World-Class Medical Datasets
Partnerships with a wide variety of world-renowned academic and community hospitals as well as private clinics gives us the raw materials to achieve our mission.
Founded by Canadian-trained radiologists, 16 Bit is well versed in the challenges facing medicine today and where AI can be leveraged to overcome them.
Advanced Networks and Computation
Amidst a revolution in artificial intelligence, we design custom neural network architectures and train them using state-of-the-art hardware.
The purpose of this initiative is two-fold. First, to collate a large high-quality clinical dataset on hospitalized COVID-19 patients and make this data freely accessible for the purposes of mobilizing the world's innovators and researchers. Secondly, we aim to use this dataset to develop a clinical tool to predict the course of hospitalized COVID-19 patients in an effort to improve morbidity and mortality as well as improve healthcare resource utilization and predictability at the systems level.Partner With Us
At least 1 in 3 women and 1 in 5 men suffer from an osteoporotic fracture in their lifetime. The current clinically accepted gold-standard to screen for osteoporosis is a dual-energy x-ray absorptiometry (DEXA) scan. 16 Bit plans to change this paradigm with its patent-pending technology which will enable less costly and more ubiquitous population screening for osteoporosis as well as more robust fracture risk stratification. To achieve this, 16 Bit has partnered with the Canadian Multi-Center Osteoporosis Study (CaMos) with funding support from Amgen.
Breast Cancer Screening
1 in 8 women will be diagnosed with breast cancer in their lifetime. Mammography is a well-established modality used to screen for breast cancer. 16 Bit is working on a screening algorithm to triage mammograms and assist radiologists in their interpretation.
Pediatric Bone Age
Pediatric populations frequently require correlation between skeletal maturation and chronological age. Currently, radiographs of hands are used and patients are categorized based on the presence and absence of bony features. This method is dated and cumbersome. 16 Bit participated in the 2017 RSNA Machine Learning Challenge and achieved 1st place.Try our bone age model
You will be joining a passionate multi-disciplinary team whose core value is to improve healthcare quality and equity for all people around the globe. Your contributions will be invaluable in helping 16 Bit achieve this grand vision.
Lean and Agile Team
Work together directly with the founders and participate in key decision making that will help guide the future direction of 16 Bit.
Work where you are most productive and comfortable.
A deep-dive into how we trained a neural network to predict pediatric bone age with a mean absolute difference of 4.265 months.Read more
Get in touch if you would like to partner with us or if you have any questions or comments.