Surgisphere has developed an intelligent tool that uses as few as three common laboratory tests to identify patients likely to have coronavirus infection. With a sensitivity of 93.7% and specificity of 99.9%, this highly accurate test can help limit transmission of this deadly virus by identifying and isolating affected patients sooner, mobilizing appropriate public health resources, and avoiding the delays associated with current testing.
"Surgisphere exists to help make the world a better place. This tool is the first effective weapon in the fight against this global pandemic. Early diagnosis means faster treatment, which means more lives saved," stated Dr. Sapan Desai, President and Chief Executive Officer of Surgisphere.
Surgisphere used its cloud-based healthcare data analytics platform (QuartzClinical) to identify patients diagnosed with COVID-19 in five countries. A machine learning model using decision tree analysis was created with clinical and lab data on 430 patients to develop this decision support tool. This resource is now available for public use at https://www.SurgicalOutcomes.com/. These advances have been submitted to a leading medical journal for rapid peer review and publication.
The power of machine learning grows with high-quality data. Surgisphere is seeking physicians and healthcare systems to work collaboratively by sharing data to increase the sample size of patients infected with COVID-19. Higher quality data means a more accurate model, which can lead to early diagnosis and treatment. Participation in the global research network is funded by Surgisphere and is free for physicians and healthcare systems. Patients, foundations, and other organizations seeking to support high-quality outcomes research can contribute to this international effort via the website.