Machine learning-based prediction of COVID-19 mortality using immunological and metabolic biomarkers.

COVID-19 mortality prediction Background COVID-19 has become a major global public health problem, despite prevention and efforts. The daily number of COVID-19 cases rapidly increases, and the time and financial costs associated with testing procedure are burdensome. Method To overcome this, we aim to identify immunological and metabolic biomarkers to predict COVID-19 mortality using a machine learning model. We included inpatients from Hong Kong's public hospitals between January 1, and September 30, 2020, who were diagnosed with COVID-19 using RT-PCR. We developed three machine learning models to predict the mortality of COVID-19 patients based on data in their electronic medical records. We performed statistical analysis to compare the trained machine learning models which are Deep Neural Networks (DNN), Random Forest Classifier (RF) and Support Vector Machine (SVM) using data from a cohort of 5,059 patients (median age = 46 years; 49.3% male) who had tested positive for COVID-19 based on electronic health records and data from 532,427 patients as controls. Result We identified top 20 immunological and metabolic biomarkers that can accurately predict the risk of mortality from COVID-19 with ROC-AUC of 0.98 (95% CI 0.96-0.98). Of the three models used, our result demonstrate that the random forest (RF) model achieved the most accurate prediction of mortality among COVID-19 patients with age, glomerular filtration, albumin, urea, procalcitonin, c-reactive protein, oxygen, bicarbonate, carbon dioxide, ferritin, glucose, erythrocytes, creatinine, lymphocytes, PH of blood and leukocytes among the most important biomarkers identified. A cohort from Kwong Wah Hospital (131 patients) was used for model validation with ROC-AUC of 0.90 (95% CI 0.84-0.92). Conclusion We recommend physicians closely monitor hematological, coagulation, cardiac, hepatic, renal and inflammatory factors for potential progression to severe conditions among COVID-19 patients. To the best of our knowledge, no previous research has identified important immunological and metabolic biomarkers to the extent demonstrated in our study. Supplementary Information: The online version contains supplementary material available at 10.1186/s44247-022-00001-0.

A territory-wide study on the factors associated with recurrent asthma exacerbations requiring hospitalization in Hong Kong.

BACKGROUND: The real-world relationships between the demographic and clinical characteristics of asthma patients, their prehospitalization management and the frequency of hospitalization due to asthma exacerbation is poorly established. OBJECTIVE: To determine the risk factors of recurrent asthma exacerbations requiring hospitalizations and evaluate the standard of baseline asthma care. METHODS: A territory-wide, multicentre retrospective study in Hong Kong was performed. Medical records of patients aged ≥18 years admitted to 11 acute general hospitals from January 1 to December 31, 2016 for asthma exacerbations were reviewed. RESULTS: There were 2280 patients with 3154 admissions (36.7% male, median age 66.0 [interquartile range: 48.0-81.0] years, 519 had ≥2 admissions). Among them, 1830 (80.3%) had at least one asthma-associated comorbidity, 1060 (46.5%) and 885 (38.9%) of patients had Accident and Emergency Department (AED) attendance and hospitalization in the preceding year, respectively. Patients with advancing age (incidence rate ratio [IRR]: 1.003 for every year increment), a history of AED visits or hospitalization (IRR: 1.018 and 1.070 for every additional episode, respectively) for asthma exacerbation in the preceding year, the presence of neuropsychiatric (IRR: 1.142) and gastrointestinal (IRR: 1.154) comorbidities were risk factors for an increasing number of admissions for asthma exacerbation. For patients with ≥2 admissions, 17.1% were not prescribed inhaled corticosteroid and only 44.6% had spirometry checked before the index admission. Asthma phenotyping was often incomplete, as assessment of atopy (total serum immunoglobulin E level and senitization to aeroallergens) was only performed in 30 (5.8%) patients with ≥2 admissions. CONCLUSIONS AND CLINICAL RELEVANCE: Improving asthma care, especially in elderly patients with a prior history of urgent healthcare utilization and comorbidities, may help reduce healthcare burden. Suboptimal management before the index admission was common in patients hospitalized for asthma exacerbations. Early identification of patients at risk and enhancement of baseline asthma management may help to prevent recurrent asthma exacerbation and subsequent hospitalization.

Accuracy of forced oscillation technique to assess lung function in geriatric COPD population.

INTRODUCTION: Performing lung function test in geriatric patients has never been an easy task. With well-established evidence indicating impaired small airway function and air trapping in patients with geriatric COPD, utilizing forced oscillation technique (FOT) as a supplementary tool may aid in the assessment of lung function in this population. AIMS: To study the use of FOT in the assessment of airflow limitation and air trapping in geriatric COPD patients. STUDY DESIGN: A cross-sectional study in a public hospital in Hong Kong. ClinicalTrials.gov ID: NCT01553812. METHODS: Geriatric patients who had spirometry-diagnosed COPD were recruited, with both FOT and plethysmography performed. "Resistance" and "reactance" FOT parameters were compared to plethysmography for the assessment of air trapping and airflow limitation. RESULTS: In total, 158 COPD subjects with a mean age of 71.9±0.7 years and percentage of forced expiratory volume in 1 second of 53.4±1.7 L were recruited. FOT values had a good correlation (r=0.4-0.7) to spirometric data. In general, X values (reactance) were better than R values (resistance), showing a higher correlation with spirometric data in airflow limitation (r=0.07-0.49 vs 0.61-0.67), small airway (r=0.05-0.48 vs 0.56-0.65), and lung volume (r=0.12-0.29 vs 0.43-0.49). In addition, resonance frequency (Fres) and frequency dependence (FDep) could well identify the severe type (percentage of forced expiratory volume in 1 second <50%) of COPD with high sensitivity (0.76, 0.71) and specificity (0.72, 0.64) (area under the curve: 0.8 and 0.77, respectively). Moreover, X values could stratify different severities of air trapping, while R values could not. CONCLUSION: FOT may act as a simple and accurate tool in the assessment of severity of airflow limitation, small and central airway function, and air trapping in patients with geriatric COPD who have difficulties performing conventional lung function test. Moreover, reactance parameters were better than resistance parameters in correlation with air trapping.

Frequent Exacerbator: The Phenotype at Risk of Depressive Symptoms in Geriatric COPD Patients.

INTRODUCTION: Depression is associated with a poorer quality of life and higher rate of COPD exacerbations and mortality. However, with multiple confounding factors, 'independent' risk factor for depression among COPD patients remains ambiguous. Our study aims to identify independent risk factors for depression by specifically evaluating for any independent relationship between frequent exacerbations and various domains of the BODE index on depression. METHODS: This study is a cross-sectional study, conducted in Hong Kong SAR. Age and comorbidity-matched COPD and control subjects were recruited. Depressive symptoms were measured by a validated Chinese version of the Geriatric Depression Scale (GDS-15 items). Prevalence rates of depressive symptoms were compared between COPD and control groups. Predictors for depression (GDS ≥ 8) were determined using univariate and multivariate analyses. RESULTS: A total of 161 patients (89 and 72 patients, mean ages 75.2 and 75.6 in COPD and control group, respectively) were recruited. Higher prevalence rate of significant depressive symptoms was seen in COPD patients (20.2 vs. 4.2 %, p = 0.006*). Univariate analysis suggested that predictors for depression in COPD patients included (i) exacerbation frequencies in prior year, (ii) dyspnea level, (iii) BMI, (iv) functional status (Barthel index, 6MWD, activity domain of SGRQ), and (v) BODE index. In multivariate analysis, only the 'exacerbation frequencies in prior year' (OR 1.46, p = 0.042*) and 'dyspnea level' (MMRC) (OR 2.75, p = 0.001*) remained significant independent predictors for depression in COPD patients. CONCLUSIONS: A high prevalence of depressive symptoms was observed in COPD patients. 'Frequent exacerbation phenotype' remained a significant independent predictor for depressive symptoms in COPD. Among the BODE index domains, dyspnea level is the most important predictor for depression in COPD patients.

Update on the pathological processes, molecular biology, and clinical utility of N-acetylcysteine in chronic obstructive pulmonary disease.

Chronic obstructive pulmonary disease (COPD) is a common and morbid disease characterized by high oxidative stress. Its pathogenesis is complex, and involves excessive oxidative stress (redox imbalance), protease/antiprotease imbalance, inflammation, apoptosis, and autoimmunity. Among these, oxidative stress has a pivotal role in the pathogenesis of COPD by initiating and mediating various redox-sensitive signal transduction pathways and gene expression. The protective physiological mechanisms of the redox balance in the human body, their role in the pathogenesis of COPD, and the clinical correlation between oxidative stress and COPD are reviewed in this paper. N-acetylcysteine (NAC) is a mucolytic agent with both antioxidant and anti-inflammatory properties. This paper also reviews the use of NAC in patients with COPD, especially the dose-dependent properties of NAC, eg, its effects on lung function and the exacerbation rate in patients with the disease. Earlier data from BRONCUS (the Bronchitis Randomized on NAC Cost-Utility Study) did not suggest that NAC was beneficial in patients with COPD, only indicating that it reduced exacerbation in an "inhaled steroid-naïve" subgroup. With regard to the dose-dependent properties of NAC, two recent randomized controlled Chinese trials suggested that high-dose NAC (1,200 mg daily) can reduce exacerbations in patients with COPD, especially in those with an earlier (moderately severe) stage of disease, and also in those who are at high risk of exacerbations. However, there was no significant effect on symptoms or quality of life in patients receiving NAC. Further studies are warranted to investigate the effect of NAC at higher doses in non-Chinese patients with COPD.

Benefits of high-dose N-acetylcysteine to exacerbation-prone patients with COPD.

BACKGROUND: Although high-dose N-acetylcysteine (NAC) has been suggested to reduce COPD exacerbations, it is unclear which category of patients with COPD would benefit most from NAC treatment. The objective of this study was to compare the effect of high-dose NAC (600 mg bid) between high-risk and low-risk Chinese patients with COPD. METHODS: Patients with spirometry-confirmed stable COPD were randomized to treatment with either NAC 600 mg bid or placebo in addition to their usual treatments. Patients were followed up every 16 weeks for a total of 1 year. Further analysis was performed according to each patient's exacerbation risk at baseline as defined by the current GOLD (Global Initiative for Chronic Obstructive Lung Disease) strategy to analyze the effect of high-dose NAC in high-risk and low-risk patients. RESULTS: Of the 120 patients with COPD randomized (men, 93.2%; mean age, 70.8 ± 0.74 years; prebronchodilator FEV1, 53.9 ± 2.0%; baseline characteristics comparable between treatment groups), 108 (NAC, 52; placebo, 56) completed the 1-year study. For high-risk patients (n = 89), high-dose NAC compared with placebo significantly reduced exacerbation frequency (0.85 vs 1.59 [P = .019] and 1.08 vs 2.22 [P = .04] at 8 and 12 months, respectively), prolonged time to first exacerbation (P = .02), and increased the probability of being exacerbation free at 1 year (51.3% vs 24.4%, P = .013). This beneficial effect of high-dose NAC vs placebo was not significant in low-risk patients. CONCLUSIONS: High-dose NAC (600 mg bid) for 1 year reduces exacerbations and prolongs time to first exacerbation in high-risk but not in low-risk Chinese patients with COPD. TRIAL REGISTRY: ClinicalTrials.gov; No.: NCT01136239; URL: www.clinicaltrials.gov.