BEKhealth utilizes an AI-powered patient-matching platform that extracts structured and unstructured data from electronic medical records to identify clinically qualified participants for clinical trials. This technology enables organizations to enhance feasibility assessments and achieve up to 10 times more qualified patients and twice as fast enrollment compared to traditional methods.
Funding
$15.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Clinical trials often face delays and increased costs due to difficulties in identifying and enrolling eligible patients who meet specific inclusion/exclusion criteria. Traditional patient identification methods rely on manual chart reviews and structured data, which can be time-consuming, miss crucial information in unstructured data, and lead to slower enrollment rates.
Solution
BEKhealth offers an AI-powered patient-matching platform, BEKplatform, designed to accelerate clinical research by precisely identifying qualified patients for clinical trials and observational studies. The platform leverages natural language processing (NLP) and machine learning (ML) to extract and synthesize both structured and unstructured data from electronic medical records (EMRs), including physician notes and reports. By transforming unstructured clinical data into a searchable, longitudinal patient graph, BEKplatform enables researchers to build robust queries, analyze patient populations, and determine trial feasibility more efficiently. This comprehensive approach captures three times more trial criteria compared to traditional methods, leading to faster site selection and a significant increase in the number of clinically qualified participants.
Target Audience
The primary target audience includes clinical research sites and healthcare organizations aiming to improve patient enrollment, as well as sponsors seeking sites with right-fit patients for their clinical trials.
Features
- AI-powered patient-matching platform that analyzes structured and unstructured data from EMRs
- Natural language processing (NLP) to extract relevant information from clinical notes and reports
- Deep learning neural networks based on BERT to identify medical entities and associated attributes
- Query and cohort builder for creating targeted patient groups based on specific criteria
- Real-time feasibility reports and insights for data-driven decision-making
- Synthesized, longitudinal patient graph that provides a comprehensive view of patient history
- Searchable ontology with over 24 million terms, synonyms, and lexemes for precise patient identification
- Human-in-the-loop feedback mechanism to refine model outputs and ensure accuracy