About

Dr. Kadija Ferryman is a cultural anthropologist and Assistant Professor at the Johns Hopkins Berman Institute of Bioethics. Her research focuses on the social, cultural, and ethical implications of health information technologies, specifically examining how genomics, digital medical records, artificial intelligence, and other technologies impact racial disparities in health. She has led research studies such as the Fairness in Precision Medicine project at the Data & Society Research Institute, which investigates potential bias and discrimination in predictive precision medicine. Dr. Ferryman earned her BA in Anthropology from Yale University and her PhD in Anthropology from The New School for Social Research. Prior to her doctoral studies, she worked as a policy researcher at the Urban Institute, studying how housing and neighborhood changes affect well-being, particularly the effects of public housing redevelopment on various populations. She is a member of the Institutional Review Board for the All of Research Program, a Mozilla Open Science Fellow, and an Affiliate at the Center for Critical Race and Digital Studies. Her research has been published in several academic journals and featured in prominent outlets such as Nature, STAT, and The Financial Times.

Research topics

• Computer Science
• Political Science
• Artificial Intelligence
• Data science
• Psychology

Selected publications

• Current Practices and Preferences Regarding Race and Spirometry Interpretation

  CHEST Pulmonary · 2026-02-01

  articleOpen access
  PublisherDOI

• A roadmap for addressing the use of race and ethnicity in clinical algorithms

  Nature Health · 2026-03-23

  article
  PublisherDOI

• Population-Level Digital Stroke Surveillance: Building a Fair and Accurate ICD-10 Detection Model

  Cerebrovascular Diseases · 2026-03-20

  articleOpen accessSenior author

  INTRODUCTION: The International Classification of Diseases, 10th Revision (ICD-10), is widely used for clinical care, quality assurance, and stroke research. Its ubiquity across healthcare systems makes it an attractive foundation for digital health tools that can support stroke surveillance and population health monitoring. However, a major limitation is that stroke detection algorithms derived from ICD codes have been developed primarily in socially homogenous populations, raising concerns about generalizability and fairness across racially diverse populations. METHODS: We developed and validated an acute ischemic stroke (AIS) detection algorithm using Classification and Regression Tree (CART) supervised machine learning, using a diverse derivation cohort. Input variables consisted of diagnostic and procedural ICD-10 codes, stratified by position and presence on admission. The model was trained on 75% and tested on 25% of the derivation cohort and externally validated in a second tertiary institution serving patients living in predominantly underrepresented and socially vulnerable communities. Performance of the algorithm was measured by sensitivity, specificity, positive predictive value (PPV), and Cohen's κ. Subgroup analyses were conducted by sex and race/ethnicity. RESULTS: In the derivation cohort, the CART model achieved sensitivity of 96%, specificity of 90%, PPV of 99%, and κ = 0.78. Applied to the independent validation cohort, the algorithm identified 1,050 AIS cases and 1,664 non-AIS cases, with sensitivity 89%, specificity 95%, PPV of 92%, and κ = 0.84. Performance was comparable between women and men (κ = 0.80 for both), and strong across Black (κ = 0.81), Hispanic (κ = 0.76), and White (κ = 0.80) subgroups. Lower accuracy was observed in the Asian subgroup (κ = 0.73, PPV = 62%). CONCLUSION: Our findings demonstrate that CART-based algorithms can provide accurate and interpretable AIS detection using ICD-10 data while explicitly addressing social fairness. The algorithm's reproducibility across independent and diverse populations highlights its potential as a low-friction, scalable, and cost-efficient tool for clinical care, surveillance, and quality improvement. Importantly, subgroup analyses underscore the necessity of ongoing fairness evaluation as performance varied by race/ethnicity, particularly in the Asian subgroup. Limitations include potential missed cases in the gold standard, lack of confidence intervals due to retrospective data, and dependence on local coding practices. This study shows that ICD-10-based machine learning algorithms, specifically CART, can serve as a model for developing an accurate and equitable digital health platform for AIS surveillance.

  PublisherOA PDFDOI

• Ethical sourcing in the context of health data supply chain management: a value sensitive design approach

  JAMIA Open · 2025-09-02 · 5 citations

  articleOpen access

  Objective: The Bridge2AI program is establishing rules of practice for creating ethically sourced health data repositories to support the effective use of ML/AI in biomedical and behavioral research. Given the initially undefined nature of ethically sourced data, this work concurrently developed definitions and guidelines alongside repository creation, grounded in a practical, operational framework. Materials and Methods: A Value Sensitive Design (VSD) approach was used to explore ethical tensions across stages of health data repository development. The conceptual investigation drew from supply chain management (SCM) processes to (1) identify actors who would interact with or be affected by the data repository use and outcomes; (2) determine what values to consider (ie, traceability accountability, security); and (3) analyze and document value trade-offs (ie, balancing risks of harm to improvements in healthcare). This SCM framework provides operational guidance for managing complex, multi-source data flows with embedded bias mitigation strategies. Results: This conceptual investigation identified the actors, values, and tensions that influence ethical sourcing when creating a health data repository. The SCM steps provide a scaffolding to support ethical sourcing across the pre-model stages of health data repository development. Ethical sourcing includes documenting data provenance, articulating expectations for experts, and practices for ensuring data privacy, equity, and public benefit. Challenges include risks of ethics washing and highlight the need for transparent, value-driven practices. Discussion: Integrating VSD with SCM frameworks enables operationalization of ethical values, improving data integrity, mitigating biases, and enhancing trust. This approach highlights how foundational decisions influence repository quality and AI/ML system usability, addressing provenance, traceability, redundancy, and risk management central to ethical data sourcing. Conclusion: To create authentic, impactful health data repositories that serve public health goals, organizations must prioritize transparency, accountability, and operational frameworks like SCM that comprehensively address the complexities and risks inherent in data stewardship.

  PublisherDOI

• Nesting a Target Study within a Target Trial: A Framework for Evaluating Intervention Effects on Disparities

  ArXiv.org · 2025-08-20

  preprintOpen access

  We present a novel framework (TS+TT) to nest a Target Study (TS) within a Target Trial (TT) for evaluating the effects of interventions on disparities. The TS component grounds the measurement of disparity in ethical assumptions, based on the concept of allowability, and anchors it to an explicit population within calendar time. It specifies an enrollment plan of stratified sampling of eligible persons to yield a sample where social groups are distributionally similar on covariates deemed allowable for measuring disparity. Within this enrolled sample, the TT component specifies randomization of intervention strategies within each social group. Because social groups are similarly situated on allowable covariates at baseline, and because assigned intervention arms are exchangeable within social groups, TS+TT reflects a meaningful causal estimand for evaluating how interventions impact disparity. We describe the framework's key components, its emulation, and demonstrate its application to evaluate how hypothetical interventions on pulse oximeter bias affect disparities in treatment receipt in clinical care. We also extend semiparametric G-computation to accommodate continuous stochastic interventions and estimate counterfactual disparities in time-to-event outcomes. The TS+TT framework offers a versatile and policy-relevant approach for generating ethically informed causal evidence to reduce disparities and avoid exacerbating disparities.

  PublisherOA PDFDOI

• Health System Purchasing Professionals’ Approaches to Considering Equity in Procurement

  American Journal of Respiratory and Critical Care Medicine · 2025-05-01

  article

  Abstract RATIONALE: Growing evidence of racial bias in pulse oximeters and artificial intelligence has sparked calls for health systems to drive device innovation by ensuring purchased devices function equitably. We sought to identify how healthcare purchasing professionals integrate equity concerns into purchasing decision-making. METHODS: Between 8/2023-3/2024, we conducted semi-structured interviews via videoconferencing with healthcare purchasing professionals, identified through an industry organization website and through LinkedIn searches, about purchasing processes for pulse oximeters and other devices—and whether and how equity concerns arise in decision-making. An abductive approach was used to analyze perspectives in interview transcripts. RESULTS: Healthcare purchasing professionals (N=30) worked in sourcing, value analysis, contracting, and other supply chain roles across the US. Participants were currently working in academic medical centers (12); private hospitals or health systems (7); public hospitals or health systems (3); or supply chain support or consulting companies (8). Respondents had a median 7 years of experience in health system purchasing, 60% (N=18) were women, and 70% (N=21) were White. Healthcare purchasing professionals described very few considerations of equity in current purchasing processes. They described some receptivity to diversity, equity, and inclusion initiatives, largely focused on diversifying suppliers, rather than ensuring devices and products functioned equitably, and that they are “just now starting to see these types of discussions coming to a forefront.” Respondents reported that they depended on clinician partners to establish requirements for equitable performance and that there is limited assessment of products after purchase decisions. Few had heard about racial bias in pulse oximetry. Respondents also described a number of barriers, including that current sources of evidence used in making purchasing decisions provide limited information about equitable performance; contracts, including with group purchasing organizations (GPOs), may limit purchasing options; competing priorities such as lowering costs, and a preference for well-established products or vendors could limit innovation. Frankly racist beliefs were also disclosed during interviews. CONCLUSIONS: Health system purchasing professionals described very limited incorporation of diversity, equity, and inclusion considerations in health system purchasing processes, largely focused on diverse supplier initiatives. Explicit approaches for incorporating equitable performance into healthcare purchasing are needed, and current processes depend on clinicians advising against inequitable devices.

  PublisherDOI

• Public Opinion on Use of Race in Clinical Algorithms

  JAMA Internal Medicine · 2025-12-22 · 1 citations

  articleOpen access

  This survey study assesses public opinion and preferences among US adults regarding the use of race in clinical algorithms.

  PublisherOA PDFDOI

• Predicting postoperative chronic opioid use with fair machine learning models integrating multi-modal data sources: a demonstration of ethical machine learning in healthcare

  Journal of the American Medical Informatics Association · 2025-03-27 · 5 citations

  articleOpen access

  OBJECTIVE: Building upon our previous work on predicting chronic opioid use using electronic health records (EHR) and wearable data, this study leveraged the Health Equity Across the AI Lifecycle (HEAAL) framework to (a) fine tune the previously built model with genomic data and evaluate model performance in predicting chronic opioid use and (b) apply IBM's AIF360 pre-processing toolkit to mitigate bias related to gender and race and evaluate the model performance using various fairness metrics. MATERIALS AND METHODS: Participants included approximately 271 All of Us Research Program subjects with EHR, wearable, and genomic data. We fine-tuned 4 machine learning models on the new dataset. The SHapley Additive exPlanations (SHAP) technique identified the best-performing predictors. A preprocessing toolkit boosted fairness by gender and race. RESULTS: The genetic data enhanced model performance from the prior model, with the area under the curve improving from 0.90 (95% CI, 0.88-0.92) to 0.95 (95% CI, 0.89-0.95). Key predictors included Dopamine D1 Receptor (DRD1) rs4532, general type of surgery, and time spent in physical activity. The reweighing preprocessing technique applied to the stacking algorithm effectively improved the model's fairness across racial and gender groups without compromising performance. CONCLUSION: We leveraged 2 dimensions of the HEAAL framework to build a fair artificial intelligence (AI) solution. Multi-modal datasets (including wearable and genetic data) and applying bias mitigation strategies can help models to more fairly and accurately assess risk across diverse populations, promoting fairness in AI in healthcare.

  PublisherOA PDFDOI

• Using Large Language Models to Promote Health Equity

  NEJM AI · 2025-01-13 · 16 citations

  article
  PublisherDOI

• Community engagement for artificial intelligence health research in Africa

  Wellcome Open Research · 2025-03-20 · 1 citations

  preprintOpen access

  Artificial Intelligence holds the potential to benefit communities in numerous areas, including health. Artificial intelligence health research is, among other things, advancing the accuracy of diagnosis, enabling new drug and treatment options, and reducing costs in healthcare. Like elsewhere, artificial intelligence health research is rapidly expanding across the African continent; however, numerous co-travelling ethical challenges - including those related to data protection, equitable access, and data colonization - are under-addressed. Community engagement is a process through which a number of pertinent health research ethics issues affecting communities can be identified and collaboratively pursued; however, there currently is limited understanding of the opportunities and challenges for community engagement in artificial intelligence research globally. In order to advance collective understanding and support policy and practice innovation, this paper interrogates how communities in Africa could be engaged in artificial intelligence health research. It provides a justification for community engagement in artificial intelligence health research, and discusses its application in African communities. It concludes by offering some context-specific recommendations for priority attention.

  PublisherDOI

Recent grants

• Bridge2AI: Salutogenesis Data Generation Project

  NIH · $32.7M · 2022–2026

Frequent coauthors

• Carol R. Horowitz

  26 shared

• Erwin P. Böttinger

  26 shared

• Mayra Rodríguez

  Edward Via College of Osteopathic Medicine

  25 shared

• Randi F. Zinberg

  Icahn School of Medicine at Mount Sinai

  25 shared

• Tatiana Sabin

  Icahn School of Medicine at Mount Sinai

  25 shared

• Rennie Negron

  Icahn School of Medicine at Mount Sinai

  25 shared

• Theodore J. Iwashyna

  VA Center for Clinical Management Research

  8 shared

• Deidra C. Crews

  Johns Hopkins University

  6 shared

Awards & honors

• Mozilla Open Science Fellow