Machine Learning/AI Can ID People Who Need Specialist Care for Depression

Researchers have created decision models to predict which patients might need more treatment for their depression than what their primary care provider can offer. Scientists say the algorithms are specifically designed to provide information the clinician can act on and fit into existing clinical workflows.

Experts note that depression is the most commonly occurring mental illness in the world. The World Health Organization estimates that it affects about 350 million people. The illness may vary in intensity ranging from a relatively mild mood disorder to advanced or severe depression.

Some people may be able to manage their depression on their own or with guidance from a primary care provider. However, others may have more severe depression that requires advanced care from mental health care providers.

Scientists at Regenstrief Institute and Indiana University created algorithms to mine the electronic health record and identify individuals who would benefit from advanced care. The information system then provides primary care providers a notice so that they can refer the the individual to appropriate mental health specialists.

“Our goal was to build reproducible models that fit into clinical workflows,” said Suranga N. Kasthurirathne, Ph.D., first author of the paper and research scientist at Regenstrief Institute.

“This algorithm is unique because it provides actionable information to clinicians, helping them to identify which patients may be more at risk for adverse events from depression.”

The algorithms combined a wide variety of behavioral and clinical information from the Indiana Network for Patient Care, a statewide health information exchange. Dr. Kasthurirathne and his team developed algorithms for the entire patient population, as well as several different high-risk groups.

“By creating models for different patient populations, we offer health system leaders the option of selecting the best screening approach for their needs,” said  Kasthurirathne.

“Perhaps they don’t have the computational or human resources to run models on every single patient. This gives them the option to screen select high-risk patients.”

“Primary care doctors often have limited time, and identifying patients with more severe forms of depression can be challenging and time consuming. Our model helps them help their patients more efficiently and improve quality of care simultaneously,” said Shaun Grannis, M.D., M.S., a co-author.

“Our approach is also well-suited to leverage increasing health information technology adoption and interoperability to enable preventive care and improve access to wraparound health services,” said Grannis.

The study appears in the Journal of Medical Internet Research.

Source: Regenstrief Institute/EurekAlert

New Tech Methods to Combat Online Domestic Abuse

Researchers have developed a new tool to systematically and effectively detect online abuse and then take remedial action to protect victims.

Working with the New York City Mayor’s Office to End Domestic and Gender-Based Violence, Cornell Tech researchers created and piloted a questionnaire, a spyware scanning tool and a diagram for assessing clients’ digital footprints.

Investigators explain that the first-of-its-kind model can help counselors without tech expertise pinpoint online abuse and protect the safety of abuse victims and their advisers. Using this strategy, researchers found potential spyware, compromised accounts or exploitable misconfigurations for 23 of the 44 clients they advised.

“Prior to this work, people were reporting that the abusers were very sophisticated hackers, and clients were receiving inconsistent advice,” said Diana Freed, a doctoral student in the field of information science. Freed is the co-lead author of “Clinical Computer Security for Victims of Intimate Partner Violence,” a paper presented at the USENIX Security Symposium in Santa Clara, California.

“Some people were saying, ‘Throw your device out.’ Other people were saying, ‘Delete the app.’ But there wasn’t a clear understanding of how this abuse was happening and why it was happening,” Freed said.

“We felt that a methodical approach through a uniform, data-driven consultation would yield better results so we can help other advocates do this type of work at the level it’s needed.”

Co-first author of the paper is Sam Havron, a Cornell Tech doctoral student in computer science, senior authors are Drs. Nicola Dell, an assistant professor and associate professor Thomas Ristenpart.

The authors are among the researchers from Cornell Tech and New York University collaborating to improve technological safety and security for survivors of intimate partner violence. Dell and Ristenpart were recently awarded a $1.2 million grant from the National Science Foundation to continue their research examining the role of tech in intimate partner abuse.

Abusers use a range of digital tools to stalk or harass their victims, from traditional spyware to tracking apps intended for more benign purposes, like finding one’s phone.

Authorities confess that it can be extremely challenging to detect vulnerabilities amid the sheer number of apps, digital devices and online accounts most people use daily – particularly for counselors without tech skills.

“They were making their best efforts, but there was no uniform way to address this,” Havron said. “They were using Google to try to help clients with their abuse situations.”

At the same time, tech experts don’t have the background to advise clients how to fix problems in ways that won’t endanger them, such as angering an abuser who just noticed a deleted app or a changed password.

The researchers run a weekly tech clinic in New York City’s Family Justice Centers, which provide a full range of services for intimate partner abuse victims. Through this work, the team developed and piloted its Technology Assessment Questionnaire, which includes such questions as, “Does the abuser show up unexpectedly or know things they shouldn’t know?” and “Is there a chance the abuser knows (or could guess) the answers to your password reset questions?”

They also created the “technograph,” a diagram which helps summarize clients’ digital assets; and ISDi (IPV Spyware Discovery), a spyware scanning tool.

ISDi scans devices for known spyware apps through a USB cable, rather than a downloadable app, making it impossible for an abuser to detect.

“This sort of tool doesn’t exist anywhere else,” Havron said. “In earlier work, we did a comprehensive scrape of the Google Play Store and eventually compiled a list of thousands of apps across marketplaces, and that’s what the ISDi is based on.”

The questionnaire, technograph and ISDi are all freely available on the project team’s website.

Though the paper focused on intimate partner abuse, this method could be useful for any victims of online abuse, such as activists, dissidents or journalists, the researchers said.

“It’s consistent, it’s data-driven and it takes into account at each phase what the abuser will know if the client makes changes,” Freed said.

“This is giving people a more accurate way to make decisions and providing them with a comprehensive understanding of how things are happening.”

Source: Cornell University

Virtual Reality Body Swapping an Effective Tool for Talking Through Issues

It is common for a person to be much better at giving useful advice to a friend in trouble than they are in dealing with their own problems. Researchers explain that although we usually have continuous internal dialogue, we become trapped inside our own way of thinking with our own history and point of view.

A research team from the University of Barcelona (UB), IDIBAPS and Virtual BodyWorks, is using immersive virtual reality to observe the effects of talking to ourselves as if we were another person.

In a new study, published in the journal Scientific Reports, researchers discovered that a conversation with oneself embodied as Dr. Sigmund Freud was more effective than talking with Freud about personal problems in a virtual conversation with pre-scripted comments.

The study researchers suggest the method could be used by clinicians to help people dealing with minor personal problems.

The study was led by Mel Slater and Solène Neyret, researchers at the Experimental Virtual Environments Lab for Neuroscience and Technology (Event Lab) at UB and, clinical psychologist Guillem Feixas, of the UB Department of Clinical Psychology and Psychobiology.

Previous studies developed by this research team have shown that when we adopt a different body using virtual reality, we change our behavior, attitude and perception of things.

“We showed earlier that it is possible for people to talk to themselves as if they were another person, body swapping to two different avatars, and that participants’ mood and happiness improved.

However, we didn’t know whether this was due to simply the participant talking about their problem or whether the virtual body swapping really made a difference,” said Mel Slater, also a member of the research team.

In order to test the body swapping idea, researchers compared one group who talked to themselves first embodied as the participant and then body swapping to a virtual Sigmund Freud; and a control group who spoke to the virtual Freud, but in this case, Freud responded with pre-scripted questions and comments (there was no body swapping).

For this method, researchers scanned the person to obtain an ‘avatar’ which is a 3D-likeness of the person.

In virtual reality, when they look at themselves, at their body parts, or in a mirror, they will see a representation of themselves. When they move their real body, their virtual body will move in the same way and at the same time. Seated across the table is another virtual human, in the case of this experiment, a representation of Freud.

The participant can explain their personal problem to Freud and then switch to being embodied as Freud. Once embodied as Freud, they will see Freud’s body rather than their own, and this Freud body will move in synchrony with their own movements.

“They will see and hear their own likeness explaining the problem, and they see their virtual self as if this were another person. Now they themselves have become the ‘friend’ who is listening and trying to help,” said Mel Slater.

While embodied as Freud, and after perceiving a strong likeness of themselves describing a problem, they can respond, as Freud, back to themselves and ask a question or help the person (themselves) find a solution.

After this, they are embodied once again in their own body and they can see and hear Freud’s answer. Although it was really themselves who had spoken through Freud, their voice will be disguised as Freud’s. They can keep switching back and forth between the two bodies and have a conversation with themselves.

Researchers discovered the technique greatly helped participants deal with personal problems.

Specifically, one week after the completion of the experiment more than 80 percent of participants in the body swapping group reported a change with respect to their problem, compared to less than 50 percent in the control group.

“We found that those in the body swapping group got better knowledge, understanding, control, and new ideas about their problem compared to the control group,” said Slater.

Participants were guided by clinical psychologist Tania Johnston about how to formulate their problem. Therefore, a limitation to the study is that researchers do not know whether this method could be used without this prior clinical advice, and the extent to which the clinician could be incorporated into the virtual reality as part of the procedure.

However, researchers believe that this method could be a useful tool for clinicians.

“Now that virtual reality is available as a consumer product, with high quality at less than the cost of a good Smartphone, this method could be widely used by clinicians, for example, by giving ‘homework’ to their clients to carry out this type of method at home,” said Slater.

Source: University of Barcelona

Online Self-Management Helpful for Anxiety, Depression and Pain

Emerging research suggests that for some individuals, online symptom self-management plus clinician telecare is the best strategy for treating anxiety, depression and pain.

As a background, it is well documented that pain is the most common physical symptom for which adults seek medical attention in the United States. Moreover, anxiety and depression are the most common mental health issues for which adults visit a doctor. We also now understand that medications, especially opioids for pain, may not be the only or best therapy.

In the new study, Regenstrief Institute research scientist Kurt Kroenke, M.D., a pioneer in the treatment of patient symptoms, discovered online symptom self-management or online symptom self-management plus clinician telecare can be effective solutions for individuals with anxiety, depression and pain.

“Pain, anxiety and depression can produce a vicious cycle in which the presence of one symptom, if untreated, may negatively affect the response to treatment of the other two symptoms,” said Dr. Kroenke.

“So treating not just pain, but pain and mood symptoms simultaneously is quite important, as is doing it how, when and where the patient is most receptive.”

In the study, published in the Journal of General Internal Medicine, Dr. Kroenke and colleagues discovered that online symptom self-management works to decrease pain, anxiety and depression symptoms. They also found that online symptom self-management works even better when coupled with clinician telecare.

Prior studies have found a benefit to adding telecare to usual care in the doctor’s office. The researchers have now shown that the intermediate (and less costly) mechanism of online pain and mood self-management is effective and, for some, even more effective when coupled with live phone follow-up with a nurse.

“The magnitude of effect on pain, anxiety and depression we report is comparable to the effect of online and telecare interventions for chronic disorders like hypertension, diabetes and heart disease,” said Dr. Kroenke.

“The moderate improvement in symptoms we saw at a group level indicates that some individuals had great symptom improvement while others had little improvement.

Our results strongly suggest that web-based self-management might be enough for some patients while others may require a combination of online self-management and phone consultations with a nurse manager in order to experience symptom reduction.”

To test whether pain, anxiety and depression symptoms could be simultaneously addressed by patients in their homes or other location of their choice, Dr. Kroenke and colleagues conducted the CAMMPS (Comprehensive vs. Assisted Management of Mood and Pain Symptoms) trial.

This randomized comparative effectiveness study builds upon previous research, including the design of widely used depression and anxiety screening tools, and the conduct of several studies demonstrating the effectiveness of telecare.

For the study, a total of 294 individuals with arm, leg, back, neck or widespread pain which persisted (for 10 or more years in more than half of participants) despite medication, who also had at least moderately severe depression and anxiety, were divided into two groups.

One group received a web-based self-management program comprised of nine modules (coping with pain; pain medications; communicating with providers; depression; anxiety; sleep; anger management; cognitive strategies; and problem-solving).

The other group was given this program plus telecare by a nurse who made scheduled telephone calls as well as contacts prompted by patient responses to the online self-management program or e-mail requests.

A supplementary paper, published in the journal Telemedicine and Telecare, reports that participants in both arms of the study found it helpful and were satisfied. They also discovered higher satisfaction in the group that received both online self-management and telecare.

While those in the online self-management group indicated they wanted more human contact, participants in the group that received telecare from a nurse were divided — some wanted more contact, others desired less contact.

This finding led the paper’s authors, including first author Michael A. Bushey, M.D., of the Indiana School of Medicine and senior author Dr. Kroenke, to conclude that customizable solutions would best suit a range of patients.

Source: Regenstrief Institute

Smartphone Games May Ease Work Stress Better Than Mindfulness Apps

A new U.K. study finds that digital games, typical of those used on smartphones, may outperform mindfulness apps when it comes to relieving work-related stress.

Researchers from University College London (UCL) and the University of Bath gave a 15-minute math test to 45 student participants, ages 19 to 36, to induce a sense of work strain.

Next, the participants played either a shape-fitting game called “Block! Hexa Puzzle” or used the Headspace mindfulness app for 10 minutes. Participants in the control group were given a fidget-spinner toy.

In a survey before and after using the game, app or toy, the volunteers rated on a four-point scale how tired and energetic they felt.

According to the findings, published in the journal JMIR Mental Health, participants who played the shape-fitting game reported feeling more energized and less tired afterwards, while those in the mindfulness and fidget-spinner groups reported the opposite: Their level of “energetic arousal” appeared to decline.

In a second part of the study, a different group of 20 participants played either the shape-fitting game or used the Headspace mindfulness app after arriving home from work for five days straight. After finishing the activities, the participants completed an online survey.

While no differences were found between the two groups in terms of how energized participants felt, the shape-fitting game appeared to offer increasing benefits throughout the week in terms of “recovery experience” — that is, to what degree participants felt relaxed, detached, in control and able to improve their skills.

This was measured by asking participants to what extent they agreed with statements such as “During the activity, I forgot about work.” Surprisingly, participants who followed a beginners’ course on the Headspace mindfulness app scored progressively less well on this measure throughout the five days.

“Far from feeling guilty about being absorbed by their phone, people who play such games after a stressful day at work should know they are likely to be gaining a real benefit,” said study co-author Professor Anna Cox from UCL Interaction Centre.

The authors noted that digital games appear to fulfill four criteria necessary for post-work recovery: they tend to be relaxing, they provide opportunities for mastering a new skill, they are highly immersive and distracting, and they allow people to feel in control.

The researchers also noted that the level of enjoyment of the digital game was tied to the amount of benefit it offered in terms of post-work recovery.

“To protect our long-term health and well-being, we need to be able to unwind and recuperate after work,” said lead author Dr. Emily Collins from the University of Bath, who started the research while at UCL. “Our study suggests playing digital games can be an effective way to do this.”

Source: University of Bath



Loneliness, Social Anxiety May Bode Ill for Dating App Outcomes

A new study discovers loneliness and social anxiety can be a bad combination for single people who use dating apps on their phones. Ohio State University researchers discovered that people who fit that profile were more likely than others to say they’ve experienced negative outcomes because of their dating app use.

“It’s not just that they’re using their phone a lot,” said Kathryn Coduto, lead author of the study and doctoral student in communication at The Ohio State University.

“We had participants who said they were missing school or work, or getting in trouble in classes or at work because they kept checking the dating apps on their phones.”

Coduto said it is a problem she has seen firsthand.

“I’ve seen people who use dating apps compulsively. They take their phones out when they’re at dinner with friends or when they’re in groups. They really can’t stop swiping,” she said.

The study appears online in the Journal of Social and Personal Relationships with a print edition forthcoming.

For the investigation, participants were 269 undergraduate students with experience using one or more dating apps. All answered questions designed to measure their loneliness and social anxiety (for example, they were asked if they were constantly nervous around other people).

Compulsive use was measured by asking participants how much they agreed with statements like “I am unable to reduce the amount of time I spend on dating apps.”

Participants also reported negative outcomes from using dating apps, such as missing class or work or getting in trouble because they were on their phones.

Results showed, not surprisingly, that socially anxious participants preferred to meet and talk to potential dating partners online rather than in person. They tended to agree with statements like “I am more confident socializing on dating apps than offline.”

But that alone didn’t lead them to compulsively use dating apps, Coduto said.

“If they were also lonely, that’s what made the problem significant,” she said. “That combination led to compulsive use and then negative outcomes.”

Coduto said people need to consider whether they may have a problem with such apps. If they have trouble setting limits for themselves, they can use apps that restrict dating app use to certain times of day or to a set amount of time each day.

“Especially if you’re lonely, be careful in your choices. Regulate and be selective in your use,” she said.

Source: Ohio State University