Aayush Sisodia.
Every day, millions of healthcare decisions stall not because information is missing, but because it is buried. A claim sits in a queue, coded in a language patients were never taught. A prior authorization request loops between a provider's office and a payer's system, each side waiting on documentation the other thinks has already been sent. A quality measure tells an administrator that performance improved, but not why, or for whom, or what to do next. Healthcare runs on data. The problem is that very little of that data was designed to be understood by the people who need it most.
That gap-between information that exists and information that is usable-is where Aayush Sisodia has built his career.
Sisodia's path into healthcare analytics was not a straight line. He first trained in dentistry in India, a clinical foundation that gave him an early, ground-level understanding of how healthcare delivery actually works: the documentation burdens, the communication gaps between providers and patients, the distance between what a system records and what a person experiences. Clinicians, he observed, spent significant time translating between what they knew and what the systems around them could capture-and patients were rarely part of that conversation at all. That clinical lens became the starting point for a broader shift. After earning a Master of Science in Health Informatics from Northeastern University in Boston, Sisodia moved into research programming and health services analysis, applying technical methods to problems he had first encountered at the chairside.
His early roles reinforced a pattern he would return to throughout his career. As a Programmer Research Analyst at Northeastern, he worked with CMS Medicare Current Beneficiary Survey data to study food insecurity and health inequality-projects that required not just statistical technique but careful interpretation of what claims and survey data could and could not reveal about people's lived experiences. At bluebird bio, he supported SAS-based analysis in a regulated pharmaceutical environment, learning the discipline of working with data under strict compliance and reproducibility requirements.
The provider side of healthcare deepened that perspective. At Johns Hopkins HealthCare, Sisodia focused on claims-based quality measurement, working to align clinical guidelines with the real-world data used to evaluate them-a process that routinely exposed how much meaning gets lost when clinical intent is compressed into billing codes and administrative categories. As Population Health Data Manager at Maimonides Medical Center in Brooklyn, he managed provider-performance analytics, population health reporting, and quality initiatives across a hospital and IPA network. The role demanded fluency in both the clinical questions driving population health strategy and the data infrastructure needed to answer them.
More recently, as a Business Analytics Advisor at Evernorth Health Services, a Cigna company, Sisodia's scope expanded to enterprise-level payer analytics. One notable project involved building a reusable SQL data model for a claims-based time-to-treatment metric across a large member cohort-a framework designed with multiple adoption windows so it could be adapted for future use without requiring a full rebuild. He developed cohort identification and funnel analysis workflows, supported dashboards on medication utilization and cost trends, and worked across therapeutic areas where the ability to interpret claims data directly shaped program strategy.
What connects these roles is less the tooling than the underlying problem. Healthcare generates enormous volumes of data, but the systems that produce it-claims platforms, EHRs, quality reporting engines-were built to serve operational and regulatory needs, not to communicate clearly. Sisodia's work has consistently focused on closing that distance: turning fragmented records, codes, and measures into information that helps someone make a better decision. A poorly designed metric obscures a problem. A clear one reveals where patients are delayed, where costs are shifting, or where interventions are not reaching the people who need them.
That conviction has also led Sisodia to develop a growing portfolio of early-stage health technology concepts, each targeting a specific breakdown in how healthcare information reaches people. The Teach-Back Engine explores how AI-enabled tools could translate complex healthcare information into plain language, adapting the teach-back method-a clinical communication technique used to confirm patient understanding-into a digital format that helps patients and care teams identify confusion before it leads to missed care or poor adherence.
PriorAuth Autopilot targets one of healthcare's most persistent friction points. Rather than attempting to replace payer or clinical decision-making, the concept focuses on helping users understand what documentation matters, what questions to ask, and how to prepare for each step of the authorization process-reducing existing confusion rather than adding another layer of complexity.
RespiScope takes a different angle, exploring smartphone-first respiratory and cardiac sound screening using AI-supported audio classification. It reflects a broader pattern across Sisodia's work: use accessible technology to surface clinical signals earlier, explain them more clearly, and help people take the next reasonable step rather than waiting for the system to catch up.
Sisodia's focus on healthcare clarity also extends into writing and thought leadership. His Health Affairs Forefront article, "AI Equity Mandates Versus Unequal AI Capacity," published in February 2026, examines the gap between policy expectations for artificial intelligence in healthcare and the uneven ability of organizations to implement AI responsibly. He is also under contract with Routledge/Productivity Press to author a healthcare analytics book for non-technical professionals, tentatively titled Data Fluent: A Healthcare Professional's Guide to Analytics. Both projects reflect the same practical concern that runs through his analytics and prototype work: advanced tools matter only when people and organizations can understand, use, and act on them.
Beyond his core analytics and innovation work, Sisodia has served as an invited peer reviewer for The American Journal of Managed Care and maintains memberships in IEEE, the American Medical Informatics Association, and the American Public Health Association. Earlier in his career, he supported HIMSS global events and served as a teaching assistant for a Northeastern University course on society, behavior, and health-experiences that reinforced his interest in how healthcare information reaches diverse audiences. His technical foundation is supported by certifications in SAS programming, Tableau, Lean Six Sigma, and Scrum.
Healthcare is in the middle of a data transition. Organizations are adopting more analytics, more automation, and more AI-but the risk is that complexity migrates rather than resolves. Information becomes more abundant without becoming more useful. Dashboards multiply while the people reading them struggle to connect what they see to what they should do. Sisodia's career is built around the idea that the highest-value work in healthcare data is not generating more of it but making what already exists navigable, actionable, and genuinely understandable for the people whose care, coverage, and decisions depend on it.
In a system often criticized for being impossible to understand, that clarity may be among the most valuable forms of innovation.
Author: Ravi Gupta
