Obtaining patient phenotypes in SARS-CoV-2 pneumonia, and their association with clinical severity and mortality.

BACKGROUND: There exists consistent empirical evidence in the literature pointing out ample heterogeneity in terms of the clinical evolution of patients with COVID-19. The identification of specific phenotypes underlying in the population might contribute towards a better understanding and characterization of the different courses of the disease. The aim of this study was to identify distinct clinical phenotypes among hospitalized patients with SARS-CoV-2 pneumonia using machine learning clustering, and to study their association with subsequent clinical outcomes as severity and mortality. METHODS: Multicentric observational, prospective, longitudinal, cohort study conducted in four hospitals in Spain. We included adult patients admitted for in-hospital stay due to SARS-CoV-2 pneumonia. We collected a broad spectrum of variables to describe exhaustively each case: patient demographics, comorbidities, symptoms, physiological status, baseline examinations (blood analytics, arterial gas test), etc. For the development and internal validation of the clustering/phenotype models, the dataset was split into training and test sets (50% each). We proposed a sequence of machine learning stages: feature scaling, missing data imputation, reduction of data dimensionality via Kernel Principal Component Analysis (KPCA), and clustering with the k-means algorithm. The optimal cluster model parameters -including k, the number of phenotypes- were chosen automatically, by maximizing the average Silhouette score across the training set. RESULTS: We enrolled 1548 patients, each of them characterized by 92 clinical attributes (d=109 features after variable encoding). Our clustering algorithm identified k=3 distinct phenotypes and 18 strongly informative variables: Phenotype A (788 cases [50.9% prevalence] - age ∼ 57, Charlson comorbidity ∼ 1, pneumonia CURB-65 score ∼ 0 to 1, respiratory rate at admission ∼ 18 min-1, FiO2 ∼ 21%, C-reactive protein CRP ∼ 49.5 mg/dL [median within cluster]); phenotype B (620 cases [40.0%] - age ∼ 75, Charlson ∼ 5, CURB-65 ∼ 1 to 2, respiration ∼ 20 min-1, FiO2 ∼ 21%, CRP ∼ 101.5 mg/dL); and phenotype C (140 cases [9.0%] - age ∼ 71, Charlson ∼ 4, CURB-65 ∼ 0 to 2, respiration ∼ 30 min-1, FiO2 ∼ 38%, CRP ∼ 152.3 mg/dL). Hypothesis testing provided solid statistical evidence supporting an interaction between phenotype and each clinical outcome: severity and mortality. By computing their corresponding odds ratios, a clear trend was found for higher frequencies of unfavourable evolution in phenotype C with respect to B, as well as more unfavourable in phenotype B than in A. CONCLUSION: A compound unsupervised clustering technique (including a fully-automated optimization of its internal parameters) revealed the existence of three distinct groups of patients - phenotypes. In turn, these showed strong associations with the clinical severity in the progression of pneumonia, and with mortality.

Basic host response parameters to classify mortality risk in COVID-19 and community-acquired pneumonia.

Improved phenotyping in pneumonia is necessary to strengthen risk assessment. Via a feasible and multidimensional approach with basic parameters, we aimed to evaluate the effect of host response at admission on severity stratification in COVID-19 and community-acquired pneumonia (CAP). Three COVID-19 and one CAP multicenter cohorts including hospitalized patients were recruited. Three easily available variables reflecting different pathophysiologic mechanisms-immune, inflammation, and respiratory-were selected (absolute lymphocyte count [ALC], C-reactive protein [CRP] and, SpO2/FiO2). In-hospital mortality and intensive care unit (ICU) admission were analyzed as outcomes. A multivariable, penalized maximum likelihood logistic regression was performed with ALC (< 724 lymphocytes/mm3), CRP (> 60 mg/L), and, SpO2/FiO2 (< 450). A total of 1452, 1222 and 462 patients were included in the three COVID-19 and 1292 in the CAP cohort for the analysis. Mortality ranged between 4 and 32% (0 to 3 abnormal biomarkers) and 0-9% in SARS-CoV-2 pneumonia and CAP, respectively. In the first COVID-19 cohort, adjusted for age and sex, we observed an increased odds ratio for in-hospital mortality in COVID-19 with elevated biomarkers altered (OR 1.8, 3, and 6.3 with 1, 2, and 3 abnormal biomarkers, respectively). The model had an AUROC of 0.83. Comparable findings were found for ICU admission, with an AUROC of 0.76. These results were confirmed in the other COVID-19 cohorts Similar OR trends were reported in the CAP cohort; however, results were not statistically significant. Assessing the host response via accessible biomarkers is a simple and rapidly applicable approach for pneumonia.

How Does the Burden of Respiratory Syncytial Virus Compare to Influenza in Spanish Adults?

BACKGROUND: Respiratory syncytial virus (RSV) and influenza infections cause significant annual morbidity and mortality worldwide in at-risk populations. This study is aimed at assessing hospital burden and healthcare resource utilization (HRU) of RSV and influenza in adults in Spain. METHODS: Data were obtained from the Projected Hospitalisation Database of inpatient episodes (ages: younger adults 18-50 and 51-64 years; older adults 65-74, 75-84, and ≥ 85 years) during 2015, 2017, and 2018 in Spanish public hospitals. Incidence, mean hospitalization, and HRU assessments, including length of stay (LOS), intensive care unit (ICU) usage, and age-standardized mortality rates, were collected and stratified by age group, with analyses focusing on the adult population (≥ 18 years old). RESULTS: Mean hospitalization rate in the population across all years was lower in individuals with RSV versus influenza (7.2/100,000 vs. 49.7/100,000 individuals). ICU admissions and median LOS were similar by age group for both viruses. Age-standardized mortality was 6.3/100,000 individuals and 6.1/100,000 individuals in patients with RSV and influenza, respectively, and mortality rates were similar in older adults (≥ 65 years) for both viruses. CONCLUSIONS: RSV and influenza infection were associated with considerable HRU. There is a substantial disease burden for RSV infection in older adults ≥ 65 years. While RSV hospitalization rates in adults reported here appeared lower than influenza, RSV is still underdiagnosed in the hospital setting and its incidence might be similar to, or higher than, influenza.

Effect of immediate initiation of invasive ventilation on mortality in acute hypoxemic respiratory failure: a target trial emulation.

PURPOSE: Invasive ventilation is a fundamental treatment in intensive care but its precise timing is difficult to determine. This study aims at assessing the effect of initiating invasive ventilation versus waiting, in patients with hypoxemic respiratory failure without immediate reason for intubation on one-year mortality. METHODS: Emulation of a target trial to estimate the benefit of immediately initiating invasive ventilation in hypoxemic respiratory failure, versus waiting, among patients within the first 48-h of hypoxemia. The eligible population included non-intubated patients with SpO2/FiO2 ≤ 200 and SpO2 ≤ 97%. The target trial was emulated using a single-center database (MIMIC-IV) which contains granular information about clinical status. The hourly probability to receive mechanical ventilation was continuously estimated. The hazard ratios for the primary outcome, one-year mortality, and the secondary outcome, 30-day mortality, were estimated using weighted Cox models with stabilized inverse probability weights used to adjust for measured confounding. RESULTS: 2996 Patients fulfilled the inclusion criteria of whom 792 were intubated within 48 h. Among the non-invasive support devices, the use of oxygen through facemask was the most common (75%). Compared to patients with the same probability of intubation but who were not intubated, intubation decreased the hazard of dying for the first year after ICU admission HR 0.81 (95% CI 0.68-0.96, p = 0.018). Intubation was associated with a 30-day mortality HR of 0.80 (95% CI 0.64-0.99, p = 0.046). CONCLUSION: The initiation of mechanical ventilation in patients with acute hypoxemic respiratory failure reduced the hazard of dying in this emulation of a target trial.

Sleep and Circadian Health of Critical Survivors: A 12-Month Follow-Up Study.

OBJECTIVES: To investigate the sleep and circadian health of critical survivors 12 months after hospital discharge and to evaluate a possible effect of the severity of the disease within this context. DESIGN: Observational, prospective study. SETTING: Single-center study. PATIENTS: Two hundred sixty patients admitted to the ICU due to severe acute respiratory syndrome coronavirus 2 infection. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The cohort was composed of 260 patients (69.2% males), with a median (quartile 1-quartile 3) age of 61.5 years (52.0-67.0 yr). The median length of ICU stay was 11.0 days (6.00-21.8 d), where 56.2% of the patients required invasive mechanical ventilation (IMV). The Pittsburgh Sleep Quality Index (PSQI) revealed that 43.1% of the cohort presented poor sleep quality 12 months after hospital discharge. Actigraphy data indicated an influence of the disease severity on the fragmentation of the circadian rest-activity rhythm at the 3- and 6-month follow-ups, which was no longer significant in the long term. Still, the length of the ICU stay and the duration of IMV predicted a higher fragmentation of the rhythm at the 12-month follow-up with effect sizes (95% CI) of 0.248 (0.078-0.418) and 0.182 (0.005-0.359), respectively. Relevant associations between the PSQI and the Hospital Anxiety and Depression Scale (rho = 0.55, anxiety; rho = 0.5, depression) as well as between the fragmentation of the rhythm and the diffusing lung capacity for carbon monoxide (rho = -0.35) were observed at this time point. CONCLUSIONS: Our findings reveal a great prevalence of critical survivors presenting poor sleep quality 12 months after hospital discharge. Actigraphy data indicated the persistence of circadian alterations and a possible impact of the disease severity on the fragmentation of the circadian rest-activity rhythm, which was attenuated at the 12-month follow-up. This altogether highlights the relevance of considering the sleep and circadian health of critical survivors in the long term.

Airway clearance management in people with bronchiectasis: data from the European Bronchiectasis Registry (EMBARC).

BACKGROUND: International guidelines recommend airway clearance management as one of the important pillars of bronchiectasis treatment. However, the extent to which airway clearance is used for people with bronchiectasis in Europe is unclear. The aim of the study was to identify the use of airway clearance management in patients with bronchiectasis across different countries and factors influencing airway clearance use. METHODS: This was a prospective observational study using data from the European Multicentre Bronchiectasis Audit and Research Collaboration (EMBARC) Registry between January 2015 and April 2022. Prespecified options for airway clearance management were recorded, including airway clearance techniques, devices and use of mucoactive drugs. RESULTS: 16 723 people with bronchiectasis from 28 countries were included in the study. The mean age was 67 years (interquartile range 57-74 years, range 18-100 years) and 61% were female. 72% of the participants reported daily sputum expectoration and 52% (95% CI 51-53%) of all participants reported using regular airway clearance management. Active cycle of breathing technique was used by 28% of the participants and airway clearance devices by 16% of participants. The frequency of airway clearance management and techniques used varied significantly between different countries. Participants who used airway clearance management had greater disease severity and worse symptoms, including a higher daily sputum volume, compared to those who did not use it regularly. Mucoactive drugs were also more likely to be used in participants with more severe disease. Access to specialist respiratory physiotherapy was low throughout Europe, but particularly low in Eastern Europe. CONCLUSIONS: Only a half of people with bronchiectasis in Europe use airway clearance management. Use of and access to devices, mucoactive drugs and specialist chest physiotherapy appears to be limited in many European countries.

Diabetes Mellitus and Pneumococcal Pneumonia.

Currently, there are more than 500 million people suffering from diabetes around the world. People aged 65 years or older are the most affected by this disease, and it is estimated that approximately 96% of diabetes cases worldwide are type 2 diabetes. People with diabetes mellitus are at an increased risk of infections such as pneumonia, due to a series of factors that may contribute to immune dysfunction, including hyperglycemia, inhibition of neutrophil chemotaxis, impaired cytokine production, phagocytic cell dysfunction, altered T cell-mediated immune responses and the co-existence of chronic comorbidities. Rates of infection, hospitalization and mortality in diabetic patients are reported to be higher than in the general population. Research into the risk of infectious diseases such as pneumonia in these patients is very important because it will help improve their management and treatment.

Objective sputum colour assessment and clinical outcomes in bronchiectasis: data from the European Bronchiectasis Registry (EMBARC).

BACKGROUND: A validated 4-point sputum colour chart can be used to objectively evaluate the levels of airway inflammation in bronchiectasis patients. In the European Bronchiectasis Registry (EMBARC), we tested whether sputum colour would be associated with disease severity and clinical outcomes. METHODS: We used a prospective, observational registry of adults with bronchiectasis conducted in 31 countries. Patients who did not produce spontaneous sputum were excluded from the analysis. The Murray sputum colour chart was used at baseline and at follow-up visits. Key outcomes were frequency of exacerbations, hospitalisations for severe exacerbations and mortality during up to 5-year follow-up. RESULTS: 13 484 patients were included in the analysis. More purulent sputum was associated with lower forced expiratory volume in 1 s (FEV1), worse quality of life, greater bacterial infection and a higher bronchiectasis severity index. Sputum colour was strongly associated with the risk of future exacerbations during follow-up. Compared to patients with mucoid sputum (reference group), patients with mucopurulent sputum experienced significantly more exacerbations (incident rate ratio (IRR) 1.29, 95% CI 1.22-1.38; p<0.0001), while the rates were even higher for patients with purulent (IRR 1.55, 95% CI 1.44-1.67; p<0.0001) and severely purulent sputum (IRR 1.91, 95% CI 1.52-2.39; p<0.0001). Hospitalisations for severe exacerbations were also associated with increasing sputum colour with rate ratios, compared to patients with mucoid sputum, of 1.41 (95% CI 1.29-1.56; p<0.0001), 1.98 (95% CI 1.77-2.21; p<0.0001) and 3.05 (95% CI 2.25-4.14; p<0.0001) for mucopurulent, purulent and severely purulent sputum, respectively. Mortality was significantly increased with increasing sputum purulence, hazard ratio 1.12 (95% CI 1.01-1.24; p=0.027), for each increment in sputum purulence. CONCLUSION: Sputum colour is a simple marker of disease severity and future risk of exacerbations, severe exacerbations and mortality in patients with bronchiectasis.

Invasive Fungal Diseases in Adult Patients in Intensive Care Unit (FUNDICU): 2024 consensus definitions from ESGCIP, EFISG, ESICM, ECMM, MSGERC, ISAC, and ISHAM.

PURPOSE: The aim of this document was to develop standardized research definitions of invasive fungal diseases (IFD) in non-neutropenic, adult patients without classical host factors for IFD, admitted to intensive care units (ICUs). METHODS: After a systematic assessment of the diagnostic performance for IFD in the target population of already existing definitions and laboratory tests, consensus definitions were developed by a panel of experts using the RAND/UCLA appropriateness method. RESULTS: Standardized research definitions were developed for proven invasive candidiasis, probable deep-seated candidiasis, proven invasive aspergillosis, probable invasive pulmonary aspergillosis, and probable tracheobronchial aspergillosis. The limited evidence on the performance of existing definitions and laboratory tests for the diagnosis of IFD other than candidiasis and aspergillosis precluded the development of dedicated definitions, at least pending further data. The standardized definitions provided in the present document are aimed to speed-up the design, and increase the feasibility, of future comparative research studies.

New Guidelines for Severe Community-acquired Pneumonia.

In 2023, the new European guidelines on severe community-acquired pneumonia, providing clinical practice recommendations for the management of this life-threatening infection, characterized by a high burden of mortality, morbidity, and costs for the society. This review article aims to summarize the principal evidence related to eight different questions covered in the guidelines, by also highlighting the future perspectives for research activity.

Global mortality and readmission rates following COPD exacerbation-related hospitalisation: a meta-analysis of 65 945 individual patients.

Background: Exacerbations of COPD (ECOPD) have a major impact on patients and healthcare systems across the world. Precise estimates of the global burden of ECOPD on mortality and hospital readmission are needed to inform policy makers and aid preventive strategies to mitigate this burden. The aims of the present study were to explore global in-hospital mortality, post-discharge mortality and hospital readmission rates after ECOPD-related hospitalisation using an individual patient data meta-analysis (IPDMA) design. Methods: A systematic review was performed identifying studies that reported in-hospital mortality, post-discharge mortality and hospital readmission rates following ECOPD-related hospitalisation. Data analyses were conducted using a one-stage random-effects meta-analysis model. This study was conducted and reported in accordance with the PRISMA-IPD statement. Results: Data of 65 945 individual patients with COPD were analysed. The pooled in-hospital mortality rate was 6.2%, pooled 30-, 90- and 365-day post-discharge mortality rates were 1.8%, 5.5% and 10.9%, respectively, and pooled 30-, 90- and 365-day hospital readmission rates were 7.1%, 12.6% and 32.1%, respectively, with noticeable variability between studies and countries. Strongest predictors of mortality and hospital readmission included noninvasive mechanical ventilation and a history of two or more ECOPD-related hospitalisations <12 months prior to the index event. Conclusions: This IPDMA stresses the poor outcomes and high heterogeneity of ECOPD-related hospitalisation across the world. Whilst global standardisation of the management and follow-up of ECOPD-related hospitalisation should be at the heart of future implementation research, policy makers should focus on reimbursing evidence-based therapies that decrease (recurrent) ECOPD.

Bacterial Adaptive Memory in Methicillin-Resistant Staphylococcus aureus from Endotracheal Tubes.

OBJECTIVES: To evaluate the expression dynamics of biofilm genes in methicillin-resistant Staphylococcus aureus (MRSA) retrieved from endotracheal tubes (ETT) and to determine how gene regulation is attenuated in vitro where host-environmental factors are no longer present. METHODS: Biofilm was grown (24 h) in tryptic broth soy plus 0.25% glucose for a clinical MRSA isolate in planktonic state and after sessile growth named ETT-MRSA (S2, S3, S4, S5, S6, S7). Gene expression of five biofilm-related genes (icaC, clfB, ebps, fnbB, and RNA III) was assessed consecutively from day 1 to day 4 after ETT growth through real-time PCR. 16S rRNA was used as a control. RESULTS: The MRSA isolates retrieved from ETT were capable of producing biofilms dependent on ica. The gene expression dynamics of ETT-MRSA changed progressively compared to planktonic MRSA gene expression under both ambient air (p < 0.001) and ambient air with 5% CO2 (p < 0.001). Dynamic assessment of icaC expression in both atmospheric conditions showed progressive downregulation in vitro compared to in vivo ETT biofilms. The expression patterns of clfB and ebps genes were similar to icaC. In contrast, the expression of the RNA III gene showed progressive upregulation from day 1 to day 4 (p < 0.001). CONCLUSIONS: MRSA loses its biofilm gene expression in vitro, by adaptive features across multiple generations, as evidenced by the progressive downregulation of icaC and upregulation of RNA III. These findings underscore the significance of host-environment dependence in regulating bacterial biofilm genes, highlighting its importance in diagnostics. Bacterial strains lose their host-specific characteristics as they are cultured in vitro.

Understanding the nebulisation of antibiotics: the key role of lung microdialysis studies.

BACKGROUND: Nebulisation of antibiotics is a promising treatment for ventilator-associated pneumonia (VAP) caused by multidrug-resistant organisms. Ensuring effective antibiotic concentrations at the site of infection in the interstitial space fluid is crucial for clinical outcomes. Current assessment methods, such as epithelial lining fluid and tissue homogenates, have limitations in providing longitudinal pharmacokinetic data. MAIN BODY: Lung microdialysis, an invasive research technique predominantly used in animals, involves inserting probes into lung parenchyma to measure antibiotic concentrations in interstitial space fluid. Lung microdialysis offers unique advantages, such as continuous sampling, regional assessment of antibiotic lung concentrations and avoidance of bronchial contamination. However, it also has inherent limitations including the cost of probes and assay development, the need for probe calibration and limited applicability to certain antibiotics. As a research tool in VAP, lung microdialysis necessitates specialist techniques and resource-intensive experimental designs involving large animals undergoing prolonged mechanical ventilation. However, its potential impact on advancing our understanding of nebulised antibiotics for VAP is substantial. The technique may enable the investigation of various factors influencing antibiotic lung pharmacokinetics, including drug types, delivery devices, ventilator settings, interfaces and disease conditions. Combining in vivo pharmacokinetics with in vitro pharmacodynamic simulations can become feasible, providing insights to inform nebulised antibiotic dose optimisation regimens. Specifically, it may aid in understanding and optimising the nebulisation of polymyxins, effective against multidrug-resistant Gram-negative bacteria. Furthermore, lung microdialysis holds promise in exploring novel nebulisation therapies, including repurposed antibiotic formulations, bacteriophages and immunomodulators. The technique's potential to monitor dynamic biochemical changes in pneumonia, such as cytokines, metabolites and inflammation/infection markers, opens avenues for developing theranostic tools tailored to critically ill patients with VAP. CONCLUSION: In summary, lung microdialysis can be a potential transformative tool, offering real-time insights into nebulised antibiotic pharmacokinetics. Its potential to inform optimal dosing regimen development based on precise target site concentrations and contribute to development of theranostic tools positions it as key player in advancing treatment strategies for VAP caused by multidrug-resistant organisms. The establishment of international research networks, exemplified by LUMINA (lung microdialysis applied to nebulised antibiotics), signifies a proactive step towards addressing complexities and promoting multicentre experimental studies in the future.

Bronchiectasis and asthma: Data from the European Bronchiectasis Registry (EMBARC).

BACKGROUND: Asthma is commonly reported in patients with a diagnosis of bronchiectasis. OBJECTIVE: The aim of this study was to evaluate whether patients with bronchiectasis and asthma (BE+A) had a different clinical phenotype and different outcomes compared with patients with bronchiectasis without concomitant asthma. METHODS: A prospective observational pan-European registry (European Multicentre Bronchiectasis Audit and Research Collaboration) enrolled patients across 28 countries. Adult patients with computed tomography-confirmed bronchiectasis were reviewed at baseline and annual follow-up visits using an electronic case report form. Asthma was diagnosed by the local investigator. Follow-up data were used to explore differences in exacerbation frequency between groups using a negative binomial regression model. Survival analysis used Cox proportional hazards regression. RESULTS: Of 16,963 patients with bronchiectasis included for analysis, 5,267 (31.0%) had investigator-reported asthma. Patients with BE+A were younger, were more likely to be female and never smokers, and had a higher body mass index than patients with bronchiectasis without asthma. BE+A was associated with a higher prevalence of rhinosinusitis and nasal polyps as well as eosinophilia and Aspergillus sensitization. BE+A had similar microbiology but significantly lower severity of disease using the bronchiectasis severity index. Patients with BE+A were at increased risk of exacerbation after adjustment for disease severity and multiple confounders. Inhaled corticosteroid (ICS) use was associated with reduced mortality in patients with BE+A (adjusted hazard ratio 0.78, 95% CI 0.63-0.95) and reduced risk of hospitalization (rate ratio 0.67, 95% CI 0.67-0.86) compared with control subjects without asthma and not receiving ICSs. CONCLUSIONS: BE+A was common and was associated with an increased risk of exacerbations and improved outcomes with ICS use. Unexpectedly we identified significantly lower mortality in patients with BE+A.

MicroRNA-centered theranostics for pulmoprotection in critical COVID-19.

Elucidating the pathobiological mechanisms underlying post-acute pulmonary sequelae following SARS-CoV-2 infection is essential for early interventions and patient stratification. Here, we investigated the potential of microRNAs (miRNAs) as theranostic agents for pulmoprotection in critical illness survivors. Multicenter study including 172 ICU survivors. Diffusion impairment was defined as a lung-diffusing capacity for carbon monoxide (DLCO) <80% within 12 months postdischarge. A disease-associated 16-miRNA panel was quantified in plasma samples collected at ICU admission. Bioinformatic analyses were conducted using KEGG, Reactome, GTEx, and Drug-Gene Interaction databases. The results were validated using an external RNA-seq dataset. A 3-miRNA signature linked to diffusion impairment (miR-27a-3p, miR-93-5p, and miR-199a-5p) was identified using random forest. Levels of miR-93-5p and miR-199a-5p were independently associated with the outcome, improving patient classification provided by the electronic health record. The experimentally validated targets of these miRNAs exhibited enrichment across diverse pathways, with telomere length quantification in an additional set of samples (n = 83) supporting the role of cell senescence in sequelae. Analysis of an external dataset refined the pathobiological fingerprint of pulmonary sequelae. Gene-drug interaction analysis revealed four FDA-approved drugs. Overall, this study advances our understanding of lung recovery in postacute respiratory infections, highlighting the potential of miRNAs and their targets for pulmoprotection.

Cost-sensitive ordinal classification methods to predict SARS-CoV-2 pneumonia severity.

OBJECTIVE: To study the suitability of costsensitive ordinal artificial intelligence-machine learning (AIML) strategies in the prognosis of SARS-CoV-2 pneumonia severity. MATERIALS & METHODS: Observational, retrospective, longitudinal, cohort study in 4 hospitals in Spain. Information regarding demographic and clinical status was supplemented by socioeconomic data and air pollution exposures. We proposed AI-ML algorithms for ordinal classification via ordinal decomposition and for cost-sensitive learning via resampling techniques. For performance-based model selection, we defined a custom score including per-class sensitivities and asymmetric misprognosis costs. 260 distinct AI-ML models were evaluated via 10 repetitions of 5×5 nested cross-validation with hyperparameter tuning. Model selection was followed by the calibration of predicted probabilities. Final overall performance was compared against five well-established clinical severity scores and against a 'standard' (non-cost sensitive, non-ordinal) AI-ML baseline. In our best model, we also evaluated its explainability with respect to each of the input variables. RESULTS: The study enrolled n = 1548 patients: 712 experienced low, 238 medium, and 598 high clinical severity. d = 131 variables were collected, becoming d ' = 148 features after categorical encoding. Model selection resulted in our best-performing AI-ML pipeline having: a) no imputation of missing data, b) no feature selection (i.e. using the full set of d ' features), c) 'Ordered Partitions' ordinal decomposition, d) cost-based reimbalance, and e) a Histogram-based Gradient Boosting classifier. This best model (calibrated) obtained a median accuracy of 68.1% [67.3%, 68.8%] (95% confidence interval), a balanced accuracy of 57.0% [55.6%, 57.9%], and an overall area under the curve (AUC) 0.802 [0.795, 0.808]. In our dataset, it outperformed all five clinical severity scores and the 'standard' AI-ML baseline. DISCUSSION & CONCLUSION: We conducted an exhaustive exploration of AI-ML methods designed for both ordinal and cost-sensitive classification, motivated by a real-world application domain (clinical severity prognosis) in which these topics arise naturally. Our model with the best classification performance exploited successfully the ordering information of ground truth classes, coping with imbalance and asymmetric costs. However, these ordinal and cost-sensitive aspects are seldom explored in the literature.

MicroRNA-guided drug discovery for mitigating persistent pulmonary complications in critical COVID-19 survivors: A longitudinal pilot study.

BACKGROUND AND PURPOSE: The post-acute sequelae of SARS-CoV-2 infection pose a significant global challenge, with nearly 50% of critical COVID-19 survivors manifesting persistent lung abnormalities. The lack of understanding about the molecular mechanisms and effective treatments hampers their management. Here, we employed microRNA (miRNA) profiling to decipher the systemic molecular underpinnings of the persistent pulmonary complications. EXPERIMENTAL APPROACH: We conducted a longitudinal investigation including 119 critical COVID-19 survivors. A comprehensive pulmonary evaluation was performed in the short-term (median = 94.0 days after hospital discharge) and long-term (median = 358 days after hospital discharge). Plasma miRNAs were quantified at the short-term evaluation using the gold-standard technique, RT-qPCR. The analyses combined machine learning feature selection techniques with bioinformatic investigations. Two additional datasets were incorporated for validation. KEY RESULTS: In the short-term, 84% of the survivors exhibited impaired lung diffusion (DLCO  < 80% of predicted). One year post-discharge, 54.4% of this patient subgroup still presented abnormal DLCO . Four feature selection methods identified two specific miRNAs, miR-9-5p and miR-486-5p, linked to persistent lung dysfunction. The downstream experimentally validated targetome included 1473 genes, with heterogeneous enriched pathways associated with inflammation, angiogenesis and cell senescence. Validation studies using RNA-sequencing and proteomic datasets emphasized the pivotal roles of cell migration and tissue repair in persistent lung dysfunction. The repositioning potential of the miRNA targets was limited. CONCLUSION AND IMPLICATIONS: Our study reveals early mechanistic pathways contributing to persistent lung dysfunction in critical COVID-19 survivors, offering a promising approach for the development of targeted disease-modifying agents.

Estimated Respiratory Syncytial Virus-Related Hospitalizations and Deaths Among Children and Adults in Spain, 2016-2019.

INTRODUCTION: Respiratory syncytial virus (RSV) causes a substantial disease burden among infants. In older children and adults, incidence is underestimated due to nonspecific symptoms and limited standard-of-care testing. We aimed to estimate RSV-attributable hospitalizations and deaths in Spain during 2016-2019. METHODS: Nationally representative hospitalization and mortality databases were obtained from the Ministry of Health and the National Statistical Office. A quasi-Poisson regression model was fitted to estimate the number of hospitalizations and deaths attributable to RSV as a function of periodic and aperiodic time trends and viral activity, while allowing for potential overdispersion. RESULTS: In children, the RSV-attributable respiratory hospitalization incidence was highest among infants aged 0-5 months (3998-5453 cases/100,000 person-years, representing 72% of all respiratory hospitalizations) and decreased with age. In 2019, estimated rates in children 0-5, 6-11, 12-23 months and 6-17 years were approximately 1.3, 1.4, 1.5, and 6.5 times higher than those based on standard-of-care RSV-specific codes. In adults, the RSV-attributable cardiorespiratory hospitalization rate increased with age and was highest among persons ≥ 80 years (1325-1506 cases/100,000, 6.5% of all cardiorespiratory hospitalizations). In 2019, for persons aged 18-49, 50-59, 60-79, and ≥ 80 years, estimated rates were approximately 8, 6, 8, and 16 times higher than those based on standard-of-care RSV-specific codes. The RSV-attributable cardiorespiratory mortality rate was highest among ≥ 80 age group (126-150 deaths/100,000, 3.5-4.1% of all cardiorespiratory deaths), when reported mortality rate ranged between 0 and 0.5/100,000. CONCLUSIONS: When accounting for under-ascertainment, estimated RSV-attributable hospitalizations were higher than those reported based on standard-of-care RSV-specific codes in all age groups but particularly among older children and older adults. Like other respiratory viruses, RSV contributes to both respiratory and cardiovascular complications. Efficacious RSV vaccines could have a high public health impact in these age and risk groups.