ABSTRACT
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.
ABSTRACT
Respiratory infection is the most frequent and characteristic infectious comorbidity in patients with chronic obstructive pulmonary disease (COPD) and can lead to two clinical scenarios. The first and most common is exacerbation, although not all exacerbations are caused by infections, which account for 50-70% of these processes. The second scenario is pneumonia, since COPD is the most frequent comorbidity associated with the development of pneumonia. Of the infectious agents causing exacerbations, 50-60% of cases correspond to bacteria, which are the most widely studied microorganisms and whose role is becoming increasingly notorious. Among bacteria, a greater number of Pseudomonas aeruginosa and more aggressive microorganisms are being isolated in exacerbations. A second cause of infectious exacerbations are viruses, which seem to play an important role in these processes, although less so than bacteria. Viral infections seem to predispose many patients to a subsequent bacterial infection. Community-acquired pneumonia (CAP) is highly common in patients with COPD and between 25 and 50% of patients hospitalized with this diagnosis have COPD. Nevertheless, COPD has not been considered as a risk factor for poor outcome in patients with CAP and the Pneumonia Severity Index (PSI) showed that COPD was not among the comorbidities associated with mortality at 30 days. Although some studies have recently associated COPD with increased mortality, this association is questionable and the possible improved outcome could be due to the use of systemic corticosteroids in most patients with COPD.
