Browsing by Author "Downs, S."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Adolescent suicide assessment and management in primary care
    (BMC, 2022-07-02) Aalsma, M.; Keys, J.; Ferrin, S.; Shan, M.; Garbuz, T.; Scott, T.; Adams, Z.; Hulvershorn, L.; Downs, S.; Pediatrics, School of Medicine
    Background: To understand how suicide management occurs within the primary care setting in terms of follow-up assessments and referral practices. Methods: At an initial primary care visit, adolescents (aged 12-20 years old) completed electronic screening. Data were focused on youth who endorsed a suicidal risk item while completing screening at two Midwestern primary care clinics. Data were collected through retrospective chart reviews to analyze actions taken by the primary care physician at the youth's initial visit and follow-up visit within the next 12 months. Results: At initial visits 200 adolescents endorsed a suicidal risk item and 39 (19.5%) were considered to be concerning by their primary care physician. The average age was 14.7 years old (SD ± 2.0). Seventy-two percent (n = 144) were female, and 65% (n = 129) identified as Black. At initial visits, significant differences between suicidal concern groups were found in reporting active suicidal ideation, past suicide attempts, those who were referred to behavioral health counseling, and those who had a diagnosis of depression. Interestingly, only 13% (n = 25) of all patients who endorsed the suicide item were asked whether or not there were weapons in their home and primary care providers asked only 7% (n = 13) of all patients whether they had a safety plan. Conclusions: There was inconsistent follow-up for adolescents with a history of suicide concerns. At this time, national guidelines do not exist regarding primary care follow-up of youth with suicide concerns. Guidelines are a necessary precursor for practice improvement.
  • Thumbnail Image
    Item
    Community engagement of adolescents in the development of a patient-centered outcome tool for adolescents with a history of hypospadias repair
    (Elsevier, 2019-10-01) Chan, K. H.; Panoch, J.; Carroll, A.; Downs, S.; Cain, M. P.; Frankel, R.; Cockrum, B.; Moore, C.; Wiehe, Sarah; Urology, School of Medicine
    Introduction: Hypospadias may lead to long-term issues with urination, sexual function and psychosocial well-being. Limited evidence exists regarding the healthcare communication preferences of male adolescents regarding sensitive topics. Objective: The purpose of this qualitative study was to explore the healthcare communication preferences of male adolescents regarding sensitive topics (e.g. urinary and sexual issues) and engage them in in the initial stages of development a patient-centered outcomes tool for adolescents with a history of hypospadias repair. Study Design: A multi-disciplinary team with communication design expertise, pediatric urology experts, and health services researchers developed a self-reported toolkit for adolescent patients who had hypospadias repair as children. The toolkit featured short writing/diagramming exercises and scales to facilitate participant reflections about genital appearance, urination, sexual function and psychosocial well-being. We recruited students from two local high schools for two focus groups to obtain feedback about the usability/acceptability of the toolkit’s appearance/content. We inquired about language preferences and preferred format and/or setting for sharing sensitive information with researchers. The focus groups were audio recorded, professionally transcribed, checked for accuracy and analyzed by two coders using qualitative content analysis. Major themes and subthemes were identified and representative quotes were selected. Results: We conducted two focus groups in January 2018 with 33 participants, ages 14-18. Participants preferred language that would make patients feel comfortable as well as serious, clinical language rather than slang terms/sexual humor (Extended Summary Table). They recommended avoidance of statements implying that something is wrong with a patient or statements that would pressure the patient into providing answers. They suggested fill-in-the-blank and open-ended responses to encourage freedom of expression and colorful graphics to de-emphasize the test-like appearance of the toolkit. Most participants preferred a toolkit format to a one-on-one interview to discuss sensitive topics such as urinary or sexual issues. Participants would prefer either a male interviewer or would like to have a choice of interviewer gender for individual qualitative interviews, and they recommended a focus group leader with a history of hypospadias repair. Discussion: This study provides a rich description of a group of male high school students’ experiences with healthcare providers and researchers. Its qualitative design limits generalizability and our findings may not be similar to adolescents with a history of hypospadias repair. Conclusion: We used focus group feedback on the toolkit prototype to refine the tool for use in a future study of adolescents with history of hypospadias repair.
  • Thumbnail Image
    Item
    Machine Learning Techniques for Prediction of Early Childhood Obesity
    (Schattauer, 2015-08-12) Dugan, T.M.; Mukhopadhyay, S.; Carroll, A.; Downs, S.; Department of Computer and Information Science, School of Science
    Objectives This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Methods Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Results Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. Conclusions This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.