How Technology Is Disrupting the Behavioural Health Field

Technological innovation is changing the behavioural healthcare landscape. The intersection of cloud computing, artificial intelligence, natural language processing, and biometrics sensors offer untold opportunities patient-centered stepped-care models, earlier and more accurate problem diagnosis, personalized intervention, and improved accessibility of care, to name a few. 

In any given year, nearly 60% of all people with a mental health condition receive no treatment and accessing care in a timely manner relies primarily on the individual, whose condition may involve a loss of motivation, stigmatization, a sense of hopelessness, and/or impaired judgment, all of which interfere with seeking help. Additionally, demand for care far outstrips the number of care providers available, and treatment costs can be prohibitive.

This article briefly examines several of the technologies transforming the landscape of behavioural health. These technologies foretell an important shift in the industry towards better access to services, earlier and more accurate diagnosis, more personalized treatment plans, and patient empowerment.

Interoperability 

Interoperability (sharing health record data) ensures continuity of care across multiple venues via secure data exchange. When information is pulled out of silos and a technology infrastructure is in place to enable the exchange of data between primary care and behavioural health providers, the ability to provide better care becomes possible. Additionally, with Apple and Google investing heavily in promoting interoperability, I expect we will witness major strides in interoperability in 2020. For example, Apple’s HealthKit and Health Records API* allows users to share their health record data, including lab results, medications, and more, and provides a central repository for health and fitness data on iPhone and Apple Watch.

 * An application program interface (API) is a set of protocols and tools for building software applications. Simply put, an API specifies how software components should interact so that different programs can communicate with one another. A good API makes it easier to develop a program by providing all the building blocks. A programmer then puts the blocks together.

Now is the time to bring patients, care providers, and technology together to ensure we can identify and intervene early enough to change the future of the behavioural health care landscape for patients and providers alike. Paul Gionfriddo, president and CEO of Mental Health America

Chatbots (Conversational User Interface)

A chatbot is a computer program with artificial intelligence (AI) that simulates conversations using natural language processing.** While therapists observe body language and speech, a chatbot can detect patterns in typing speed, sentence length, active or passive voice and other indicators that point to varying emotional states. 

Chatbots promise to be a major player in the field of mental health. While this technology is still in its infancy, chatbots can increase access to healthcare, improve therapist–client and clinic–client communication, and help to manage the increasing demand for behavioural health services such as teleconsultations, mental health surveys, and health reminders/alerts. Chatbots like Woebot and Babylon offer real-time advice, facilitate booking appointments, and guide users toward the proper steps for care. In many cases, chatbots can be accessed through SMS, Facebook Messenger, WhatsApp and web browsers where they hold can administer highly personalized psychotherapy and psychoeducation.

I expect that health chatbots will experience significant growth in 2020, particularly with respect to research and validation studies.

**Of note. Twenty-plus years ago I co-developed one of the first ‘cybertherapy’ programs in North America and at the time had not recognized it as an early version of a conversational user interface. The program, Mastering Stress, was a computer-guided assessment and problem-solving tool. Though early on the scene (this was in the era I was coding in HTML, Java...and GUI interfaces were in their infancy) the program had significant uptake in the corporate wellbeing arena. It is remarkable to see how far this technology has c

Biometric Sensors

Today, people are measured continuously by sensors, mostly from those embedded in mobile phones, measuring location, movement, communication or social interaction. The data produced from these sensors (the “digital exhaust”) contains rich information about people’s behaviour and potentially their emotions, thoughts, and mental health. “Wearables” such as Fitbit and the Apple Watch are examples of devices that contain sensors tracking activity and physiological functions (e.g. the number of steps taken in a day).

The most widely used sensor in wearables is the accelerometer. Accelerometer-based wearable devices have been developed for tracking physical exercise, detecting falls, and monitoring activities of daily living. Increasingly, wearable devices are including a broader range of sensors that can measure variables that are useful for mental health researchers, such as skin conductance and heart rate. For example, investigators have noted that greater asymmetries in skin conductance amplitude on the left and right sides of the body are an indicator of emotional arousal. Wearables are even being developed dedicated to behaviours that have been difficult to detect and monitor in the past but are often disrupted in mental health conditions (e.g. appetite). 

The main criticism logged against biometric sensors is their potential for error. This raises the question of how much error or uncertainty is acceptable (e.g. sensitivity to detection of false positives or negatives) and the effect of inaccurate identification could be mitigated. 

Social Media

With almost three quarters of North Americans using social media platforms such as Facebook, Twitter, and Pinterest, social spaces have become common places where people share their opinions, feelings, and daily experiences. Consequently, social media is particularly well suited for detecting behavioural markers that involve cognitive or motivational states.

As one example, researchers found that depressed Twitter users can be distinguished from non-depressed users based on later posting times, less frequent posting, greater use of ?rst person pronouns, and greater disclosure about symptoms, treatment, and relationships. Further, the development of a future depressive episode could be predicted with 70% accuracy (De Choudhury, M., Gamon, M., Counts, S., & Horvitz, E. (2013). Predicting depression via social media. Proceedings of the 7th. International Association for Advanced Artificial Intelligence Conference, Boston, pp. 128–37).

In other studies, analysis of a person’s social media postings has identified with great accuracy whether that person is suicidal.Suicidal ideation has been associated with language used in social media that shows heightened self-attention focus, poor linguistic coherence and coordination with the community, reduced social engagement, and manifestations of hopelessness, anxiety, impulsiveness, and loneliness. One study demonstrated that machine learning is up to 93 percent accurate in correctly classifying a suicidal person and 85 percent accurate in identifying a person who is suicidal, has a mental illness but is not suicidal, or neither (Pestian, J.P., et al. (2016). A Machine Learning Approach to Identifying the Thought Markers of Suicidal Subjects: A Prospective Multicenter Trial. Suicide and Life-Threatening Behaviour. 47(1), 112-121.). 

Virtual Reality

Virtual reality (VR) is a relatively new field, but progress is fast and the potential impact on the behavioural health field is tremendous. For example, VR headsets can help desensitize individuals suffering from post-traumatic stress disorder by recreating their personal triggers. This helps them to develop coping techniques in a safe environment (the therapist office or at home). VR can also help patients suffering from depression, anxiety, and other disorders. Further, some research suggests VR has benefits for individuals with more severe disorders like paranoia.

Currently the development of VR environments is a complicated and expensive undertaking. However, as more developers explore the potential of VR in the mental health field, we will see an abundance of new opportunities for treatment. This is particularly true given advances in the technological infrastructure that allows developers to explore new possibilities for VR (e.g. Apple’s augmented reality (AR) kit).

Robotics

A major benefit of robotics is that the robot is proactive as opposed to smartphones or laptops, which are reactive. 

Consider this. According to the Center for Disease Control and Prevention, older adults are at an increased risk for depression and this largely stems from feelings of isolation. Indeed, the AARP Foundation calls social isolation a major health epidemic that has the equivalent impact of smoking 15 cigarettes a day. Robotics may provide the ideal ‘social companion’ for many of these isolated adults.

ElliQ is an AI-driven social robot designed to prompt older adults toward increased engagement with connected loved ones and by suggesting activities. It may, for example, suggest that the person go for a walk or call up family and friends. According to Dafna Presler, VP of Marketing for Intuition Robotics (the makers of ElliQ) “If you’re in the room and you walked by her, then she can just look at you, and maybe the cognitive computing algorithm decides that it’s a good time to maybe suggest an activity to you...and those activities can be mental, cognitive games or a suggestion to to call your family members.”

We want to help fight social isolation and loneliness and keep older adults actively engaged by doing things that are a little bit different than technologies that are out there today. We designed ElliQ first and foremost with older adults in the design process. Dafna Presler, VP of Marketing for Intuition Robotics.

Apps

Over half of the population in the North America owns a smartphone and check them as often as 150 times a day. Thus, when it comes to behavioural healthcare, people will often consult their devices before turning to their providers for information and treatment.

Excitement about the huge range of opportunities has led to a burst of app development and there are thousands of mental health apps available in iTunes and Android app stores; the number growing every year. However, there is no formally accepted industry guide for the development of evidence-based apps. Thus, it is a “wild west” of choices with varying degrees of evidence. Additionally, the wealth of data that is required for many of these apps to function effectively raises serious concerns about data security and patient privacy that these apps are useful and, more importantly, protect consumers from harm and privacy breaches.

The very first apps appeared around 2009 and since then, many more have been developed. Apps can be used anywhere, as they are tied to a mobile device rather than a desktop computer. This portability makes them incredibly useful, especially for the younger generation. I discuss the pros and cons of apps, and how to best select them, in this previous article on LinkedIn (Separating the Good From the Bad in a Wild West Landscape of Apps, Wearables and Websites. https://www.dhirubhai.net/pulse/separating-good-from-bad-wild-west-landscape-apps-scott/) .

Some of the more common types of apps in the behavioural health field include:

• Self-management apps. The user puts information into the app so that the app can provide feedback. For example, the user might set up medication reminders, or use the app to develop tools for managing stress, anxiety, or sleep problems. Apps allow users to self-treat mental health disorders, but they work best when used in conjunction with professional counselling and therapy.
• Skills-training apps. These apps help users learn new coping or thinking skills.
• (Passive) symptom-tracking. These apps collect data using sensors (as per biometric sensors, discussed above) may be able to recognize changes in behaviour patterns that signal a mood episode such as mania, depression, or psychosis before it occurs.
• Research/data collection apps. The typical randomized-controlled trials are too long, as technology changes far too quickly. This then, calls for new statistical and research methods. Thankfully, research via smartphone app is a reality. Data collection apps can gather data without any help from the user. Receiving information from a large number of individuals at the same time can increase researchers’ understanding of mental health and help them develop better interventions.

For more several behavioural health disorders, some exciting development in the apps world have emerged. For example, what if someone invented a smartphone app that could help detect autism spectrum disorder (ASD) in children as young as 2 years old? In fact, someone has.

EurekAlert! is an app that tracks eye movements of a child looking at pictures of social scenes, such as those showing multiple people. The eye movements of someone with ASD are often different from those of a person without autism. It takes less than a minute to administer the test, which can be done by a parent at home to determine if a child requires professional evaluation. The app can detect autism spectrum disorder (ASD) in children as young as two years old with nearly 94 percent accuracy.

Conclusion

Human interaction and diagnostic expertise will always be the foundation of good mental health care—technology cannot duplicate the sense of a human connection and feeling of being understood and cared about cannot that comes from a person-to-person relationship. Human connection and the sense of being accepted and care about cannot be duplicated by any technology. So while technology won’t replace therapists or mental health care treatments, it has the potential to usher in a new generation of personalized mental health tools and systems of deliver.

What an exciting time in the behavioural health field these next few years promise to be!

About Avail

At Avail, we believe that optimal mental health and well-being can be achieved by anyone, anywhere, without worry, stigma, or lack of available support and is key to resilience, productivity, engagement, and mitigating healthcare costs.

Avail is evolving the behavioural health landscape. By encouraging regular well-being check-ups and confidentially connecting members to evidence-based behavioural health services through our mobile platform, we make optimal mental health and well-being possible for everyone, everywhere, overcoming typical barriers of worry, stigma, lack of awareness, or lack of specialist support. For employers, Avail opens up new possibilities to mitigate healthcare-related costs (e.g. absenteeism, presenteeism) and improve productivity, engagement and retention.

Avail is a Software-as-a-Service (Saas) based holistic well-being solution for organizations and their employees. Avail's proactive, mobile-first, anytime platform uses clinical and behavioural data-driven insights to provide employees with personalized well-being profiles that are increasingly refined to reflect changes in well-being as circumstances change. Each profile aims to equip employees with insight and actionable skills to achieve optimal mental well-being, strengthened resilience and a mindset that promotes high engagement and performance.

For employees with untreated mental health problems or who want to improve their mental wellbeing without stigma or privacy concerns, Avail's Care Navigator recommends options ranging from psycho-educational content (e.g. articles, videos) to professional care from our national provider network. Care resources can be augmented with any care options your organization provides. For administrators, Avail's aggregate analytics and insights track your organization's care service utilization and identifies trends in the mental health and well-being of your workforce.

https://avail.app