Lead Data Scientist - Aetna Medicare Stars

We’re building a world of health around every individual — shaping a more connected, convenient and compassionate health experience. At CVS Health®, you’ll be surrounded by passionate colleagues who care deeply, innovate with purpose, hold ourselves accountable and prioritize safety and quality in everything we do. Join us and be part of something bigger – helping to simplify health care one person, one family and one community at a time.

The Aetna Medicare Stars business is seeking a Lead Data Scientist to own analytics and decision support for the Patient Safety measure set, medication adherence (diabetes, hypertension, statins), SUPD, and polypharmacy, within Stars Data Science. This role translates measure-level performance into actionable, member- and provider-level interventions that close gaps and protect Star Ratings.

The Lead Data Scientist operates as both a senior individual contributor and a technical leader, building the analytical frameworks, cohort models, and decision tools that inform outreach prioritization, vendor pilot evaluation, and cross-functional strategy for the Patient Safety domain. This role partners closely with clinical pharmacy, population health, and program leaders to ensure analytics translate into practical, deployable interventions.

·       Own end-to-end analytics for the Patient Safety measure set: medication adherence (diabetes, hypertension, cholesterol), SUPD, and polypharmacy (opioid, anticholinergic, CNS-active).

·       Build and maintain cohort segmentation, risk scoring, and gap-prediction models that identify members likely to fall out of adherence or into a polypharmacy risk category before it affects the measure.

·       Design and evaluate outreach and intervention pilots (for example, combined medication adherence and HEDIS gap outreach) using rigorous pre/post and control-group methodology, and quantify ROI.

·       Lead technical mentoring of junior and mid-level data scientists on the Patient Safety analytics workstream, reviewing methodology and code, not just outputs.

·       Partner with clinical pharmacy, population health, and vendor management leaders to translate measure-level findings (denominator composition, adherence trends, drug interaction risk) into specific, actionable business recommendations.

·       Present findings and recommendations to Stars leadership, framing technical analysis in business and clinical terms.

·       Maintain a working command of CMS Patient Safety measure specifications, cut points, and scoring methodology, and flag measure or specification changes that affect strategy.

·       Evaluate vendor and program performance for Patient Safety-adjacent interventions (MTM, medication therapy management outreach, pharmacy partnerships) using consistent, defensible measurement standards.

·       Contribute to the broader Stars Data Science analytical roadmap, ensuring Patient Safety work is coordinated with adjacent measure teams (HEDIS, PCR, member experience) rather than run in isolation.

·       8+ years of experience in data science, analytics, or decision science, ideally with healthcare, pharmacy, or Medicare Advantage/Part D experience.

·       Deep hands-on technical skill: SQL, Python, and experience building production-grade cohort and predictive models on large claims or clinical datasets (BigQuery or equivalent).

·       Working knowledge of Medicare Part D Patient Safety measures (medication adherence, SUPD, polypharmacy) and CMS Star Ratings methodology, or the demonstrated ability to ramp quickly on measure-specific technical detail.

·       Demonstrated experience designing and evaluating outreach or intervention pilots, including control-group and ROI methodology.

·       Track record of mentoring and technically leading other data scientists, without requiring formal people-management scope.

·       Strong communication skills, with the ability to translate complex analysis into clear, clinically and operationally grounded recommendations for non-technical stakeholders.

·       Comfortable operating with significant autonomy in a fast-moving, ambiguous environment, and prioritizing across multiple concurrent measure-level asks.

The typical pay range for this role is: