AI to find the right patients, right now.

In a galaxy full of patients, turn to BEKhealth to identify more clinically qualified patients for your clinical research. Leverage our AI-powered patient-matching platform to find the perfect patients every time. With BEKhealth by your side, dramatically speed up feasibility and detect more protocol-eligible candidates leading to 10x more qualified patients and 2x faster enrollment.


Precise patient matching to accelerate your clinical research

It’s time to stop wasting time going down dead ends. BEKhealth harnesses its AI-powered patient-matching platform to help organizations conducting clinical trials and observational studies better understand their patient populations, optimize feasibility, speed up site selection, and rapidly identify clinically qualified participants by extracting structured and unstructured data from electronic medical records (EMRs) that captures three times more trial criteria.

Take a look inside BEKplatform, the AI-powered patient-matching technology for sites and healthcare organizations

Query and Cohort Builder

BEKplatform transforms patient-level structured and unstructured medical data to detect more protocol-eligible candidates so you can build robust queries and patient cohorts. Turning disorganized, unstructured clinical data into a synthesized, longitudinal patient graph that is easily queryable.

Feasibility Reports and Insights

BEKplatform facilitates powerful decision making from easily digestible reports, allowing researchers to access real-time patient data and use it to analyze their patient populations, quickly determine trial feasibility, automate processes and identify untapped trial opportunities.

Turn unstructured data into searchable patient information

BEKplatform accesses the saved files, reports, and notes associated with patient charts. After accessing the unstructured data, BEKplatform divides each note/record into sentences and transforms the underlying text. The platform than analyzes and transforms text using deep learning neural net based on BERT to identify medical entities and associated attributes for key domains (e.g.: demographics, diagnosis, medications, etc.).

Text is now mapped to a searchable ontology that is made of more than 24 million search terms, synonyms, and lexemes. Combined with structured medical data, the BEKplatfom generates a synthesized, longitudinal patient graph. To support its industry leading 93% accuracy in interpreting EMR records, BEKhealth employs a human-in-the-loop feedback mechanism to hone the models’ outputs, ensuring a high level of reliability and relevance to clinical contexts.

Our numbers speak for themselves


more patients identified


more qualified patients enrolled

Patients found in


rather than months


faster enrollment goals

Finding the
unfindable patients

“We were able to pre-screen 10+ new lung cancer patients in the last three weeks and offer the study to three patients. As you may be aware, this is a very selective and cutting-edge clinical trial, and prior to the BEKhealth project, we were unable to find patients who might qualify.”

Oncology Clinical Research
Memorial Cancer Insitute

Patient identification is the most vital part of any study

EMR data isn’t meant for you, it’s meant for insurance. So, we built a product that translates that data to make sense of it for clinical research. By sifting through structured data and translating handwritten notes and charts, the BEKplatform can find clinically-qualified patients for even the most rigorous inclusion/exclusion criteria. Find your perfect patients faster, more accurately, and more successfully than ever.


Who want to rapidly and accurately find the right patients for their clinical research.

AI-powered clinical research


Who need sites with the right-fit patients for their studies and trials.