HDS Senior Data Analyst Job Somerville area,Massachusetts USA,IT/Tech

Senior Data Analyst Overview

The Senior Data Analyst, within the Mass General Brigham Enterprise Analytics (EA) Department, providing dedicated analytical support to Health Data Solutions (HDS), is responsible for identifying, querying, analyzing, curating and visualizing clinical data to support initiatives throughout Mass General Brigham. The Senior Data Analyst will be responsible for using MGB data assets to build curated datasets according to complex requirements. The position requires close collaboration and dialogue with external collaborators, clinical personnel, various analytic groups, and hospital and system leadership.

The Senior Data Analyst partners closely with clinicians, researchers, and analytics and digital colleagues to translate complex questions into rigorous analytical approaches. The role requires strong expertise in Snowflake SQL, Python, and R, with an emphasis on reproducible, well-documented analytical workflows.

In addition, the Senior Data Analyst will serve as a resource and role model for other data analysts, sharing best practice methodologies, training other analysts and end-users, and growing the team's wealth of knowledge and documentation. The team primarily leverages Snowflake SQL, Python, R, and the Microsoft Office suite, and is partnering with the MGB Digital data platform teams on a journey to build a new data platform with Microsoft Azure Cloud and Snowflake, and leverages other tools and technologies on an as needed basis.

Principal

Duties and Responsibilities

Partners with researchers, clinicians, and other stakeholders to define research-oriented analytic questions and data requirements, translating study objectives and protocols into clear analytical specifications.

Queries and analyzes data from hospital systems such as our electronic medical record system (Epic), enterprise data warehouse (EDW), vendor neutral archive (VNA) and more, to identify and curate cohorts based on dataset specifications and other project requirements. The analyst should be comfortable performing data wrangling across multiple data sources.

Produces and maintains data dictionaries, dataset versioning and release notes.

Presents data and analyses to key stakeholders, including creating materials for and giving presentations as needed.

Uses programmatic tools such as Python or R to support data QA and exploratory analysis. This includes identifying missing data, detecting outliers, and assessing whether anomalies reflect true variation or unreliable data.

Applies data de-identification techniques and tools to protect sensitive healthcare information in accordance with HIPAA and related regulations.

Develops, maintains, and delivers programmatic analytical outputs, including reproducible reports, analytical datasets, figures, and written summaries, to support stakeholder decision-making.

Collaborates with EA, HDS, and MGB Digital partners to continually improve analytical capabilities using SQL, Python, R, and other programmatic analytics tools, including documentation of analytical methods, assumptions, and limitations.

Performs comprehensive quality assurance, ensuring that data and reports meet end user specifications and are accurate and reliable.

Works with new and existing EA analysts to share knowledge in methods of data analysis, summarization, and presentation. Trains other analysts and end-users on key analytic and reporting systems and databases.

Partner with MGB Digital teams to leverage existing tools, methods, and processes in order to deliver timely information to stakeholders across MGB, including Snowflake SQL.

Effectively recognizes when additional help or guidance is needed and seeks it out proactively.

Represents EA on internal and external committees or task forces as needed.

Performs all other related duties as required.

Skills and Abilities

Strong ability to work and communicate effectively with staff at all levels within the organization, including senior hospital management.
Experience with querying, manipulating, cleansing, and statistically analyzing large data sets using tools such as SQL Server Management Studio, Python, and R.
Strong experience presenting analytical findings using programmatic and narrative-driven approaches, including creation of tables, figures, statistical summaries, and written insights appropriate for executive and clinical audiences. With limited input from others, creates data visualizations that are suitable for presentation to senior leaders.
Demonstrated ability to handle protected health information (PHI) under HIPAA, organizational policies and IRB protocols.
Familiarity with LLM-based tools to help review unstructured clinical text, extract structured variables, and support pre-labeling workflows.
Ability to clearly communicate complex and sensitive data to senior executives as well as peers and external collaborators.
Strong written and verbal communication skills, with the ability to tailor message to individuals and audiences throughout the…