/w=3840,quality=90,fit=scale-down)
Raphael Thys
Predictive AI applications are relatively new to mental and behavioral health, but are already showing a lot of promise. In a recent publication on detecting suicide risk through analyzing text messages, UW Medicine researchers found that algorithms performed as well as trained evaluators. This is great news for predictive AI and the ability to save lives at risk for suicide through data analysis in real-time, when and where the individual is located. This is important because some healthcare providers may be concerned when they communicate by text message with a patient, they might miss something they are trained to pick up from voice inflection, facial expression, and other auditory or physical signals. Algorithms like this can help enhance the provider’s ability to analyze the patient when communicating by text, an increasingly popular way for people to access mental health.
Beyond text messaging, there are many companies already working on analyzing a person’s speech through vocal biomarkers. Vocal biomarkers describe using someone’s voice and speech as vital signs. Digitizing the human voice and metricizing the various features of voice and speech means software programs can find patterns and detect small changes humans might not recognize. Vocal biomarker measurements and analysis for anxiety, stress, sleepiness and depression are some of the early applications.
A great example of AI voice technology that can be used directly by healthcare providers now to detect mental illness is Ellipsis Health. By harnessing the power of the human voice as a biomarker for mental health, Ellipsis Health can be used as a clinical decision support tool during clinic visits. Its technology augments the care team by helping to assess the severity of stress, anxiety, and depression.
In 2020, Amazon launched its Halo Wearable, which also leverages AI voice technology. Halo is worn on a user’s wrist and comes equipped with an accelerometer, temperature sensor, heart rate monitor, pulse oximeter, and two microphones. Halo measures a patient’s voice to determine and categorize that person’s emotions. Halo can tell the wearer how their voice tone may come across to others, such as “hopeful,” “elated,” or “hesitant.”
Sonde Health has identified 4,000 unique features of the human voice and compiled a database of over 1.2 million voice samples. Currently, they have a consumer-facing smartphone app that analyzes a user’s mood through a 30-second voice sample of the user talking about subjects like work, school, family, or friends. Sonde measures aspects of speech smoothness, control, liveliness, energy, clarity, crispness, rate, and pause duration for this application.
As AI predictive applications continue to grow, with a user’s permission, the applications could access a multitude of data from sources not previously available a decade ago.
Data streams from GPS tracking can determine if someone has decreased their daily activity and may be combined with data from other actions like the amount of time on a smartphone compared to that individual’s norm. With clinical-grade wearables, data including blood pressure, heart rate, activity level, sleep quality, and sleep length can add even more precision. Since AI excels at pattern analysis, it can recognize when someone deviates from their baseline, which could be an indication of a problem.
Feel is an example of a behavioral health company that combines Remote Patient Monitoring with coaching. Through a smart wristband with five sensors, Feel analyzes heart rate, heart rate variability, temperature, and electrodermal response. Electrodermal response, also known as galvanic skin response, is a measurement of the electrical changes in sweat glands. This has been shown to help categorize someone’s emotional state. By leveraging cutting-edge AI, Feel can learn about an individual’s normal daily patterns and identify the individual’s emotional changes. That, in turn, helps to identify triggers so Feel can provide personalized guidance to help that individual learn how to regulate their negative emotions. Personalized behavioral medicine where and when someone needs it the most.
Predictive AI in mental health is still in the early stages of adoption, but expect it to rapidly expand over the next five years due to several factors, including the entrance of giant companies like Amazon. The FDA announced updated guidelines for AI in healthcare applications in late September of 2022, including software tools that can be used to guide clinical decisions. The updated guidelines also leave room for software to improve over time, one of the main advantages of AI.
[To share your insights with us, please write to sghosh@martechseries.com]