Doctoral Student | Researcher

Advancing Patient Safety Through AI

Investigating bias mitigation frameworks in population health predictive models and diagnostic algorithms. Helping healthcare organizations implement evidence-based frameworks for algorithmic bias detection, mitigation, and governance.

Johns Hopkins Bloomberg School of Public Health
Doctor of Public Health (DrPH) Student
Director of Data Science, Association for Diagnostics & Laboratory Medicine

Research Collaboration Work Together View Publications

Research Focus

Primary Research Areas

Areas of Expertise

My doctoral research investigates the intersection of algorithmic bias, patient safety, and health equity in diagnostic and population health settings. Evidence-based expertise in algorithmic governance, bias mitigation, and patient safety frameworks for healthcare organizations.

Algorithmic Bias Mitigation

Developing and validating frameworks for detecting and mitigating bias in clinical decision support systems and population health predictive models. Implementing bias detection frameworks and audit methodologies for clinical algorithms, diagnostic systems, and population health models.

Fairness Metrics Clinical Algorithms Model Auditing

AI Governance & Policy

Contributing to federal AI strategy development and examining organizational governance structures for responsible AI deployment in healthcare settings. Governance framework design and policy implementation for responsible AI deployment, aligned with emerging federal requirements and industry best practices.

HHS AI Strategy Governance Frameworks Policy Development

Patient Safety & Quality

Investigating the patient safety implications of algorithmic errors and bias, with focus on diagnostic excellence and equitable health outcomes. Patient safety risk assessment for AI-enabled diagnostic systems, including error detection protocols and quality assurance frameworks.

Diagnostic Safety Quality Metrics Health Equity

Selected Work

Publications & Contributions

Peer-reviewed research and policy contributions advancing algorithmic fairness and patient safety in healthcare AI systems.

HHS AI Strategy Contribution • 2024

Patient Safety Considerations and Health Equity

Andrea Hobby

Department of Health and Human Services AI Strategy Working Group

Health Innovation Newsletter • Ongoing

Health Innovation: AI Governance, Algorithmic Bias, and Patient Safety

[Andrea Hobby]

Independent newsletter examining emerging trends in healthcare AI governance

Thought Leadership

Speaking & Advisory

Available for speaking engagements, advisory board positions, and expert consultations on healthcare AI governance, algorithmic bias, and patient safety.

Conference Presentations

Healthcare AI governance, algorithmic fairness, and patient safety frameworks for technical and executive audiences.

Advisory Roles

Strategic guidance for health systems, AI vendors, and healthcare organizations implementing responsible AI programs.

Expert Consultation

Technical review, regulatory compliance assessment, and bias audit design for healthcare AI initiatives.

Services

Algorithmic Governance Consulting

Evidence-based consulting services for healthcare organizations implementing responsible AI systems.

Governance Framework Design

Develop customized governance structures for algorithmic oversight, including committee formation, review processes, and accountability mechanisms aligned with organizational goals and regulatory requirements.

Bias Detection & Auditing

Implement systematic bias audit methodologies for clinical algorithms, including fairness metric selection, validation protocols, and remediation planning for identified disparities.

Policy & Compliance Strategy

Navigate evolving AI regulations and develop internal policies that ensure compliance while enabling innovation in patient care and population health management.

Background

About

I am a doctoral student at Johns Hopkins Bloomberg School of Public Health, where my research focuses on algorithmic bias mitigation in population health predictive models and diagnostic algorithms. My work sits at the intersection of health informatics, patient safety, and health equity.

As Director of Data Science at the Association for Diagnostics & Laboratory Medicine (ADLM), I lead initiatives advancing data-driven approaches to laboratory medicine and diagnostic excellence. Previously, I contributed to federal AI strategy development through the HHS AI Strategy Working Group and held data scientist positions at HRSA and Accenture Federal Services.

Through my research and newsletter, Health Innovation, I examine emerging challenges in healthcare AI governance, working toward frameworks that ensure algorithmic systems serve all patients equitably and safely.

I translate academic research into practical frameworks for healthcare organizations navigating the complexities of AI implementation, governance, and bias mitigation. My approach combines rigorous evidence with real-world applicability.

Education & Affiliations

DrPH Student, Johns Hopkins Bloomberg School of Public Health (Expected 2029)
MS Epidemiology, Georgetown University
BA Political Science, Wellesley College
Director of Data Science, Association for Diagnostics & Laboratory Medicine

Research Collaboration

Let's Work Together

I welcome opportunities for research collaboration, speaking engagements, and discussions on algorithmic bias, patient safety, and AI governance in healthcare settings.

Ready to implement evidence-based algorithmic governance frameworks? Let's discuss how we can work together to ensure your AI systems are fair, safe, and compliant.

[email protected]

Health Innovation Newsletter