Personalized Depression Treatment

Traditional therapies and medications are not effective for a lot of people suffering from depression treatment techniques. The individual approach to treatment could be the solution.

Cue is a digital intervention platform that transforms passively acquired sensor data from smartphones into personalised micro-interventions that improve mental health. We analyzed the best-fitting personalized ML models to each subject, using Shapley values to discover their characteristic predictors. This revealed distinct features that changed mood in a predictable manner over time.

Predictors of Mood

Depression is the leading cause of mental illness across the world.1 Yet only half of those suffering from the condition receive treatment. To improve outcomes, clinicians must be able identify and treat patients most likely to respond to specific treatments.

The ability to tailor depression treatments is one way to do this. By using sensors for mobile phones as well as an artificial intelligence voice assistant and other digital tools researchers at the University of Illinois Chicago (UIC) are working on new ways to predict which patients will benefit from the treatments they receive. With two grants totaling more than $10 million, they will employ these tools to identify biological and behavioral predictors of responses to antidepressant medications as well as psychotherapy.

The majority of research done to the present has been focused on clinical and sociodemographic characteristics. These include demographic variables such as age, gender and education, clinical characteristics including symptom severity and comorbidities, and biological markers like neuroimaging and genetic variation.

While many of these variables can be predicted by the data in medical records, very few studies have employed longitudinal data to study predictors of mood in individuals. They have not taken into account the fact that mood varies significantly between individuals. Therefore, it is crucial to devise methods that allow for the determination and quantification of the individual differences between mood predictors treatments, mood predictors, etc.

The team's new approach uses daily, in-person evaluations of mood and lifestyle variables using a smartphone app called AWARE, a cognitive evaluation with the BiAffect app and electroencephalography -- an imaging technique that monitors brain activity. The team can then develop algorithms to detect patterns of behavior and emotions that are unique to each person.

In addition to these modalities, the team also developed a machine-learning algorithm to model the dynamic factors that determine a person's depressed mood. The algorithm combines the individual characteristics to create a unique "digital genotype" for each participant.

This digital phenotype was associated with CAT DI scores, a psychometrically validated symptom severity scale. The correlation was weak, however (Pearson r = 0,08, P-value adjusted for BH = 3.55 10 03) and varied significantly among individuals.

Predictors of symptoms

Depression is among the world's leading causes of disability1 yet it is often underdiagnosed and undertreated2. In addition an absence of effective interventions and stigma associated with depressive disorders prevent many individuals from seeking help.

To assist in individualized treatment, it is important to determine the predictors of symptoms. Current prediction methods rely heavily on clinical interviews, which aren't reliable and only identify a handful of features associated with depression.

Machine learning can improve the accuracy of the diagnosis and treatment of depression by combining continuous digital behavior phenotypes collected from smartphone sensors with a validated mental health tracker online (the Computerized Adaptive Testing Depression Inventory CAT-DI). These digital phenotypes are able to capture a variety of unique actions and behaviors that are difficult to record through interviews, and also allow for continuous, high-resolution measurements.

The study comprised University of California Los Angeles students who had mild depression Treatments to severe depression symptoms who were enrolled in the Screening and Treatment for Anxiety and Depression program29 that was developed as part of the UCLA Depression Grand Challenge. Participants were referred to online assistance or medical care based on the severity of their depression. Patients with a CAT DI score of 35 65 students were assigned online support by an instructor and those with a score 75 were sent to clinics in-person for psychotherapy.

Participants were asked a set of questions at the beginning of the study regarding their psychosocial and demographic characteristics as well as their socioeconomic status. The questions covered age, sex and education as well as marital status, financial status and whether they were divorced or not, the frequency of suicidal thoughts, intentions or attempts, as well as how to treat depression and anxiety often they drank. The CAT-DI was used for assessing the severity of depression symptoms on a scale from 0-100. The CAT-DI tests were conducted every other week for the participants who received online support and once a week for those receiving in-person care.

Predictors of the Reaction to Treatment

The development of a personalized depression treatment is currently a top research topic and a lot of studies are aimed at identifying predictors that enable clinicians to determine the most effective medications for each patient. Pharmacogenetics in particular uncovers genetic variations that affect the way that our bodies process drugs. This lets doctors choose the medications that will likely work best for each patient, while minimizing the time and effort needed for trials and errors, while eliminating any adverse negative effects.

Another promising approach is to create prediction models combining clinical data and neural imaging data. These models can be used to identify which variables are most likely to predict a specific outcome, like whether a medication will improve mood or symptoms. These models can also be used to predict a patient's response to an existing treatment, allowing doctors to maximize the effectiveness of their current therapy.

A new generation uses machine learning methods such as algorithms for classification and supervised learning, regularized logistic regression and tree-based methods to integrate the effects from multiple variables and improve predictive accuracy. These models have been proven to be useful in predicting the outcome of treatment, such as response to antidepressants. These approaches are becoming more popular in psychiatry and will likely become the standard of future treatment.

In addition to ML-based prediction models research into the underlying mechanisms of depression is continuing. Recent research suggests that depression is related to the dysfunctions of specific neural networks. This suggests that an individualized treatment for depression will be based on targeted therapies that restore normal functioning to these circuits.

One way to do this is to use internet-based interventions that can provide a more individualized and personalized experience for patients. One study found that a web-based program improved symptoms and improved quality of life for MDD patients. A controlled study that was randomized to a personalized treatment for depression showed that a significant number of patients experienced sustained improvement and fewer side consequences.

Predictors of Side Effects

A major issue in personalizing depression treatment is predicting which antidepressant medications will have very little or no side effects. Many patients are prescribed a variety drugs before they find a drug that is both effective and well-tolerated. Pharmacogenetics offers a new treatments for depression and exciting method of selecting antidepressant medications that is more effective and precise.

A variety of predictors are available to determine the best antidepressant to prescribe, including genetic variants, phenotypes of patients (e.g., sex or ethnicity) and the presence of comorbidities. However, identifying the most reliable and accurate factors that can predict the effectiveness of a particular treatment will probably require randomized controlled trials of significantly larger numbers of participants than those normally enrolled in clinical trials. This is because it could be more difficult to detect the effects of moderators or interactions in trials that contain only one episode per person rather than multiple episodes over a long period of time.

Furthermore the prediction of a patient's reaction to a particular medication is likely to require information on symptoms and comorbidities as well as the patient's previous experience of its tolerability and effectiveness. Presently, only a handful of easily measurable sociodemographic and clinical variables are believed to be correlated with response to MDD, such as gender, age race/ethnicity, SES BMI, the presence of alexithymia, and the severity of depression symptoms.

The application of pharmacogenetics to depression treatment is still in its infancy and there are many hurdles to overcome. First, it is essential to have a clear understanding and definition of the genetic factors that cause depression, as well as an understanding of an accurate indicator of the response to treatment. Additionally, ethical issues, such as privacy and the ethical use of personal genetic information, should be considered with care. The use of pharmacogenetics may be able to, over the long term, reduce stigma surrounding treatments for mental illness and improve the quality of treatment. However, as with any approach to psychiatry careful consideration and implementation is necessary. In the moment, it's ideal to offer patients a variety of medications for depression that are effective and encourage patients to openly talk with their doctor.