Case Study

Clinical Research Support

Clinical research support provided for Cleveland Clinic Abu Dhabi

K Pro
AI Scientist
Prostate Cancer
Owkin transformed siloed, unstructured clinical data into a queryable patient registry.

We aligned with Cleveland Clinic Abu Dhabi (CCAD) on a first proof of concept to demonstrate how K Pro could support clinical practice.

‍

‍We focused the scope on prostate cancer and built a two phase solution:

  • Processing and harmonizing multimodal, multisource data to break siloes and build a unified registry.
  • Connecting K Pro and unlocking agentic exploration of the data.

We showed concrete value: identifying patients and exploring their characteristics in seconds, while drastically reducing the time-to-insight with potential applications for tumor board meetings.

‍

An AI scientist for clinicians

‍Data Transformation AI integrated CCAD’s electronic health record (EPIC) clinical tables, free-text notes, and 994 pathology PDFs via optical character recognition + LLM extraction into a unified registry of 1,700 prostate cancer patients.

AI-augmented pathology through Owkin's Pathology Explorer Tool analysing digitised H&E prostate cancer slides for cell segmentation and annotation, validated by a CCAD pathologist.

Secure, compliant deployment within CCAD's closed Azure environment using UAE in-region AI models - no data left the hospital, fully compliant with UAE governance rules.

K Pro brought the natural language interface to allow clinicians to query cohort characteristics, treatment patterns, and recurrence outcomes in real time.

‍

We built an AI scientist for clinicians
Before

Days or weeks to manually assemble a patient cohort for tumor board.

After

Seconds to query similar patients, treatments, and outcomes.

Before

Clinical variables buried in PDFs and free-text – inaccessible at scale.

After

Structured, queryable registry with 317+ extracted variables per patient.

Before

Pathology slides not integrated with clinical data.

After

AI cell segmentation linked to patient records – foundational for precision oncology research.