Researchers from the University of Sheffield, published in the journal The Lancet the article, "Dynamic prediction of psychological treatment outcomes: development and validation of a prediction model using routinely collected symptom data"
The most common mental health-related conditions can receive effective treatment through psychotherapy; however, this pattern may not be repeated in all patients. Some patients require timely identification to achieve correct treatment. Researchers at the University of Sheffield, published a study that aimed to: "develop and validate a dynamic model to predict psychological treatment outcomes, and to compare the model with currently used methods, including expected treatment response models and machine learning models.".
This study worked to achieve validation and development of a prediction model. The authors used data from two UK studies containing data from adult patients aged 16 years and older who had accessed therapy through Improving Access to Psychological Therapies (IAPT) services between Mallet 2012 and June 2018.
“To develop and validate a dynamic model to predict psychological treatment outcomes, and to compare the model with currently used methods, including expected treatment response models and machine learning models.” Patients generally access guided self-help, however, they then have the option to access high-intensity therapies if symptoms persist.
Low-intensity sessions are based on cognitive-behavioral therapy, and include learning coping skills with the support of a clinician, the authors explain. High-intensity interventions, on the other hand, "are psychotherapies of longer duration (up to 20 sessions), including cognitive behavioural therapy, interpersonal psychotherapy, person-centred counselling, and other empirically-supported treatments."
The dynamic prediction model developed was trained through iterative logistic regression analysis with variables such as patient profile, neural networks, among others.
See the results of the study at the following link:https://www.thelancet.com/journals/landig/article/PIIS2589-7500(21)00018-2/fulltext#seccestitle80
