Researchers at George Mason University in Fairfax, Va.<\/a>, have revamped MeAgainMeds.com<\/a>, their free tool that uses AI to recommend antidepressants to patients based on their demographics and medical history. Farrokh Alemi, PhD<\/a>, a professor of health informatics at GMU\u2019s College of Public Health<\/a>, spearheaded the effort.<\/p>\n \u201cMe Again Meds, it\u2019s a play on the fact that many people who take antidepressants feel that they are not themselves,\u201d Alemi tells Fortune<\/em>. \u201cWe want to help them with a selection of an antidepressant that has fewer side effects for them and is more effective for them.\u201d<\/p>\n The pursuit is personal. After losing a loved one to suicide, Alemi has in recent years dedicated the bulk of his research to AI in depression management<\/a>.<\/p>\n Alemi and his colleagues have published several studies in conjunction with the development of Me Again Meds. In research published in 2021 in the journal eClinicalMedicine<\/em><\/a>, they used the OptumLabs<\/a> health insurance database to analyze nearly 3.7 million U.S. patients who had been diagnosed with major depression and were taking antidepressants. From 2001\u20132018, patients collectively recorded more than 10.2 million treatment episodes, or courses of medication.<\/p>\n Researchers assessed patients taking 15 of the most commonly prescribed antidepressants\u2014including citalopram (Celexa)<\/a>, escitalopram (Lexapro)<\/a>, fluoxetine (Prozac)<\/a>, and sertraline (Zoloft)<\/a>\u2014and found vast differences in how the medications benefitted distinct groups of people. For instance, 25% of teenage boys treated with fluoxetine experienced symptom remission, while 59% of women ages 65\u201379 saw symptom remission on the same medication.<\/p>\n No medication was best for everyone and within the age\/sex subgroups, the best antidepressant was on average over 20 times more effective than the worst. Alemi\u2019s team showed that if clinicians had prescribed the medications with the highest remission rates, 1.5 times more patients, or 1.6 million more treatment episodes, would have had symptom remission.<\/p>\n \u201cPeople are going through three or four trials before they get the right medication. Many don\u2019t even get the right medication,\u201d Alemi says. \u201cAfrican Americans are not given the right medication, Hispanics are given the wrong medication; all kinds of minority differences are ignored. All kinds of medical history information is ignored.\u201d<\/p>\n An engineer by trade, Alemi expects systems to function well. Despite clinicians\u2019 best intentions, the U.S. health care system\u2019s practice of prescribing antidepressants \u201creminds me of 18th-century medicine,\u201d he says. \u201cWhy are we not getting the right medication the first time around?\u201d<\/p>\n Joe Raedle\u2014Getty Images<\/p>\n<\/div>\n In the same 2021 study, Alemi\u2019s team went beyond age and biological sex to match patients to the most effective antidepressants<\/a>. They incorporated study participants\u2019 medical histories to generate nearly 17,000 patient subgroups. Not expecting doctors and patients<\/a> to sift through so many options, researchers turned to AI<\/a>, delivering the first iteration of Me Again Meds.<\/p>\n For example, if you\u2019re a man 41\u201364 years old with alcohol dependence, Me Again Meds determines sertraline may be most likely to relieve your symptoms<\/a> based on an analysis of more than 700 patients with a similar medical history. If you\u2019re a woman 20\u201340 years old with obesity and polycystic ovary syndrome, Me Again Meds recommends bupropion (Wellbutrin)<\/a>, with the caveat that the medication may be ineffective because so few patients in the database match your criteria. The website doesn\u2019t ask for identifying information but provides a report ID you can share with your doctor.<\/p>\n Though patient feedback has been overwhelmingly positive, Alemi says clinicians\u2019 reactions have been mixed. In focus groups and interviews, for example, providers said the analytical model failed to match the nuance of real-world antidepressant prescription and wasn\u2019t representative of the patients they treat. Despite the database\u2019s volume, some clinicians also took issue that it wasn\u2019t a randomized sample of patients with depression.<\/p>\n Me Again Meds has been revised several times in the last three years. Most recently, in a study published in March in the Journal of Mental Health Policy and Economics<\/em><\/a>, Alemi\u2019s team analyzed roughly 2,500 of the site\u2019s subgroups of patients who had received psychotherapy. Still, Me Again Meds remains a survey-based AI that outputs varying multiple-choice questions based on respondents\u2019 previous answers. It\u2019s also brief, taking just minutes to complete. A more advanced chatbot is coming soon.<\/p>\n \u201cOur eventual goal is to create a standalone AI system that diagnoses patients and suggests treatments for the patient in behavioral health,\u201d Alemi says. \u201cThat intake process is a long conversation, and I don\u2019t see any long conversations right now in the published literature.\u201d<\/p>\n Last year, GMU launched a prototype chatbot site<\/a> that\u2019s still active; the conversation kicks off with the bot asking the patient if they\u2019ve experienced major depression. More than 13% of U.S. adults use antidepressants\u2014including 18% of women and 8% of men\u2014according to data the Centers for Disease Control and Prevention<\/a> collected from 2015\u201318. The COVID-19 pandemic<\/a> exacerbated their use.<\/p>\n \u201cWe are conscious that the demand for the service would be very large,\u201d Alemi says.<\/p>\n Patient safety is a top concern in bringing an artificial clinician to scale, Alemi says. For example, if a patient is displaying risk factors for suicide, the chatbot would need to terminate the conversation and connect the patient to a live person who is trained to help. Even at a smaller scale, having people monitor chats in real time will help keep the chatbot running smoothly. What\u2019s more, Alemi and his colleagues are working to reduce AI hallucination<\/a>, or the generation of false or misleading information. They\u2019re also developing a referral system to connect patients without a primary care provider to a prescribing clinician.<\/p>\n \u201cThis is a very complicated product; it\u2019s not something that you click on the switch and it works,\u201d Alemi says. \u201cIt has many significant parts, and we are working component by component to put it in place.\u201d<\/p>\n Alemi expects the chatbot\u2019s human monitoring feature will be live by the end of the year. He\u2019s also tackling the disparities he sees in the prescription of antidepressants to patients of color. Alemi\u2019s team recently received a grant from the National Institutes of Health (NIH) to research how Black patients with depression respond to medication<\/a>, using Me Again Meds and the NIH\u2019s All of Us<\/a> database.<\/p>\n da-kuk\u2014Getty Images<\/p>\n<\/div>\n Contrary to what its name suggests, antidepressant medication is prescribed to treat more than clinical depression. The Food and Drug Administration<\/a> has approved certain antidepressants to treat these disorders<\/a>:<\/p>\n In addition, clinicians may prescribe antidepressants for off-label use to treat conditions such as migraine<\/a>, chronic pain, and insomnia<\/a>.\u00a0<\/p>\n While Me Again Meds may ask you about a variety of mood, depression, and anxiety disorders<\/a>, it was designed to help people diagnosed with major depression.<\/p>\n Alemi hopes Me Again Meds proves a powerful resource for patients and providers but notes it doesn\u2019t constitute medical advice. The website is meant to inform discussion between you and your doctor, and only a licensed clinician can prescribe medication Me Again Meds may recommend.<\/p>\n If you\u2019re already taking an antidepressant, don\u2019t stop doing so unless instructed by your doctor; antidepressant discontinuation syndrome<\/a> may occur without a doctor\u2019s guidance.<\/p>\n If you need immediate mental health support, contact the <\/em>988 Suicide & Crisis Lifeline<\/em><\/a>.<\/em><\/p>\n For more on mental health:<\/strong><\/p>\n<\/div>\n Subscribe to Well Adjusted, our newsletter full of simple strategies to work smarter and live better, from the Fortune Well team. <\/span>Sign up<\/span><\/a> for free today.<\/span><\/p>\n<\/div>\n![\"Bottles](\"https:\/\/fortune.com\/img-assets\/wp-content\/uploads\/2024\/08\/GettyImages-3123241-e1723583040696.jpg?w=1440&q=75\"\/)
Can AI keep up with demand for antidepressants?<\/h2>\n
![\"Patients](\"https:\/\/fortune.com\/img-assets\/wp-content\/uploads\/2024\/08\/GettyImages-1935648577-e1723494612389.jpg?w=1440&q=75\"\/)
What do antidepressants treat?<\/h2>\n
Integrating AI into your next doctor\u2019s appointment<\/h2>\n