Clusters of long COVID among patients hospitalized for COVID-19 in New York City.

BACKGROUND: Recent studies have demonstrated that individuals hospitalized due to COVID-19 can be affected by "long-COVID" symptoms for as long as one year after discharge. OBJECTIVES: Our study objective is to identify data-driven clusters of patients using a novel, unsupervised machine learning technique. METHODS: The study uses data from 437 patients hospitalized in New York City between March 3rd and May 15th of 2020. The data used was abstracted from medical records and collected from a follow-up survey for up to one-year post-hospitalization. Hospitalization data included demographics, comorbidities, and in-hospital complications. The survey collected long-COVID symptoms, and information on general health, social isolation, and loneliness. To perform the analysis, we created a graph by projecting the data onto eight principal components (PCs) and running the K-nearest neighbors algorithm. We then used Louvain's algorithm to partition this graph into non-overlapping clusters. RESULTS: The cluster analysis produced four clusters with distinct health and social connectivity patterns. The first cluster (n = 141) consisted of patients with both long-COVID neurological symptoms (74%) and social isolation/loneliness. The second cluster (n = 137) consisted of healthy patients who were also more socially connected and not lonely. The third cluster (n = 96) contained patients with neurological symptoms who were socially connected but lonely, and the fourth cluster (n = 63) consisted entirely of patients who had traumatic COVID hospitalization, were intubated, suffered symptoms, but were socially connected and experienced recovery. CONCLUSION: The cluster analysis identified social isolation and loneliness as important features associated with long-COVID symptoms and recovery after hospitalization. It also confirms that social isolation and loneliness, though connected, are not necessarily the same. Physicians need to be aware of how social characteristics relate to long-COVID and patient's ability to cope with the resulting symptoms.

Resident pre-dictation of ED case delay signoff of those reports, but overall, residents improve report turnaround time.

PURPOSE: In academic radiology departments, attendings and resident are increasingly working together overnight for Emergency Department (ED) radiology coverage. The purpose of this study was to quantify reporting turnaround time for overnight cases read by residents and for overnight shifts with residents on duty. METHODS: A retrospective study was performed at a hospital system where one overnight attending covers two hospitals with a 2nd/3rd year overnight resident, and a second overnight attending covers two other hospitals 80% of the time independently and 20% of the time with a fourth-year resident. In the first analysis, the median difference in turnaround time, from the time when the case was completed by the technologist to the time the attending finalized it, between cases read independently by attendings and cases pre-dictated by residents was calculated. In the second analysis, the median difference in turnaround time for all cases performed at the second two hospitals was compared on nights when an attending was on duty alone versus nights when a fourth-year resident was also on duty, regardless of if the resident had pre-dictated the case. RESULTS: For computed tomography (CT), radiographs (XR), and ultrasound (US), there was a significant delay in turnaround time for cases pre-dictated by residents compared to cases read independently by attendings, ranging between 11 and 49 min depending on resident seniority and modality (p ≤ 0.001). For all cases on nights with a 4th year resident working, overall median report turnaround time decreased by 7 min (p < 0.001). CONCLUSION: Resident pre-dictation causes delay in the finalization of individual CT, US, and XR reports; however, overall, working with residents results in a significant decrease in report turnaround time supporting the belief that overnight resident education does not delay patient care.