Bell Eapen MD, PhD.

Bringing Digital health & Gen AI research to life!

About Me

Translational research in health IT is my passion.

Bell Eapen MD, PhD.

Digital Health & Gen AI Consultant
I am Bellraj (Bell) Eapen, a techie MD (dermatologist) with a PhD in Information Systems from McMaster University. As an R&D lead engineer at Mayo clinic, I specialize in cloud architecture for Gen AI and multimodal machine learning using FHIR.

I maintain several software libraries on GitHub. I facilitate the adoption of Generative AI and FHIR in healthcare organizations. As a consultant, I deliver prototypes & models instead of reports and recommendations!

Checkout my GitHub repo and Contact Me for your next project!

Services

Things that I work on.

Cloud Architecture for ML

Deploy healthcare machine learning pipelines on the cloud

ML & AI Research in Healthcare

Facilitate ML and AI research in healthcare

Generative AI

Chatbot & Conversational AI for clinical workflows

AI Application Design

Design AI applications that fits enterprise architecture

FHIR & Analytics

Data warehousing and health data analytics for healthcare (FHIR & OHDSI OMOP)

Customize Health Information Systems

Customize OSCAR, OpenMRS, DHIS2 and RedCap

Skills

Things that I'm good at.

FHIR
90%
GCP
80%
AI
90%
JAVA
80%
Python
70%
OSCAR EMR
100%
DERMATOLOGY
100%
TensorFlow
85%

Blog

My thoughts.

LLM-in-the-Loop CQL execution

V. LLM-in-the-Loop CQL execution with unstructured data and FHIR terminology support

- June 4, 2025

Here is how you can run the CQL execution with unstructured data and FHIR terminology support using our LLM-in-the-Loop stack as presented at AMIA #CIC25.

Rijksdienst voor het Cultureel Erfgoed, CC BY-SA 4.0 , via Wikimedia Commons

IV. DocumentReference hook in CQL execution

- June 3, 2025

The GitHub repository below is a fork of the CQL Execution Framework, which provides a TypeScript/JavaScript library for executing Clinical Quality Language (CQL) artifacts expressed as JSON ELM. The fork introduces an experimental feature supporting LLM-based assertion checking on DocumentReference. The framework enables execution of CQL logic within different data models, such as QDM and FHIR, but does not provide direct support for data models or terminology services. The library implements various features from CQL 1.4 and 1.5 but has some limitations, such as incomplete support for specific datatypes and functions.

III. MedPromptJS: Simplifying GenAI Application Development

III. MedPromptJS: Simplifying GenAI Application Development

- June 2, 2025

MedpromptJS converts CQL statements to natural language, splits unstructured data into chunks, and generates yes/no answers based on LLM-mapped facts.

Photographer’s Mate Airman Apprentice Ricardo Reyes, Public domain, via Wikimedia Commons

II. VSAC-on-FHIR

- May 30, 2025

My enhancement now extends support beyond VSAC, enabling the use of FHIR-compliant terminology servers for private or custom-defined Value Sets. This added feature allows healthcare organizations to leverage their own FHIR-based terminology repositories, improving flexibility for institutions that need localized or proprietary clinical vocabularies while maintaining compliance with existing standards. Users can specify a FHIR Base URL to direct queries toward non-VSAC terminology servers, ensuring broader accessibility to domain-specific terminologies.

I. CQL to ELM translator API with SpringBoot

I. CQL to ELM translator API with SpringBoot

- May 29, 2025

Clinical Query Language (CQL) is a flexible, domain-independent query language designed to support clinical decision-making by enabling intuitive and standardized queries without requiring extensive technical knowledge. It works with any data model, integrates with widely used programming languages, and relies on the Expression Logical Model (ELM) as an intermediary format to ensure consistency with existing healthcare data standards. The open-source CQL-to-ELM Translator, built in Java, facilitates seamless execution of CQL queries by converting them into ELM representations, supporting various customization options and integrating with FHIR, QDM, and QUICK models to enhance clinical data interoperability.

Loading MIMIC dataset onto a FHIR server in two easy steps

Loading MIMIC dataset onto a FHIR server in two easy steps

- November 20, 2024

The integration of generative AI into healthcare has the potential to revolutionize the industry, from drug discovery to personalized medicine. However, the success of these applications hinges on the availability of high-quality, curated datasets such as MIMIC. These datasets are crucial for training and testing AI models to ensure they can perform tasks accurately and […]