Applicability of an unsupervised cluster model developed on first wave COVID-19 patients in second/third wave critically ill patients.

OBJECTIVE: To validate the unsupervised cluster model (USCM) developed during the first pandemic wave in a cohort of critically ill patients from the second and third pandemic waves. DESIGN: Observational, retrospective, multicentre study. SETTING: Intensive Care Unit (ICU). PATIENTS: Adult patients admitted with COVID-19 and respiratory failure during the second and third pandemic waves. INTERVENTIONS: None. MAIN VARIABLES OF INTEREST: Collected data included demographic and clinical characteristics, comorbidities, laboratory tests and ICU outcomes. To validate our original USCM, we assigned a phenotype to each patient of the validation cohort. The performance of the classification was determined by Silhouette coefficient (SC) and general linear modelling. In a post-hoc analysis we developed and validated a USCM specific to the validation set. The model's performance was measured using accuracy test and area under curve (AUC) ROC. RESULTS: A total of 2330 patients (mean age 63 [53-82] years, 1643 (70.5%) male, median APACHE II score (12 [9-16]) and SOFA score (4 [3-6]) were included. The ICU mortality was 27.2%. The USCM classified patients into 3 clinical phenotypes: A (n = 1206 patients, 51.8%); B (n = 618 patients, 26.5%), and C (n = 506 patients, 21.7%). The characteristics of patients within each phenotype were significantly different from the original population. The SC was -0.007 and the inclusion of phenotype classification in a regression model did not improve the model performance (0.79 and 0.78 ROC for original and validation model). The post-hoc model performed better than the validation model (SC -0.08). CONCLUSION: Models developed using machine learning techniques during the first pandemic wave cannot be applied with adequate performance to patients admitted in subsequent waves without prior validation.

Estimation of the prevalence and incidence of motor neuron diseases in two Spanish regions: Catalonia and Valencia.

According to the degree of upper and lower motor neuron degeneration, motor neuron diseases (MND) can be categorized into amyotrophic lateral sclerosis (ALS), primary lateral sclerosis (PLS) or progressive muscular atrophy (PMA). Although several studies have addressed the prevalence and incidence of ALS, there is a high heterogeneity in their results. Besides this, neither concept has been previously studied in PLS or PMA. Thus, the objective of this study was to estimate the prevalence and incidence of MND, (distinguishing ALS, PLS and PMA), in the Spanish regions of Catalonia and Valencia in the period 2011-2019. Two population-based Spanish cohorts were used, one from Catalonia and the other from Valencia. Given that the samples that comprised both cohorts were not random, i.e., leading to a selection bias, we used a two-part model in which both the individual and contextual observed and unobserved confounding variables are controlled for, along with the spatial and temporal dependence. The prevalence of MND was estimated to be between 3.990 and 6.334 per 100,000 inhabitants (ALS between 3.248 and 5.120; PMA between 0.065 and 0.634; and PLS between 0.046 and 1.896), and the incidence between 1.682 and 2.165 per 100,000 person-years for MND (ALS between 1.351 and 1.754; PMA between 0.225 and 0.628; and PLS between 0.409-0.544). Results were similar in the two regions and did not differ from those previously reported for ALS, suggesting that the proposed method is robust and that neither region presents differential risk or protective factors.