Discriminating Acute Respiratory Distress Syndrome from other forms of respiratory failure via iterative machine learning.

Acute Respiratory Distress Syndrome (ARDS) is associated with high morbidity and mortality. Identification of ARDS enables lung protective strategies, quality improvement interventions, and clinical trial enrolment, but remains challenging particularly in the first 24 hours of mechanical ventilation. To address this we built an algorithm capable of discriminating ARDS from other similarly presenting disorders immediately following mechanical ventilation. Specifically, a clinical team examined medical records from 1263 ICU-admitted, mechanically ventilated patients, retrospectively assigning each patient a diagnosis of "ARDS" or "non-ARDS" (e.g., pulmonary edema). Exploiting data readily available in the clinical setting, including patient demographics, laboratory test results from before the initiation of mechanical ventilation, and features extracted by natural language processing of radiology reports, we applied an iterative pre-processing and machine learning framework. The resulting model successfully discriminated ARDS from non-ARDS causes of respiratory failure (AUC = 0.85) among patients meeting Berlin criteria for severe hypoxia. This analysis also highlighted novel patient variables that were informative for identifying ARDS in ICU settings.

Intensive Home Care for COVID-19 to Reduce Admissions.

Hospitalization for COVID-19 has placed a significant financial and logistical burden on hospitals and health care systems. Limitations on visitation and isolation precautions have made hospitalization more isolating for patients in the time of COVID-19. Increasing the provision of healthcare delivered at home has the potential to decrease healthcare costs by providing care at home which may be preferred for many patients. We describe a series of 39 patients who were treated with intravenous remdesivir at home in addition to oxygen, dexamethasone, and anticoagulants. These patients were at high risk for decompensation due to COVID-19 and met accepted criteria for admission-need for supplemental oxygen and intravenous remdesivir. All patients had home lab monitoring and frequent telehealth visits. Over the study period 13 (33%) of patients were admitted for worsening COVID-19 and 5 (13%) died. Twenty-six patients avoided admission, and none experienced a severe adverse effect from in-home treatment. The expanded use of telehealth services due to the COVID-19 pandemic has the potential to increase the frequency of patient monitoring by physicians and the provision of care and monitoring usually restricted to hospitalized patients.