Bayesian predictors of very poor health related quality of life and mortality in patients with COPD

Predicting 6-minute walking test outcomes in patients with chronic obstructive pulmonary disease without physical performance measures

BACKGROUND AND OBJECTIVE

Chronic obstructive pulmonary disease (COPD) requires a multifactorial assessment, evaluating the airflow limitation and symptoms of the patients. The 6-min walk test (6MWT) is commonly used to evaluate the functional exercise capacity in these patients. This study aims to propose a novel predictive model of the major 6MWT outcomes for COPD assessment, without physical performance measurements.

METHODS

Cardiopulmonary and clinical parameters were obtained from fifty COPD patients. These parameters were used as inputs of a Bayesian network (BN), which integrated three multivariate models including the 6-min walking distance (6MWD), the maximum HR (HR_max) after the walking, and the HR decay 3 min after (HRR₃). The use of BN allows the assessment of the patients' status by predicting the 6MWT outcomes, but also inferring disease severity parameters based on actual patient's 6MWT outcomes.

RESULTS

Firstly, the correlation obtained between the estimated and actual 6MWT measures was strong (R = 0.84, MAPE = 8.10% for HR_max) and moderate (R = 0.58, MAPE = 15.43% for 6MWD and R = 0.58, MAPE = 32.49% for HRR₃), improving the classical methods to estimate 6MWD. Secondly, the classification of disease severity showed an accuracy of 78.3% using three severity groups, which increased up to 84.4% for two defined severity groups.

CONCLUSIONS

We propose a powerful two-way assessment tool for COPD patients, capable of predicting 6MWT outcomes without the need for an actual walking exercise. This model-based tool opens the way to implement a continuous monitoring system for COPD patients at home and to provide more personalized care.

Forecast the Exacerbation in Patients of Chronic Obstructive Pulmonary Disease with Clinical Indicators Using Machine Learning Techniques

Preventing exacerbation and seeking to determine the severity of the disease during the hospitalization of chronic obstructive pulmonary disease (COPD) patients is a crucial global initiative for chronic obstructive lung disease (GOLD); this option is available only for stable-phase patients. Recently, the assessment and prediction techniques that are used have been determined to be inadequate for acute exacerbation of chronic obstructive pulmonary disease patients. To magnify the monitoring and treatment of acute exacerbation COPD patients, we need to rely on the AI system, because traditional methods take a long time for the prognosis of the disease. Machine-learning techniques have shown the capacity to be effectively used in crucial healthcare applications. In this paper, we propose a voting ensemble classifier with 24 features to identify the severity of chronic obstructive pulmonary disease patients. In our study, we applied five machine-learning classifiers, namely random forests (RF), support vector machine (SVM), gradient boosting machine (GBM), XGboost (XGB), and K-nearest neighbor (KNN). These classifiers were trained with a set of 24 features. After that, we combined their results with a soft voting ensemble (SVE) method. Consequently, we found performance measures with an accuracy of 91.0849%, a precision of 90.7725%, a recall of 91.3607%, an F-measure of 91.0656%, and an AUC score of 96.8656%, respectively. Our result shows that the SVE classifier with the proposed twenty-four features outperformed regular machine-learning-based methods for chronic obstructive pulmonary disease (COPD) patients. The SVE classifier helps respiratory physicians to estimate the severity of COPD patients in the early stage, consequently guiding the cure strategy and helps the prognosis of COPD patients.

The Impact of Pursed-lips Breathing Maneuver on Cardiac, Respiratory, and Oxygenation Parameters in COPD Patients

BACKGROUND

Respiratory system, together with the cardiovascular and central nervous system, is responsible for all processes related to oxygenation and hemodynamics and the defect in the functioning of each of these systems, along with ageing, can have mutual effects on their performance and physiological symptoms. The use of Pursed-lips Breathing (PLB) training is an essential part of the treatment of patients with the obstructive pulmonary disease, PLB stimulates the autonomic nervous system and causes relaxation and improvement of physiological parameters.

AIM

This study was conducted to evaluate the effect of PLB on cardiac, pulmonary and oxygenation level in patients with Chronic Obstructive Pulmonary Disease (COPD).

METHODS

A three-group clinical trial study with experimental and control which was purposefully conducted with the participation of patients with COPD and healthy individuals referring to Madani hospital Khoy, in 2017. The sample size was selected to be 60 subjects. The patients were randomly allocated to two groups of intervention and control with 20 patients, and 20 healthy subjects were assigned to the healthy intervention group. The demographic, anthropometric information form and checklist recording changes in levels of oxygenation, respiration, temperature, heart rate and blood pressure with cardiopulmonary follow up in three stages before, during and after PLB were used for data collection. Data were analysed using descriptive statistics, repeated measure test, ANOVA, and Chi-square.

RESULTS

On evaluation within the COPD patient intervention group in Saturation of Peripheral Oxygen (SPO₂) index with the mean difference of 2.05 percent, Respiratory Rate(RR)-0.65 minute and Pulse Rate(PR)-1.6 bpm was significant (p ≤ 0.05), and systolic blood pressure index in healthy subjects was increased (3.35 mmHg).

CONCLUSION

The results of this study indicated that using effective PLB as an easy, inexpensive, non- invasive and non-pharmacological method is considered as an important factor in improving the status of oxygenation and physiological indicators in patients with COPD and should be considered as an important part of rehabilitation programs for these patients.

Effect of Aerobic Exercises on Serum Levels of Apolipoprotein A1 and Apolipoprotein B, and Their Ratio in Patients with Chronic Obstructive Pulmonary Disease

BACKGROUND

Cardiovascular disease is one of the most common disorders associated with chronic obstructive pulmonary disease (COPD). There are few studies on the effects of physical exercises, especially aerobic exercises, on serum levels of apolipoprotein A1 and apolipoprotein B in patients with COPD. The current study aimed at determining the effect of aerobic exercises on serum levels of apolipoprotein A1 and B and apo-A1/apo-B ratio.

MATERIALS AND METHODS

In the current randomized, controlled, clinical trial, with a pretest posttest control group design, 22 males with COPD were randomly assigned to the aerobic exercise and control groups. The aerobic exercise program was performed within two months based on three 30-40-minute sessions per week. Serum levels were measured and evaluated before and after aerobic exercises. Data were analyzed using the paired samples t test.

RESULTS

In the aerobic exercise group, the mean of Apo A1 and Apo B after the intervention (169.36±5.42 and 93.63±5.24 mg/dL, respectively) was significantly higher than that of before the intervention (146±6.09 and 83.27±4.44 mg/dL, respectively) (P-value=0.001). However, apoA1/Apo B ratio did not significantly change after the intervention compared with that of before the intervention (1.85±0.10 vs. 1.80±0.13) (P >0.05). There was no significant change in the mean Apo A1 and Apo B levels and Apo A1/Apo B ratio after the intervention in the control group.

CONCLUSION

Regular aerobic physical exercises are effective in increasing the serum level of Apo A1 in patients with COPD. Due to the proven protective role of Apo A1 in patients with COPD, this biomarker can improve respiratory efficacy in such patients.

Context Relevant Prediction Model for COPD Domain Using Bayesian Belief Network

In the last three decades, researchers have examined extensively how context-aware systems can assist people, specifically those suffering from incurable diseases, to help them cope with their medical illness. Over the years, a huge number of studies on Chronic Obstructive Pulmonary Disease (COPD) have been published. However, how to derive relevant attributes and early detection of COPD exacerbations remains a challenge. In this research work, we will use an efficient algorithm to select relevant attributes where there is no proper approach in this domain. Such algorithm predicts exacerbations with high accuracy by adding discretization process, and organizes the pertinent attributes in priority order based on their impact to facilitate the emergency medical treatment. In this paper, we propose an extension of our existing Helper Context-Aware Engine System (HCES) for COPD. This project uses Bayesian network algorithm to depict the dependency between the COPD symptoms (attributes) in order to overcome the insufficiency and the independency hypothesis of naïve Bayesian. In addition, the dependency in Bayesian network is realized using TAN algorithm rather than consulting pneumologists. All these combined algorithms (discretization, selection, dependency, and the ordering of the relevant attributes) constitute an effective prediction model, comparing to effective ones. Moreover, an investigation and comparison of different scenarios of these algorithms are also done to verify which sequence of steps of prediction model gives more accurate results. Finally, we designed and validated a computer-aided support application to integrate different steps of this model. The findings of our system HCES has shown promising results using Area Under Receiver Operating Characteristic (AUC = 81.5%).

Relationship between polycythemia and in-hospital mortality in chronic obstructive pulmonary disease patients with low-risk pulmonary embolism

BACKGROUNDS

Pulmonary embolism (PE) is frequent in subjects with chronic obstructive pulmonary disease (COPD) and associated with high mortality. This multi-center retrospective study was performed to investigate if secondary polycythemia is associated with in-hospital mortality in COPD patients with low-risk PE.

METHODS

We identified COPD patients with proven PE between October, 2005 and October, 2015. Patients in risk classes III-V on the basis of the PESI score were excluded. We extracted demographic, clinical and laboratory information at the time of admission from medical records. All subjects were followed until hospital discharge to identify all-cause mortality.

RESULTS

We enrolled 629 consecutive patients with COPD and PE at low risk: 132 of them (21.0%) with and 497 (79.0%) without secondary polycythemia. Compared with those without polycythemia, the polycythemia group had significantly lower forced expiratory volume in one second (FEV₁) level (0.9±0.3 vs. 1.4±0.5, P=0.000), lower PaO₂ and SpO₂ as well as higher PaCO₂ (P=0.03, P=0.03 and P=0.000, respectively). COPD patients with polycythemia had a higher proportion of arrhythmia in electrocardiogram (ECG) (49.5% vs. 35.7%, P=0.02), a longer hospital duration time (15.3±10.1 vs. 9.7±9.1, P=0.001), a higher mechanical ventilation rate (noninvasive and invasive, 51.7% vs. 30.3%, P=0.04 and 31.0% vs. 7.9%, P=0.04, respectively), and a higher in-hospital mortality (12.1% vs. 6.6%, P=0.04). Multivariate logistic regression analysis revealed that polycythemia was associated with mortality in COPD patients with low-risk PE (adjusted OR 1.11; 95% CI, 1.04-1.66).

CONCLUSIONS

Polycythemia is an independent risk factor for all-cause in-hospital mortality in COPD patients with PE at low risk.

Hyperuricemia is a biomarker of early mortality in patients with chronic obstructive pulmonary disease

Patients with chronic obstructive pulmonary disease (COPD) are often at high risk of early death. Identification of prognostic biomarkers for COPD may aid in improving their survival by providing early strengthened therapy for high-risk patients. In the present study, we investigated the prognostic role of hyperuricemia at baseline on the prognosis of patients with COPD. Thirty-four patients with COPD with hyperuricemia were matched (1:2) to 68 patients with COPD without hyperuricemia and of similar age and sex. Data from those patients with COPD were evaluated retrospectively. The role of hyperuricemia on mortality was first analyzed using the Kaplan-Meier method, and multivariate Cox regression model was then used to evaluate the prognostic significance of hyperuricemia in patients with COPD. Hyperuricemia was not associated with other baseline characteristics in patients with COPD. Kaplan-Meier survival curve showed that patients with COPD with hyperuricemia had higher risk of mortality compared with patients with normouricemia, and the P-value for log-rank test was 0.005. In univariate analysis, hyperuricemia was associated with higher risk of mortality in patients with COPD (hazard ratio =2.29, 95% CI =1.07-4.88, P=0.032). In the multivariate analysis, hyperuricemia was independently associated with higher risk of mortality in patients with COPD (hazard ratio =2.68, 95% CI =1.18-6.09, P=0.019). In conclusion, hyperuricemia is a promising biomarker of early mortality in patients with COPD.

Co-morbidities are the key nominators of the health related quality of life in mild and moderate COPD

Background

Co-morbidities are common in chronic obstructive pulmonary disease (COPD). We assessed the contribution of common co-morbidities on health related quality of life (HRQoL) among COPD patients.

Methods

Using both generic (15D) and respiratory-specific (AQ20) instruments, HRQoL was assessed in a hospital based COPD population (N = 739, 64% males, mean age 64 years, SD 7 years) in this observational study with inferential analysis. The prevalence of their co-morbidities was compared with those of 5000 population controls. The patients represented all severity stages of COPD and the patterns of common concomitant disorders differed between patients.

Results

Co-morbidities such as psychiatric conditions, alcohol abuse, cardiovascular diseases, and diabetes were more common among COPD patients than in age and gender matched controls. Psychiatric conditions and alcohol abuse were the strongest determinants of HRQoL in COPD and could be detected by both 15D (Odds Ratio 4.7 and 2.3 respectively) and AQ20 (OR 2.0 and 3.0) instruments. Compared to respiratory specific AQ20, generic 15D was more sensitive to the effects of comorbidities while AQ20 was slightly more sensitive for the low FEV₁. FEV₁ was a strong determinant of HRQoL only at more severe stages of disease (FEV₁ < 40% of predicted). Poor HRQoL also predicted death during the next five years.

Conclusions

The results suggest that co-morbidities may impair HRQoL at an early stage of the disease, while bronchial obstruction becomes a significant determinant of HRQoL only in severe COPD.

Clinical characteristics and prognostic significance of chronic obstructive pulmonary disease in patients with atrial fibrillation: results from a multicenter atrial fibrillation registry study

OBJECTIVES

Atrial fibrillation (AF) and chronic obstructive pulmonary disease (COPD) are 2 common morbidities and often coexist. Studies have shown that COPD is a risk factor for cardiovascular disease, but the characteristics in patients with COPD and AF, as well as the impact of COPD on the outcomes of AF were lacking. The aim of present study was to analyze the clinical characteristics and to evaluate the association of COPD with 1-year outcomes in patients with AF.

DESIGN

Longitudinal observational study.

PARTICIPANTS

A total of 1975 consecutive patients with AF were registered. Patients were divided into COPD group and non-COPD group according to whether AF coexisted with COPD.

MEASUREMENTS

Outcome measures included all-cause mortality, stroke, and major adverse events (MAE) during 1-year follow-up.

RESULTS

A group of 227 (11.5%) patients had concomitant COPD. Compared with non-COPD patients, patients with COPD were older and tended to have other coexisting cardiovascular morbidities, and had a significantly higher percentage of smoking history. Anticoagulation with warfarin was adopted by only a few patients both with and without COPD. During 1-year follow-up, the all-cause mortality and major adverse event rate in the COPD group were significantly higher than that of non-COPD group (26.9% vs 12.3%, P < .001 and 25.6% vs 19.1%, P = .027, respectively), whereas the incidence of stroke in the 2 groups was comparable (7.9% vs 7.4%, P = .788). Moreover, the cause-specific mortality between the 2 groups was comparable. After multivariate adjustments, COPD was still an independent risk factor for both 1-year all-cause mortality [hazard rate (HR) = 1.491, 95% confidence interval (CI) 1.110-2.002, P = .008] and cardiovascular mortality (HR = 1.595, 95% CI 1.071-2.376, P = .022), but not a risk factor for stroke (HR = 0.879, 95% CI 0.527-1.464, P = .620).

CONCLUSIONS

Anticoagulation treatment is inadequate in patients with AF and COPD. The presence of COPD in patients with AF is an independent risk factor for 1-year all-cause mortality and cardiovascular mortality but not a risk factor for stroke.