AI COVID-19 Survival Calculator Provides Patient's Risk Score, Expected Time to Death and Survival Probability

A new artificial intelligence (AI) tool can estimate the expected time-to-death of hospitalized COVID-19 patients.

Deep Longevity Limited (Hong Kong) has announced the publication of its COVID Risk Calculator. The study features a collection of over 5,000 COVID-positive patients admitted to 11 public New York hospitals. Blood tests obtained during the admission were analyzed by a deep-learning neural network - BloodAge, to quantify the intensity of the aging process. The network takes in a typical blood panel and returns their biological age, which can be higher or lower than their chronological age.


Two survival models (Cox proportional hazards, logistic regression) showed BloodAge predictions to have more impact on a patient's survival than chronological age. In terms of expected time-to-death (TTD), each extra BloodAge year was equivalent to a one-day reduction in TTD. One of the survival models was transformed into a TTD calculator. It requires a physician to input 15 variables, including symptoms and comorbidities, to return a patient's COVID Risk Score, expected TTD, and survival probability curve.

Despite the global effort to fight the pandemic, it is still ongoing. Hospitals all over the world are stretched beyond their capacity with the emergence of new strains and the premature relaxation anti-COVID measures'. In such circumstances, risk-stratification of the admitted patients remains an essential, albeit grim, necessity.

"Age was recognized as the main risk factor affecting patients' survival at the very onset of the pandemic. The elderly have been reported to have the highest mortality rate, as well as suffer from more complications in numerous studies. In the meantime, most such studies ignore that there is no universal pace of aging," said Jamie Gibson, Chief Executive Officer of the Company. "Some people age faster than others. This notion is obvious to medical professionals, who have gained the ability to tell overagers and underagers apart throughout the years of practice. However, the official records lack any information on the true, biological age of COVID patients. The research project by Deep Longevity in collaboration with Lincoln Medical Center highlights the importance of quantifying aging rate for accurate survival analysis."

Related Links:
Deep Longevity Limited