Final cohort selection by applying exclusion criteria
Embedded Files
Project Name: SARS-CoV-2 infection is associated with an increase in new diagnoses of schizophrenia spectrum and psychotic disorder: A study using the US national COVID cohort collaborative (N3C)
NIH Project
Summary: In this study, I investigated the potential relationship between SARS-CoV-2 infection and the onset of schizophrenia spectrum and psychotic disorders (SSPD). Using a large dataset (almost 20M data) from the U.S. National COVID Cohort Collaborative (N3C), my analysis aimed to determine whether COVID-19 infection is associated with an increased risk of developing psychiatric disorders, specifically SSPD.
Key Highlights:
1) Study Design: The study compared psychiatric outcomes in COVID-positive patients with those in control groups, including patients with Acute Respiratory Distress Syndrome (ARDS) and COVID-negative individuals, to isolate the unique impact of COVID-19 on mental health.
2) Statistical Analyses:
Schoenfeld Residuals Test: Used to test the proportional hazards assumption in survival analysis, ensuring the reliability of our hazard ratio estimates.
Cochran-Mantel-Haenszel Test: Applied to control for confounding variables across stratified data, refining our comparison between COVID-positive and control groups.
Likelihood Ratio Test, Wald Test, and Logrank Test: These tests were conducted to assess the significance of predictor variables and compare survival curves between groups.
Cox Proportional Hazards Model: Employed as the primary model to estimate hazard ratios, revealing a significant association between COVID-19 infection and an increased risk of developing SSPD.
3) Implications: These findings highlight the critical need for mental health screening and interventions for COVID-19 patients, particularly those predisposed to psychiatric conditions, and lay the groundwork for further research on the psychiatric consequences of COVID-19.
This research contributes to a growing body of evidence on the mental health implications of COVID-19, offering insights that could guide clinical practices and public health policies.
SSPD hazard ratio comparisons
Project Title: Group-Based Trajectory Modeling of Longitudinal Inflammatory Biomarker Patterns
Summary:
This project applies Group-Based Trajectory Modeling in R to classify how critically ill patients' inflammatory biomarker levels evolve over time, rather than relying on a single snapshot measurement. I fit and compared latent class mixed models across multiple candidate solutions, selecting a final three-class model that balanced statistical fit with clinical interpretability. The resulting patient subgroups — each following a distinct inflammatory trajectory — demonstrate how longitudinal modeling can surface risk patterns that static lab values alone would miss.
Project Title: Geospatial and Temporal Analysis of Pediatric Non-Accidental Trauma in Rural Appalachia
Summary:
This project examines 14 years of pediatric emergency department data to understand how the COVID-19 pandemic reshaped patterns of child physical abuse in a rural healthcare system. Using Python and GeoPandas, I built statistical models and custom geospatial maps that revealed a striking, sustained increase in cases beginning with the pandemic and a strong association with community-level economic distress. The analysis highlights how local health systems can use their own data to identify at-risk populations and inform targeted intervention.
Project Title: Longitudinal ICU Biomarker Data: Neutrophil to Lymphocyte Ratio (NLR) Analysis
Summary:
Designed and validated an end-to-end Python data pipeline transforming raw ICU laboratory records from long to wide format, applying deduplication and multi-step data validation (including physiologic plausibility checks) to derive a clean longitudinal biomarker dataset.
Built exploratory visualizations — distribution analysis, missingness heatmaps by year, and individual-level longitudinal trajectory plots — to characterize inflammatory biomarker patterns ahead of formal trajectory modeling.
Delivered a fully documented analytic pipeline with transparent data-quality reporting at each transformation step, ensuring reproducibility for downstream statistical modeling.
Project Title: Pulmonary Embolism (PE) Outcomes and Geospatial Analysis
Summary:
Conducted comprehensive statistical and geospatial analyses of pulmonary embolism patients to assess mortality, readmission, and demographic disparities using Python (Pandas, Seaborn, GeoPandas, Matplotlib, Contextily).
Integrated geospatial mapping to visualize regional healthcare patterns and rural–urban disparities, highlighting variations in ICU mortality and readmission rates across West Virginia.
Designed reproducible analysis workflows and advanced visualizations to communicate findings effectively to clinical teams and support evidence-based decision-making.
Merged electronic health record (EHR) data with geographical indicators (RUCA codes) to identify underserved areas and inform public health resource allocation.
Project Title: SAHARA Study: Five-Year Analysis of Sleep Apnea in Rural Hospitalized Patients (NIH Project)
Summary:
Retrospectively analyzed a REDCap database of 2,728 patients using level III unattended polysomnography, identifying that 40% of screened patients had moderate to severe sleep apnea.
Analyzed associations between sleep apnea severity and key comorbidities such as hypertension, COPD, diabetes, and congestive heart failure to uncover population-level health disparities.
Findings contributed to a published abstract at the SLEEP 2024 Conference, supporting data-driven initiatives to enhance inpatient sleep medicine programs in rural hospitals.
Project Title: OSA & Pulmonary Hypertension in Appalachia: Prognostic Impacts on Re-admission and Survival (NIH Project)
Summary:
Conducted a retrospective cohort study of 573 (rural Appalachian population) patients using Kaplan–Meier curves and Cox regression, to evaluate long-term survival and hospital readmission outcomes, adjusting for age, gender, BMI, and comorbidities.
Identified a “survival paradox”: patients with both OSA and PH demonstrated better long-term survival compared to those with PH alone (HR=1.3, p=0.002).
Discovered that BMI was inversely associated with hospital readmission rates, suggesting an “obesity paradox” protective effect.
Supported development of hospital-level sleep medicine quality improvement initiatives and contributed to a peer-reviewed abstract publication and national poster presentation (APSS).
Project Title: Geographic and Clinical Determinants of Interstitial Lung Disease Severity and Referral Patterns in Rural Appalachia
Summary:
Analyzed 312 ILD clinic patients (2021–2024) to evaluate referral patterns, geographic access, and pulmonary function outcomes in rural Appalachia.
Found that greater travel distance (>60 miles) correlated with worse lung function (FEV1, TLC, DLCO) and longer delays from symptom onset to specialty care.
Conducted geospatial and statistical analysis using Python and Excel, identifying key access barriers and trends in disease severity and referral behavior.
Project Title: INSPIRE Study: Data Analysis of Upper Airway Stimulation Therapy Outcomes in Obstructive Sleep Apnea
Summary:
Performed statistical analysis of pre and post-operative sleep study data from the INSPIRE Upper Airway Stimulation project to evaluate treatment outcomes for Obstructive Sleep Apnea (OSA) patients.
Identified correlations between facial structure and body position and how these influence therapeutic response, contributing to improved patient selection criteria and postoperative evaluation strategies.
Page updated
Google Sites
Report abuse