Data Science Intern

Prolaio • Chicago, IL

4h

About The Position

Prolaio believes that continuous learning and collaboration can make a significant difference in how heart care is administered. We are creating smarter ways to address heart disease and heart risks by integrating a connected platform enabled by smart data science to help patients access the care and attention that will inform better treatments and outcomes.
We envision a future where care teams and hospitals can be more effective, the healthcare system can be more efficient, and patients have a better care experience and more fulfilling lives.
This is precision cardiology, and we know it’s within reach.
As the Data Science Intern, you wil develop, operationalize, and validate Large Language Model (LLM) pipelines capable of extracting high-priority clinical endpoints from longitudinal Electronic Health Record (EHR) data. This role is critical for scaling the EHR study data by automating the extraction of complex clinical phenotypes and validating them against manual clinical review to ensure high-quality data for clinical analysis.

Requirements

• Currently enrolled in a Master’s or graduate-level program in Computer Science, Data Science, Biomedical Informatics, Bioengineering, Computational Biology, or a related field.
• Technical Proficiency: Strong proficiency in Python programming with experience using Large Language Model (LLM) APIs.
• NLP Knowledge: Familiarity with Natural Language Processing (NLP) concepts, specifically Prompt Engineering.
• Data Handling: Experience handling unstructured text data, cleaning messy real-world data, and/or working with human evaluation datasets.
• Analytical Skills: Ability to handle edge cases in text (e.g., negation) and validate one’s own output using standard validation metrics.

Nice To Haves

• Domain Knowledge: A basic understanding of clinical terminology, Electronic Health Records (EHR), or biomedical data is highly preferred.

Responsibilities

• Endpoint Extraction Pipeline Development: Develop Python/LLM workflows, including workflows built on purpose-built clinical extraction tools, to ingest unstructured xCures data (clinical notes, discharge summaries) and extract key study endpoints, specifically Clinical Events or “Unified Problem Lists”
• Validation Framework Execution: Design and conduct a human review validation study comparing LLM-generated abstractions against a “gold standard” dataset derived from manual chart review.
• Codebase Delivery: Build and maintain a documented code repository that inputs raw xCures EHR data and outputs structured clinical datasets for study data.
• Performance Analysis & Reporting: Analyze pipeline performance to establish concordance, sensitivity, and specificity metrics, delivering a final validation report with performance metric for multiple approaches.
• Cross-Functional Collaboration: Collaborate with clinical and technical mentors to translate clinical requirements into technical solutions.

Benefits

• Impactful Work: You will join in the fight against heart failure (HF) and hypertrophic cardiomyopathy (HCM) with the goal of extending and saving the lives of our patients while also being at the forefront of changing the healthcare industry through technology.
• Innovative Environment: You will be part of an organization doing something that’s never been done before.
• Professional Growth: You will join a growing team and have a substantial impact on our daily and future operations with the opportunity to continuously learn and grow.
• Collaborative Team: You will be part of a team of collaborative, curious, and committed individuals focused on the collective good, inclusiveness, scientific excellence, and advancing digital health for cardiology.

What This Job Offers

• Career Level: Intern