CV

Technical Project Manager for the Data Quality Assurance Tools and Analytic Querying Tools teams, drafting business, user, functional, and technical requirements across both portfolios. Responsible for delivery of a $5–7 million annual portfolio representing 15% of the FDA Sentinel Initiative's annual budget, and for preparing the organization's data quality assurance infrastructure for the Sentinel RFP. - Managed and mentored team of two technical project managers - Managed research teams developing machine learning methods to detect cannabis use, venous thromboembolism, and encapsulated bacterial infections from unstructured clinical notes and EHR data, delivering demonstration projects for FDA's Real World Evidence program - Managed implementation of FDA Sentinel's Real World Evidence Data Enterprise (RWE-DE), adding 25 million linked claims-EHR patient lives to the distributed database - Delivered production QA data aggregation pipeline in Python via AI agent-assisted development, cutting storage to 10% of the legacy SAS pipeline and enabling Power BI characterization of the Sentinel Distributed Database - Leading project assessing viability of adopting OMOP Common Data Model within HPHCI - Technical advisor to internal pilot project converting health data querying tools from SAS to Python, enabling use of routine querying tools with Apache Spark and Databricks - Designed architecture and drafted technical requirements for automating cross-ETL quality assurance checks, reducing time-to-data-delivery - Led modernization of Sentinel's Mother-Infant Identification Program Package: drafted functional requirements, managed team delivering methodological updates and software implementation - Pioneered use of Sentinel's common data model and tools for transnational drug safety research across the United States, Canada, UK, and Denmark - Delivered updated Sentinel Common Data Model to FDA, coordinating upgrade of 14 external data partners

Boston

Boston

Member, Data Science and Ethics Group (a nascent inter-agency working group focused on the risks posed to displaced persons by advanced data science, machine learning, and artificial intelligence) - Ethics Reviewer, Humanitarian Data Science Review - Freelance cartographic, network, and data visualizations for political risk clientele

Cambridge

Researched governance and management issues related to the use of ICTs and information in humanitarian response with a particular focus on standards and ethics, and the impact of technology on humanitarian crises and affected populations. - Investigated the safe, ethical, and rights-based use of digital ICTs and data in humanitarian settings through scholarly research and field assessments: - Co-authored a rights-based approach for assessing digital technology and data use during humanitarian crises, as well as the subsequent obligations necessary for humanitarian agencies to realize these rights - Developed an assessment template and capacity development curriculum to help organizations understand the scope of the digital technology use and associated risks - Created and facilitated workshops on the use of digital information and communication technologies for humanitarian practitioners - Engaged with internal and external stakeholders to support the Signal Program’s research aims: - Collaborated across institutions to help produce interdisciplinary work on topics ranging from GDPR compliance to the impact of disinformation on the Syria conflict - Facilitated workshops and panels on future technological threats to the humanitarian system - Promoted the Signal Program’s research through digital outreach, public speaking, and written communications - Designed promotional materials, including posters for speaking engagements and event invitations, as well as document layout for research reports - Held Signal Program corporate card, made team travel arrangements, and managed reimbursements per University guidelines

Developed strategies with pharmaceutical industry clients for the generation of real-world evidence for drug safety surveillance and health economics and outcomes research - Wrote landscape reports monitoring policy changes and industry trends and assessed the business impacts and opportunities of emerging technologies - Designed research frameworks, governance policies, and procedures for the creation of multi-stakeholder distributed research networks using real-world evidence to monitor drug safety and effectiveness - Convened industry, healthcare, academia, and government actors to build organizations which met the varied regulatory and business needs of stakeholders, including: • the Biologics and Biosimilars Collective Intelligence Consortium (BBCIC), a $8M, multi-stakeholder distributed research network to monitor the safety and effectiveness of biologics and biosimilars • a three-year, $18M research plan for the Observational Medical Outcomes Partnership (OMOP) drug safety methods public private partnership

Cambridge

Hudson

Natick

Human Security

Political Science

History

Purpose The US Food and Drug Administration's Sentinel Innovation Center aimed to establish a query-ready, quality-checked distributed data network containing electronic health records (EHRs) linked with insurance claims data for at least 10 million individuals to expand the utility of real-world data for regulatory decision-making. Methods In this report, we describe the resulting network, the Real-World Evidence Data Enterprise (RWE-DE), including data from two commercial EHR-claims linked assets collectively termed the Commercial Network covering 21 million lives, and four academic partner institutions collectively termed the Development Network covering 4.5 million lives. Results We discuss provenance and completeness of the data converted in the Sentinel Common Data Model (SCDM), describe patient populations, and report on EHR-claims linkage characterization for all contributing data sources. Further, we introduce a standardized process to store free-text notes in the Development Network for efficient retrieval as needed. Conclusions Finally, we outline typical use cases for the RWE-DE where it can broaden the reach of the types of questions that can be addressed by the Sentinel system.

To examine valsartan, losartan and irbesartan usage and switching patterns in the USA, UK, Canada and Denmark before and after July 2018, when the first Angiotensin-Receptor-Blocker (ARB) (valsartan) was recalled.

This research examines the competing narratives about the role and function of Syria Civil Defence, a volunteer humanitarian organization popularly known as the White Helmets, working in war-torn Syria. Using a mixed-method approach based on seed data collected from Twitter, and then extending out to the websites cited in that data, we examine content sharing practices across distinct media domains that functioned to construct, shape, and propagate these narratives. We articulate a predominantly alternative media “echo-system” of websites that repeatedly share content about the White Helmets. Among other findings, our work reveals a small set of websites and authors generating content that is spread across diverse sites, drawing audiences from distinct communities into a shared narrative. This analysis also reveals the integration of government-funded media and geopolitical think tanks as source content for anti-White Helmets narratives. More broadly, the analysis demonstrates the role of alternative newswire-like services in providing content for alternative media websites. Though additional work is needed to understand these patterns over time and across topics, this paper provides insight into the dynamics of this multi-layered media ecosystem.

The Signal Code: Ethical Obligations for Humanitarian Information Activities translates and applies the foundational sources of ethical humanitarian practice to humanitarian information activities, such as mobile devices, WiFi provision, data collection, storage and analysis, and biometric registration tools. This document provides humanitarian practitioners and researchers with comprehensive ethical guidance for this increasingly commonplace and critical area of humanitarian practice.

Crisis-affected populations and humanitarian aid providers are both becoming increasingly reliant on information and communications technology (ICTs) for finding and provisioning aid. This is exposing critical, unaddressed gaps in the legal and ethical frameworks that traditionally defined and governed the professional conduct of humanitarian action. The most acute of these gaps is a lack of clarity about what human rights people have regarding information in disaster, and the corresponding obligations incumbent upon governments and aid providers. This need is lent urgency by emerging evidence demonstrating that the use of these technologies in crisis response may be, in some cases, causing harm to the very populations they intend to serve. Preventing and mitigating these harms, while also working to responsibly ensure access to the benefits of information during crises, requires a rights-based framework to guide humanitarian operations. In this brief report, we provide a commentary that accompanies our report, the Signal Code: A Human Rights Approach to Information During Crisis, where we have identified five rights pertaining to the use of information and data during crisis which are grounded in current international human rights and customary law. It is our belief that the continued relevance of the humanitarian project, as it grows increasingly dependent on the use of data and ICTs, urgently requires a discussion of these rights and corresponding obligations.

Sirona is a custom agent that translates natural language questions into sophisticated SQL queries against Sentinel Common Data Model formatted data. Code is written and executed in a sandboxed Deno runtime for token efficiency and execution safety—the sandbox prevents network access, filesystem writes, and source data modification.

@skywatch.blue is one of the largest and best-known community labelers on Bluesky and the ATProto network, leveraging the Osprey rules engine and agent based workflows to handle high volumes of user-created reports, and providing trusted safety signals for third-party ATProto infrastructure providers, such as selfhosted.social and npmx.social - Designed and built Skywatch's original labeling and moderation infrastructure, a Typescript-based rules engine, operating it in production from 2024 before migrating the service to the Osprey rules engine in 2026 - Deploy and operate the Osprey rules engine for automated report triage and threat detection across the ATProto network - Built statistical sidecar services for anomaly detection (network clustering, overdispersion scanning, first-mover analysis) supporting large-scale coordinated inauthentic behavior investigations, such as high-volume inauthentic fundraising networks - Built and maintain MCP tools and agent skills enabling LLM-assisted moderation at scale, reducing manual investigation workload - Recipient, ATProto Community Fund Grant

Website creation for the Manya Krobo Queen Mothers Association.

Multi-Company Advisory Service on Healthcare Information Technology and Life Sciences Informatics Standards and Strategy

What has it been like to run a large community labeler over the course of two years? I'll focus heavily on lessons learned, including reflections on what and who it serves, the missteps and pitfalls made along the way, and what I would do differently if I were to start all over again. I'll reflect on how I've come to view community labeling is distinct from Trust & Safety or moderation and the role it can still play in the ecosystem, along with thoughts on what directions the labeler ecosystem might explore in the future.

humanitarianRelief