Are Digital Biomarkers the Future for Mental Health?

By David Stephen who looks at Digital Biomarkers in this article. 

There is a recent [January 15, 2026 4.04pm SAST] analysis in The Conversation, Reports of ‘AI psychosis’ are emerging — here’s what a psychiatric clinician has to say, stating that, “AI psychosis is not a formal psychiatric diagnosis. Rather, it’s an emerging shorthand used by clinicians and researchers to describe psychotic symptoms that are shaped, intensified or structured around interactions with AI systems.”

What do Digital Biomarkers offer?

“Some patients report beliefs that genAI is sentient, communicating secret truths, controlling their thoughts or collaborating with them on a special mission. These themes are consistent with longstanding patterns in psychosis, but AI adds interactivity and reinforcement that previous technologies did not.”

“AI is not going away. The task now is to integrate mental health expertise into AI design, develop clinical literacy around AI-related experiences and ensure that vulnerable users are not unintentionally harmed.”

“As AI becomes more human-like, the question that follows is how can we protect those most vulnerable to its influence?”

“Psychosis has always adapted to the cultural tools of its time. AI is simply the newest mirror with which the mind tries to make sense of itself.”

Digital Biomarkers

There is a recent [January 14, 2026] spotlight on New Scientist, Psychiatry has finally found an objective way to spot mental illness, stating that, “According to some psychiatrists, chatbots like this may one day play a major role in the diagnostic toolkit. Their aim is to establish a series of “digital biomarkers”, analysed by AI, that will help assess people’s current condition, inform treatment options and keep track of their mental health. The list of candidate biomarkers so far includes the cadences of our voice, flickers of our facial expression, alterations in bodily movements and changes in heart rate that accompany sleep.”

“Much of the necessary data is already available on the devices that we carry with us every day, providing psychiatrists with an unprecedented view of someone’s life. If it works, it should help to build more personalised treatment plans and pre-empt relapses before someone falls into a crisis. Yet there are also some major questions about the reliability of these diagnoses, not to mention the inevitable privacy concerns.”

“Other candidate biomarkers include measures of bodily movement measured through wearable devices’ accelerometers.”

“If digital biomarkers do come of age, they will mark one of the biggest shifts in psychiatry’s history. Since the earliest days of the field, diagnosis has been based almost entirely on in-depth conversations between doctors and patients. These consultations tend to explore whether someone is experiencing a cluster of symptoms associated with the condition. Depression, for instance, typically involves changes in mood, appetite, sex drive, motivation and sleep.”

“The collection of symptoms ascribed to each mental health condition can be frustratingly imprecise. There are so many possible presentations of depression, for example – with signs including sleeping both too much and too little – that two people with no overlapping symptoms can be handed the same diagnosis. Meanwhile, the onset of depressive traits could be straightforward unipolar depression, or it could be the start of something more complex like bipolar disorder. Psychiatry has long tried to mimic the diagnostic precision seen elsewhere in medicine, and has always fallen short.”

Digital Biomarkers

The dominance of technology indicates that digital biomarkers would become prevalent through the rest of this decade and beyond.

Digital biomarkers would be excellent in some areas of physical health, but their reach, for mental health may be uncertain.

The problem of psychiatry is the problem of the mind. So, the identification of what the mind is, its components and mechanisms are the ultimate biomarkers for psychiatry. This means that even if everything about the mind is unknown, what parts can be used to track and explain mental anomalies?

For example, the problem of AI psychosis is the most direct case to germinate digital biomarkers. Since the problem is digitally stoked, it means it can also be explored digitally, for solution.

AI psychosis is linked with AI sycophancy, where AI is excessively deferential. AI is also said to reinforce delusions. When AI outputs some words, those words can be postulated to target certain destinations on the mind.

Because the words are also coming from AI, the relays can be assumed to also be different, from if they were from human.

Now, developing a simple sketch of the mind that is dynamic to show what AI is doing to the mind will be a way to test for and track AI psychosis.

This digital biomarker architecture can then be extended to the entire human mind, with the concept that the human mind is the collection of all the electrical and chemical signals, with their interactions and attributes, in sets, in clusters of neurons, across the central and peripheral nervous systems. Simply, the human mind is the sets of signals.

Progress for digital biomarkers are connected with conceptual brain science, where the physiology of the mind is necessary.

David Stephen currently does research in conceptual brain science with focus on the electrical and chemical configurators for how they mechanize the human mind with implications for mental health, disorders, neurotechnology, consciousness, learning, artificial intelligence and nurture. He was a visiting scholar in medical entomology at the University of Illinois at Urbana Champaign, IL. He did computer vision research at Rovira i Virgili University, Tarragona.

See more breaking stories here.