In a new study just published in Nature Mental Health (details below), we developed and validated machine learning (ML) biomarkers based on electroencephalography (EEG) data for predicting outcome with two types of psychotherapy for Post-Traumatic Stress Disorder (PTSD) patients.

The main types of evidence-based therapy for PTSD are:

1. Progressive mastery over trauma-related emotion through exposure –like prolonged exposure (PE), or
2. Working through of daily emotion/cognitive-bias driven challenges –like cognitive processing therapy (CPT)

Despite clinical evidence supporting PE or CPT, many patients do not respond.

• Who the responders are is not known before treatment (a biomarker question!).
• Also, not known is whether the same kind of person responds to only one or both treatments (a transfer learning question!)

We collected EEG data on a large number of US military veterans getting PE or CPT in several Veteran Affairs (VA) clinics and then trained ML models to predict outcome (improvement in PTSD symptoms). Not only could EEG ML predict treatment, but models trained on one therapy could predict the other.

Not only could EEG ML predict responders, but it could also identify non-responders.…people for whom neither therapy works.

This work is an exciting advance in precision psychiatry — finding the right treatment for each patient — and further shows the power of electroencephalography (EEG) and machine learning (ML).

– Dr. Amit Etkin is the Founder and CEO at Alto Neuroscience and a Professor at Stanford University, and expreses his thanks to funders Cohen Veterans Bioscience and National Institute of Mental Health (NIMH), as well as the support of U.S. Department of Veterans Affairs and patients.

The Study:

Machine learning-based identification of a psychotherapy-predictive electroencephalographic signature in PTSD (Nature Mental Health). From the Abstract:

Although psychotherapy is at present the most effective treatment for posttraumatic stress disorder (PTSD), its efficacy is still limited for many patients, due mainly to the substantial clinical and neurobiological heterogeneity in the disease … This study investigates whether individual patient-level resting-state EEG connectivity can predict psychotherapy outcomes in PTSD. We developed a treatment-predictive EEG signature using machine learning applied to high-density resting-state EEG collected from military veterans with PTSD. The predictive signature was dominated by theta frequency EEG connectivity differences and was able to generalize across two types of psychotherapy—prolonged exposure and cognitive processing therapy. Our results also advance a biological definition of a PTSD patient subgroup who is resistant to psychotherapy, which is currently the most evidence-based treatment for the condition. The findings support a path towards clinically translatable and scalable biomarkers that could be used to tailor interventions for each individual or drive the development of novel treatments.

The Study in Context:

• Alto Neuroscience raises $60M (equity + credit) to help fix the “trial and error” approach to psychiatric medication
• Precision psychiatry pioneer Alto Neuroscience raises $35M to advance digital biomarker-to-treatment platform
• Machine-learning study finds EEG brain signatures that predict response to antidepressant treatments

The post Study shows the power of electroencephalography and machine learning to help predict response to psychotherapy (or lack thereof) in patients with PTSD appeared first on SharpBrains.