Search

The COVID-19 outbreak caused saturations of hospitals, highlighting the importance of early patient triage to optimize resource prioritization. Herein, our objective was to test if high definition metabolomics, combined with ML, can improve prognostication and triage performance over standard clinical parameters using COVID infection as an example. Using high resolution mass spectrometry, we obtained metabolomics profiles of patients and combined them with clinical parameters to design machine learning (ML) algorithms predicting severity (herein determined as the need for mechanical ventilation during patient care). A total of 64 PCR-positive COVID patients at the Poitiers CHU were recruited. Clinical and metabolomics investigations were conducted 8 days after the onset of symptoms. We show that standard clinical parameters could predict severity with good performance (AUC of the ROC curve: 0.85), using SpO2, first respiratory rate, Horowitz quotient and age as the most important variables. However, the performance of the prediction was substantially improved by the use of metabolomics (AUC = 0.92). Our small-scale study demonstrates that metabolomics can improve the performance of diagnosis and prognosis algorithms, and thus be a key player in the future discovery of new biological signals. This technique is easily deployable in the clinic, and combined with machine learning, it can help design the mathematical models needed to advance towards personalized medicine.

Background: Elderly people in nursing homes are particularly vulnerable to COVID-19 due to their age, the presence of comorbidities, and community living. On March 14, 2020, at the beginning of the first epidemic wave of COVID-19 in France, a cluster was reported in a nursing home in the Nouvelle-Aquitaine region. We monitored the outbreak as well as the infection prevention and control (IPC) measures implemented., Methods: A confirmed case was defined as laboratory-confirmed COVID-19 in a resident or staff member present in the nursing home between March 7 and May 1, 2020; and a probable case as a person presenting an acute respiratory illness after contact with a confirmed case. Symptomatic inpatient residents and symptomatic staff members were systematically tested for SARS-CoV-2. In addition, two screening sessions were held on site., Results: We identified 109 cases (98 confirmed, 11 probable). The attack rate was 66% among residents and 45% among staff. Half of all cases were identified during the screening sessions. One-quarter of cases had minor symptoms or were asymptomatic. The case fatality rate among residents was 29%. IPC measures were rapidly implemented such as the quarantine of residents, the reinforcement of staff personal protective equipment, and home quarantine of staff testing positive, which were supplemented in April by systematic controls at the entrance of the nursing home and the creation of additional staff break rooms., Conclusions: This outbreak confirmed the considerable health impact of SARS-CoV-2 transmission in a nursing home. In addition to the implementation of IPC measures, the early detection of cases through the screening of residents and staff is essential to identify asymptomatic and pre-symptomatic cases and limit the spread of the virus.