Nearly half of all patients receiving treatment for cancer will receive radiation treatment. The radiation treatment process takes clinicians hours, sometimes days, to complete. Curait Medical has a patent-protected platform providing automated, quantitative quality review enabling the radiation team to make more informed clinical decisions for each radiation treatment with reduced costs, increased quality, higher patient throughput, and fewer treatment errors. Curait's medical platform is Software as a Service (SaaS) based, enabling users access to machine learning of clinical practice and the ability to build models based on their clinical expertise. In addition, the platform facilitates more objective and consistent clinical practices across cancer centers, making it a valuable tool for healthcare managers.

‍UNMET NEED

There is a significant shortage of clinically trained experts in radiation oncology able to deliver radiation treatment to cancer  patients. In short, we will not be able to train enough professionals to meet  the increasing clinical demands associated with treatment delivery.

The radiation treatment process requires tremendous clinical expertise, is highly time consuming and expensive. Radiation treatments are planned (i.e. simulated) using specialized software and are subject to rigorous review by the entire radiation treatment team, before any radiation is approved and delivered to the patient. The radiation treatment plan is customized for each patient and specifies how the radiation treatment machine will deliver the radiation, and the radiation expected to reach the targeted tumour and any healthy organs.

RT treatment planning involves collaborating with a multidisciplinary team through repeated touchpoints. Curait’s patented SaaS uses machine learning to aid the team in evaluating and reviewing thousands of characteristics for each treatment plan in minutes. Whereas the total treatment planning process can take many hours to days to complete, with Curait, that time can be reduced by 30%, typically saving 3-6 hours per patient. This is because the Curait platform is designed to perform on-demand consultation, helping technicians complete treatment plans quickly, as well as expedite the mandatory treatment plan reviews for medical physicists and radiation oncologists. Curait’s SaaS improves workflow and eliminates expensive process bottlenecks resulting from handoffs within the radiation treatment team, thereby helping patients get their treatment faster.

The platform is vendor-agnostic, scalable, and can readily be integrated into the clinical workflow of any cancer center. It increases both the quality of and access to radiation treatment, while  providing immediate savings. The increased capacity realized using the Curait platform will positively impact revenues.

‍INNOVATION

Curait’s SaaS learns the characteristics of high quality treatment plans to build machine learning “models”.  It has been developed based on a comprehensive database from one of the world’s top 5 cancer centres,the Princess Margaret Cancer Centre. Curait’s SaaS also connects the radiation treatment team to a constantly expanding database of models.

Curait’s SaaS creates a personalized approach for reviewing each patient’s care by drawing on thousands of relevant historical cases and it can automatically access the most applicable patient data without relying on hard-coded metrics being entered by the user, as is common practice.

Curait also provides the team with understandable reasoning behind the evaluation of each component of the radiation treatment plan to aid in both identifying specific issues/errors, saving the radiation oncologist from having to complete multiple intermediary reviews, and in providing direct insights for making necessary adjustments to improve the radiation treatment plan quality.

For more information: https://curaitmedical.com/

‍APPLICATION/UTILITIES

‍Curait’s QA solution is applicable to all cancer patients requiring radiation treatment.  The technology can be easily integrated into any healthcare application that leverages a treatment plan.

‍INVESTMENT & OBJECTIVES

‍Investment Raise: $2 Million

Investment would be targeted to:

·  Product Development (45%) 

·  Sales-Marketing Commercialization (30%)

·  General Administration (25%)

‍COMPETITIVE ADVANTAGE
Patent pending with priority date in the U.S.; AI training using patient datasets from one of the world’s top 5 cancer centres; automatically learned clinical practice metrics.

‍MARKET SIZE
RT addressable market:  >US$500M

‍IP PORTFOLIO
The company's IP portfolio includes a patent pending for  automated quality assurance in radiation therapy.

US patent 201180211725A1: https://patents.google.com/patent/US20180211725A1/  

‍CURRENT MANAGEMENT TEAM
Curait's management team is experienced and has a track record of successfully navigating early-stage companies to commercial success.

‍CURRENT READINESS LEVEL

‍Curait’s platform (“Thor”) contains the following products:

Thor Data; completed – ready for sale.

Thor Audit; completion and sale readiness Q4 2023 (assuming financing)

Thor On-Demand; requires 510K for regulatory approval – completion  and sale readiness in 2024

Note: a NON-AI version of Thor Audit and On-Demand is  being used clinically (>9,000 patients) – the products are not fully  commercial-ready, but functional.

‍

‍‍SCIENTIFIC FOUNDER(S)
Dr. Thomas Purdie, Medical Physicist, Princess Margaret Cancer Centre; Associate Professor, University of Toronto.

Dr. Purdie is a staff medical physicist/clinician scientist and is the recipient of academic awards from NSERC and CIHR. Dr. Purdie’s research lab focuses on developing and deploying machine learning algorithms and methods for automating clinical radiation oncology workflow processes, including radiation treatment planning, quality assurance, and decision support.

‍Dr. Chris McIntosh, Toronto General Hospital Research Institute

Dr. McIntosh is the recipient of academic awards from NSERC, CIHR, and the Michael Smith Foundation for Health Research. His lab is focused on the theory and clinical application of AI in medicine for improving patient care including transfer learning, meta learning, computer vision, and explainable AI. Applications include deep learning for automated diagnosis, segmentation, quality assurance, and treatment planning.