Endpoint Health Presents Published Results from a Retrospective Study of Adult ARDS Patients, Identifying an Innovative Approach to Predicting Clinical Outcomes

Novel, proprietary model from Endpoint Health could help shape future clinical trial enrollment strategies and streamline the development of targeted therapies, with the potential for improved treatment for adult ARDS patients

Palo Alto, Calif. – January 6, 2022 – Endpoint Health, Inc., a precision-first therapeutics company dedicated to addressing urgent needs in immune-driven critical and chronic illnesses, today announced that researchers have identified two new, clinically distinct subgroups (subphenotypes) of adults with acute respiratory distress syndrome (ARDS). The study, published in BMJ Open, marks the first time subphenotyping for ARDS was accomplished based on just nine (9), widely available clinical variables that are collected in the routine care of all ARDS patients.

The identification of subphenotypes based on commonly identifiable data among patients with ARDS has the potential to streamline clinical trials and aid in the future development of targeted therapies for this syndrome.1 The results come from a retrospective analysis of six randomized controlled studies with nearly 4,800 patients, the largest patient cohort used to date to identify distinct subphenotypes in ARDS.1

ARDS is a heterogeneous condition. Clinical differences among patient populations are associated with varying disease progression and health outcomes. This heterogeneity often results in a wide variation of patient response to treatments and interventions.1 Identifying subphenotypes of patients with similar clinical, physiologic, or biomarker traits could lead to better risk stratification for patients suffering from ARDS and diseases that can lead to ARDS like sepsis. Ultimately, this approach to subphenotypic clustering could serve as a basis for development of future targeted therapeutics. The clinical utility of subphenotypic assessment in ARDS would require validation in a prospective clinical study.

“In current clinical practice, risk stratification for patients with ARDS solely depends on the PaO2/FiO2 clinical measure. The application of this single assessment often results in bedside challenges in evaluating optimal treatment options for patients. It can also lead to challenges in assessing the impact of interventions in clinical trials,” said study lead author Abhijit Duggal, MD, Department of Critical Care Medicine, Respiratory Institute at the Cleveland Clinic in Cleveland, OH. “While our findings warrant further study before they can be generalized, this analysis demonstrates that it may be possible to enhance risk stratification strategies by using a few additional clinical variables that are collected during routine ARDS care.”

The retrospective analysis published in BMJ Open identified two ARDS subphenotypes (A and B) that are differentiated by the review of nine routinely collected clinical variables.1 Patients in subphenotype B had consistently higher mortality, lower numbers of ventilator-free days at day 28, and longer duration of ventilation compared to subphenotype A patients.1 They also presented increased levels of pro-inflammatory markers.1

This post-hoc analysis had some limitations. The developed models were exclusively based on patients enrolled in other clinical trials. Due to strict inclusion and exclusion criteria in these trials, the generalizability of these results needs to be evaluated in unselected ARDS populations. Additionally, the biomarker analysis was limited to those patients in which the data was publicly available. Future research should analyze previous trials to identify possible differential treatment responses for the subphenotypes of ARDS patients identified in this study.

“Previous studies in ARDS have relied on models with up to 40 predictor variables, including many that are not commonly available, which makes their translation into clinical practice difficult,” said study co-author Diego Rey, PhD, Chief Scientific Officer at Endpoint Health. “It is encouraging that in this study we narrowed ARDS subphenotyping based on nine commonly available clinical variables, using a novel proprietary clustering approach from Endpoint Health.”

About the Study

The retrospective analysis drew on data from six randomized clinical trials in adult patients with ARDS (five U.S. and one international study). These studies were previous clinical trials in ARDS, which assessed different interventions, such as mechanical ventilator settings, fluid management strategy and enteral feeding strategy. Altogether, the retrospective analysis included data from a total of 4,773 participants, representing the largest data cohort of patients used to date to identify subphenotypes for ARDS.1

Using a novel proprietary clustering model from Endpoint Health, the study tested 10 different models, with varying combinations of proposed clinical variables.1 The goal was to determine the optimal number of clusters of patients with distinct clinical outcomes, while using the most commonly available clinical variables closest to time of randomization, and minimizing the overall number of variables.1 The primary endpoints of the randomized clinical trials that were analyzed were 60-day mortality for the U.S. studies, and 28-day mortality for the international study.1 Secondary outcomes included 90-day mortality, number of ventilator free days at day 28, and duration of mechanical ventilation in survivors within the first 28 days post enrollment.1

The final model included nine clinical variables that are routinely collected during ARDS care: Heart rate, mean arterial pressure, respiratory rate, bilirubin, bicarbonate, creatinine, partial pressure of oxygen (PaO2), arterial pH, and fraction of inspired oxygen (FiO2). This model identified two distinct subphenotypes in adult ARDS patients. One subphenotype has increased levels of pro-inflammatory markers, consistently higher mortality, lower number of ventilator-free days at day 28, and longer duration of ventilation when compared to the other subphenotype.1

The study, Duggal A, Kast R, Van Ark E, et al. Identification of acute respiratory distress syndrome subphenotypes de novo using routine clinical data: a retrospective analysis of ARDS clinical trials, is available at BMJ Open 2022;12:e053297. doi:10.1136/bmjopen-2021-053297.

The scientific information discussed in this release related to our pipeline of therapies and therapy-guiding tests is preliminary and investigative. Such product and diagnostic candidates are not approved by the U.S. Food and Drug Administration, and no conclusions can or should be drawn regarding the safety or effectiveness of the product or diagnostic candidates.

About ARDS

Acute respiratory distress syndrome (ARDS) is a life-threatening condition, which leads to inflammation and buildup of fluid in the lungs. These clinical manifestations prevent the lungs from adequately providing enough oxygen into the blood. ARDS can be caused by direct injuries, such as pneumonia, inhalation of harmful fumes and chest injuries, or indirect injuries like sepsis (severe and widespread bacterial infection in the body) and acute pancreatitis (inflammation of the pancreas).2 ARDS impacts an estimated 150,000 Americans each year. Despite intensive therapy, approximately 40% of people with ARDS die from lung failure.2

About Endpoint Health

Endpoint Health is a precision-first therapeutics company dedicated to addressing urgent needs in immune-driven critical and chronic illnesses by building a pipeline of therapies designed to personalize treatment to each patient’s biology. We combine therapeutics, therapy guiding tests, and AI to develop targeted therapies for patients with inflammatory illnesses, such as acute respiratory distress syndrome (ARDS), sepsis, and rheumatoid arthritis. Our vision is a world in which all patients have effective, personalized treatment because therapies are targeted to the right patient at the right time. For more information, visit

Follow us on Social Media: LinkedIn, Twitter

Christian Pflaumer
Ruder Finn
[email protected]

[1] Duggal A, Kast R, Van Ark E, et al. Identification of Acute Respiratory Distress Syndrome subphenotypes de novo using routine clinical data: a retrospective analysis of ARDS clinical trials. BMJ Open 2022;12:e053297. doi:10.1136/bmjopen-2021-053297
[2] American Thoracic Society. What is Acute Respiratory Distress Syndrome? Updated April 2020. Available at Last accessed December 2021.