete this clinical trial which will provide clinicians across North America with a much-needed clinical tool. 

Aifred’s current patient <> physician clinical decision support tool is accessible on any device, supporting both telehealth and in-person appointments. A patient enters behavioral health information, which is then processed by a clinical algorithm based on best-evidence guidelines. Outputs help the physician understand: where the patient is on the disease cycle, monitor the patient over time, and determine ‘what to do next’ at each stage, e.g. adding psychotherapy or making adjustments to medication.

For additional information about this landmark clinical trial can consult: https://clinicaltrials.gov/ct2/show/NCT04655924  

Source: Aifred Health Website

Video of interviews by XPRIZE Foundation of unscripted comments by medical professionals working with Aifred [Link]

NICE’s Early Value Assessment for Medtech

The explosion in digital health products has left National Health Service commissioners in the UK wondering how they can possibly sift out what works and what provides maximum benefit for the service and for patients.

The Early Value Assessment for Medtech will offer a rapid assessment of digital products, devices and diagnostics for clinical effectiveness and value for money. The goal of this new approach is that the service and patients will be able to benefit sooner.

Early Value Assessment is being designed to draw in the most promising and impactful medical technologies where the evidence base is still emerging, starting with digital products, in areas where there is greatest need.  Whether its empowering patients to better manage their own health and seek clinical advice, reducing admissions and waiting lists or supporting clinicians and other front-line staff to provide better quality care this new program will help to alleviate system pressures as the NHS recovers from the COVID pandemic.

In this accelerated approach, the first two pilot digital health topics will begin their early value assessments this month (June) with a view to publishing findings in October. This is much faster than a full NICE Medtech evaluation meaning benefits will be realized sooner, while companies generate more evidence required for a full NICE evaluation at a later stage.  

The first two pilots are digital apps for depression and anxiety in children and others will quickly follow in adult mental health, early cancer diagnosis, cardiovascular disease and other areas that support elective recovery following the pandemic.

In this ‘fast-track’ approach, NICE is working closely with NHS England and all its system partners to help develop commercial and data collection arrangements to support the technologies that go through early value assessment in adoption and scaling and to make this new program of work deliver on the potential of digital health for patients.

Source: NHS Blog

Rethinking Time Spent on Social Media: Exploring Dissociation

People sometimes experience daydreaming or become engrossed in reading a page of a book and then realize that their mind was somewhere else, occupied in an unrelated train of thought. In a similar way, many have become completely absorbed in a movie or computer game, resulting in losing track of external stimuli.  These experiences are described as normative dissociation.

Researchers at the University of Washington wondered if people enter a similar state of dissociation when surfing social media, and if that explains why users might feel out of control after spending so much time on their favorite app. (There are multiple types of dissociation including trauma-based dissociation and the everyday dissociation associated with spacing out or focusing intently on a task)

A study presented at the recent CHI Conference on Human Factors in Computing Systems entitled “I Don’t Even Remember What I Read”: How Design Influences Dissociation on Social Media observed how participants interacted with a Twitter-like platform to show that some people are spacing out while they’re scrolling. Researchers also designed intervention strategies that social media platforms could use to help people retain more control over their online experiences. 

The research team designed and built an app called Chirp, which was connected to participants’ Twitter accounts. Through Chirp, users’ likes and tweets appear on the real social media platform, but researchers can control people’s experience, adding new features or quick pop-up notices or surveys. 

Researchers asked 43 Twitter users from across the U.S. to use Chirp for a month. For each session, after three minutes users would see a dialog box asking them to rate on a scale from one to five how much they agreed with this statement: “I am currently using Chirp without really paying attention to what I am doing.” The dialog box continued to pop up every 15 minutes. 

“We used their rating as a way to measure dissociation,” lead author Baughan said. “It captured the experience of being really absorbed and not paying attention to what’s around you, or of scrolling on your phone without paying attention to what you’re doing.”

Over the course of the month, 42% of participants (18 people) agreed or strongly agreed with that statement at least once. After the month, the researchers did in-depth interviews with 11 participants. Seven described experiencing dissociation while using Chirp. 

In addition to receiving the dissociation survey while using Chirp, users experienced different intervention strategies. The researchers divided the strategies into two categories: changes within the app’s design (internal interventions) and broader changes that mimicked the lockout mechanisms and timers that are available to users now (external interventions). Over the course of the month, participants spent one week with no interventions, one week with only internal interventions, one week with only external interventions and one week with both.  

When internal interventions were activated, participants got a “you’re all caught up!” message when they had seen all new tweets. People also had to organize the accounts they followed into lists. 

For external interventions, participants had access to a page that displayed their activity on Chirp for the current session. A dialog box also popped up every 20 minutes asking users if they wanted to continue using Chirp. 

In general, participants liked the changes to the app’s design. The “you’re all caught up!” message together with the lists allowed people to focus on what they cared about. 

The problem with social media platforms, the researchers said, is not that people lack the self-control needed to not get sucked in, but instead that the platforms themselves are not designed to maximize what people value.

“Taking these so-called mindless breaks can be really restorative,” Baughan said. “But social media platforms are designed to keep people scrolling. When we are in a dissociative state, we have a diminished sense of agency, which makes us more vulnerable to those designs and we lose track of time. These platforms need to create an end-of-use experience, so that people can have it fit in their day with their time-management goals.”

Study:
Baugnan A, Zhang MR, Rao R, et al. “I Don’t Even Remember What I Read”: How Design Influences Dissociation on Social Media. CHI ’22: CHI Conference on Human Factors in Computing Systems. April 2022 Article No.: 18, Pages 1–13 https://doi.org/10.1145/3491102.3501899

[Link to slides with audio of presentation at CHI Conference 5/22]

Don’t Blame Social Media for the Decrease In Face-to-Face Interaction.

An new article in Current Opinion in Psychology reviews the best available evidence to debunk the “social displacement hypothesis” that holds that use of mobile and social media is the cause of decreased face-to-face (FtF) interaction. Lead author Jeffrey Hall, PhD has uncovered a worrisome trend: In the United States, Great Britain and Australia, there has been a steady, uniform decline in FtF time that began well before the rise of social media. This new analysis shows the decline continued through the stay-at-home orders and social distancing of the COVID-19 pandemic.

Dr. Hall, a professor of communication studies and director of the Relationships and Technology Lab at the University of Kansas, and his co-author, Dong Liu of Renmin University in China, take on that notion in a new paper titled “Social media use, social displacement, and well-being” 

The ‘social displacement hypothesis’ is probably the most well-known, long-lasting explanation that blames the new technologies (especially texting and social media) for usurping everyone’s time away from person-to-person contact. Hall states that “the best available evidence suggests that it’s just not so.”

Hall took data on FtF time from the U.S. Department of Labor’s annual American Time Use Survey and from similar governmental studies in Australia and Great Britain between 1995 and 2021 and plotted them on a single chart. Interestingly, all three lines decline over time at a similar rate.

According to Hall,  “it’s the case that social media rates of consumption have grown across demographic groups and across the world. Yes, it’s the case that face-to-face time has declined. However, it’s not the case it takes from face-to-face time.”

If the evidence doesn’t support the social displacement theory, then where is the time for increased social media use coming from?

The paper highlights that there has been a transformation of where people are putting their attention. While it is true that TikTok and YouTube are increasingly popular outlets for watching streaming content, Hall suggests social media time is most likely borrowing from time spent watching TV, which, for decades, has been a major place where Americans spend their time. “Social-media time is also borrowing from time at work or doing household chores” Hall said.

Similar Data In 3 Countries

The paper reports a new analysis showing that FtF time has declined across three countries in a similar fashion. “The fact that the UK data track U.S. data so tightly despite using slightly different methods in different years, is surprising,” Hall said. This international trend of reduced time in face-to-face communication may reflect growing rates of loneliness.

Hall’s analysis shows that these trends of declining face-to-face communication existed well before the pandemic, and the pandemic may have exacerbated some of them. When people had some time back because they weren’t commuting to work or able to go out as much, they didn’t turn to face-to-face communication. “What’s discouraging about that,” Hall notes, “is even when people have time, they don’t seem to use it in a way that promotes their social health.” Noting the widespread evidence that FtF socialization is beneficial to well-being, “we’re not on the right path to being able to reclaim that face-to-face time,” said Hall, “at least in these three nations.”

Why is FtF time declining?

“The best available evidence suggests face-to-face is in competition with hours spent at work and commuting,” Hall says. In other words, people who work longer spend more of their leisure time alone. During the pandemic, when people got that time back from commuting, “they still spent it working virtually,” Hall said. “They didn’t spend it socializing with each other.”

And, Hall says, friendship and social media are not enemies: “Social media can be used in many friendship-promoting ways, especially now that many people use messaging programs supported by social media platforms.” As the paper claims, “social people are active both online and offline.”   

“It seems we live in a society that privileges working and media consumption over everything else,” Hall said. “The decline in face-to-face time is a matter of priority and a matter of availability. And we are neither prioritizing face to face time, nor are we available to do so.”

Source: Hall JA, Lui D. Social media use, social displacement, and well-being. Current Opinion in Psychology. Volume 46, August 2022, 101339

Patient influencers’ the new frontier in direct-to-consumer drug marketing

Pharma companies are increasingly partnering with patients to share stories and advocate for brands online. 

It began in 2015, when a celebrity influencer named Kim Kardashian was pregnant and began singing the praises of a new morning sickness drug called Diclegis to her tens of millions followers on Instagram.

In addition to a selfie and picture of the pill bottle, she wrote, “It’s been studied and there’s no increased risk to the baby, I’m so excited and happy with the results.” The Food and Drug Administration swiftly flagged the post for omitting risks, and required Kardashian to remove the post and sent the drug maker a serious warning letter.

But seven years later, so-called patient influencers are alive and well, with pharmaceutical companies increasingly partnering with real-life patients who share their personal stories and advocate for brands online.

A Trend Again?

This trend has drawn the attention of Erin Willis, an associate professor of Advertising, Public Relations and Media Design at CU Boulder. In a new paper, published in the Journal of Medical Internet Research, she calls on the academic community to take a closer look. “This is a growing phenomenon, but there is virtually no research on it and very little regulation,” said Willis, who is interviewing dozens of patient influencers for a new study. “Is it going to help patients be better informed? Or is it going to get patients to ask their doctors for drugs they don’t really need? We just don’t know, because no one has studied it.”

New twist on ‘direct to consumer’ marketing

In one of the first academic papers to date to explore the phenomenon, Willis and co-author Marjorie Delbaere, a professor of marketing at the University of Saskatchewan, framed patient influencers as “the next frontier in direct-to-consumer (DTC) pharmaceutical marketing.”

This controversial form of marketing, which is legal only in the United States and New Zealand, enables drug companies to target consumers directly, rather than through physicians. Since the first DTC ad ran in the 1980s, the ads have exploded, leading patients to ask their doctors about drugs they see on TV or in print. As Willis notes, aproximately 44% who ask their doctor about a drug, get it.

Having learned from the Kardashian incident, many ad agencies now avoid celebrity influencers altogether and instead engage “micro-influencers” like individual patients who share their personal stories and endorsements in condition-specific support groups (diabetes, heart disease, etc.) or those with a niche social media following.

“It’s a lot like what we used to see with doctors and pharmaceutical companies,” said Willis. “Only now it is patients using social media to advocate for disease awareness, and in some cases—pharmaceutical medications.”

A blurring of the lines between ad and opinion

The Federal Trade Commission (FTC) now requires that patient influencers disclose whether they are being paid (influencers use #ad or #sponcon to alert followers). And the FDA has published rules about what can and cannot be said on social posts. But such rules are open to interpretation and hard to enforce, said Willis.

The authors also have concerns that “a blurring of the lines” between ad and opinion could potentially deceive patients.

Unlike other forms of DTC advertising, social media is interactive.

“If an influencer recommends a drug, there is an entire community of voices that get to weigh in on it and support it or share their negative experiences,” said Willis.

Thus far in her interviews of patient influencers, Willis said she has found that only a small number  are paid to post (some get free trips to conferences or are paid to sit on advisory boards). Some aren’t paid at all.

“They all say they are really doing this so that other patients have information and can have a better life,” said Willis. “That is their No. 1 motivation and I think that’s awesome.”

She said she hopes that her work, funded in part by the Arthur W. Page Center for Integrity in Public Communication, and the new research agenda she has launched, will lead to a set of best practices for both patient influencers and the companies they work with.

“There is both value and risk in this growing trend and, like anything, it has the potential to become dangerous if we’re not careful,” Willis said.

Source: Willils E, Delbaere M. Patient Influencers: The Next Frontier in Direct-to-Consumer Pharmaceutical Marketing. JMIR Published on 1.3.2022 in Vol 24, No 3 (2022): March

A Study To Understand The Lack Of Diversity In The Use Of Fitness Trackers.

As the world continues to become increasingly connected, mobile devices have become ubiquitous. Wearable devices, including fitness trackers provide nearly continuous information on physical activity, heart rate, and sleep. As the use of these monitoring increases, data are increasingly integrated into clinical and research settings. There is emerging evidence that fitness trackers can identify changes in heart rate variability, and other symptoms including the potential to identify COVID-19 prior to a clinical diagnosis.

Unfortunately, an understanding of how digital health technologies can be used for equitable healthcare across diverse communities is needed.  

It seems that most people who use smartwatches and other wearable devices that can track health are white, well-educated, and wealthy. 

Recent research published in Nature’s NPJ Digital Medicine Journal, intentionally included groups that are historically underrepresented in medical research e.g. lower-income groups and racial minority groups. The goal was to find out the reasons for lack of interest or reduced adoption of fitness trackers.

The study was conducted by researchers at the All of Us Research Program, an initiative at the National Institutes of Health aiming to build a health database that’s representative of the United States. As part of the program, the researchers wanted to let program participants send health data directly from Fitbit devices. They found, though, that the demographics of the people who decided to send data were whiter and wealthier than the racial and socioeconomic diversity of the project as a whole.

To figure out why, the team surveyed over 1,000 patients at six Federally Qualified Health Centers, which provide medical care to underserved communities. Around 40 percent of the people who responded identified as Hispanic, 36 percent as non-Hispanic Black or African American, and 15 percent as non-Hispanic white. Two-thirds of the surveys were done in English, and one-third were done in Spanish. Most had a high school education or less.

Over half of the people who responded to the survey said that they’d be interested in a fitness tracker, saying that they’d be interested in things like tracking their steps or heart rate.

Of the group that was interested, 49 percent said that they don’t have a tracker because they’re too expensive. Almost 20 percent said that they don’t know how to use them, and 15 percent said that they don’t know how a tracker could help — but want to learn.

The research team also found that language barriers can dissuade people from using a smartwatch: many Spanish-speaking participants were concerned by the use of “tracker” to describe the devices and thought that their movements would be monitored.

As more and more health features get built into wearable devices, they’re becoming a major tool used both for individual people’s health and for medical research. But if groups like the ones served by Federally Qualified Health Centers are shut out from the products, smartwatches just end up reinforcing existing equity gaps in healthcare and in health research. When groups aren’t represented in studies, results can’t be generalized to those groups, and they miss out on the benefits of new findings.

Source: Hook M, Litwin TR, Munoz F, et al. Wearable fitness tracker use in federally qualified health center patients: strategies to improve the health of all of us using digital health devices. npj Digital Medicine Vol 5, Article number:53 (2022).

Americans Cautious About Advances in Artificial Intelligence and Human Enhancement Technologies

A new Pew Research Center survey finds that Americans believe that AI and human enhancements via technology have the potential to improve daily life and human abilities. Yet public views are also cautiously defined by 1) the context of how these technologies would be used, 2) what constraints would be in place and 3) who would stand to benefit – or lose – if these advances become widespread.

Public caution is mostly centered around concerns about privacy, autonomy, unintended consequences and the amount of change these developments might mean for humans and society.

This survey looks at a broad arc of scientific and technological developments – some in use now, some still emerging. Three highlight the burgeoning array of AI applications: the use of facial recognition technology by police, the use of algorithms by social media companies to find false information on their sites and the development of driverless passenger vehicles.

Another three are often described as types of human enhancements, revolve around developments tied to the convergence of AI, biotechnology, nanotechnology and other fields. They raise the possibility of dramatic changes to human abilities in the future: computer chip implants in the brain to advance people’s cognitive skills, gene editing to greatly reduce a baby’s risk of developing serious diseases or health conditions, and robotic exoskeletons with a built-in AI system to greatly increase strength for lifting in manual labor jobs.

Americans are far more positive than negative about the widespread use of facial recognition technology by police to monitor crowds and look for people who may have committed a crime: 46% of U.S. adults think this would be a good idea for society, while 27% think this would be a bad idea and another 27% are unsure.

By narrower margins, more describe the use of computer algorithms by social media companies to find false information on their sites as a good rather than bad idea for society (38% vs. 31%), and the pattern is similar for the use of robotic exoskeletons with a built-in AI system to increase strength for manual labor jobs (33% vs. 24%).

The survey of 10,260 U.S. adults was conducted between Nov. 1 and 7, 2021. There are five key themes that run through people’s answers on these questions.

  1. Americans’ judgments about the potential impact of this set of applications are varied and, for portions of the public, marked by uncertainty. [Link to graphic]
  2. Less than half of the public believes these technologies would improve things over the way they are now. [Link to graphic]
  3. Americans see a need for higher standards to assess the safety of technologies on the horizon than are currently used. [Link to graphic]
  4. There are sharp partisan divisions when people think about possible government regulation of these new and developing technologies.
  5. There are mitigating steps people say would make these AI and human enhancement developments more acceptable. [Link to graphic]

Source: Pew Research

AI and Human Enhancement: Americans’ Openness Is Tempered by a Range of Concerns

Mayo Clinic launches AI startup program to help early-stage companies get market-ready

Mayo Clinic launched its artificial intelligence startup program this week with four early-stage health tech companies. The program also features additional expert assistance from Google and electronic health records giant Epic.

This is a 20-week program called Mayo Clinic Platform_Accelerate. The aims are to help AI-based startups get market-ready by offering access to Mayo Clinic experts in regulatory, clinical, technology and business domains with a focus on AI model validation and clinical readiness.

According to John Halamka, M.D., president of the Mayo Clinic Platform, “Health tech startups are critical contributors to the cycle of innovation. We are excited to collaborate with these innovators to solve some of the most complex problems in medicine today.”

Mayo Clinic says its AI startup program is different from other typical accelerator programs. It focuses on helping drive a company’s success with valuable in-kind investments—from data sets to validation tools and from mentorship to clinical workflow planning, the company said on the program website.

As part of this in-kind investment, Mayo Clinic Platform will take an equity position in participating startups based on most recent valuations or a convertible note or SAFE, the organization said.

The four participating companies will work with data science experts to delineate AI model requirements, check for fairness and bias in their AI models and gain an understanding of the Food and Drug Administration clearance pathways.

The startups also will gain access to de-identified Mayo Clinic patient data, conduct model validation with guidance from data science experts, plan clinical validation studies such as clinical simulation or clinical trials and explore the potential to partner with Mayo.

Link: Mayo Clinic Platform_Accelerate

Predicting Early Antidepressant Outcomes For Children and Adolescents with MDD Using AI

Mayo Clinic researchers have taken the first step in using artificial intelligence (AI) to predict early outcomes with antidepressants in children and adolescents with major depressive disorder, in a study published in The Journal of Child Psychology and Psychiatry.

In the study, researchers identified variation in six depressive symptoms: difficulty having fun, social withdrawal, excessive fatigue, irritability, low self-esteem and depressed feelings.

They assessed these symptoms with the Children’s Depression Rating Scale-Revised to predict outcomes to 10 to 12 weeks of antidepressant pharmacotherapy:

  • The six symptoms predicted 10- to 12-week outcomes at four to six weeks in fluoxetine testing datasets, with an average accuracy of 73%.
  • The same six symptoms predicted 10- to 12-week outcomes at four to six weeks in duloxetine testing datasets, with an average accuracy of 76%.
  • In placebo-treated patients, predicting response and remission accuracy was significantly lower than for antidepressants at 67%.

According to the researchers, ‘these outcomes show the potential of AI and patient data to ensure children and adolescents receive treatment that has the highest likelihood of delivering therapeutic benefits with minimized side effects. We designed the algorithm to mimic a clinician’s logic of treatment management at an interim time point based on their estimated guess of whether a patient will likely or not benefit from pharmacotherapy at the current dose,” says Dr. Athreya, lead author. “Hence, it was essential for me as a computer engineer to embed and observe the practice closely to not only understand the needs of the patient, but also how AI can be consumed and useful to the clinician to benefit the patient.”

This preliminary work suggests that AI has promise for assisting clinical decisions by informing physicians on the selection, use and dosing of antidepressants for children and adolescents with major depressive disorder,” says Paul Croarkin, D.O., a Mayo Clinic psychiatrist and senior author of the study. “We saw improved predictions of treatment outcomes in samples of children and adolescents across two classes of antidepressants.”

Key points from the study

  • The optimal treatment of depression in children and adolescent is a substantial public health problem.
  • Machine learning and probabilistic graphical models were used to predict treatment outcomes with antidepressants in a training and testing databases.
  • Variation in six depression symptoms predicted outcomes with fluoxetine or duloxetine.
  • Future work should augment probabilistic graphical models with biological data to refine tools to assist decision making in clinical practice.

This work was a collaborative effort between the departments of Molecular Pharmacology and Experimental Therapeutics, and Psychiatry and Psychology, at Mayo Clinic, with support from Mayo Clinic’s Center for Individualized Medicine.

Study:
Athreya AP, Vande Voort JL, Shekunov J, et al. The Journal of Child Psychology and Psychiatry. 15 March 2022