Researchers in the Netherlands have harnessed AI to successfully predict within a week whether an antidepressant would work in patients with major depresssive disorder (MDD).
Using an AI algorithm, a brain scan and an individual’s clinical information, the team from Amsterdam UMC and Radboudumc could see up to eight weeks faster whether or not the medication would work.
The finding are published in the American Journal of Psychiatry.
Liesbeth Reneman, Professor of Neuroradiology at Amsterdam UMC, said: “This is important news for patients.
“Normally, it takes six to eight weeks before it is known whether an antidepressant will work.”
The researchers whether they could predict the effect of the antidepressant sertraline, which is one of the most commonly prescribed drugs in the United States and Europe.
In a previous US study, MRI scans were administered to 229 patients with MDD before and after a week of treatment with sertraline or placebo.
The Amsterdam research team then developed and applied an algorithm to this data to investigate whether they could predict the treatment response to sertraline.
This analysis showed that a third of patients would respond to the drug while two-thirds would not.
Prof. Reneman said: “With this method, we can already prevent two thirds of the number of ‘erroneous’ prescriptions of sertraline and thus offer better quality of care for the patient.
“Because the drug also has side effects.”
Eric Ruhé, psychiatrist at Radboudumc, added: “The algorithm suggested that blood flow in the anterior cingulate cortex, the area of brain involved in emotion regulation, would be predictive of the efficacy of the drug.
“And at the second measurement, a week after the start, the severity of their symptoms turned out to be additionally predictive.”
In the future, the new method may help to better tailor sertraline treatment to the individual patient.
Currently, there is no precise prediction tool in clinical use.
Instead, the patient is given the medication and after six to eight weeks – or in practice, often up to several months – a clinician will check whether the medication is working.
If the symptoms do not subside, the patient is given another antidepressant, in process that can repeat itself several times.
Enhancing empathy and outcomes: The impact of digital design and UX for rare disease communities
Exploring success: Intelligent fieldwork and Fearsome in usability testing
Europe’s dedicated event for neuro rehabilitation experts returns
100th patient undergoes Deep Brain Stimulation at The London Clinic
Free app for people with Parkinson’s receives charity funding
Listen: Transforming the NHS skin cancer pathway
SurgTech 2024 will shine a light on innovation across the surgical pathway
Trusts to use AI to reduce skin cancer backlog and increase efficiency
Times are hard, but trusts can still make positive IT choices
AI helps cut nuisance alerts for healthcare teams
- Mental health3 weeks ago
Blood test predicts schizophrenia psychosis and matches treatments
- Medtech7 days ago
British tech firm gets green light on fibroids patent
- Digital health4 weeks ago
Highland Marketing welcomes Natasha Phillips to its advisory board
- Research2 weeks ago
Health tech powers recruitment of 10,000+ into Parkinson’s study