Person:
Harstad, Elizabeth

Profile Picture

Email Address

AA Acceptance Date

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Harstad

First Name

Elizabeth

Name

Harstad, Elizabeth
Author's Publications: search.filters.isAuthorOfPublication.877c5409-aceb-4041-b655-b51cb429af8d

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    A Screening Tool for Assessing Alcohol Use Risk among Medically Vulnerable Youth
    (Public Library of Science, 2016) Levy, Sharon; Dedeoglu, Fatma; Gaffin, Jonathan M.; Garvey, Katharine C.; Harstad, Elizabeth; MacGinnitie, Andrew; Rufo, Paul A.; Huang, Qian; Ziemnik, Rosemary E.; Wisk, Lauren E.; Weitzman, Elissa
    Background: In an effort to reduce barriers to screening for alcohol use in pediatric primary care, the National Institute on Alcoholism and Alcohol Abuse (NIAAA) developed a two-question Youth Alcohol Screening Tool derived from population-based survey data. It is unknown whether this screening tool, designed for use with general populations, accurately identifies risk among youth with chronic medical conditions (YCMC). This growing population, which comprises nearly one in four youth in the US, faces a unique constellation of drinking-related risks. Method To validate the NIAAA Youth Alcohol Screening Tool in a population of YCMC, we performed a cross-sectional validation study with a sample of 388 youth ages 9–18 years presenting for routine subspecialty care at a large children’s hospital for type 1 diabetes, persistent asthma, cystic fibrosis, inflammatory bowel disease, or juvenile idiopathic arthritis. Participants self-administered the NIAAA Youth Alcohol Screening Tool and the Diagnostic Interview Schedule for Children as a criterion standard measure of alcohol use disorders (AUD). Receiver operating curve analysis was used to determine cut points for identifying youth at moderate and highest risk for an AUD. Results: Nearly one third of participants (n = 118; 30.4%) reported alcohol use in the past year; 86.4% (106) of past year drinkers did not endorse any AUD criteria, 6.8% (n = 8) of drinkers endorsed a single criterion, and 6.8% of drinkers met criteria for an AUD. Using the NIAAA tool, optimal cut points found to identify youth at moderate and highest risk for an AUD were ≥ 6 and ≥12 drinking days in the past year, respectively. Conclusions: The NIAAA Youth Alcohol Screening Tool is highly efficient for detecting alcohol use and discriminating disordered use among YCMC. This brief screen appears feasible for use in specialty care to ascertain alcohol-related risk that may impact adversely on health status and disease management.
  • Thumbnail Image
    Publication
    Use of Machine Learning to Shorten Observation-based Screening and Diagnosis of Autism
    (Nature Publishing Group, 2012) Wall, Dennis Paul; Kosmicki, Jack; DeLuca, Todd; Harstad, Elizabeth; Fusaro, Vincent Alfred
    The Autism Diagnostic Observation Schedule-Generic (ADOS) is one of the most widely used instruments for behavioral evaluation of autism spectrum disorders. It is composed of four modules, each tailored for a specific group of individuals based on their language and developmental level. On average, a module takes between 30 and 60 min to deliver. We used a series of machine-learning algorithms to study the complete set of scores from Module 1 of the ADOS available at the Autism Genetic Resource Exchange (AGRE) for 612 individuals with a classification of autism and 15 non-spectrum individuals from both AGRE and the Boston Autism Consortium (AC). Our analysis indicated that 8 of the 29 items contained in Module 1 of the ADOS were sufficient to classify autism with 100% accuracy. We further validated the accuracy of this eight-item classifier against complete sets of scores from two independent sources, a collection of 110 individuals with autism from AC and a collection of 336 individuals with autism from the Simons Foundation. In both cases, our classifier performed with nearly 100% sensitivity, correctly classifying all but two of the individuals from these two resources with a diagnosis of autism, and with 94% specificity on a collection of observed and simulated non-spectrum controls. The classifier contained several elements found in the ADOS algorithm, demonstrating high test validity, and also resulted in a quantitative score that measures classification confidence and extremeness of the phenotype. With incidence rates rising, the ability to classify autism effectively and quickly requires careful design of assessment and diagnostic tools. Given the brevity, accuracy and quantitative nature of the classifier, results from this study may prove valuable in the development of mobile tools for preliminary evaluation and clinical prioritization—in particular those focused on assessment of short home videos of children—that speed the pace of initial evaluation and broaden the reach to a significantly larger percentage of the population at risk.