Leveraging AI to match patients with medical research
Curewiki is a startup on a mission to democratize access to medical research for patients worldwide. They're revolutionizing the process by shifting from a research-centric recruitment model to a patient-centric one, empowering patients to find research opportunities that are right for them. The Curewiki team approached us with ambitious goals and we jointly embarked on a mission to build an industry-altering product.
Challenge
We faced a two-fold challenge: (1) designing & building a seamless end-to-end workflow for both researchers and patients, and (2) developing a system to automatically interpret the medical text within clinical trials, accurately identifying eligibility criteria for patient participation.
Solution
Together we created a comprehensive digital platform with a user-friendly experience for both researchers and patients. Alongside this, the operational tools and practices were put in pace for the platform and the necessary documentation for data privacy and security compliance was provided.
Approach
We assembled a dedicated joint product team, comprising a product manager, a designer, and a team of skilled software engineers. To build the AI agent, we utilized highly specialized medical LLM's to interpret clinical trial content, while simultaneously training and evaluating the AI agent to gather relevant patient health information.
Jean-Sebastien Gosuin
Co-founder & CEO Curewiki
"It's remarkable how well Panenco grasped our vision and ambitions. Given that Curewiki was still in its early stages, we needed an entrepreneurial partner that could make the bridge from strategy to product delivery. That's exactly what Panenco provided to us, in a spirit of true co-creation."
Solving a two-sided marketplace problem with AI
To ensure the success of the Curewiki model, we needed to create value for both patients and researchers, while adhering to all regulatory considerations.
Building distinct conversational flows for patients/researchers
We built a patient-facing bot, which employs targeted questioning to pre-screen individuals while prioritizing privacy and collecting only relevant data; and a researcher-facing workflow tool designed to validate research criteria and improve patient communication, thereby addressing the challenges researchers face in identifying suitable participants.
Reaching a broad audience of patients worldwide
The two-sided marketplace of Curewiki is used by a broad group of patients worldwide. With more than 35 000 patients and 1.8 million research questions answered, we built a platform that can handle global scale with minimal latency and adequate cost efficiency.
Organising a highly effective product development process
Co-creation: We set up a joint, dedicated product development team, mixing product development and domain expertise together. The team consisted of a product manager, engineering manager, designer and dedicated software engineers.
Release early, release often:
Curewiki operates as a serverless SaaS product built on AWS infrastructure. We implemented automated pipelines with extensive test coverage to enable frequent and reliable releases.
Validating with users:
We developed several tools to interact with users and ensure that their needs are met. User feedback plays a crucial role in shaping the key product roadmap decisions.
"The Curewiki team is tackling an enormous global problem that only recently became feasible to solve through the advancements in the field of generative AI. It's heartwarming for us to consider how many lives this technology will touch. We wish the Curewiki team the very best of luck as they are driving the go-to-market of this technology. We'll gladly keep supporting you every step of the way!"
Stefanos Peros
Software engineer
Fred Versyck
Product manager