Role & Responsibilities
Our client is seeking a highly analytical and client-focused Data Scientist with 4-7 years of experience in Patient-level data. The ideal candidate will combine deep clinical understanding, strong patient-level data expertise, and advanced analytical skills to generate insights that drive strategic and operational decisions. This role requires hands-on experience with integrated healthcare datasets (claims, EHR, lab, pharmacy) and the ability to translate complex analyses into clear, actionable business recommendations.
Key Responsibilities:
- Apply strong understanding of healthcare delivery models and patient care pathways
- Conduct patient centric analysis like treatment pattern, line-of-therapy, and disease progression analyses etc.
Patient-Level Data Integration & Journey Mapping:
- Integrate and analyze claims, EHR, lab, and pharmacy datasets etc to develop longitudinal patient journeys across multiple care settings
- Define cohorts, enrolment logic, and episode-of-care frameworks
- Ensure data quality, consistency, and reproducibility
Advanced Analytics & Predictive Modelling:
- Develop complex SQL /Python queries for large-scale healthcare datasets
- Developed risk stratification models using machine learning techniques to prioritize patients based on clinical and behavioural risk factors.
- Applied time-series and survival analysis to study treatment duration, drop-offs, and patient retention trends.
- Leveraged NLP on patient interaction data (notes, call logs) to identify common barriers like side effects, cost issues, and therapy fatigue
Data Interpretation & Storytelling:
- Translate analytical findings into clear, strategic insights and develop executive-ready presentations and dashboards
- Communicate complex methodologies to both technical and non-technical stakeholders
- Quantify business and clinical impact of recommendations
Innovation & Learning Agility:
- Innovation & Learning Agility
- Quickly ramp up in new therapeutic areas and problem domains
- Test innovative analytical methods and modelling approaches
- Adapt to evolving client priorities and ambiguous problem statements
