Case studies

Jackalope automates transforming complex medical data into standardized formats of OMOP CDM and SNOMED Clinical Terms (CT). This enables healthcare providers, practitioners, and scientists to effectively use real-world evidence (RWE) in healthcare for research and delivering enhanced patient care.

The client is a professional healthcare technology provider whose platform is used by multiple medical institutions to support clinical medical data interoperability. The project focused on enabling medical semantic search using LLMs and vector databases, allowing healthcare teams to structured clinical data extraction from free-text input. To achieve this, the platform integrates large language models for real-time query normalization and a locally deployed Quadrant vector database for high-performance concept retrieval. The solution was designed to deliver accurate concept mapping at scale, while aligning with MLOps and DevOps best practices to ensure reproducibility, modularity, and operational stability across environments.

The client provides an AI for quick service restaurants (QSR) restaurants that uses a custom NLP system to interpret natural customer speech and convert it into structured, kitchen-ready orders. The menu-aware NLP system handles complex, brand-specific menus with customizable combos, modifiers, and promotional items. It recognizes varied phrasing, synonyms, and marketing terms, and maintains contextual awareness across multi-turn conversations. The AI-driven order automation system supports slot filling, multilingual input (English and Spanish), real-time menu updates, and upselling logic.

We built an AI-powered Knowledge Assistant for enterprise resource planning provider, delivering instant, accurate answers to complex queries. It uses NLP, vector search, and contextual understanding to integrate with knowledge bases and enhance customer experience. Our client is a leading provider of enterprise digital transformation solutions for various sectors, with a strong focus on the financial industry as well as manufacturing, distribution, and retail. Their offerings include tools for managing supply chain operations, financials, production, and customer relationships. They requested us to develop an LLM-based chatbot for internal documentation and ERP knowledge that gives users quick access to information about the company’s products and services. It uses a detailed database of presentations, documents, and common questions to provide fast and accurate answers to inquiries, helping their client to get a comprehensive consultation without the need to wait for a response from sales team members.

A private research organization focused on evaluating the safety and effectiveness of medications. Their goal is to use advanced medical data analytics and data harmonization in healthcare to support healthcare decisions and meet regulatory standards. For this project, they aimed to assess the safety of hydroxychloroquine, used alone or with azithromycin, for treating rheumatoid arthritis. The study focused on identifying short-term side effects and long-term risks, especially related to heart health and the use of multiple medications together. The client needed a data-driven approach, similar to methods used in federated healthcare data platforms, to fill gaps in existing evidence by combining different clinical data sources and applying patient similarity networks for clinical decision-making to identify patient groups with similar characteristics and address factors that could affect treatment outcomes.

We have extensive experience in automating mappings between medical coding and classification systems by computationally processing their semantic meaning, which can be extracted using NLP methodology or explicitly available from the classification model. Our successful applications include mappings made from ICD-10-PCS, LOINC, and ICD-O-3 systems for OHDSI OMOP Standardized Vocabularies.

The client is a healthcare company focused on medical imaging and diagnostics, working to improve the diagnosis of lung diseases like tuberculosis and COVID-19. They wanted to create an AI for chest X-ray analysis for lung disease detection to spot abnormal changes and automatically prioritize the most urgent cases. The healthcare automation platform functions as an automated radiology triage system using deep learning, identifying abnormalities and highlighting critical cases to make diagnosis faster and more accurate. It supports reducing radiologist workload with automated image analysis by handling routine tasks, allowing specialists to focus on complex cases. By solving issues like delayed diagnoses and heavy workloads, the automated diagnostics system ensures patients with serious conditions get quicker and more reliable care.

Our solution uses advanced Natural Language Processing (NLP) and Machine Learning (ML) to automate the extraction of detailed specifications and measurements from complex product spec sheets. The client is a company in the manufacturing industry that provides advanced technology solutions to improve and simplify production processes. They needed a sophisticated system to manage various types of documents, such as spec sheets, technical manuals, and product datasheets.