Mental health includes our emotional, psychological and social well-being, and affects how we think, act and feel. There are multiple factors that contribute to your mental health, such as biological factors, life experiences and family history.
Data science, also known as big data and data analytics, is the process of analyzing raw information to find trends and answer questions. There are four general types of data analytics:
Mental health awareness is continuing to grow. In fact, some believe that implementing data science can help it grow even further.
The Current State of Mental Health Treatment
Mental illness can affect tens of millions of people every year. The following statistics provide a look into how many people face a mental health illness:
- In the United States alone, 46.4% of adults will experience a mental illness during their lifetime.
- 5% of adults ages 18 or older experience a mental illness in any one year — this is equivalent to 43.8 million people.
- Of adults in the United States with any mental disorder in a one-year period, 14.4% have one disorder, 5.8% have two disorders and 6% have three or more.
- Half of all mental disorders begin by age 14 and three-quarters by age 24.
- In the United States, only 41% of the people who had a mental disorder in the past year received professional health care or other services.
Other mental health disorder statistics include:
- Mental health disorders account for several of the top causes of disability in established market economies, such as the U.S., and include: major depression (also called clinical depression), manic depression (also called bipolar disorder), schizophrenia and obsessive-compulsive disorder.
- Many people suffer from more than one mental disorder at a given time. In particular, depressive illnesses tend to co-occur with substance abuse and anxiety disorders.
- Most people who die by suicide have a diagnosable mental disorder — most commonly a depressive disorder or a substance abuse disorder.
The Role of Data Science in Improving Mental Health
Data science could be the missing key that is needed to help create personalized care for those who are facing a mental illness or substance abuse. In fact, MQ Mental Health reports that big data can do a lot for mental health treatment. By using large sets of information, researchers and health professionals can identify patterns that are typically more difficult to detect.
Some researchers also believe that big data can help put an end to the trial and error of finding medications that patients will need to properly treat their diagnoses.
“Machine learning approaches are often contrasted with theory-driven approaches, such as those promoted by the computational psychiatry movement, which endeavor to explain psychiatric phenomena in terms of detailed models of brain function. This theory-driven strategy might help improve treatment outcomes in one of two ways,” says Claire M. Gillan and Robert Whelan in an article on What Big Data Can Do for Treatment in Psychiatry.
The Future of Using Data Science in Mental Health Services
Currently, there is no single source of information that researchers consider reliable enough to be utilized. In the same article, MQ Mental Health reports that in order to get around this dilemma, data scientists must find models that will link and combine different data sources together in hopes of providing useful results.
If this tool is utilized properly, it could help ensure that big data allows researchers to identify risk factors for mental illness — by giving people the right treatment for them, tracking how well they improve, and even investigating how we could prevent mental health conditions from developing.
Case Studies for Using Data Science for Mental Health Care
The following case studies and real-life scenarios provide details about different instances when data science impacted mental health care.
Analyzing EHR for Predicting Suicide Risk, Mental Health Research Network
The American Journal for Psychiatry (AJP) published an article titled “Predicting Suicide Attempts and Suicide Deaths Following Outpatient Visits Using Electronic Health Records.” It discusses how the authors sought to develop models that use electronic health records to predict suicide attempts and deaths following an outpatient visit.
Across seven health systems, the researchers monitored health system records and state death certificate data that identified suicide attempts and suicide deaths over 90 days following each visit.
They found that the mental health specialty visits with risk scores in the top 5% accounted for 43% of subsequent suicide attempts and 48% of suicide deaths. And primary care visits with scores in the top 5% accounted for 48% of suicide attempts and 43% of suicide deaths.
They concluded that prediction models that incorporate both health record information and responses to self-report questionnaires substantially outperform existing suicide risk prediction tools.
Artificial Intelligence and Suicide Prevention, CrisisText Line
Vox published an article on “How Data Scientists Are Using AI for Suicide Prevention.” Data scientists at Crisis Text Line use machine learning, a type of artificial intelligence, to pull out the words and emojis that can signal a person at higher risk of suicide ideation or self-harm. The computer tells them who on hold needs to jump to the front of the line to be helped.
“Our data gives the rich context around why a particular crisis event happened. We get both the cause and the effect, and we get how they actually talk about these issues. I think it’s going to provide a lot more context on how we can actually spot these events and prevent them,” said Bob Filbin, chief data scientist at CTL.
University of Southern California, Virtual Therapist
Parie Garg and Sam Glick, the authors of Artificial Intelligence’s Potential to Diagnose and Treat Mental Illness, state that “patients, who are often embarrassed to reveal problems to a therapist they’ve never met before, let down their guard with AI-powered tools.”
They also mention that AI may:
- Help psychiatrists and other mental health professionals do their jobs better.
- In mental health, chat-bots are being pressed into service by employers and health insurers to root out individuals who might be struggling with substance abuse, depression, or anxiety and provide access to convenient and cost-effective care.
- It can recommend pre-emptive follow-up in cases where patients may become depressed or anxious after receiving a bad diagnosis or treatment for a major physical illness.
Researchers and medical professionals are working to spread the importance of being aware of not only your physical health, but your mental health as well. With the help of data science, they can to accomplish this goal more accurately and efficiently — as well as provide the public with statistics as to why it is relevant.