Personalized Interventions for Alcoholism and Anxiety

Overseen By Marilyn Piccirillo, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Rutgers, The State University of New Jersey

Disqualifiers: Currently receiving counseling, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 12 weeks

81 Participants Needed

Trial Summary

What is the purpose of this trial?

Anxiety and anxiety-related disorders frequently co-occur with alcohol use problems resulting in an enormous humanitarian and economic cost to society. The proposed research will use digital technology to examine person-specific risk factors predicting problematic alcohol use in individuals vulnerable to anxiety and anxiety-related disorders and will use this information to design a personalized intervention for individuals seeking psychological treatment. Results from this research will integrate output from novel and innovative digital technology methods into psychotherapy, advancing research on personalized treatment and prevention efforts.

Will I have to stop taking my current medications?

The trial does not specify if you need to stop taking your current medications, but you must be on a stable dose of any psychiatric medication for the duration of the study.

What data supports the effectiveness of the treatment Digital Phenotyping, Digital Phenotyping, Personalized Digital Intervention for alcoholism and anxiety?

Research shows that digital phenotyping, which uses data from smartphones to track behavior, has been effective in predicting relapse in mental health conditions like schizophrenia and improving depression diagnostics. This suggests it could help tailor interventions for alcoholism and anxiety by providing real-time insights into patients' behaviors and symptoms. ^{1 2 3 4 5}

Is the treatment using digital phenotyping and personalized digital intervention generally safe for humans?

The research articles provided do not contain specific safety data for digital phenotyping or personalized digital interventions, but they discuss general methods for detecting and managing adverse drug events, which are important for ensuring the safety of treatments. ^{6 7 8 9 10}

How does the treatment in the 'Personalized Interventions for Alcoholism and Anxiety' trial differ from other treatments?

This treatment is unique because it focuses on personalized interventions, potentially using technology like digital phenotyping and machine learning to tailor the approach to individual needs, unlike traditional one-size-fits-all methods. ^{11 12 13 14 15}

Research Team

Marilyn Piccirillo, PhD

Principal Investigator

Rutgers Robert Wood Johnson Medical School

Eligibility Criteria

This trial is for adults aged 18-65 with anxiety or related disorders and problematic alcohol use, who are interested in telehealth psychotherapy. Participants must have a smartphone and live in the state where the principal investigator is licensed.

Inclusion Criteria

I have access to a smartphone.

I experience significant anxiety or have an anxiety disorder.

I struggle with alcohol use.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-3 weeks

Treatment

Participants receive a personalized intervention using CBT skills or participate in control conditions for comparison

12 weeks

Weekly sessions

Follow-up

Participants are monitored for safety and effectiveness after treatment

3 weeks

Treatment Details

Interventions

• Digital Phenotyping

Trial Overview The study tests personalized interventions using digital technology to manage anxiety-related disorders and reduce problematic alcohol use. It compares cognitive behavioral therapy skills tailored to individuals versus standard supportive counseling.

Participant Groups

Group I: Personalized intervention condition Experimental Treatment 1 Intervention

This experimental condition will test a data-driven, person-specific intervention using CBT skills.

Group II: Therapeutic control condition Active Control 1 Intervention

This control condition will provide an experimental comparison to test the process of personalization.

Group III: Tracking control condition Active Control 1 Intervention

This second control condition will provide an experimental comparison to test the effects of health-related tracking and therapeutic contact.

Who Is Running the Clinical Trial?

Rutgers, The State University of New Jersey

Lead Sponsor

Trials

471

Recruited

81,700+

University of Washington

Lead Sponsor

Trials

1,858

Recruited

2,023,000+

National Institute on Alcohol Abuse and Alcoholism (NIAAA)

Collaborator

Trials

865

Recruited

1,091,000+

Findings from Research

The study involving 24 individuals with alcohol-associated liver disease demonstrated that smartphone sensors can effectively track alcohol craving and mood, suggesting their potential as useful tools for monitoring these conditions.

Significant correlations were found between alcohol craving and features derived from smartphone sensors, such as location entropy and accelerometer data, indicating that digital phenotyping could help predict relapse risk and disease progression.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Smartphone sensor data estimate alcohol craving in a cohort of patients with alcohol-associated liver disease and alcohol use disorder. Wu, T., Sherman, G., Giorgi, S., et al.[2023]

Smartphone-based digital phenotyping can effectively detect behavioral anomalies in individuals with serious mental illnesses, achieving 89% sensitivity and 75% specificity in predicting relapse in schizophrenia.

This technology allows for real-time monitoring of symptoms and behaviors, highlighting its potential for personalized clinical care, although further research is needed to enhance its specificity and integrate it into clinical practice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Anomaly detection to predict relapse risk in schizophrenia. Henson, P., D'Mello, R., Vaidyam, A., et al.[2021]

Using data from personal electronic devices like smartphones can provide continuous and objective measures of human function, which may enhance diagnosis and treatment in psychiatry.

To ensure the successful adoption of digital phenotyping in clinical settings, research must focus on practical applications, safety concerns, and the needs of patients, while also developing scalable technology platforms and fostering collaboration among various stakeholders.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety. Huckvale, K., Venkatesh, S., Christensen, H.[2023]

Digital phenotyping (DP) using mobile health technologies can significantly improve the accuracy of depression diagnostics by providing objective measurements through ecological momentary assessments (EMA), which include both active and passive data collection.

The integration of DP into clinical settings, supported by interdisciplinary collaboration between psychiatry and engineering, can enhance clinical decision-making and potentially lead to better treatment outcomes for patients with depression.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Digital phenotyping in depression diagnostics: Integrating psychiatric and engineering perspectives. Kamath, J., Leon Barriera, R., Jain, N., et al.[2022]

Digital phenotyping (DP) is an emerging approach that captures a wide range of biopsychosocial data in real time, which can help predict mental health issues in children and adolescents, especially given that 75% of mental disorders start early in life.

While DP has the potential to revolutionize mental health care by enabling early intervention through comprehensive data analysis, challenges remain in effectively capturing, storing, and analyzing this complex data to improve treatment outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Digital Phenotyping With Mobile and Wearable Devices: Advanced Symptom Measurement in Child and Adolescent Depression. Sequeira, L., Battaglia, M., Perrotta, S., et al.[2020]

The study developed ADEpedia-on-OHDSI, an informatics platform that integrates FDA's Adverse Event Reporting System (FAERS) data into a standardized format, allowing for improved pharmacovigilance research with a total of 4,619,362 adverse event cases processed.

Mapping accuracy for drug names was high at 96%, and the platform successfully detected triptan-related vascular event signals, demonstrating that combining spontaneous reporting and electronic health record data can enhance signal detection in drug safety monitoring.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model. Yu, Y., Ruddy, KJ., Hong, N., et al.[2020]

Adverse drug reactions are a significant issue in both patient care and drug development, highlighting the need for improved prediction and prevention strategies in the pharmaceutical industry.

The integration of clinical knowledge and patient context into the drug design process is expected to enhance drug safety and efficacy, with advancements in data analysis and cloud computing likely to play a crucial role in this evolution over the next five years.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Fusion of nonclinical and clinical data to predict human drug safety. Johnson, DE.[2013]

The definition of an adverse drug event (ADE) should be tailored to the specific purpose of the evaluation, with stricter definitions needed for scientific studies and more flexible ones for clinical use.

Postmarketing safety data for drugs is limited at launch, but can be supplemented through systems like the FDA's Spontaneous Reporting System and targeted research projects, emphasizing the importance of robust epidemiological evidence for regulatory actions like drug recalls.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Adverse drug events: identification and attribution. Rogers, AS.[2022]

In 2001, there were approximately 4.3 million visits to healthcare facilities in the U.S. due to adverse drug events (VADEs), indicating a significant patient safety concern.

The study found that VADEs were more common in elderly patients aged 65-74 and in females, highlighting the need for targeted safety measures in these populations.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Ambulatory care visits for treating adverse drug effects in the United States, 1995-2001. Zhan, C., Arispe, I., Kelley, E., et al.[2019]

The proposed three-part framework for analyzing adverse events includes phases for documenting incidents, conducting in-depth reviews, and assessing the association between exposure and adverse events, which can enhance product safety.

By standardizing the evaluation of adverse events through this framework, companies can better manage risks and improve consumer products based on reliable data.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Post-market surveillance of consumer products: Framework for adverse event management. Kingston, R., Sioris, K., Gualtieri, J., et al.[2022]

A digital intervention for generalized anxiety disorder (GAD) showed moderate effectiveness in reducing daytime worry duration and nighttime worry frequency among 163 participants over a six-day period.

The study found that individuals with higher baseline worry levels and fewer subjective health complaints were more likely to benefit from the intervention, suggesting that personalized treatment approaches could enhance efficacy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention. Gyorda, JA., Nemesure, MD., Price, G., et al.[2023]

A study involving 264 participants demonstrated that machine learning models can accurately predict symptoms of generalized anxiety disorder (GAD) using just one week of passive movement data, achieving a correlation of r = 0.511.

The models showed high accuracy in identifying individuals with elevated GAD symptoms, with an area under the curve (AUC) of 0.892, indicating that wearable technology can provide a scalable and cost-effective method for monitoring anxiety symptoms in real-time.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Digital phenotyping of generalized anxiety disorder: using artificial intelligence to accurately predict symptom severity using wearable sensors in daily life. Jacobson, NC., Feng, B.[2022]

Substance use disorders (SUDs) are complex and diverse, requiring personalized treatment approaches rather than a one-size-fits-all solution, as factors like severity and type of substance vary widely among individuals.

To effectively address SUDs, there is a need for multivariate phenotyping to identify individual characteristics and for the development of flexible, technology-based interventions, such as computer-based cognitive behavioral therapy (CBT4CBT), to tailor treatments to specific needs.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The profound heterogeneity of substance use disorders: Implications for treatment development. Carroll, KM.[2022]

A study involving 189 outpatients with opioid-use disorder used a randomForest algorithm to predict cravings for heroin and cocaine, achieving high overall accuracy (up to 0.93) in predicting when cravings would not occur, but lower accuracy in predicting actual cravings.

The findings suggest that while passive monitoring through GPS data can provide some predictive insights, accurately predicting subtle events like cravings or stress may require active user input, as high overall accuracy can sometimes hide the prevalence of false alarms.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. Epstein, DH., Tyburski, M., Kowalczyk, WJ., et al.[2023]

The Drinker's Check-Up (DCU) software program is designed to help problem drinkers by providing integrated assessment and feedback, making it accessible for therapists without specialized training in substance abuse.

Preliminary data from an ongoing clinical trial suggest that the DCU is an effective stand-alone intervention for a variety of individuals experiencing alcohol-related issues.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Using technical innovations in clinical practice: the Drinker's Check-Up software program. Squires, DD., Hester, RK.[2019]

References

1. United States pubmed.ncbi.nlm.nih.gov

Smartphone sensor data estimate alcohol craving in a cohort of patients with alcohol-associated liver disease and alcohol use disorder. [2023]

2. United States pubmed.ncbi.nlm.nih.gov

Anomaly detection to predict relapse risk in schizophrenia. [2021]

3. England pubmed.ncbi.nlm.nih.gov

Toward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety. [2023]

4. United States pubmed.ncbi.nlm.nih.gov

Digital phenotyping in depression diagnostics: Integrating psychiatric and engineering perspectives. [2022]

5. United States pubmed.ncbi.nlm.nih.gov

Digital Phenotyping With Mobile and Wearable Devices: Advanced Symptom Measurement in Child and Adolescent Depression. [2020]

6. United States pubmed.ncbi.nlm.nih.gov

ADEpedia-on-OHDSI: A next generation pharmacovigilance signal detection platform using the OHDSI common data model. [2020]

7. England pubmed.ncbi.nlm.nih.gov

Fusion of nonclinical and clinical data to predict human drug safety. [2013]

8. United States pubmed.ncbi.nlm.nih.gov

Adverse drug events: identification and attribution. [2022]

9. Netherlands pubmed.ncbi.nlm.nih.gov

Ambulatory care visits for treating adverse drug effects in the United States, 1995-2001. [2019]

10. Netherlands pubmed.ncbi.nlm.nih.gov

Post-market surveillance of consumer products: Framework for adverse event management. [2022]

11. Netherlands pubmed.ncbi.nlm.nih.gov

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention. [2023]

12. United States pubmed.ncbi.nlm.nih.gov

Digital phenotyping of generalized anxiety disorder: using artificial intelligence to accurately predict symptom severity using wearable sensors in daily life. [2022]

13. United States pubmed.ncbi.nlm.nih.gov

The profound heterogeneity of substance use disorders: Implications for treatment development. [2022]

14. England pubmed.ncbi.nlm.nih.gov

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. [2023]

15. United States pubmed.ncbi.nlm.nih.gov

Using technical innovations in clinical practice: the Drinker's Check-Up software program. [2019]