My work has demonstrated how artificial intelligence (AI) and machine learning (ML) can characterize challenging elements of disease progression important for evaluating research designs and treatment decisions.

Fun Fact: research studies that use data-driven disease progression models to inform participant selection can demonstrate higher efficacy and safety.

We have used artificial intelligence (AI), operations research (OR) methods, and other computational techniques to improve the flow of patients through hospitals, surgical units, and patient transport services.

Fun Fact: We reduced the closure rate of one emergency department by 30%, enabling care to thousands of additional patients every year.

Several solutions reflect the fact that sustainable healthcare costs require a deeper understanding of the relationship between treatment options, costs, and patient outcomes delivered.

Fun Fact: My team’s solutions have successfully identified drugs, medical devices, and medical practitioners that demonstrate better outcomes at lower costs.

As providers pursue bundled reimbursement models, artificial intelligence (AI) and predictive models can be used to characterize the specific care services and treatments associated with higher individual patient outcomes.

Fun Fact: My team was able to develop help a provider increase their reimbursement rates by providing richer insights on their episodes of care.

Our data and analytics projects commonly need to describe how factors such as patient demographics, risk factors, treatment decisions, and care practices influence observable healthcare quality and outcomes.

Fun Fact: When building healthcare quality insights, my teams focus on creating a “single source of truths” that can be used to guide clinical and operational decisions.

Because trusted data is the fuel for high-impact artificial intelligence (AI) and analytical insights, I’ve developed several commercial software products that gather, aggregate, and standardize life sciences and healthcare data.

Fun Fact: My work at companies like Microsoft and SAS led to platform-wide adoption of industry standards such as CDISC, HL7, open source interoperability, and regulatory compliant e-signatures.

I’ve helped many organizations assess, develop, and implement improvements that increase the power, scalability, and usability of their data assets.

Fun Fact: I designed and implemented a specific data architecture that ensures investments in AI, data visualization, and business intelligence are trustworthy, reusable, and scalable.

My teams have designed, engineered, and commercialized industry-standard software used to store, analyze, and report clinical research safety and efficacy findings for novel therapies all around the world.

Fun Fact: During my time at IQVIA and GSK, my teams developed and deployed the first generation of web-based electronic data capture (EDC) systems to conduct clinical research.