The world is facing a mental health epidemic. One in five adults suffers from some form of mental illness in the United States, yet more than 50% of these illnesses are left untreated. Mental health does not discriminate against age, race, gender or economic status, and unfortunately, treatment and research still have a long way to go before the number of diagnosed individuals decreases.

However, one optimistic element to this crisis is the existence of new technology that we did not have even a decade or two ago – one of which is Artificial Intelligence (AI). Advanced technology plays a major role in positively shaping the healthcare industry, and now digital solutions such as artificial intelligence are making their way into the psychiatry department to reduce the decline in mental wellness across the globe. But how does the use of predictive analytics tools such as artificial intelligence really help in solving the mental health crisis? Let’s examine.

AI and mental health in action

Researchers are finding there could be a way to help screen, diagnose, and test mental illness using Artificial Intelligence, but those solutions are still being tested. In one example, researchers from the World Well-Being Project (WWBP) analyzed social media with an AI algorithm to detect linguistic cues that may predict depression. In comparison to those with other chronic conditions, individuals suffering from depression were much more likely to express themselves on social media platforms using mentions of loneliness and words that may link to warnings of depression. WWBP analyzed half a million Facebook posts from people who consented to provide both their status updates and medical records, and as a result, researchers found that analyzing linguistic markers using AI tools could predict depression up to three months before the person receives a formal diagnosis.

One anticipated mental healthcare tool is an AI program called Super Learning (SL). While this program is still in the midst of being developed, its goal is to help predict outcomes to treatments of substance use disorders. But how does this work? Essentially, Super Learning extracts all identified prediction algorithms that are appropriate for certain prediction issues. Using these algorithms, Super Learning generates a model that best predicts an outcome to the given situation. This work compares the performance of logistic regression, random forests, deep learning neural networks, and SL to predict successful substance use disorders (SUD) treatment.

Using AI to create personalized plans

Quartet Health is a company whose AI-enabled system partners with health plans and systems to create a personalized plan for users through virtual collaboration. For providers and primary care doctors, Quartet’s platform offers assessments, webinars, and even assists in setting up teletherapy and telepsychiatry sessions. For patients, Quartet’s platform provides live support and flags possible mental health conditions. Quartet then works with patients’ doctors to find local mental health providers who check off criteria such as accepting the patient’s insurance or they can refer patients to computerized cognitive behavioral therapy programs using telehealth. To learn more about telehealth, click here.

ChampionMX, Inc. is a digital health technology company that provides mental health tracking directly through an individual’s mobile device, and can be used for those who suffer from conditions such as depression or bipolar disorder. According to ChampionMX, its system uses “active monitoring of voice and passive monitoring of other smartphone metadata to continuously produce acoustic and behavioral biomarkers that predict core symptoms of mood and anxiety disorders,” and has been used by more than 1,500 patients, behavioral health care clinicians and researchers. Individuals who use this system are able to create audio logs (similar to a written diary, except using audio only). With artificial intelligence, ChampionMX’s tool is able to analyze the individual’s recording log and look for changes in behavior.

Artificial Intelligence researcher David Plans founded digital health company BioBeats in 2012 after a near-death experience in 2003. While at an airport in Brussels, Plans suddenly passed out and flatlined on the way to the hospital. He later found that his health scare could have been a result of overwork and stress. Plans then decided to build a system that would help warn him if the situation were to ever happen again. Using artificial intelligence and big data, BioBeats developed a wearable device as well as an application and machine learning system to collect data and monitor the user’s level of stress, which also provides them with real-time data that they are able to track. Plan states that “AI helps use personalize the experience to each user’s data as well as identify patterns leading to disorder before it manifests itself more visibly.”

The benefits of using AI to tackle the mental health crisis

According to Forbes, there are four main benefits of using AI to help tackle the mental health crisis:

  • The support mental health professionals
  • 24/7 access
  • Inexpensive services
  • Patient comfort in talking to a bot

Although using AI in mental healthcare is on the rise, it is not meant to replace human healthcare professionals. AI clinicians can essentially work together with human clinicians to help support ongoing treatment plans as, algorithms can analyze data much faster than humans, can suggest possible treatments, monitor a patient’s progress and alert the human professional to any concerns.

Using artificial intelligence is also beneficial as it allows the patient to access services 24/7. Peter Foltz, research professor at the University of Colorado Boulder, emphasizes the lack of patient interaction clinicians actually experience during mental health treatment. “Patients tend to be remote, it’s very hard to get appointments and oftentimes they may be seen by a clinician [only] once every three months or six months… AI could be an effective way for clinicians to both make the best of the time they do have with patients, and bridge any gaps in access.”

Unfortunately, it’s also very common for individuals to resist or delay treatment for their mental health issues due to the cost being too burdensome. Individuals often have to choose between treatment or financial stability, but with AI, mental health providers will be able to incorporate a broad range of conventional treatments and evidence-based complementary and alternative medicine (CAM) modalities, therefore being much more cost-effective and effective for patients.

Lastly, incorporating artificial intelligence in with mental health treatment may allow patients to feel as though they can open up more. Patients who are often embarrassed to reveal problems to a therapist they’ve never met before, let down their guard with AI-powered tools which can ultimately result in a faster treatment plan and improve the odds of treatment being effective.

Conclusion

As previously emphasized, artificial intelligence tools are not being made to replace human medical professionals, but rather to assist them and provide additional support to patients. There has been a great focus in enabling clinicians to make better decisions through the use of technology, and what we see today is only the beginning. Healthcare providers have been on a life-long search for effective ways in which they can help patients using during and before treatment, and now they are one step closer with the various AI-healthcare programs in development.

Lindsey Berke