Browsing by Subject "Health services needs and demand"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Behavioral Health Care Needs, Detention-Based Care, and Criminal Recidivism at Community Reentry From Juvenile Detention: A Multisite Survival Curve Analysis
    (American Public Health Association, 2015-07) Aalsma, Matthew C.; White, Laura M.; Lau, Katherine S. L.; Perkins, Anthony; Monahan, Patrick; Grisso, Thomas; Pediatrics, School of Medicine
    OBJECTIVES: We examined the provision of behavioral health services to youths detained in Indiana between 2008 and 2012 and the impact of services on recidivism. METHOD: We obtained information about behavioral health needs, behavioral health treatment received, and recidivism within 12 months after release for 8363 adolescents (aged 12-18 years; 79.4% male). We conducted survival analyses to determine whether behavioral health services significantly affected time to recidivating. RESULTS: Approximately 19.1% of youths had positive mental health screens, and 25.3% of all youths recidivated within 12 months after release. Of youths with positive screens, 29.2% saw a mental health clinician, 16.1% received behavioral health services during detention, and 30.0% received referrals for postdetention services. Survival analyses showed that being male, Black, and younger, and having higher scores on the substance use or irritability subscales of the screen predicted shorter time to recidivism. Receiving a behavior precaution, behavioral health services in detention, or an assessment in the community also predicted shorter time to recidivating. CONCLUSIONS: Findings support previous research showing that behavioral health problems are related to recidivism and that Black males are disproportionately rearrested after detention.
  • Thumbnail Image
    Item
    Comparing the performance of screening surveys versus predictive models in identifying patients in need of health-related social need services in the emergency department
    (Public Library of Science, 2024-11-20) Mazurenko, Olena; Hirsh, Adam T.; Harle, Christopher A.; Shen, Joanna; McNamee, Cassidy; Vest, Joshua R.; Health Policy and Management, Richard M. Fairbanks School of Public Health
    Background: Health-related social needs (HRSNs), such as housing instability, food insecurity, and financial strain, are increasingly prevalent among patients. Healthcare organizations must first correctly identify patients with HRSNs to refer them to appropriate services or offer resources to address their HRSNs. Yet, current identification methods are suboptimal, inconsistently applied, and cost prohibitive. Machine learning (ML) predictive modeling applied to existing data sources may be a solution to systematically and effectively identify patients with HRSNs. The performance of ML predictive models using data from electronic health records (EHRs) and other sources has not been compared to other methods of identifying patients needing HRSN services. Methods: A screening questionnaire that included housing instability, food insecurity, transportation barriers, legal issues, and financial strain was administered to adult ED patients at a large safety-net hospital in the mid-Western United States (n = 1,101). We identified those patients likely in need of HRSN-related services within the next 30 days using positive indications from referrals, encounters, scheduling data, orders, or clinical notes. We built an XGBoost classification algorithm using responses from the screening questionnaire to predict HRSN needs (screening questionnaire model). Additionally, we extracted features from the past 12 months of existing EHR, administrative, and health information exchange data for the survey respondents. We built ML predictive models with these EHR data using XGBoost (ML EHR model). Out of concerns of potential bias, we built both the screening question model and the ML EHR model with and without demographic features. Models were assessed on the validation set using sensitivity, specificity, and Area Under the Curve (AUC) values. Models were compared using the Delong test. Results: Almost half (41%) of the patients had a positive indicator for a likely HRSN service need within the next 30 days, as identified through referrals, encounters, scheduling data, orders, or clinical notes. The screening question model had suboptimal performance, with an AUC = 0.580 (95%CI = 0.546, 0.611). Including gender and age resulted in higher performance in the screening question model (AUC = 0.640; 95%CI = 0.609, 0.672). The ML EHR models had higher performance. Without including age and gender, the ML EHR model had an AUC = 0.765 (95%CI = 0.737, 0.792). Adding age and gender did not improve the model (AUC = 0.722; 95%CI = 0.744, 0.800). The screening questionnaire models indicated bias with the highest performance for White non-Hispanic patients. The performance of the ML EHR-based model also differed by race and ethnicity. Conclusion: ML predictive models leveraging several robust EHR data sources outperformed models using screening questions only. Nevertheless, all models indicated biases. Additional work is needed to design predictive models for effectively identifying all patients with HRSNs.
  • Thumbnail Image
    Item
    Measuring Practicing Clinicians’ Information Literacy: An Exploratory Analysis in the Context of Panel Management
    (Thieme, 2017-02-15) Dixon, Brian E.; Barboza, Katherine; Jensen, Ashley E.; Bennett, Katelyn J.; Sherman, Scott E.; Schwartz, Mark D.; Epidemiology, School of Public Health
    BACKGROUND: As healthcare moves towards technology-driven population health management, clinicians must adopt complex digital platforms to access health information and document care. OBJECTIVES: This study explored information literacy, a set of skills required to effectively navigate population health information systems, among primary care providers in one Veterans' Affairs (VA) medical center. METHODS: Information literacy was assessed during an 8-month randomized trial that tested a population health (panel) management intervention. Providers were asked about their use and comfort with two VA digital tools for panel management at baseline, 16 weeks, and post-intervention. An 8-item scale (range 0-40) was used to measure information literacy (Cronbach's α=0.84). Scores between study arms and provider types were compared using paired t-tests and ANOVAs. Associations between self-reported digital tool use and information literacy were measured via Pearson's correlations. RESULTS: Providers showed moderate levels of information literacy (M= 27.4, SD 6.5). There were no significant differences in mean information literacy between physicians (M=26.4, SD 6.7) and nurses (M=30.5, SD 5.2, p=0.57 for difference), or between intervention (M=28.4, SD 6.5) and control groups (M=25.1, SD 6.2, p=0.12 for difference). Information literacy was correlated with higher rates of self-reported information system usage (r=0.547, p=0.001). Clinicians identified data access, accuracy, and interpretability as potential information literacy barriers. CONCLUSIONS: While exploratory in nature, cautioning generalizability, the study suggests that measuring and improving clinicians' information literacy may play a significant role in the implementation and use of digital information tools, as these tools are rapidly being deployed to enhance communication among care teams, improve health care outcomes, and reduce overall costs.
  • Thumbnail Image
    Item
    Public Health and Epidemiology Informatics: Recent Research and Trends in the United States
    (Thieme, 2015) Dixon, Brian E.; Kharrazi, H.; Lehmann, H. P.; Epidemiology, School of Public Health
    Objectives To survey advances in public health and epidemiology informatics over the past three years. Methods We conducted a review of English-language research works conducted in the domain of public health informatics (PHI), and published in MEDLINE between January 2012 and December 2014, where information and communication technology (ICT) was a primary subject, or a main component of the study methodology. Selected articles were synthesized using a thematic analysis using the Essential Services of Public Health as a typology. Results Based on themes that emerged, we organized the advances into a model where applications that support the Essential Services are, in turn, supported by a socio-technical infrastructure that relies on government policies and ethical principles. That infrastructure, in turn, depends upon education and training of the public health workforce, development that creates novel or adapts existing infrastructure, and research that evaluates the success of the infrastructure. Finally, the persistence and growth of infrastructure depends on financial sustainability. Conclusions Public health informatics is a field that is growing in breadth, depth, and complexity. Several Essential Services have benefited from informatics, notably, “Monitor Health,” “Diagnose & Investigate,” and “Evaluate.” Yet many Essential Services still have not yet benefited from advances such as maturing electronic health record systems, interoperability amongst health information systems, analytics for population health management, use of social media among consumers, and educational certification in clinical informatics. There is much work to be done to further advance the science of PHI as well as its impact on public health practice.