With no tools available to support physician decision making, this new study approach opens up new opportunities to rapidly accelerate the field of personalized psychiatry and improve care
TEL AVIV, Israel (PRWEB)
July 21, 2021
Taliaz, a mental health startup harnessing science and artificial intelligence (AI) to revolutionise mental health treatment and management, today announced the publication of a new study validating its unique scientific data-driven approach to predict response to antidepressant treatment. The study shows that analyzing combinations of patients’ genetic, clinical, and demographic factors using machine learning offers a promising new method to improve accuracy in prescribing antidepressants.
The new study published in the peer-reviewed Nature journal, Translational Psychiatry, was led by Taliaz’s CEO and experimental neuroscientist, Dr. Dekel Taliaz, Taliaz’s Chief Scientific Officer, Amit Spinrad, and psychiatrist, Prof. Bernard Lerer of the Biological Psychiatry Laboratory at the Hadassah-Hebrew University Medical Center, Jerusalem, Israel and an Advisor to Taliaz.
“Today, treating major depressive disorder (MDD), in everyday clinical practice is highly complex with limited consultation time and many possible factors affecting physician treatment decisions, such as patient’s medical history, medical comorbidities and their socio-demographic background. This makes tailoring the optimal medication for each patient highly challenging,” said Prof. Bernard Lerer. “Current practice for MDD treatment relies mainly on trial and error, with an estimated 42–53% response rates for antidepressant use. With no tools available to support physician decision making, this new study approach opens up new opportunities to rapidly accelerate the field of personalized psychiatry and improve care.”
The authors employed a data-driven approach using proprietary deep analytic methods and a comprehensive literature research to select and analyze thousands of combinations of patients’ genetic, clinical, and demographic features, considered important factors in predicting antidepressant treatment response. The authors analyzed response patterns of more than 4500 patients to antidepressant medications in the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study and the Pharmacogenomics Research Network Antidepressant Medication Pharmacogenomic Study (PGRN-AMPS). State-of-the-art machine learning (ML) tools were then applied to generate a predictive treatment algorithm. STAR*D and PGRN-AMPS are two of the world’s largest prospective studies for optimal antidepressant administration.
The developed algorithm successfully predicted response to antidepressant medication the first time with a balanced accuracy rate of 72.3% (SD 8.1) and 70.1% (SD 6.8) across the different medications in the validation and test set, respectively (p < 0.01 for all models).
“This peer-reviewed publication corroborates our unique approach for the design of the PREDICTIX prediction algorithm to optimize treatment for mental health. With the efficacy of current practice antidepressants in the range of 42–53%, and currently available pharmacogenomic tests, based on using solely genetic data, yielding only slightly higher response rates (39–64%), we are delighted to achieve a first-time prescribing accuracy of greater than 72%,” said Dr. Dekel Taliaz, CEO and co-founder of Taliaz.
Taliaz is revolutionizing mental health treatment and management with PREDICTIX. Combining science with AI, PREDICTIX translates complex genetic, demographic and clinical patient data into a time-saving assessment, management and prescribing support tool for healthcare providers. PREDICTIX improves treatment prescribing accuracy and can save a minimum of 12% in mental health costs. PREDICTIX is currently available for commercial use in the European Union, United Kingdom, Australia and Israel.
For more information, please visit https://www.predictix.ai.
 Taliaz D, et al. Optimizing prediction of response to antidepressant medications using machine learning and integrated genetic, clinical, and demographic data. Transl Psychiatry. 2021 Jul 8;11(1):381. https://www.nature.com/articles/s41398-021-01488-3.
 Khan A, Fahl Mar K, Faucett J, Khan Schilling S, Brown WA. Has the rising placebo response impacted antidepressant clinical trial outcome? Data from the US Food and Drug Administration 1987-2013. World Psychiatry. 2017;16:181–92. 59.
 Cipriani A, Salanti G, Furukawa TA, Egger M, Leucht S, Ruhe HG, et al. Antidepressants might work for people with major depression: Where do we go from here? Lancet Psychiatry. 2018;5:461–63.
 Rosenblat JD, Lee Y, McIntyre RS. The effect of pharmacogenomic testing on response and remission rates in the acute treatment of major depressive disorder: a meta-analysis. J Affect Disord. 2018;241:484–91.
Share article on social media or email: