Publications of Michel Moutschen
Bookmark and Share    
Full Text
See detailAge-dependent impact of the major common genetic risk factor for COVID-19 on severity and mortality.
Nakanishi, Tomoko; Pigazzini, Sara; Degenhardt, Frauke et al

in Journal of Clinical Investigation (2021), Online ahead of print.

BACKGROUND: There is considerable variability in COVID-19 outcomes amongst younger adults-and some of this variation may be due to genetic predisposition. We characterized the clinical implications of the ... [more ▼]

BACKGROUND: There is considerable variability in COVID-19 outcomes amongst younger adults-and some of this variation may be due to genetic predisposition. We characterized the clinical implications of the major genetic risk factor for COVID-19 severity, and its age-dependent effect, using individual-level data in a large international multi-centre consortium. METHOD: The major common COVID-19 genetic risk factor is a chromosome 3 locus, tagged by the marker rs10490770. We combined individual level data for 13,424 COVID-19 positive patients (N=6,689 hospitalized) from 17 cohorts in nine countries to assess the association of this genetic marker with mortality, COVID-19-related complications and laboratory values. We next examined if the magnitude of these associations varied by age and were independent from known clinical COVID-19 risk factors. FINDINGS: We found that rs10490770 risk allele carriers experienced an increased risk of all-cause mortality (hazard ratio [HR] 1·4, 95% confidence interval [CI] 1·2-1·6) and COVID-19 related mortality (HR 1·5, 95%CI 1·3-1·8). Risk allele carriers had increased odds of several COVID-19 complications: severe respiratory failure (odds ratio [OR] 2·0, 95%CI 1·6-2·6), venous thromboembolism (OR 1·7, 95%CI 1·2-2·4), and hepatic injury (OR 1·6, 95%CI 1·2-2·0). Risk allele carriers ≤ 60 years had higher odds of death or severe respiratory failure (OR 2·6, 95%CI 1·8-3·9) compared to those > 60 years OR 1·5 (95%CI 1·3-1·9, interaction p-value=0·04). Amongst individuals ≤ 60 years who died or experienced severe respiratory COVID-19 outcome, we found that 31·8% (95%CI 27·6-36·2) were risk variant carriers, compared to 13·9% (95%CI 12·6-15·2%) of those not experiencing these outcomes. Prediction of death or severe respiratory failure among those ≤ 60 years improved when including the risk allele (AUC 0·82 vs 0·84, p=0·016) and the prediction ability of rs10490770 risk allele was similar to, or better than, most established clinical risk factors. INTERPRETATION: The major common COVID-19 risk locus on chromosome 3 is associated with increased risks of morbidity and mortality-and these are more pronounced amongst individuals ≤ 60 years. The effect on COVID-19 severity was similar to, or larger than most established risk factors, suggesting potential implications for clinical risk management. FUNDING: Funding was obtained by each of the participating cohorts individually. [less ▲]

Detailed reference viewed: 259 (12 ULiège)
Full Text
See detailImpact of the COVID-19 pandemic situation on HIV care in Liège, Belgium
El Moussaoui, Majdouline ULiege; Lambert, Nicolas ULiege; MAES, Nathalie ULiege et al

in HIV Research & Clinical Practice (2021)

Background: The COVID-19 pandemic and associated containment measures dramatically affected the health care systems including the screening of human immunodeficiency virus and the management people living ... [more ▼]

Background: The COVID-19 pandemic and associated containment measures dramatically affected the health care systems including the screening of human immunodeficiency virus and the management people living with HIV around the world by making the access to preventive care services and specific medical monitoring more difficult. Objective: To study the impact of the COVID-19 pandemic on the holistic care of people living with HIV in Liège (Belgium). Methods: In this retrospective observational study conducted in Liège University Hospital, we compared the out-patient follow-up of HIV-infected individuals as well as the number of new HIV diagnoses between 2019 and 2020 and between the different waves of the COVID-19 pandemic in 2020. Results: In 2020, when compared to 2019, we observed a significant decrease in the number of new HIV diagnoses, especially during the first wave of the pandemic, and in the number of consultations undertaken by sexual health services, psychologists and specialists in infectious diseases at our HIV clinic. We also observed a decrease in the number of viral load assays and blood CD4 + T-cells count analyses performed, although we found less patients with HIV plasma viral load above 400 copies per mL in 2020. Finally, we noted a significant reduction in terms of screening of our HIV-infected patients for hepatitis C, syphilis, colorectal and anal cancers and hypercholesterolemia. Conclusions: Our experience exhibits the deleterious impact of the COVID-19 pandemic on the HIV care and the need to implement new strategies to guarantee its continuum. [less ▲]

Detailed reference viewed: 147 (86 ULiège)
Full Text
See detailComparison of clinical and biological characteristics of HIV infected patients presenting Cryptococcus neorformans versus C. curvatus /C. laurentii meningitis
Zono, Bive ULiege; MOUTSCHEN, Michel ULiege; Situakibanza, Hippolyte et al

Poster (2021, June 12)

Clinical presentation of Cn meningitis is certainly more severe than that of Cc/Cl meningitis, but Cc/Cl infection should be considered in the management of HIVIP with meningeal syndrome because of the ... [more ▼]

Clinical presentation of Cn meningitis is certainly more severe than that of Cc/Cl meningitis, but Cc/Cl infection should be considered in the management of HIVIP with meningeal syndrome because of the diagnostic difficulty and the high MICs of antifungal agents required for the treatment of meningitis due to these cryptococcal species. [less ▲]

Detailed reference viewed: 32 (5 ULiège)
Full Text
See detailLung and liver sarcoidosis‐like reaction induced by tocilizumab
Lambert, Nicolas ULiege; Hansen, Isabelle ULiege; El Moussaoui, Majdouline ULiege et al

in British Journal of Clinical Pharmacology (2021)

A drug‐induced sarcoidosis‐like reaction is a systemic granulomatous reaction indistinguishable from sarcoidosis and occurring in temporal relationship with a drug initiation. In this article, we report a ... [more ▼]

A drug‐induced sarcoidosis‐like reaction is a systemic granulomatous reaction indistinguishable from sarcoidosis and occurring in temporal relationship with a drug initiation. In this article, we report a patient who developed lung and liver granulomatous lesions following tocilizumab initiation for a giant cell arteritis. Infectious, toxic, neoplastic and inflammatory differential diagnoses were ruled out and lesions regressed after treatment cessation, leading to the diagnosis of tocilizumab induced sarcoidosis‐like reaction. We review the six cases reported so far and emphasize the value of a prompt diagnosis. Finally, we discuss the potential pathophysiological mechanisms underlying this rare reaction, which could help to better understand the pathophysiology of sarcoidosis. [less ▲]

Detailed reference viewed: 68 (20 ULiège)
Full Text
See detailImmunosuppression Withdrawal After Liver Transplantation for Common Variable Immunodeficiency.
Detry, Olivier ULiege; MEURISSE, Nicolas ULiege; Jouret, François ULiege et al

in Liver Transplantation (2021), 27(3), 456-458

Detailed reference viewed: 38 (6 ULiège)
Full Text
See detailAsthma and COPD Are Not Risk Factors for ICU Stay and Death in Case of SARS-CoV2 Infection
CALMES, Doriane ULiege; Graff, Sophie ULiege; MAES, Nathalie ULiege et al

in Journal of Allergy and Clinical Immunology: In Practice (2021), 9(1), 160-169

BACKGROUND: Asthmatics and patients with chronic obstructive pulmonary disease (COPD) have more severe outcomes with viral infections than people without obstructive disease. OBJECTIVE: To evaluate if ... [more ▼]

BACKGROUND: Asthmatics and patients with chronic obstructive pulmonary disease (COPD) have more severe outcomes with viral infections than people without obstructive disease. OBJECTIVE: To evaluate if obstructive diseases are risk factors for intensive care unit (ICU) stay and death due to coronavirus disease 2019 (COVID19). METHODS: We collected data from the electronic medical record from 596 adult patients hospitalized in University Hospital of Liege between March 18 and April 17, 2020, for severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) infection. We classified patients into 3 groups according to the underlying respiratory disease, present before the COVID19 pandemic. RESULTS: Among patients requiring hospitalization for COVID19, asthma and COPD accounted for 9.6% and 7.7%, respectively. The proportions of asthmatics, patients with COPD, and patients without obstructive airway disease hospitalized in the ICU were 17.5%, 19.6%, and 14%, respectively. One-third of patients with COPD died during hospitalization, whereas only 7.0% of asthmatics and 13.6% of patients without airway obstruction died due to SARS-CoV2. The multivariate analysis showed that asthma, COPD, inhaled corticosteroid treatment, and oral corticosteroid treatment were not independent risk factors for ICU admission or death. Male gender (odds ratio [OR]: 1.9; 95% confidence interval [CI]: 1.1-3.2) and obesity (OR: 8.5; 95% CI: 5.1-14.1) were predictors of ICU admission, whereas male gender (OR 1.9; 95% CI: 1.1-3.2), older age (OR: 1.9; 95% CI: 1.6-2.3), cardiopathy (OR: 1.8; 95% CI: 1.1-3.1), and immunosuppressive diseases (OR: 3.6; 95% CI: 1.5-8.4) were independent predictors of death. CONCLUSION: Asthma and COPD are not risk factors for ICU admission and death related to SARS-CoV2 infection. [less ▲]

Detailed reference viewed: 158 (32 ULiège)
Full Text
See detailCan predicting COVID-19 mortality in a European cohort using only demographic and comorbidity data surpass age-based prediction: An externally validated study.
Chatterjee, Avishek; Wu, Guangyao; Primakov, Sergey et al

in PLoS ONE (2021), 16(4), 0249920

OBJECTIVE: To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a ... [more ▼]

OBJECTIVE: To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a precursor to implementing smart lockdowns and vaccine distribution strategies. METHODS: The training cohort comprised 2337 COVID-19 inpatients from nine hospitals in The Netherlands. The clinical outcome was death within 21 days of being discharged. The features were derived from electronic health records collected during admission. Three feature selection methods were used: LASSO, univariate using a novel metric, and pairwise (age being half of each pair). 478 patients from Belgium were used to test the model. All modeling attempts were compared against an age-only model. RESULTS: In the training cohort, the mortality group's median age was 77 years (interquartile range = 70-83), higher than the non-mortality group (median = 65, IQR = 55-75). The incidence of former/active smokers, male gender, hypertension, diabetes, dementia, cancer, chronic obstructive pulmonary disease, chronic cardiac disease, chronic neurological disease, and chronic kidney disease was higher in the mortality group. All stated differences were statistically significant after Bonferroni correction. LASSO selected eight features, novel univariate chose five, and pairwise chose none. No model was able to surpass an age-only model in the external validation set, where age had an AUC of 0.85 and a balanced accuracy of 0.77. CONCLUSION: When applied to an external validation set, we found that an age-only mortality model outperformed all modeling attempts (curated on www.covid19risk.ai) using three feature selection methods on 22 demographic and comorbid features. [less ▲]

Detailed reference viewed: 38 (4 ULiège)
Full Text
See detailCould KL-6 levels in COVID-19 help to predict lung disease?
Frix, Anne-Noëlle ULiege; Schoneveld, Lauranne ULiege; LADANG, Aurélie ULiege et al

in Respiratory Research (2020), 21(309),

BACKGROUND: Coronavirus disease COVID-19 has become a public health emergency of international concern. Together with the quest for an effective treatment, the question of the post-infectious evolution of ... [more ▼]

BACKGROUND: Coronavirus disease COVID-19 has become a public health emergency of international concern. Together with the quest for an effective treatment, the question of the post-infectious evolution of affected patients in healing process remains uncertain. Krebs von den Lungen 6 (KL-6) is a high molecular weight mucin-like glycoprotein produced by type II pneumocytes and bronchial epithelial cells. Its production is raised during epithelial lesions and cellular regeneration. In COVID-19 infection, KL-6 serum levels could therefore be of interest for diagnosis, prognosis and therapeutic response evaluation. MATERIALS AND METHODS: Our study retrospectively compared KL-6 levels between a cohort of 83 COVID-19 infected patients and two other groups: healthy subjects (n = 70) on one hand, and a heterogenous group of patients suffering from interstitial lung diseases (n = 31; composed of 16 IPF, 4 sarcoidosis, 11 others) on the other hand. Demographical, clinical and laboratory indexes were collected. Our study aims to compare KL-6 levels between a COVID-19 population and healthy subjects or patients suffering from interstitial lung diseases (ILDs). Ultimately, we ought to determine whether KL-6 could be a marker of disease severity and bad prognosis. RESULTS: Our results showed that serum KL-6 levels in COVID-19 patients were increased compared to healthy subjects, but to a lesser extent than in patients suffering from ILD. Increased levels of KL-6 in COVID-19 patients were associated with a more severe lung disease. DISCUSSION AND CONCLUSION: Our results suggest that KL-6 could be a good biomarker to assess ILD severity in COVID-19 infection. Concerning the therapeutic response prediction, more studies are necessary. [less ▲]

Detailed reference viewed: 73 (20 ULiège)
Full Text
See detailObstacles à la guérison de l'infection par le VIH. Partie 1 : les réservoirs latents
Fombellida-Lopez, Céline ULiege; Chaslain, A.; SUSIN, Fabrice ULiege et al

in Revue Médicale de Liège (2020), 75(9), 573-577

The human immunodeficiency virus (HIV), responsible for acquired immunodeficiency syndrome or AIDS, is a major public health problem. In Belgium, 2 to 3 new cases are diagnosed every day. Since the advent ... [more ▼]

The human immunodeficiency virus (HIV), responsible for acquired immunodeficiency syndrome or AIDS, is a major public health problem. In Belgium, 2 to 3 new cases are diagnosed every day. Since the advent of combined antiretroviral treatments in 1996, the life expectancy and quality of life of infected patients have greatly improved. However, to date there is no cure for HIV. Individuals infected with HIV must remain on antiretroviral treatment for life. One of the reasons for the difficulty in finding a cure for HIV is that the virus can remain in a latent form, i.e. dormant, in some of the cells it infects. These latent reservoirs are not recognized by the immune system and can reactivate and thus restart the infection if the patient stops the treatment. These latent reservoirs are therefore a major obstacle to cure HIV and a great deal of research is being conducted by the scientific community to find an eradication strategy. In this article, we will present the different characteristics of these latent reservoirs and the different strategies put in place to identify and eliminate them. [less ▲]

Detailed reference viewed: 45 (13 ULiège)
Full Text
See detailObstacles à la guérison de l'infection par le VIH. Partie 2 : la réplication continue malgré le traitement
Chaslain, A.; Fombellida-Lopez, Céline ULiege; SUSIN, Fabrice ULiege et al

in Revue Médicale de Liège (2020), 75(9), 582-587

The antiretroviral therapy (ART) has proven its effectiveness in improving the life expectancy of people infected with human immunodeficiency virus (HIV). Based on the inhibition of HIV replication, ART ... [more ▼]

The antiretroviral therapy (ART) has proven its effectiveness in improving the life expectancy of people infected with human immunodeficiency virus (HIV). Based on the inhibition of HIV replication, ART ensures the reduction of plasma viral load to undetectable levels on long-term. Unfortunately, once ART is interrupted, the viral load rises up. Consequently, the therapy remains not curative. The reasons for this failure lie in the presence of latent reservoirs of the virus and/or the presence of ongoing replication, responsible for the persistence of the virus. This ongoing replication despite ongoing therapy has been demonstrated in sanctuary sites where the penetration of antiretroviral drugs is suboptimal. Moreover, some treatment intensification studies, mostly through addition of an integrase inhibitor, transiently resulted in increases in HIV replication by-products, highlighting that such strategies could reduce ongoing replication. Although the debate is still open, confirming the presence of this ongoing replication and finding strategies to eliminate it would be part of the key to a cure for HIV. [less ▲]

Detailed reference viewed: 22 (6 ULiège)
Full Text
See detailLe point sur les stratégies médicamenteuses contre la COVID-19 : entre espoirs et déceptions.
Scheen, André ULiege; Moutschen, Michel ULiege

in Revue medicale de Liege (2020), 75(S1), 162-169

The COVID-19 outbreak has raised numerous attempts of diverse pharmacological interventions to improve the prognosis of the infection, especially among hospitalized patients due to an acute respiratory ... [more ▼]

The COVID-19 outbreak has raised numerous attempts of diverse pharmacological interventions to improve the prognosis of the infection, especially among hospitalized patients due to an acute respiratory distress syndrome (ARDS). Initially, these interventions used known medications capable to directly target SARS-CoV-2 by investigating several antiviral therapies already applied with some success in other viral infections. Among them remdesivir appears to be the most promising drug against SARS-CoV-2. Then, owing to the deleterious impact of the cytokine storm, medications that more specifically inhibit proinflammatory cytokines (especially interleukin-1 and interleukin-6) were tested. Hydroxychloroquine, sometines combined with azithromycin, has benefited for a while from a media buzz. However, hopes initially founded in all such drugs turned into disappointments because the specificities of SARS-CoV-2 make this virus resistant to most pharmacological interventions. Only glucocorticoids, dexamethasone and hydrocortisone, were associated with a significant reduction in mortality of patients with ARDS due to COVID-19, most probably via non-specific anti-inflammatory effects. These corticosteroids are currently recommended by the World Health Organisation. An intensive research is ongoing worldwide to find effective combined therapies or innovative drugs which could unequivocally improve the prognosis of COVID-19 at the different stages of the infection. [less ▲]

Detailed reference viewed: 349 (6 ULiège)
Full Text
See detailImpact of coronavirus pandemic and containment measures on HIV diagnosis
DARCIS, Gilles ULiege; VAIRA, Dolorès ULiege; MOUTSCHEN, Michel ULiege

in Epidemiology and Infection (2020)

Detailed reference viewed: 95 (17 ULiège)
Full Text
See detailLe syndrome de Schnitzler
Ilbert, Cédric ULiege; SABATIELLO, Murielle ULiege; KURTH, William ULiege et al

in Revue Médicale de Liège (2020)

Detailed reference viewed: 100 (14 ULiège)
Full Text
See detailEvolution of Drug Interactions With Antiretroviral Medication in People With HIV.
El Moussaoui, Majdouline ULiege; Lambert, Iseult ULiege; MAES, Nathalie ULiege et al

in Open Forum Infectious Diseases (2020), 7(11), 416

BACKGROUND: Polypharmacy and drug interactions are important issues for HIV-infected individuals. The number and nature of those interactions are continuously evolving with the use of new antiretroviral ... [more ▼]

BACKGROUND: Polypharmacy and drug interactions are important issues for HIV-infected individuals. The number and nature of those interactions are continuously evolving with the use of new antiretroviral drugs and the aging of HIV-infected individuals. We aimed to analyze this evolution over time. METHODS: This retrospective cohort study was conducted in the University Hospital of Liège (Belgium). Treatments of HIV-infected outpatients attending Liège University Hospital were collected and analyzed in 2012 and 2016. The University of Liverpool HIV drug interactions database was used to determine drug interactions. RESULTS: We included 1038 patients in 2016, of whom 78% had 1 comedication. Polypharmacy was seen in 20% of the cohort. Four percent of the patients presented red flag interactions, and 38% had orange flag interactions. Nonantiretroviral (non-ARV) therapeutic classes involved in drug interactions were mostly cardiovascular and central nervous system drugs. They were followed by hormone drugs and dietary supplements for orange flag interactions. Two factors significantly contributed to both red and orange flag interactions: the number of non-ARV comedications and protease inhibitor-based ARV regimens. The proportion of patients with red or orange flag interactions remained stable from 2012 to 2016. CONCLUSIONS: This study highlights the persistence of an alarming number of contraindicated drug interactions and a high prevalence of potential drug interactions over time. Identification, prevention, and management of drug interactions remain a key priority in HIV care. [less ▲]

Detailed reference viewed: 73 (27 ULiège)
Full Text
See detailSingle-center experience of patients with interstitial lung diseases during the early days of te COVID-19 pandemic.
GUIOT, Julien ULiege; HENKET, Monique ULiege; Frix, Anne-Noëlle ULiege et al

in Respiratory Investigation (2020), 58(6), 437-9

Introduction: Patients with interstitial lung diseases (ILD) can be suspected to be at risk of experiencing a rapid flare-up due to COVID-19. However, no specific data are currently available for these ... [more ▼]

Introduction: Patients with interstitial lung diseases (ILD) can be suspected to be at risk of experiencing a rapid flare-up due to COVID-19. However, no specific data are currently available for these patients. <br /> <br />Methods: We retrospectively analyzed a cohort of 401 patients with ILD and determined the proportion of patients hospitalized for proven severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and specific symptoms of COVID-19. <br /> <br />Results: We found that 1% of patients (n = 4) were hospitalized (1 in ICU) for COVID-19. In total, 310 of the 401 patients answered the phone call. Only 33 patients (0.08%) experienced specific symptoms of SARS-CoV-2 infection. <br /> <br />Conclusion: Our study did not demonstrate any increased occurrence of severe COVID-19 in ILD patients compared to the global population. Based on our findings, we could not make any conclusion on the incidence rate of SARS-CoV-2 infection in patients with ILDs, or on the overall outcome of immunocompromised patients affected by COVID-19. [less ▲]

Detailed reference viewed: 50 (17 ULiège)
Full Text
See detailDevelopment and validation of an automated radiomic CT signature for detecting COVID-19
Vaidyantahan, Akshayaa; GUIOT, Julien ULiege; DEPREZ, Louis ULiege et al

in European Respiratory Journal (2020)

Detailed reference viewed: 113 (32 ULiège)
Full Text
See detailDevelopment and Validation of an Automated Radiomic CT Signature for Detecting COVID-19.
GUIOT, Julien ULiege; Vaidyanathan, Akshayaa; DEPREZ, Louis ULiege et al

in Diagnostics (Basel, Switzerland) (2020), 11(1),

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status. Drastic measures of social distancing are enforced in society and healthcare systems are being pushed to and beyond their ... [more ▼]

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status. Drastic measures of social distancing are enforced in society and healthcare systems are being pushed to and beyond their limits. To help in the fight against this threat on human health, a fully automated AI framework was developed to extract radiomics features from volumetric chest computed tomography (CT) exams. The detection model was developed on a dataset of 1381 patients (181 COVID-19 patients plus 1200 non COVID control patients). A second, independent dataset of 197 RT-PCR confirmed COVID-19 patients and 500 control patients was used to assess the performance of the model. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). The model had an AUC of 0.882 (95% CI: 0.851-0.913) in the independent test dataset (641 patients). The optimal decision threshold, considering the cost of false negatives twice as high as the cost of false positives, resulted in an accuracy of 85.18%, a sensitivity of 69.52%, a specificity of 91.63%, a negative predictive value (NPV) of 94.46% and a positive predictive value (PPV) of 59.44%. Benchmarked against RT-PCR confirmed cases of COVID-19, our AI framework can accurately differentiate COVID-19 from routine clinical conditions in a fully automated fashion. Thus, providing rapid accurate diagnosis in patients suspected of COVID-19 infection, facilitating the timely implementation of isolation procedures and early intervention. [less ▲]

Detailed reference viewed: 50 (7 ULiège)
Full Text
See detailDevelopment of a Clinical Decision Support System for Severity Risk Prediction and Triage of COVID-19 Patients at Hospital Admission: an International Multicenter Study.
Wu, Guangyao; Yang, Pei; Xie, Yuanliang et al

in European Respiratory Journal (2020)

BACKGROUND: The outbreak of the coronavirus disease 2019 (COVID-19) has globally strained medical resources and caused significant mortality. OBJECTIVE: To develop and validate machine-learning model ... [more ▼]

BACKGROUND: The outbreak of the coronavirus disease 2019 (COVID-19) has globally strained medical resources and caused significant mortality. OBJECTIVE: To develop and validate machine-learning model based on clinical features for severity risk assessment and triage for COVID-19 patients at hospital admission. METHOD: 725 patients were used to train and validate the model including a retrospective cohort of 299 hospitalised COVID-19 patients at Wuhan, China, from December 23, 2019, to February 13, 2020, and five cohorts with 426 patients from eight centers in China, Italy, and Belgium, from February 20, 2020, to March 21, 2020. The main outcome was the onset of severe or critical illness during hospitalisation. Model performances were quantified using the area under the receiver operating characteristic curve (AUC) and metrics derived from the confusion-matrix. RESULTS: The median age was 50.0 years and 137 (45.8%) were men in the retrospective cohort. The median age was 62.0 years and 236 (55.4%) were men in five cohorts. The model was prospectively validated on five cohorts yielding AUCs ranging from 0.84 to 0.89, with accuracies ranging from 74.4% to 87.5%, sensitivities ranging from 75.0% to 96.9%, and specificities ranging from 57.5% to 88.0%, all of which performed better than the pneumonia severity index. The cut-off values of the low, medium, and high-risk probabilities were 0.21 and 0.80. The online-calculators can be found at www.covid19risk.ai. CONCLUSION: The machine-learning model, nomogram, and online-calculator might be useful to access the onset of severe and critical illness among COVID-19 patients and triage at hospital admission. [less ▲]

Detailed reference viewed: 97 (17 ULiège)
Full Text
See detailEtude des motifs d'admission au service des Urgences d'une cohorte de patients
Pirotte, Benoit; FRIPPIAT, Frédéric ULiege; DARCIS, Gilles ULiege et al

in Revue Médicale de Liège (2019)

Detailed reference viewed: 87 (22 ULiège)