Application of machine learning approach in emergency department to support clinical decision making for SARS-CoV-2 infected patients.

To support physicians in clinical decision process on patients affected by Coronavirus Disease 2019 (COVID-19) in areas with a low vaccination rate, we devised and evaluated the performances of several machine learning (ML) classifiers fed with readily available clinical and laboratory data. Our observational retrospective study collected data from a cohort of 779 COVID-19 patients presenting to three hospitals of the Lazio-Abruzzo area (Italy). Based on a different selection of clinical and respiratory (ROX index and PaO2/FiO2 ratio) variables, we devised an AI-driven tool to predict safe discharge from ED, disease severity and mortality during hospitalization. To predict safe discharge our best classifier is an RF integrated with ROX index that reached AUC of 0.96. To predict disease severity the best classifier was an RF integrated with ROX index that reached an AUC of 0.91. For mortality prediction the best classifier was an RF integrated with ROX index, that reached an AUC of 0.91. The results obtained thanks to our algorithms are consistent with the scientific literature an accomplish significant performances to forecast safe discharge from ED and severe clinical course of COVID-19.

Fall of viral and bacterial pneumonia hospitalizations following COVID-19 pandemic mitigation strategies: a central Italian Region retrospective study.

Community-Acquired Pneumonia (CAP) represents one of the first causes of hospitalization and death in the elderly all over the world and weighs heavily on public health system. Since the beginning of the COVID-19 (CoronaVirus Disease-19) pandemic, everybody's behavior was forced to change, as the result of a global lockdown strategy and the obligation of using personal protection equipment (PPE). We aimed to evaluate how the mitigation strategies adopted to fight SARS-CoV-2 (Severe Acute Respiratory Coronavirus Syndrome 2) infection have influenced hospitalizations due to CAP in two different Local Health Boards (LHBs) of central Italy. We considered two main periods of observation: before and after the national start of lockdown, in two Abruzzo's LHBs. We analyzed 19,558 hospital discharge records of bacterial and viral CAP. Excluding SARS-CoV2 infection, a significant decrease in CAP hospitalizations was observed. Through the analysis of Diagnosis Related Group (DRG) values, we highlighted a significant saving of founds for the Regional Health Service. The enactment of social distancing measures to contain COVID-19 spread, brought down admissions for bacterial and viral pneumonia. Our study emphasizes that costs for hospitalizations due to CAP could be drastically reduced by mask wearing and social distancing.

Alteration of Inflammatory Parameters and Psychological Post-Traumatic Syndrome in Long-COVID Patients.

The aim of our study is to evaluate the correlation between the psychological status of patients recovered from SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2) infection (long-COVID patients) and their inflammatory status. Three months after hospital discharge, ninety-three patients were recruited and categorized into two distinct populations: control and long-COVID (COrona VIrus Disease) group. Patients belonging to the control group presented with an entering diagnosis of cardiovascular, metabolic, or respiratory disease and a negative history of SARS-CoV-2 infection, whereas the long-COVID population presented with a severe SARS-CoV-2 infection treated in the sub-intensive Care Unit. Psychological evaluation was performed through the administration of the Symptom Checklist-90 (SCL90) and LDH (Lactate dehydrogenase), ferritin, CRPhs (C-high sensitivity Reactive Protein), NLR (Neutrophil-to-lymphocyte ratio), PLR (Platelet-to-lymphocyte ratio), and SII (systemic immune-inflammation index) were investigated. We highlighted that beyond the first three months after contagion, patients recovered from SARS-CoV-2 infection are characterized by the persistence of a systemic inflammatory state and are at high risk for developing somatization, depression, anxiety, and sleep disturbances. Interestingly, ferritin value was strongly correlated with sleep disorders (p < 0.05). Our study emphasizes how COVID-19 strategies for risk stratification, prognosis, and therapy management of patients should be implemented with a psychological follow-up.

PaO2/FiO2 ratio forecasts COVID-19 patients' outcome regardless of age: a cross-sectional, monocentric study.

We studied the predictive value of the PaO2/FiO2 ratio for classifying COVID-19-positive patients who will develop severe clinical outcomes. One hundred fifty patients were recruited and categorized into two distinct populations ("A" and "B"), according to the indications given by the World Health Organization. Patients belonging the population "A" presented with mild disease not requiring oxygen support, whereas population "B" presented with a severe disease needing oxygen support. The AUC curve of PaO2/FiO2 in the discovery cohort was 0.838 (95% CI 0.771-0.908). The optimal cut-off value for distinguishing population "A" from the "B" one, calculated by Youden's index, with sensitivity of 71.79% and specificity 85.25%, LR+4.866, LR-0.339, was < 274 mmHg. The AUC in the validation cohort of 170 patients overlapped the previous one, i.e., 0.826 (95% CI 0.760-0.891). PaO2/FiO2 ratio < 274 mmHg was a good predictive index test to forecast the development of a severe respiratory failure in SARS-CoV-2-infected patients. Moreover, our work highlights that PaO2/FiO2 ratio, compared to inflammatory scores (hs-CRP, NLR, PLR and LDH) indicated to be useful in clinical managements, results to be the most reliable parameter to identify patients who require closer respiratory monitoring and more aggressive supportive therapies. Clinical trial registration: Prognostic Score in COVID-19, prot. NCT04780373 https://clinicaltrials.gov/ct2/show/NCT04780373 (retrospectively registered).

Laboratory parameters related to severe disease and death in SARS-CoV-2 pneumonia: Retrospective analysis.

The clinical evolution of coronavirus disease 2019 (COVID-19) is highly variable and hospitalized patients can rapidly develop conditions requiring oxygen support, intensive care unit (ICU) or high dependency unit (HDU) care. Early identification of high-risk patients is mandatory. We retrospectively collected the medical history, symptoms, radiological, and laboratory findings of COVID-19 patients hospitalized between February and April 2020. Laboratory data were collected at the first, last, and middle times of hospitalization. We used arterial oxygen partial pressure and fractional inspired oxygen ratio (P/F) to evaluate respiratory status. Outcomes considered were death and ICU/HDU admission. We used the χ2 or Fisher's exact test to examine differences between categorical variables. Continuous variables were analyzed using the Wilcoxon matched pairs signed-ranks test and Mann-Whitney test sample test. Of 71 patients admitted, 92% had interstitial pneumonia, and 17% an unfavorable outcome. Negative predictors were age, cerebrovascular disease, obesity, and chronic obstructive pulmonary disease. Baseline P/F was strongly associated with all outcomes. Markers linked to immunological dysregulation like elevated neutrophil-to-lymphocyte ratio exhibited prognostic significance over time. A validated prognostic score comprehensive of all these conditions for early staging and management of COVID-19 patients is urgently needed. Further studies are desirable to evaluate whether laboratory tests can target early treatment in high-risk patients.

Three Cases of COVID-19 Pneumonia in Female Patients in Italy Who Had Pulmonary Fibrosis on Follow-Up Lung Computed Tomography Imaging.

BACKGROUND Since December 2019, an outbreak caused by a novel coronavirus infection (severe acute respiratory syndrome coronavirus 2, SARS-CoV-2) occurred in Wuhan, China, and it rapidly spread all over the world. The clinical spectrum of coronavirus disease 2019 (COVID-19) is wide, with acute respiratory distress syndrome (ARDS) occurring in 15% of patients affected, requiring high oxygen support. Currently, there is no clearly effective antiviral therapy. Steroids and immunomodulators are under investigation for potential activity. Little is known about middle and long-term sequelae on respiratory function. According to some authors, COVID-19 could cause pulmonary fibrosis. We report 3 cases of pulmonary fibrosis detected on follow-up computed tomography (CT) imaging in 3 female patients who recovered from COVID-19 pneumonia in Italy (L'Aquila, Abruzzo). CASE REPORT All patients were female and had no significant previous respiratory disease or history of smoke exposure, and none had received high-flow oxygen support during treatment of the disease. In all cases, late onset of mild dyspnea, slow and incomplete respiratory recovery, and early evidence of fibrous signs on chest CT scan were characteristic of the clinical course. CONCLUSIONS This report focuses on a possible scenario of long-term lung damage in COVID-19 pneumonia survivors. Limitations are lack of long-term follow-up and functional data in the very early phase. It is advantageous that all COVID-19 pneumonia patients undergo serial chest CT and spirometry long-term follow-up for at least 1 year to assess residual damage. This is particularly relevant in those with slow respiratory recovery and long hospitalization.

Follow-up and Management of Kidney Transplant Recipients During the COVID-19 Lockdown: The Experience of an Italian Transplant Center, Including Two Cases of COVID-19 Pneumonia.

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a new infectious disease that emerged in China in late 2019 and is now spreading around the world. Social distancing measures were needed to reduce transmission, and lockdown included restricted access to health care facilities. The impact of COVID-19 on transplant recipients is unknown, but considering their immunosuppression status and associated comorbidities, they should be considered a high-risk population. METHODS: A kidney transplant center in Central Italy implemented a strategy to maintain follow-up of kidney transplant recipients by phone and e-mail during lockdown. Telephone interviews were used to administer a clinical questionnaire to patients, and e-mail was used to receive the results of diagnostic tests conducted in outpatient settings. RESULTS: From March 17 to April 23, 2020, a total of 143 kidney transplant recipients were contacted. Twenty-eight patients needed in-hospital consultation for problems unrelated to COVID-19, 3 of whom needed hospitalization. Eleven patients were managed at home for mild urinary or respiratory diseases, and 1 was referred to the hematologist. We identified 2 suspected cases of COVID-19 infection, and the patients were referred to hospital care. Immunosuppressive therapy was modulated, and intravenous corticosteroids and potentially effective antiviral therapy were administered with a favorable outcome. CONCLUSIONS: In the context of a lockdown, such as that occurring in response to COVID-19, we suggest implementing remote surveillance programs in kidney transplant recipients with the help of any available technology and offering medical consulting and logistic support as needed.