RESUMO
Tools for predicting COVID-19 outcomes enable personalized healthcare, potentially easing the disease burden. This collaborative study by 15 institutions across Europe aimed to develop a machine learning model for predicting the risk of in-hospital mortality post-SARS-CoV-2 infection. Blood samples and clinical data from 1286 COVID-19 patients collected from 2020 to 2023 across four cohorts in Europe and Canada were analyzed, with 2906 long non-coding RNAs profiled using targeted sequencing. From a discovery cohort combining three European cohorts and 804 patients, age and the long non-coding RNA LEF1-AS1 were identified as predictive features, yielding an AUC of 0.83 (95% CI 0.82-0.84) and a balanced accuracy of 0.78 (95% CI 0.77-0.79) with a feedforward neural network classifier. Validation in an independent Canadian cohort of 482 patients showed consistent performance. Cox regression analysis indicated that higher levels of LEF1-AS1 correlated with reduced mortality risk (age-adjusted hazard ratio 0.54, 95% CI 0.40-0.74). Quantitative PCR validated LEF1-AS1's adaptability to be measured in hospital settings. Here, we demonstrate a promising predictive model for enhancing COVID-19 patient management.
Assuntos
COVID-19 , Mortalidade Hospitalar , Aprendizado de Máquina , RNA Longo não Codificante , SARS-CoV-2 , Humanos , COVID-19/mortalidade , COVID-19/virologia , COVID-19/genética , Masculino , Feminino , Idoso , RNA Longo não Codificante/genética , Pessoa de Meia-Idade , SARS-CoV-2/genética , SARS-CoV-2/isolamento & purificação , Europa (Continente)/epidemiologia , Canadá/epidemiologia , Estudos de Coortes , Idoso de 80 Anos ou mais , AdultoRESUMO
OBJECTIVE: There is a need to increase patient and clinician awareness on the effectiveness of pneumococcal vaccination in at-risk groups. The aim of the study was to evaluate the effect of reminders for physicians and patients using the vaccination tracking system created in the hospital information management system (HIMS) on the vaccination rate, and the effect of pneumococcal vaccination on pneumonia-related hospitalization and mortality over a 12-month period. MATERIAL AND METHODS: This prospective observational cohort study was undertaken during a 2-year period in 3 tertiary care centers. Patients were followed up for 12 months following vaccination, and hospital admissions and mortality were recorded via HIMS. During the campaign, HIMS transmitted pneumococcal immunization reminder messages in accordance with guideline recommendations to physicians' computers and patients' mobile phones. Educational posters on pneumococcal vaccination were posted in outpatient clinics. Regular seminars on the evidence for pneumococcal vaccination were organized. All patients who were hospitalized during the follow-up period for chronic obstructive pulmonary disease (COPD), asthma, lung cancer, or pneumonia were analyzed in relation to their vaccination history regarding clinical outcomes. RESULTS: A total of 29530 patients were included in the study. During the study period, the annual vaccination rate increased by 74.4% and reached 4.8% in 3 hospitals (P = .001). The rates were 3.9% in patients older than 65 years without comorbidities and 5.2% in those with COPD and asthma (P = .002). In pneumococcal vaccine recipients, pneumonia-related hospital mortality was lower (relative risk (RR) = 0.19, CI 0.09-0.35, P < .001). CONCLUSION: It is possible to raise the rate of pneumococcal vaccination through awareness campaigns. Individuals with COPD and asthma are more willing to receive pneumococcal vaccination. Among patients hospitalized for pneumonia, prior pneumococcal vaccination is associated with lower mortalit.