Researchers at George Mason University's College of Public Health have harnessed the power of artificial intelligence (AI) analytical models to match a patient's medical history with the most effective antidepressant, allowing patients to catch symptoms earlier. The free website MeAgainMeds.com provides evidence-based recommendations, allowing doctors and patients to find the optimal antidepressant the first time .
Many people with depression have to try several antidepressants before they find the right drug that relieves their symptoms. Our website reduces the number of drugs that patients are asked to try. This system advises the patient that it has worked for at least 100 other patients with the same exact medical history ."
Farrokh Alami, Principal Investigator and Professor of Health Informatics at George Mason University College of Public Health
Artificial intelligence has helped make the very complex task of creating thousands of prescriptions easy for patients and doctors. The prescriptions that researchers have created are complex because of the amount of clinical information associated with prescribing an antidepressant. Artificial intelligence seamlessly simplifies the work .
MeAgainMeds.com is a site that uses artificial intelligence to analyze a doctor's or patient's answers to a few anonymous medical history questions to determine which oral antidepressant best meets specific needs. The website does not ask for any personally identifiable information and does not prescribe medication changes. Patients are advised to consult a doctor for any change in medication .
In 2018, the Centers for Disease Control reported that more than 13 percent of adults are taking antidepressants, and that number has increased since 2020 following pandemics and other epidemics.
Alami and his team analyzed 3,678,082 patients who had taken 10,221,145 antidepressants. Oral antidepressants analyzed were: amitriptyline, bupropion, citalopram, desvenlafaxine, doxepin, duloxetine, escitalopram, fluoxetine, mirtazapine, nortriptyline, paroxetine, sertraline, trazodone, and venlafaxine. From the data, they created 16,770 subgroups of at least 100 cases using responses to previous antidepressants, current medications, history of physical illness, history of mental illness, key procedures and other information. Subtypes and recovery rates lead artificial intelligence to provide an evidence-based drug recommendation .
"By matching patients to subgroups, doctors can prescribe a drug that works best for people with a similar medical history," says Alami. The researchers and the website recommend that patients who use the site provide the information to their doctors so that they can ultimately decide whether to prescribe the recommended drug or not .
Alami and his team tested an early version of the site in 2023, promoting it on social media. At that time, 1500 patients were using this website. Their goal is to improve the website and expand its user base. Initial research was funded by the Commonwealth of Virginia and the Robert Wood Johnson Foundation .
The researchers' latest paper in a series of articles on response to antidepressants analyzed 2,467 subgroups of patients who received psychotherapy. "Efficacy of Antidepressants in Combination with Psychotherapy" was published online in March 2024 in the Journal of Mental Health Policy and Economics.
Other authors include Tulay J. Suillow of Temple University, and Mary Cannon and Conor McCandless of the Royal College of Surgeons in Dublin, Ireland. .
Source : news-medical