This article is part of a limited series about the potential of artificial intelligence to solve everyday problems.
Imagine a test as quick and simple as taking your temperature or measuring your blood pressure, which can reliably identify an anxiety disorder or predict an impending depressive relapse.
Healthcare providers have many tools to measure a patient’s physical condition, but there are no reliable biomarkers — objective indicators of medical conditions observed from outside the patient — for assessing mental health.
But some artificial intelligence researchers now believe that the sound of your voice may hold the key to understanding your mental state — and AI is perfectly suited to detect such changes, which are otherwise difficult, if not impossible, to perceive. to be. The result is a suite of apps and online tools designed to track your mental status, as well as programs that provide real-time mental health assessments to telehealth and call center providers.
Psychologists have long known that certain mental health problems can be detected by not just listening to: what one person just says how they say it, said Maria Espinola, a psychologist and assistant professor at the University of Cincinnati College of Medicine.
In depressed patients, Dr. Espinola: “Their speech is generally more monotonous, flatter and softer. They also have a narrower pitch range and lower volume. They take more pauses. They stop more often.”
Patients with anxiety feel more tension in their bodies, which can also change the way their voices sound, she said. “They tend to talk faster. They have more trouble breathing.”
Today, these types of vocal characteristics are used by machine learning researchers to predict depression and anxiety, as well as other mental illnesses such as schizophrenia and post-traumatic stress disorder. Using in-depth algorithms can reveal additional patterns and features, as captured in short voice recordings, that may not be apparent even to trained experts.
“The technology we’re using now can extract features that can be meaningful that even the human ear can’t pick up,” said Kate Bentley, an assistant professor at Harvard Medical School and a clinical psychologist at Massachusetts General Hospital.
“There is a lot of excitement about finding biological or more objective indicators of psychiatric diagnoses beyond the more subjective forms of assessment traditionally used, such as clinician-rated interviews or self-report measures,” she said. Other clues researchers are tracking include changes in activity levels, sleep patterns and social media data.
These technological advancements come at a time when the need for mental health care is particularly acute: by 2020, one in five adults in the United States will develop a mental illness, according to a report by the National Alliance on Mental Illness. And the number continues to rise. †
While AI technology can’t address the scarcity of qualified healthcare providers — there aren’t nearly enough to meet the country’s needs, said Dr. Bentley – there is hope it can lower barriers to getting an accurate diagnosis, help clinicians identify patients who may be hesitant to seek care and facilitate self-monitoring between visits.
“A lot can happen between appointments, and technology can really give us the potential to improve monitoring and assessment in a more continuous way,” said Dr. Bentley.
To test this new technology, I started by downloading the Mental Fitness app from Sonde Health, a health technology company, to see if my feelings of malaise were a sign of something serious or if I was just wasting away. Described as “a voice-activated journaling and journaling product,” the free app invited me to record my first check-in, a 30-second verbal journal entry, which would rank my mental health on a scale of 1. up to 100.
A minute later, I had my score: a not-great 52. “Caution,” the app warned.
The app indicated that the level of vibrancy detected in my voice was remarkably low. Did I sound monotonous because I was trying to speak softly? Should I follow the app’s suggestions to improve my mental fitness by going for a walk or cleaning up my space? (The first question may point to one of the possible flaws of the app: as a consumer, it can be hard to know Why your vocal levels fluctuate.)
Later, when I was feeling nervous between interviews, I tested another speech analysis program, this program aimed at detecting anxiety levels. The StressWaves test is a free online tool from Cigna, the healthcare and insurance conglomerate, developed in collaboration with AI specialist Ellipsis Health to evaluate stress levels using 60-second samples of recorded speech.
“What keeps you up at night?” was the prompt from the website. After I spent a minute telling my lingering concerns, the program scored my recording and sent me an email saying, “Your stress level is moderate.” Unlike the Probe app, Cigna’s email didn’t include helpful self-improvement tips.
Other technologies add a potentially useful layer of human interaction, such as Kintsugi, a company based in Berkeley, California, which raised $20 million in Series A financing earlier this month. Kintsugi is named for the Japanese practice of mending broken pottery with gold veins.
Kintsugi was founded by Grace Chang and Rima Seiilova-Olson, who bonded over their shared past experiences of struggling to access mental health care. Kintsugi is developing technology for telehealth and call center providers that can help them identify patients who may benefit from further support.
For example, by using Kintsugi’s voice analysis program, a nurse might be asked to take an extra minute to ask a harried parent with a child with colic about their own well-being.
A concern in developing these kinds of machine learning technologies is the issue of bias – ensuring that the programs work equally for all patients, regardless of age, gender, ethnicity, nationality and other demographic criteria.
“For machine learning models to work well, you really need to have a very large and diverse and robust set of data,” said Ms. Chang, pointing out that Kintsugi used voice recordings from all over the world, in many different languages, to prevent that this problem in particular.
Another major concern in this burgeoning field is privacy — particularly voice data, which can be used to identify individuals, said Dr. Bentley.
And even if patients agree to be admitted, sometimes the issue of consent is twofold. In addition to assessing a patient’s mental health, some voice analysis programs use the recordings to develop and refine their own algorithms.
Another challenge, said Dr. Bentley, is the potential mistrust of consumers of machine learning and so-called black box algorithms, which work in ways that even the developers themselves can’t fully explain, especially what features they use to make predictions.
“You make the algorithm and you understand the algorithm,” said Dr. Alexander S. Young, interim director of the Semel Institute for Neuroscience and Human Behavior and chair of psychiatry at the University of California, Los Angeles, echoing the to care. that many researchers have about AI and machine learning in general: that there is little or no human supervision during the training phase of the program.
For now, Dr. Young cautiously optimistic about the potential of speech analysis technologies, especially as tools for patients to self-monitor.
“I really believe you can model people’s mental health status or approach their mental health status in a general way,” he said. “People like being able to check their status for themselves, especially with chronic illnesses.”
But before automated speech analysis technologies are widely used, some are calling for thorough research into their accuracy.
“We really need more validation of not only speech technology, but also AI and machine learning models built on other data streams,” said Dr. Bentley. “And we need to achieve that validation based on large-scale, well-designed representative studies.”
Until then, AI-powered speech analysis technology remains a promising but unproven tool, one that could eventually become an everyday method of measuring the temperature of our mental well-being.
