Development and evaluation of a machine learning-based in-hospital COvid-19 Disease Outcome Predictor (CODOP): a multicontinental retrospective study

BackgroundMore contagious SARS-CoV-2 virus variants, breakthrough infections, waning immunity, and sub-optimal rates of COVID-19 vaccination account for a new surge of infections leading to record numbers of hospitalizations and deaths in several European countries. This is a particularly concerning scenario for resource-limited countries, which have a lower vaccination rate and fewer clinical tools to fight against the next pandemic waves. There is an urgent need for clinically valuable, generalizable, and parsimonious triage tools assisting the appropriate allocation of hospital resources. We aimed to develop and extensively validate CODOP, a machine learning-based tool for accurately predicting the clinical outcome of hospitalized COVID-19 patients. MethodsCODOP was built using modified stable iterative variable selection and linear regression with lasso regularisation. To avoid generalization problems, CODOP was trained and tested with three time-sliced and geographically distinct cohorts encompassing 40 511 blood-based analyses of COVID-19 patients from more than 110 hospitals in Spain and the USA during 2020-21. We assessed the discriminative ability of the model using the Area Under the Receiving Operative Curve (AUROC) as well as horizon and Kaplan-Meier risk stratification analyses. To reckon the fluctuating pressure levels in hospitals through the pandemic, we offer two online CODOP calculators suited for undertriage or overtriage scenarios. We challenged their generalizability and clinical utility throughout an evaluation on a cohort of patients hospitalized in five hospitals from three Latin American countries. FindingsCODOP uses 12 clinical parameters commonly measured at hospital admission and associated with the pathophysiology of COVID-19. CODOP reaches high discriminative ability up to nine days before clinical resolution (AUROC: 0{middle dot}90-0{middle dot}96, 95% CI 0{middle dot}879-0{middle dot}970), it is well calibrated, and it enables an effective dynamic risk stratification during hospitalization. The two CODOP online calculators demonstrate their potential for triage decisions when challenged with the distinctive Latin American evaluation cohorts (73-100% sensitivity and 84-100% specificity). InterpretationThe high predictive performance of CODOP in geographically disperse patient cohorts and the easiness-of-use, strongly suggest its clinical utility as a global triage tool, particularly in resource-limited countries. FundingThe Max Planck Society. Research in contextO_ST_ABSEvidence before this studyC_ST_ABSWe have searched PubMed for articles about the existence of in-hospital COVID-19 mortality predictive models, using the search terms "coronavirus", "COVID-19", "risk", "death", "mortality", and "prediction", focusing on studies published between March 1, 2020 and 31 August, 2021. The studies we identified generally used small-medium size cohorts of patients that are geographically restricted to small regions of the developed world (many times, to the same city). We havent found studies that challenged their models in extended cohorts of patients from very distinct health system populations, particularly from resource-limited countries. Further, most of the previous models are rigid by not acknowledging the fluctuating availability of hospital resources during the pandemic (e.g., beds, oxygen supply). These and other limitations have been pointed out by expert reviews indicating that published in-hospital COVID-19 mortality predictive models are subject to high risk of bias, report an over-optimistic performance, and have limited clinical value in assisting daily triage decisions. A parsimonious, accurate and extensively validated model is yet to be developed. Added value of this studyWe analysed clinical data from different cohorts totalling 21 607 COVID-19 patients treated in more than 110 hospitals in Spain and the USA during three different pandemic waves extending from February 2020 to April 2021. The new CODOP in-hospital mortality prediction model is based on 11 blood biochemistry parameters (representing main biological pathways involved in the pathogenesis of SARS-CoV-2) plus Age, all of them commonly measured upon hospitalization. CODOP accurately predicted mortality risk up to nine days before clinical resolution (AUROC: 0{middle dot}90-0{middle dot}96, 95% CI 0{middle dot}879-0{middle dot}970), it is well calibrated, and it enables an effective dynamic risk stratification during hospitalization. We offer two online CODOP calculator subtypes (https://gomezvarelalab.em.mpg.de/codop/) tailored to overtriage and undertriage scenarios. The online calculators were able to reach the desired prediction performance in five independent evaluation cohorts gathered in hospitals of three Latin American countries from March 7th 2020 to June 7th 2021. Implications of all the available evidenceWe present here a highly accurate, parsimonious and extensively validated COVID-19 in-hospital mortality prediction model, derived from working with the largest number and the most geographically extended representation of patients and health systems to date. The rigorous analytical methods, the generalizability of the model in distinct world regions, and its flexibility to reckon with the changing availability of hospital resources point to CODOP as a clinically useful tool potentially improving the outcome prediction and the management of COVID-19 hospitalized patients.

Effect of in-hospital treatment with angiotensin-converting enzyme inhibitors and angiotensin II receptor blockers on mortality and complications in patients hospitalized for COVID-19: a large Spanish cohort study.

BackgroundThe use of ACEI (Angiotensin-Converting Enzyme Inhibitor) and ARB (Angiotensin II Receptor Blocker) in COVID-19 remains controversial. Our main aim was to describe the effect of ACEI/ARB treatment during COVID-19 hospitalization on mortality and complications. MethodsRetrospective, observational, multicenter study, part of the SEMI-COVID-19 Registry, comparing patients with COVID-19 treated with ACEI/ARB during hospitalization to those not treated. The primary endpoint was incidence of the composite outcome of prognosis (IMV [Invasive Mechanical Ventilation], NIMV [Non-Invasive Mechanical Ventilation], ICU admission [Intensive Care Unit], and/or all-cause mortality). The secondary endpoint was incidence of MACE (Major Adverse Cardiovascular Events). We evaluated both outcomes in patients whose treatment with ACEI/ARB continued or was withdrawn during hospitalization. ResultsBetween February and June 2020, 11,205 patients were included, with mean age 67 years (SD=16.3) and 43.1% female; 2,162 patients received ACEI/ARB treatment. ACEI/ARB treatment showed a protective effect on all-cause mortality (p<.0001). In hypertensive patients it was also protective in terms of IMV, ICU admission, and the composite outcome of prognosis (p<.0001 for all). No differences were found in incidence of MACE. Patients previously treated with ACEI/ARB who continued treatment during hospitalization had a lower incidence of the composite outcome of prognosis than those whose treatment was withdrawn (RR 0.67, 95%CI 0.63-0.76). ARB had a more beneficial effect on survival than ACEI (HR 0.77, 95%CI 0.62-0.96). ConclusionACEI/ARB treatment during COVID-19 hospitalization had a protective effect on mortality. The benefits were greater in hypertensive patients, those who continued treatment during hospitalization, and those taking ARB. SummaryTreatment with ACEI/ARB during COVID-19 hospitalization showed a beneficial effect on mortality in the general population. The benefit was greater in hypertensive patients, in those who maintained treatment during hospitalization and those taking ARB.

Predicting critical illness on initial diagnosis of COVID-19: Development and validation of the PRIORITY model for outpatient applicability.

ObjectivesCurrently available COVID-19 prognostic models have focused on laboratory and radiological data obtained following admission. However, these tests are not available on initial assessment or in resource-limited settings. We aim to develop and validate a prediction model, based on clinical history and examination findings on initial diagnosis of COVID-19, to identify patients at risk of critical outcomes. MethodsWe used data from the SEMI-COVID-19 Registry, a nationwide multicenter cohort of consecutive patients hospitalized for COVID-19 from 132 centers in Spain. Clinical signs and symptoms, demographic variables, and medical history ascertained at hospital admission were screened using Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression to construct a predictive model. We externally validated the final model in a separate cohort of patients admitted at less-complex hospitals (< 300 beds).We undertook decision curve analysis to assess the clinical usefulness of the predictive model. The primary outcome was a composite of in-hospital death, mechanical ventilation or admission to intensive care unit. ResultsThere were 10,433 patients, 7,850 (primary outcome 25.1%) in the development cohort and 2,583 (primary outcome 27.0%) in the validation cohort. Variables in the final model included: age, cardiovascular disease, chronic kidney disease, dyspnea, tachypnea, confusion, systolic blood pressure, and SpO2[≤]93% or oxygen requirement.The C-statistic in the development cohort was 0.823 (95% CI,0.813-0.834). On external validation, the C-statistic was 0.792 (95% CI,0.772-0.812). The model showed a positive net benefit for threshold probabilities between 3% and 79%. ConclusionsAmong patients presenting with COVID-19, the model based on easily-obtained clinical information had good discrimination and generalizability for identifying patients at risk of critical outcomes without the need of additional testing. The online calculator provided would facilitate triage of patients during the pandemic. This study could provide a useful tool for decision-making in health systems under pandemic pressure and resource-limited settings.

Predicting clinical outcome with phenotypic clusters in COVID-19 pneumonia: 2 an analysis of 12,066 hospitalized patients from the Spanish registry SEMI-3 COVID-19.

(1) Background: This study aims to identify different clinical phenotypes in COVID-19 88 pneumonia using cluster analysis and to assess the prognostic impact among identified clusters in 89 such patients. (2) Methods: Cluster analysis including 11 phenotypic variables was performed in a 90 large cohort of 12,066 COVID-19 patients, collected and followed-up from March 1, to July 31, 2020, 91 from the nationwide Spanish SEMI-COVID-19 Registry. (3) Results: Of the total of 12,066 patients 92 included in the study, most were males (7,052, 58.5%) and Caucasian (10,635, 89.5%), with a mean 93 age at diagnosis of 67 years (SD 16). The main pre-admission comorbidities were arterial 94 hypertension (6,030, 50%), hyperlipidemia (4,741, 39.4%) and diabetes mellitus (2,309, 19.2%). The 95 average number of days from COVID-19 symptom onset to hospital admission was 6.7 days (SD 7). 96 The triad of fever, cough, and dyspnea was present almost uniformly in all 4 clinical phenotypes 97 identified by clustering. Cluster C1 (8,737 patients, 72.4%) was the largest, and comprised patients 98 with the triad alone. Cluster C2 (1,196 patients, 9.9%) also presented with ageusia and anosmia; 99 cluster C3 (880 patients, 7.3%) also had arthromyalgia, headache, and sore throat; and cluster C4 100 (1,253 patients, 10.4%) also manifested with diarrhea, vomiting, and abdominal pain. Compared to 101 each other, cluster C1 presented the highest in-hospital mortality (24.1% vs. 4.3% vs. 14.7% vs. 102 18.6%; p<0.001). The multivariate study identified phenotypic clusters as an independent factor for 103 in-hospital death. (4) Conclusion: The present study identified 4 phenotypic clusters in patients with 104 COVID-19 pneumonia, which predicted the in-hospital prognosis of clinical outcomes.

Clinical characteristics of patients hospitalized with COVID-19 in Spain: results from the SEMI-COVID-19 Network.

BackgroundSpain has been one of the countries most affected by the COVID-19 pandemic. ObjectiveTo create a registry of patients with COVID-19 hospitalized in Spain in order to improve our knowledge of the clinical, diagnostic, therapeutic, and prognostic aspects of this disease. MethodsA multicentre retrospective cohort study, including consecutive patients hospitalized with confirmed COVID-19 throughout Spain. Epidemiological and clinical data, additional tests at admission and at seven days, treatments administered, and progress at 30 days of hospitalization were collected from electronic medical records. ResultsUp to April 30th 2020, 6,424 patients from 109 hospitals were included. Their median age was 69.1 years (range: 18-102 years) and 56.9% were male. Prevalences of hypertension, dyslipidemia, and diabetes mellitus were 50.2%, 39.7%, and 18.7%, respectively. The most frequent symptoms were fever (86.2%) and cough (76.5%). High values of ferritin (72.4%), lactate dehydrogenase (70.2%), and D-dimer (61.5%), as well as lymphopenia (52.6%), were frequent. The most used antiviral drugs were hydroxychloroquine (85.7%) and lopinavir/ritonavir (62.4%). 31.5% developed respiratory distress. Overall mortality rate was 21.1%, with a marked increase with age (50-59 years: 4.2%, 60-69 years: 9.1%, 70-79 years: 21.4%, 80-89 years: 42.5%, [≥] 90 years: 51.1%). ConclusionsThe SEMI-COVID-19 Network provides data on the clinical characteristics of patients with COVID-19 hospitalized in Spain. Patients with COVID-19 hospitalized in Spain are mostly severe cases, as one in three patients developed respiratory distress and one in five patients died. These findings confirm a close relationship between advanced age and mortality.

Alterations of specific biomarkers of metabolic pathways in vascular tree from patients with Type 2 diabetes.

The aims of this study were to check whether different biomarkers of inflammatory, apoptotic, immunological or lipid pathways had altered their expression in the occluded popliteal artery (OPA) compared with the internal mammary artery (IMA) and femoral vein (FV) and to examine whether glycemic control influenced the expression of these genes. The study included 20 patients with advanced atherosclerosis and type 2 diabetes mellitus, 15 of whom had peripheral arterial occlusive disease (PAOD), from whom samples of OPA and FV were collected. PAOD patients were classified based on their HbA1c as well (HbA1c ≤ 6.5) or poorly (HbA1c > 6.5) controlled patients. Controls for arteries without atherosclerosis comprised 5 IMA from patients with ischemic cardiomyopathy (ICM). mRNA, protein expression and histological studies were analyzed in IMA, OPA and FV. After analyzing 46 genes, OPA showed higher expression levels than IMA or FV for genes involved in thrombosis (F3), apoptosis (MMP2, MMP9, TIMP1 and TIM3), lipid metabolism (LRP1 and NDUFA), immune response (TLR2) and monocytes adhesion (CD83). Remarkably, MMP-9 expression was lower in OPA from well-controlled patients. In FV from diabetic patients with HbA1c ≤6.5, gene expression levels of BCL2, CDKN1A, COX2, NDUFA and SREBP2 were higher than in FV from those with HbA1c >6.5. The atherosclerotic process in OPA from diabetic patients was associated with high expression levels of inflammatory, lipid metabolism and apoptotic biomarkers. The degree of glycemic control was associated with gene expression markers of apoptosis, lipid metabolism and antioxidants in FV. However, the effect of glycemic control on pro-atherosclerotic gene expression was very low in arteries with established atherosclerosis.