Depression is one of the most common mental health conditions in the world. It affects hundreds of millions of people and can make everyday life extremely difficult. People with depression may feel deep sadness, lose interest in activities they once enjoyed, struggle with sleep, or have trouble concentrating.
In serious cases, depression can interfere with work, relationships, and basic daily functioning. Because of this, doctors often prescribe antidepressant medications to help manage symptoms and support recovery.
However, finding the right antidepressant for each person is not always easy. Many people respond differently to these medications. One drug may work well for one patient but cause unpleasant side effects for another.
Doctors often have to rely on a trial‑and‑error approach, where patients try one medication and then switch to another if the first one does not work or causes problems. This process can take months and can be frustrating for both patients and clinicians.
Now researchers have developed a new artificial intelligence tool that may help solve this problem. The tool, called PETRUSHKA, was created by scientists at the University of Oxford. It uses artificial intelligence to help doctors and patients choose an antidepressant that is better suited to each individual person.
The system works by analyzing several types of information about the patient. It considers clinical information such as symptoms and medical history, as well as demographic factors like age and gender.
It also includes the patient’s personal preferences, especially when it comes to possible side effects such as weight gain, sleep problems, or sexual side effects. By combining these pieces of information, the tool suggests antidepressant options that may work best for the individual.
Researchers say that involving patients in treatment decisions is an important part of the process. The PETRUSHKA tool is designed to be used during a consultation between a patient and a healthcare professional.
Together, they review the information and discuss which medication might be the most suitable choice. This shared decision‑making approach helps ensure that treatment choices reflect both medical evidence and what matters most to the patient.
To test whether the tool actually improves treatment, scientists carried out a large international clinical trial. The study involved more than 500 adults who were diagnosed with major depressive disorder, often called MDD. The research took place across 47 clinical sites in three countries: the United Kingdom, Brazil, and Canada.
Participants in the study were randomly assigned to one of two groups. One group received standard treatment, where doctors chose antidepressants using traditional methods. The other group used the PETRUSHKA system to guide the decision about which antidepressant to prescribe.
The results were encouraging. People whose treatment was guided by the PETRUSHKA tool were more likely to continue taking their medication.
In fact, they were about 40 percent less likely to stop their antidepressant during the first eight weeks of treatment compared with people receiving standard care. Staying on medication is important because antidepressants often need several weeks to begin working effectively.
The researchers also found that fewer people in the PETRUSHKA group stopped treatment because of side effects. By the 24‑week mark, participants using the AI‑guided system reported greater improvements in symptoms of depression and anxiety compared with those receiving usual care.
One of the reasons the tool may work so well is that it was designed together with people who have personal experience of depression. The developers wanted to make sure the system was practical and easy to use in everyday healthcare settings.
The tool takes only about three minutes to complete, which means it can easily be used during a normal doctor’s appointment, either in person or through telehealth consultations.
The research was led by Professor Andrea Cipriani, a professor of psychiatry at the University of Oxford and an honorary consultant psychiatrist at Oxford Health NHS Foundation Trust.
He explained that mental health treatment has lagged behind many other areas of medicine when it comes to personalized care. In many other fields, doctors use detailed patient data to guide treatment decisions. In contrast, antidepressant treatment has often relied on guesswork.
Professor Cipriani said the study shows that combining scientific evidence with patient preferences can help doctors personalize treatment from the very beginning. This approach may help more people stay on medication that works for them and avoid the frustration of repeated medication changes.
Experts believe tools like PETRUSHKA could be especially helpful in primary care settings. Many people with depression are treated by general practitioners rather than specialist psychiatrists. These doctors often have limited time during appointments, so a quick decision‑support tool could help them make better treatment choices.
The research also suggests that digital technologies may play an important role in the future of mental health care. By analyzing large amounts of data, artificial intelligence can help identify patterns that humans might overlook. When used carefully, these tools could support doctors in providing more precise and personalized treatments.
The findings from this international study were published in the medical journal JAMA. The results provide strong evidence that digital decision‑support tools can improve mental health treatment.
However, the researchers note that further studies are still needed. Scientists want to understand whether the benefits continue over longer periods and whether the system is cost‑effective when used across large healthcare systems.
Looking closely at the findings, the study highlights an important shift in how depression treatment may evolve. Instead of relying on trial and error, future treatment could be guided by data‑driven systems that match patients with the most suitable medications earlier in the process.
This could reduce suffering, shorten recovery time, and improve overall outcomes for people with depression.
At the same time, it is important to remember that technology should support human decision‑making rather than replace it.
Tools like PETRUSHKA work best when doctors and patients use them together, combining clinical experience, scientific evidence, and personal preferences. If used responsibly, AI‑based tools may become valuable partners in improving mental health care around the world.
If you care about depression, please read studies about how dairy foods may influence depression risk, and B vitamins could help prevent depression and anxiety.
For more information about mental health, please see recent studies that ultra-processed foods may make you feel depressed, and extra-virgin olive oil could reduce depression symptoms.
Copyright © 2026 Knowridge Science Report. All rights reserved.
