Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

2017 ◽  
Vol 25 (3) ◽  
pp. 811-827 ◽  
Author(s):  
Dimitris Spathis ◽  
Panayiotis Vlamos
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Random Forest ◽  
Pulmonary Disease ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Forced Expiratory Volume ◽  
Random Forest Classifier ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease

This study examines the clinical decision support systems in healthcare, in particular about the prevention, diagnosis and treatment of respiratory diseases, such as Asthma and chronic obstructive pulmonary disease. The empirical pulmonology study of a representative sample (n = 132) attempts to identify the major factors that contribute to the diagnosis of these diseases. Machine learning results show that in chronic obstructive pulmonary disease’s case, Random Forest classifier outperforms other techniques with 97.7 per cent precision, while the most prominent attributes for diagnosis are smoking, forced expiratory volume 1, age and forced vital capacity. In asthma’s case, the best precision, 80.3 per cent, is achieved again with the Random Forest classifier, while the most prominent attribute is MEF2575.

scholarly journals Serum Albumin Concentrations in Stable Chronic Obstructive Pulmonary Disease: A Systematic Review and Meta-Analysis

2021 ◽  
Vol 10 (2) ◽  
pp. 269
Author(s):  
Elisabetta Zinellu ◽  
Alessandro G. Fois ◽  
Elisabetta Sotgiu ◽  
Sabrina Mellino ◽  
Arduino A. Mangoni ◽  
...  
Keyword(s):  
Systematic Review ◽  
Chronic Obstructive Pulmonary Disease ◽  
Serum Albumin ◽  
Pulmonary Disease ◽  
Meta Analysis ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Standard Mean Difference ◽  
Copd Patients

Background: Chronic obstructive pulmonary disease (COPD) is a progressive condition characterized by chronic airway inflammation and lung parenchyma damage. Systemic inflammation and oxidative stress also play a role in the pathogenesis of COPD. Serum albumin is a negative acute-phase protein with antioxidant effects and an important marker of malnutrition. The aim of this meta-analysis was to investigate differences in serum albumin concentrations between patients with stable COPD and non-COPD subjects. Methods: A systematic search was conducted, using the terms “albumin” and “chronic obstructive pulmonary disease” or “COPD”, in the electronic databases PubMed and Web of Science, from inception to May 2020. Results: Twenty-six studies were identified on a total of 2554 COPD patients and 2055 non-COPD controls. Pooled results showed that serum albumin concentrations were significantly lower in COPD patients (standard mean difference, SMD = −0.50, 95% CI −0.67 to −0.32; p < 0.001). No significant differences were observed in SMD of serum albumin concentrations between COPD patients with forced expiratory volume in the 1st second (FEV1) < 50% and those with FEV1 > 50%. Conclusions: Our systematic review and meta-analysis showed that serum albumin concentrations are significantly lower in patients with stable COPD compared to non-COPD controls. This supports the presence of a deficit in systemic anti-inflammatory and antioxidant defense mechanisms in COPD.

Ventilation-perfusion imbalance and chronic obstructive pulmonary disease staging severity

2009 ◽  
Vol 106 (6) ◽  
pp. 1902-1908 ◽  
Author(s):  
Roberto Rodríguez-Roisin ◽  
Mitra Drakulovic ◽  
Diego A. Rodríguez ◽  
Josep Roca ◽  
Joan Albert Barberà ◽  
...  
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Gas Exchange ◽  
Pulmonary Disease ◽  
Forced Expiratory Volume ◽  
Pulmonary Gas Exchange ◽  
Airflow Limitation ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Gold Stage ◽  
Stage 1

Chronic obstructive pulmonary disease (COPD) is characterized by a decline in forced expiratory volume in 1 s (FEV1) and, in many advanced patients, by arterial hypoxemia with or without hypercapnia. Spirometric and gas exchange abnormalities have not been found to relate closely, but this may reflect a narrow range of severity in patients studied. Therefore, we assessed the relationship between pulmonary gas exchange and airflow limitation in patients with COPD across the severity spectrum. Ventilation-perfusion (V̇A/Q̇) mismatch was measured using the multiple inert gas elimination technique in 150 patients from previous studies. The distribution of patients according to the GOLD stage of COPD was: 15 with stage 1; 40 with stage 2; 32 with stage 3; and 63 with stage 4. In GOLD stage 1, AaPo2 and V̇A/Q̇ mismatch were clearly abnormal; thereafter, hypoxemia, AaPo2, and V̇A/Q̇ imbalance increased, but the changes from GOLD stages 1–4 were modest. Postbronchodilator FEV1 was related to PaO2 ( r = 0.62) and PaCO2 ( r = −0.59) and to overall V̇A/Q̇ heterogeneity ( r = −0.48) ( P < 0.001 each). Pulmonary gas exchange abnormalities in COPD are related to FEV1 across the spectrum of severity. V̇A/Q̇ imbalance, predominantly perfusion heterogeneity, is disproportionately greater than airflow limitation in GOLD stage 1, suggesting that COPD initially involves the smallest airways, parenchyma, and pulmonary vessels with minimal spirometric disturbances. That progression of V̇A/Q̇ inequality with spirometric severity is modest may reflect pathogenic processes that reduce both local ventilation and blood flow in the same regions through airway and alveolar disease and capillary involvement.

scholarly journals A machine learning approach to triaging patients with chronic obstructive pulmonary disease

PLoS ONE ◽  
2017 ◽  
Vol 12 (11) ◽  
pp. e0188532 ◽  
Author(s):  
Sumanth Swaminathan ◽  
Klajdi Qirko ◽  
Ted Smith ◽  
Ethan Corcoran ◽  
Nicholas G. Wysham ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Chronic Obstructive ◽  
Learning Approach ◽  
Obstructive Pulmonary Disease ◽  
Machine Learning Approach

Clinical Characterization of Nursing Facility Residents With Chronic Obstructive Pulmonary Disease

2021 ◽  
Vol 36 (5) ◽  
pp. 248-257
Author(s):  
H. Edward Davidson ◽  
Peter Radlowski ◽  
Lisa Han ◽  
Theresa I. Shireman ◽  
Carole Dembek ◽  
...  
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Clinical Characteristics ◽  
Symptom Burden ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
Nursing Facility ◽  
Data Set ◽  
Obstructive Pulmonary Disease ◽  
Medication Delivery

OBJECTIVE AND DESIGN: To describe clinical characteristics, medication use, and low peak inspiratory flow rate (PIFR) (< 60 L/min) prevalence in nursing facility residents with chronic obstructive pulmonary disease (COPD). PATIENTS AND SETTING: Residents 60 years of age and older with a COPD diagnosis and≥ 6 months' nursing facility residence, were enrolled between December 2017 and February 2019 from 26 geographically varied United States nursing facilities. OUTCOME MEASURES: Data, extracted from residents' charts, included demographic/clinical characteristics, COPD-related medications, exacerbations and hospitalizations within the past 6 months, and functional status from the most recent Minimum Data Set. At enrollment, residents completed the modified Medical Research Council (mMRC) Dyspnea Scale and COPD Assessment Test (CAT™). Spirometry and PIFR were also assessed. RESULTS: Residents' (N = 179) mean age was 78.0 ± 10.6 years, 63.7% were female, and 57.0% had low PIFR. Most prevalent comorbidities were hypertension (79.9%), depression (49.2%), and heart failure (41.9%). The average forced expiratory volume in 1 second (FEV11) % predicted was 45.9% ± 20.9%. On the CAT, 78.2% scored≥ 10 and on the mMRC Dyspnea Scale, 74.1% scored≥ 2, indicating most residents had high COPD symptom burden. Only 49.2% were receiving a scheduled long-acting bronchodilator (LABD). Among those with low PIFR prescribed a LABD, > 80% used dry powder inhalers for medication delivery. CONCLUSION: This study highlights underutilization of scheduled LABD therapy in nursing facility residents with COPD. Low PIFR was prevalent in residents while the majority used suboptimal medication delivery devices. The findings highlight opportunities for improving management and outcomes for nursing facility residents with COPD.

Prediction of chronic obstructive pulmonary disease stages using machine learning algorithms

2022 ◽  
Vol 14 (1) ◽  
pp. 0-0
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Predictive Value ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Chronic Obstructive ◽  
Optimal Prediction ◽  
Obstructive Pulmonary Disease ◽  
Disease Stages

Identifying chronic obstructive pulmonary disease (COPD) severity stages is of great importance to control the related mortality rates and reduce the associated costs. This study aims to build prediction models for COPD stages and, to compare the relative performance of five machine learning algorithms to determine the optimal prediction algorithm. This research is based on data collected from a private hospital in Egypt for the two calendar years 2018 and 2019. Five machine learning algorithms were used for the comparison. The F1 score, specificity, sensitivity, accuracy, positive predictive value and negative predictive value were the performance measures used for algorithms comparison. Analysis included 211 patients’ records. Our results show that the best performing algorithm in most of the disease stages is the PNN with the optimal prediction accuracy and hence it can be considered as a powerful prediction tool used by decision makers in predicting severity stages of COPD.

scholarly journals Prognostic and Functional Impact of Perioperative LAＭA/LABA Inhaled Therapy In Patients With Lung Cancer and Chronic Obstructive Pulmonary Disease 

2021 ◽  
Author(s):  
Yoko Azuma ◽  
Atsushi Sano ◽  
Takashi Sakai ◽  
Satoshi Koezuka ◽  
Hajime Otsuka ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Chronic Obstructive Pulmonary Disease ◽  
Postoperative Complications ◽  
Lung Function ◽  
Pulmonary Disease ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Long Acting

Abstract Background: Chronic obstructive pulmonary disease (COPD) is an important risk factor for postoperative complications and mortality. The utility of several perioperative bronchodilators in patients with COPD requiring surgery for lung cancer has been reported, but the most suitable agent and its specific effect on postoperative long-term prognosis remain unclear. To determine the effects of perioperative combination therapy, using a long-acting muscarinic antagonist (LAMA) and a long-acting β2 agonist (LABA), on preoperative lung function, postoperative morbidity and mortality, and long-term outcome in COPD patients.Methods: Between January 2005 and October 2019, 130 consecutive patients with newly diagnosed COPD underwent surgery for lung cancer. We conducted a retrospective review of their medical records. Patients were divided into 3 groups according to perioperative management: LAMA/LABA (n=64), LAMA (n=23) and rehabilitation only (no bronchodilator) (n=43). Results: Patients who received preoperative LAMA/LABA therapy showed significant improvement in lung function before surgery (p<0.001 for both forced expiratory volume in 1 second (FEV1) and percentage of predicted forced expiratory volume in 1 second (FEV1 %pred). Compared with patients who received preoperative LAMA therapy, patients with LAMA/LABA therapy had significantly improved lung function (ΔFEV1, 223.1 mL vs 130.0 mL, ΔFEV1 %pred, 10.8% vs 6.8%; both p<0.05). There was a trend toward a lower incidence of postoperative complications in the LAMA/LABA group compared with the LAMA and rehabilitation-only groups. In patients with moderate to severe air flow limitation (n=61), those who received LAMA/LABA therapy had significantly longer overall survival and disease-free survival compared with patients in the other groups. Perioperative LAMA/LABA therapy was also associated with lower recurrence rates. Conclusions: Patients who receive perioperative LAMA/LABA for moderate to severe COPD have improved prognosis and better pulmonary function with surgery for lung cancer. We believe this treatment combination is optimal for patients with lung cancer and COPD.

scholarly journals Phenotyping of Chronic Obstructive Pulmonary Disease Using the Modified Bhalla Scoring System for High-Resolution Computed Tomography

2013 ◽  
Vol 20 (2) ◽  
pp. 91-96 ◽  
Author(s):  
Baykal Tulek ◽  
Ali Sami Kivrak ◽  
Seda Ozbek ◽  
Fikret Kanat ◽  
Mecit Suerdem
Keyword(s):  
Computed Tomography ◽  
Chronic Obstructive Pulmonary Disease ◽  
High Resolution ◽  
Pulmonary Disease ◽  
Scoring System ◽  
Morphological Changes ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
High Resolution Computed Tomography ◽  
Obstructive Pulmonary Disease

BACKGROUND: Identifying different phenotypes of chronic obstructive pulmonary disease (COPD) is important for both therapeutic options and clinical outcome of the disease.OBJECTIVE: To characterize the phenotypes of COPD according to high-resolution computed tomography (HRCT) findings; and to correlate HRCT scores obtained using the modified Bhalla scoring system with clinical and physiological indicators of systemic inflammation.METHODS: The present study included 80 consecutive patients with stable COPD. HRCT scans were evaluated by two independent radiologists according to the modified Bhalla scoring system.RESULTS: Fifty-four patients exhibited morphological changes on HRCT examination while 26 had no pathological findings. Patients with HRCT findings had lower spirometric measurements and higher levels of inflammation, and reported more exacerbations in the previous year compared with patients with no findings on HRCT. Patients with morphological changes were classified into one of three groups according to their HRCT phenotype(s): emphysema (E) only, E + bronchiectasis (B)/peribronchial thickening (PBT) or B/PBT only. Forced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), FEV1/FVC ratio, C-reactive protein (CRP) levels and the number of exacerbations among the groups were significantly different. Pairwise comparisons between the E only and E+B/PBT groups showed significantly lower FVC, FEV1and FEV1/FVC values, and higher CRP levels and number of exacerbations compared with the B/PBT group. No significant differences were found between the E+B/PBT and the B/PBT groups. An inverse correlation was found between the total HRCT score and FVC, FEV1and FEV1/FVC; the correlation was positive with CRP level, erythrocyte sedimentation rate and number of exacerbations.CONCLUSION: The present study exposed the intimate relationship between phenotype(s) characterized by HRCT and scoring for morphological abnormalities; and clinical and functional parameters and inflammatory markers. The inclusion of HRCT among routine examinations for COPD may provide significant benefits both in the management and prognosis of COPD patients.

Sign in / Sign up

Export Citation Format

Share Document