Browsing by Subject "Predictive Modeling"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Data Analytics and Modeling for Appointment No-show in Community Health Centers
    (SAGE, 2018) Mohammadi, Iman; Wu, Huanmei; Turkcan, Ayten; Toscos, Tammy; Doebbeling, Bradley N.; BioHealth Informatics, School of Informatics and Computing
    Objectives: Using predictive modeling techniques, we developed and compared appointment no-show prediction models to better understand appointment adherence in underserved populations. Methods and Materials: We collected electronic health record (EHR) data and appointment data including patient, provider and clinical visit characteristics over a 3-year period. All patient data came from an urban system of community health centers (CHCs) with 10 facilities. We sought to identify critical variables through logistic regression, artificial neural network, and naïve Bayes classifier models to predict missed appointments. We used 10-fold cross-validation to assess the models’ ability to identify patients missing their appointments. Results: Following data preprocessing and cleaning, the final dataset included 73811 unique appointments with 12,392 missed appointments. Predictors of missed appointments versus attended appointments included lead time (time between scheduling and the appointment), patient prior missed appointments, cell phone ownership, tobacco use and the number of days since last appointment. Models had a relatively high area under the curve for all 3 models (e.g., 0.86 for naïve Bayes classifier). Discussion: Patient appointment adherence varies across clinics within a healthcare system. Data analytics results demonstrate the value of existing clinical and operational data to address important operational and management issues. Conclusion: EHR data including patient and scheduling information predicted the missed appointments of underserved populations in urban CHCs. Our application of predictive modeling techniques helped prioritize the design and implementation of interventions that may improve efficiency in community health centers for more timely access to care. CHCs would benefit from investing in the technical resources needed to make these data readily available as a means to inform important operational and policy questions.
  • Thumbnail Image
    Item
    Evaluating the Autism Knowledge Gains, Retention, and Differences Across Participant Roles in HANDS in Autism Summer Intensive Trainings (2013–2024)
    (2025-05-09) Simhambhatla, Aruna Prasanna; Neal , Tiffany; Gottipati, Mounika; Swiezy, Naomi
    This project analyzed over a decade’s worth of Autism Knowledge Survey – Revised (AKS-R) data collected during HANDS in Autism® Summer Intensive Trainings from 2013 to 2024. Using REDCap, Python, and Power BI, the study assessed knowledge improvements across pre-training, post-training, and follow-up periods. The results showed statistically significant increases in autism-related knowledge immediately following training, with positive retention trends over time. The analysis also revealed variations in knowledge gains based on participant roles, experience levels, and training years. Notably, 2014 and 2023 demonstrated the highest improvements, highlighting peak training effectiveness. Through structured scoring, statistical testing, and predictive modeling, the project reinforced the long-term impact of targeted, interdisciplinary autism education and provided actionable insights for enhancing future training strategies.
  • Thumbnail Image
    Item
    Predicting Traumatic Brain Injury Through Behavioral Pattern Analysis in Youth with Autism
    (2023-08) Battula, Madhuhasa; Neal, Tiffany; Deodhar, Aditi; Swiezy, Naomi
    This practicum, conducted at HANDS in Autism® in collaboration with the Indiana NeuroDiagnostic Institute (NDI), explored the relationship between patient behavioral profiles and the presence of Traumatic Brain Injury (TBI) in individuals with Autism Spectrum Disorder (ASD). Using a combination of pre-admission data from Cerner and post-discharge data from REDCap, a comprehensive dataset of 58 patients was coded and analyzed to identify behavioral patterns. Prediction models, including Logistic Regression and Random Forest, were developed in Python to assess the likelihood of TBI based on specific behavior indicators. Results revealed statistically significant correlations between certain behavioral patterns and the presence of TBI. This work supports the potential for predictive modeling to improve early identification and intervention strategies for patients with ASD and co-occurring neurological conditions.