Investigating Methods for Child Mental Health Conditions
Researching Children's Mental Health Problems
Rebecca McNally Keehn
Primary Investigator
Brief description of study
The purpose of the study is to learn more about children’s mental health. We are hoping to better understand how to predict and diagnose common mental health diagnoses in children.
THIS STUDY IS ENROLLING BY INVITATION ONLY - A two-step process will be used to identify and screen potential participants. In step 1, potentially eligible patients are identified either: (a) by research staff present in the outpatient clinics (OHSU, Seattle Children’s, MGH, and Indiana University) identifying the patient at the time of visit, or (b) using a “Best Practice Alert” in the Epic® electronic health record, which scans patient medical records in real time and notifies research staff when a patient meets initial eligibility based on visit presenting problem and diagnosis. In step 2, research staff will inform families about the study (either in person or via phone/email), screen for all inclusionary and exclusionary criteria and if eligible, conduct assent/consent and enrollment procedures via electronic signature.
Detailed description of study
The primary aim of the proposed study is to employ computational modeling of cognitive, behavioral, and environmental data, generated from large-scale, national mental health studies of youth, to enhance diagnostic and prognostic prediction for children with common forms of psychopathology. Effectiveness will be evaluated within pediatric and psychiatry clinic settings from several regions of the country. Year 1-2 will focus on Aims 1-2 (computational modeling), and data collection for Aims 3-4 will occur in Years 2-5 with continued focus on refining computational models.
Aim 1. Refine novel diagnostic and prognostic phenotypes in the lab. Using existing prospective research cohorts (Oregon-ADHD-1000, ABCD, Michigan-ADHD-1000), we will computationally refine the prediction of diagnoses and clinical outcomes for dysregulatory psychopathology by augmenting standard clinical measures with novel behavioral phenotype measures of: (a) emotional dysregulation along both positive and negative valence dimensions (via trait profiles and indicators), (b) computational cognitive phenotypes, and (c) environmental adversity measures.
Aim 2. Develop advanced computational models using complex EMR data to refine diagnostic and prognostic utility. Using the TriNetX Research Network, which includes 2.6 million youth with a prior mental health diagnosis and 10.4 million without a prior diagnosis (www.TriNetX.com) we will create computational models for case identification and prediction relying only on EMR data. We will identify predictors associated with current diagnosis (by diagnostic cluster: ADHD, disruptive behavior disorder, anxiety disorder, or mood disorder) and suicidality.
Aim 3. Test diagnostics in the clinic. Combine Aim 1 and Aim 2 findings with new prospective data collected in psychiatric and pediatric ambulatory clinic populations not previously examined, and use transfer learning to test models with EMR data and novel phenotypes for confident, accurate, and low-cost diagnostic identification.
Aim 4: Test 1-year follow-up prediction using prospective clinic data. We will conduct a 1-year follow up of patients studied in Aim 3 and address the same issues using the same logic for outcome one year later.
Eligibility of study
You may be eligible for this study if you meet the following criteria:
- Conditions: Dysregulatory psychopathology, inattention, impulsivity, behavioral dysregulation, emotional dysregulation, disruptive behavior problems, Riley
-
Age: 7 years - 17 years
-
Gender: All
Inclusionary criteria (Aims 3 & 4):
- Youth patients 7-17 years old with participating caregivers (age 18-89 years old)
- For psychiatry clinics, all patients without noted exclusionary criteria will be eligible for screening, with the expectation (from prior experience) that at least 50% will have dysregulatory psychopathology
- For pediatric clinics, we will enroll a sample in which 50% are presenting with dysregulatory concerns and 50% are not, identified from routine well-child visits
Exclusionary criteria for both clinics (Aims 3 & 4):
- Major chronic health or neurological condition (e.g., diabetes, cancer, TBI involving loss of consciousness > 2 minutes)
- Premature birth 28 weeks/<1200gram birthweight
- Child is non-English speaking (due to cognitive tasks)
- Previously diagnosed autism spectrum disorder or psychotic disorder
- Severe developmental delay or cognitive/intellectual impairment, by parental report or as indicated in the medical record.
The purpose of this study is to learn more about children's mental health. This study investigates how to predict and diagnose common mental health conditions in children using advanced computational models. The study will focus on conditions like ADHD, disruptive behavior disorder, anxiety disorder, and mood disorder. The research will use data from large-scale national mental health studies to improve diagnostic and prognostic predictions.
Study procedures include computational modeling of cognitive, behavioral, and environmental data. The study will use electronic medical records (EMR) data and novel phenotypes to develop models for case identification. Participants will be screened and enrolled through a two-step process, including identification by research staff or alerts in electronic health records, followed by informed consent.
- Who can participate: Children aged 7 to 17 years old, along with their caregivers aged 18 to 89, can participate. Key eligibility includes having dysregulatory psychopathology or attending routine well-child visits. Exclusions include major chronic health conditions, premature birth, non-English speaking, autism spectrum disorder, or severe developmental delay.
- Study details: Participants will be involved in computational modeling and data collection to refine diagnostic models. The study does not involve any changes in treatment, just observation and data collection.
- Study timelines: The study will last 5 years.
Interested in the study?
This study is accepting only persons who receive care at a certain clinic or doctor or who are part of an invited group. Questions about this study can be directed to the study team listed in the description or contact your doctor to see if you are eligible.
Please choose between Voice or SMS based delivery of verification code
or