New Subgroups of COVID-19 in Critically Ill Patients: Implications for Tailored Treatments

Objective Summary

The novel coronavirus disease 2019 (COVID-19) has heterogeneous clinical courses, indicating that there could be different subphenotypes in critically ill patients. Although previous research has identified these subphenotypes, the temporal pattern of multiple clinical characteristics has not been considered in cluster models.

We aimed to identify temporal subphenotypes in critically ill patients with COVID-19 using a novel sequence cluster analysis and associate them with clinically relevant outcomes.

Materials and methods

We analyzed 1036 critically ill patients with laboratory-confirmed SARS-COV-2 infection admitted to the Mount Sinai Health System in New York City. The agglomerative hierarchical clustering method with Levenshtein distance and Ward’s minimum variance link was used.

Results

We identified four subphenotypes. Subphenotype I (N = 233 [22.5%]) included patients with rapid breathing and rapid heartbeat, but less need for invasive interventions within the first 24 hours, along with a relatively good prognosis.

Subphenotype II (N = 418 [40.3%]) represented patients with the lowest degree of illness, relatively low mortality, and the highest probability of hospital discharge.

Subphenotype III (N = 259 [25.0%]) represented patients who experienced clinical deterioration during the first 24 hours of admission to the intensive care unit, leading to unfavorable outcomes.

Subphenotype IV (N = 126 [12.2%]) represented a trajectory of acute respiratory distress syndrome with a nearly universal need for mechanical ventilation.

Conclusion

We used sequence cluster analysis to identify clinical subphenotypes in critically ill COVID-19 patients who had distinct temporal patterns and different clinical outcomes. This study points towards the usefulness of including temporal information in subphenotyping approaches.

Comments

Mount Sinai researchers have outlined four new subgroups of COVID-19 that can be identified in patients within 24 hours of admission to the intensive care unit (ICU). The finding will help match patients to specific treatments, improving their overall care and outcomes.

The study, which identified subphenotypes or subgroups of COVID-19 based on biomarkers and treatments measured over time, was published in the Journal of the American Medical Informatics Association .

Mount Sinai researchers used sequence clustering analysis, a new data mining technique that can detect patterns of disease progression, to identify clinical subphenotypes in severely ill COVID-19 patients who had distinct temporal patterns during the first few weeks. 24 hours and different clinical results at 30 days. These temporal features are evident only when multiple features are considered over a period of time.

“While patients hospitalized with COVID-19 may have similar baseline characteristics, their clinical trajectories and health outcomes over time may be very different,” said corresponding author Girish N. Nadkarni, MD, Chief of the Division of Digital and Data-Driven Medicine, Co-Director of the Mount Sinai Center for Clinical Intelligence, Clinical Director of the Hasso Plattner Institute for Digital Health, and the Irene and Dr. Arthur M. Fishberg Professor of Medicine, Icahn School of Medicine at Mount Sinai. "Our study demonstrates the importance of revealing temporal disease similarities to identify reproducible and clinically relevant subphenotypes and suggests that further exploration of the temporal progressions of these clinical features is warranted."

The Mount Sinai team analyzed data from more than 1,000 critically ill patients with confirmed SARS-CoV-2 infection, the virus that causes COVID-19, who were admitted to the ICU. They transformed 10 biomarkers and 7 treatments during the first 24 hours of ICU admission into a sequence consisting of 16 non-overlapping interval windows, each 1.5 hours long and characterized as one of 10 distinct states.

The researchers identified four subphenotypes using biomarkers and treatment administrations:

Subphenotype I included patients with irregular vital signs but less need for invasive interventions within the first 24 hours. Patients in this group tended to have the highest chance of survival.
Subphenotype II represented patients with the lowest degree of illness, relatively low mortality, and the highest probability of hospital discharge. Patients in this group were younger, more likely to be black, less likely to need mechanical ventilation, and more likely to leave the hospital within 30 days.
Subphenotype III represented patients who experienced clinical deterioration during the first 24 hours leading to poor outcomes. Patients in this group tended to be older, were more likely to be male, had the highest incidence of shock on admission, and also had the greatest need for support with shock treatment and mechanical ventilation.
Subphenotype IV represented a trajectory of acute respiratory distress syndrome with a nearly universal need for mechanical ventilation. This group had a relatively higher proportion of Latino patients and a high prevalence of respiratory failure; more than half were mechanically ventilated at the time of admission.

"COVID-19 has been studied extensively, but we still have limited knowledge of effective clinical care for critically ill patients with COVID-19," said Wonsuk Oh, PhD, a postdoctoral fellow in the Nadkarni Laboratory at Icahn Mount Sinai and a member of the Institute. Hasso Plattner of Digital Health.

“State-of-the-art machine learning methods allow us to reveal new temporal subphenotypes from medical records with hourly resolution. These temporal subphenotypes provide new insights into patients’ underlying conditions and the course of disease progression during the intensive care unit stay and ultimately facilitate personalized clinical care of patients with an informed decision." .

This work was supported by National Institutes of Health (NIH) grants R01DK108803, U01HG007278, U01HG009610, U01DK116100, and K23DK124645.

New Subgroups of COVID-19 in Critically Ill Patients: Implications for Tailored Treatments

A new study identifies distinct subgroups of critically ill COVID-19 patients, providing insights that could help match patients to the most appropriate treatments based on their unique clinical characteristics and disease profiles.