Novel Machine Learning Identifies 5 Asthma Phenotypes Using Cluster Analysis of Real-World Data.

BACKGROUND: Asthma classification into different subphenotypes is important to guide personalized therapy and improve outcomes. OBJECTIVES: To further explore asthma heterogeneity through determination of multiple patient groups by using novel machine learning (ML) approaches and large-scale real-world data. METHODS: We used electronic health records of patients with asthma followed at the Cleveland Clinic between 2010 and 2021. We used k-prototype unsupervised ML to develop a clustering model where predictors were age, sex, race, body mass index, prebronchodilator and postbronchodilator spirometry measurements, and the usage of inhaled/systemic steroids. We applied elbow and silhouette plots to select the optimal number of clusters. These clusters were then evaluated through LightGBM's supervised ML approach on their cross-validated F1 score to support their distinctiveness. RESULTS: Data from 13,498 patients with asthma with available postbronchodilator spirometry measurements were extracted to identify 5 stable clusters. Cluster 1 included a young nonsevere asthma population with normal lung function and higher frequency of acute exacerbation (0.8 /patient-year). Cluster 2 had the highest body mass index (mean ± SD, 44.44 ± 7.83 kg/m2), and the highest proportion of females (77.5%) and Blacks (28.9%). Cluster 3 comprised patients with normal lung function. Cluster 4 included patients with lower percent of predicted FEV1 of 77.03 (12.79) and poor response to bronchodilators. Cluster 5 had the lowest percent of predicted FEV1 of 68.08 (15.02), the highest postbronchodilator reversibility, and the highest proportion of severe asthma (44.9%) and blood eosinophilia (>300 cells/µL) (34.8%). CONCLUSIONS: Using real-world data and unsupervised ML, we classified asthma into 5 clinically important subphenotypes where group-specific asthma treatment and management strategies can be designed and deployed.

Vaccination for COVID-19: Is it important and what should you know about it?

An effective vaccine is considered the best method to achieve herd immunity. As of February 2021, 12 vaccines were in late-stage clinical trials worldwide, with many more in development. Of those, 8 have received emergency use authorization from at least one country's governing body. These vaccines use various platforms to deliver the vaccines, each with pros and cons. Published data show these vaccines are effective in preventing the severe symptoms associated with COVID-19 in adults with few side effects, but challenges remain with storage and delivery and treating virus variants.

Novel Machine Learning Can Predict Acute Asthma Exacerbation.

BACKGROUND: Asthma exacerbations result in significant health and economic burden, but are difficult to predict. RESEARCH QUESTION: Can machine learning (ML) models with large-scale outpatient data predict asthma exacerbations? STUDY DESIGN AND METHODS: We analyzed data extracted from electronic health records (EHRs) of asthma patients treated at the Cleveland Clinic from 2010 through 2018. Demographic information, comorbidities, laboratory values, and asthma medications were included as covariates. Three different models were built with logistic regression, random forests, and a gradient boosting decision tree to predict: (1) nonsevere asthma exacerbation requiring oral glucocorticoid burst, (2) ED visits, and (3) hospitalizations. RESULTS: Of 60,302 patients, 19,772 (32.8%) had at least one nonsevere exacerbation requiring oral glucocorticoid burst, 1,748 (2.9%) requiring and ED visit and 902 (1.5%) requiring hospitalization. Nonsevere exacerbation, ED visit, and hospitalization were predicted best by light gradient boosting machine, an algorithm used in ML to fit predictive analytic models, and had an area under the receiver operating characteristic curve of 0.71 (95% CI, 0.70-0.72), 0.88 (95% CI, 0.86-0.89), and 0.85 (95% CI, 0.82-0.88), respectively. Risk factors for all three outcomes included age, long-acting ß agonist, high-dose inhaled glucocorticoid, or chronic oral glucocorticoid therapy. In subgroup analysis of 9,448 patients with spirometry data, low FEV1 and FEV1 to FVC ratio were identified as top risk factors for asthma exacerbation, ED visits, and hospitalization. However, adding pulmonary function tests did not improve models' prediction performance. INTERPRETATION: Models built with an ML algorithm from real-world outpatient EHR data accurately predicted asthma exacerbation and can be incorporated into clinical decision tools to enhance outpatient care and to prevent adverse outcomes.

Steroids in COVID-19: An overview.

Most antiviral or immunomodulatory therapies investigated for use in patients with COVID-19 have failed to show any mortality benefit. Similar to the previous pandemics caused by respiratory viruses, the role and benefit of corticosteroids has been under debate in COVID-19-related pulmonary disease. In this consult, we discuss the evidence regarding the efficacy of corticosteroid use in hospitalized patients with COVID-19, including data from the first randomized controlled trial on this subject.

Management of patients with COVID-19 in the MICU.

COVID-19 management practices devised for the medical intensive care unit are centered on 2 main goals: ensuring caregiver safety and providing the highest quality patient care through adherence to evidence-based best practices. Rapid, sweeping changes for successful management are based on creating an educational platform to introduce and then further cement these concepts through a unified approach to clinical care. Creating a culture change in a short period of time requires overcoming a host of challenges; however, the result is a more unified and focused approach.

Recognition and management of respiratory co-infection and secondary bacterial pneumonia in patients with COVID-19.

In COVID-19, respiratory infection with SARS-CoV-2 plus another virus (viral co-infection) or with SARS-CoV-2 plus a bacterial pathogen (combined viral and bacterial pneumonia) has been described. Secondary bacterial pneumonia can follow the initial phase of viral respiratory infection or occur during the recovery phase. No obvious pattern or guidelines exist for viral co-infection, combined viral and bacterial pneumonia, or secondary bacterial pneumonia in COVID-19. Based on existing clinical data and experience with similar viruses such as influenza and SARS-CoV, the management approach in COVID-19 should, ideally, take into consideration the overall presentation and the trajectory of illness.

National Trends in Admission for Aspiration Pneumonia in the United States, 2002-2012.

RATIONALE: Aspiration pneumonia is a subset of pneumonias prevalent in elderly patients and patients with neurologic disorders. Researchers in previous studies mostly reported incidence and/or mortality rates based on regional data or in specific subgroups of patients. There is a paucity of nationwide data in the contemporary U.S. OBJECTIVES: To describe U.S. national trends in acute care hospital admission for aspiration pneumonia from 2002 to 2012. METHODS: We used the U.S. National (Nationwide) Inpatient Sample database to identify patients admitted with a primary diagnosis of aspiration pneumonia between 2002 and 2012. We estimated trends in the incidence, in-hospital mortality, length of stay, and total hospitalization cost for patients admitted for aspiration pneumonia and stratified on the basis of patient age (≥65 yr vs. <65 yr). Multivariable logistic regression analysis was used to identify independent predictors for in-hospital mortality. RESULTS: A total of 406,798 patients (weighted total, 1,741,517) admitted for aspiration pneumonia were included in this study. There were 84,200 (20.7%) patients younger than 65 years of age and 322,598 patients (79.3%) aged 65 years or older. From 2002 to 2012, the overall incidence of aspiration pneumonia decreased from 8.2 to 7.1 cases per 10,000 people, and in-hospital mortality decreased from 18.6 to 9.8%. For patients aged 65 years or older, the incidence decreased from 40.7 to 30.9 cases per 10,000 people, and the in-hospital mortality decreased from 20.7 to 11.3%. The median total hospitalization charges increased in both groups (age ≥65 yr, from $16,173 to $30,280; age <65 yr, from $17,517 to $30,526). In multivariable logistic analysis, patients aged 65 years or older or treatment in a nonteaching hospital were independent predictors of in-hospital mortality. CONCLUSIONS: The incidence and mortality of patients admitted to acute care hospitals for aspiration pneumonia decreased between 2002 and 2012 in the United States. This difference was more evident for elderly patients. However, the cost of hospitalization almost doubled. Being older than 65 years of age is an independent predictor of in-hospital mortality among patients admitted for aspiration pneumonia. Strategies to prevent aspiration pneumonia in the community should be implemented in the aging U.S.