Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

Spathis, Dimitris; Vlamos, Panayiotis

doi:10.1177/1460458217723169

Cited by 94 publications

(67 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We assessed the predictive performances of our models using three main measures: AUC, SEN, and SPE, all commonly used performance measures. 39,40 The classifier's sensitivity, also known as true positive rate (TPR), is defined as the ability to correctly identify the true value (TP) of the cases. In this study the metric measures the probability of correctly identifying high-cost patients.…”

Section: Methodsmentioning

confidence: 99%

Using machine learning approaches to predict high-cost chronic obstructive pulmonary disease patients in China

Luo¹,

Li²,

Lian

et al. 2019

Health Informatics J

View full text Add to dashboard Cite

The accurate identification and prediction of high-cost Chronic obstructive pulmonary disease (COPD) patients is important for addressing the economic burden of COPD. The objectives of this study were to use machine learning approaches to identify and predict potential high-cost patients and explore the key variables of the forecasting model, by comparing differences in the predictive performance of different variable sets. Machine learning approaches were used to estimate the medical costs of COPD patients using the Medical Insurance Data of a large city in western China. The prediction models used were logistic regression, random forest (RF), and extreme gradient boosting (XGBoost). All three models had good predictive performance. The XGBoost model outperformed the others. The areas under the ROC curve for Logistic Regression, RF and XGBoost were 0.787, 0.792 and 0.801. The precision and accuracy metrics indicated that the methods achieved correct and reliable results. The results of this study can be used by healthcare data analysts, policy makers, insurers, and healthcare planners to improve the delivery of health services.

show abstract

Section: Methodsmentioning

confidence: 99%

Using machine learning approaches to predict high-cost chronic obstructive pulmonary disease patients in China

Luo¹,

Li²,

Lian

et al. 2019

Health Informatics J

View full text Add to dashboard Cite

show abstract

“…The proposed model was tested using a 10-fold cross-validation procedure. The proposed model when compared with other decision tree models such as Decision Tree with Reduced Error Pruning Method and A combination of Naïve Bayes, Decision Tree and SVM showed accuracy of 86.53%, specificity 95.5% and sensitivity of 86.5% [29]. The CAD model used Least Squares SVM (LS-SVM) classifier which was when compared to other classifiers such as ANN, and Hidden Markov Models (HMM) showed accuracy, sensitivity and specificity of 95.39%, 96.59% and 93.75% respectively [30].A comparative study by Acharya [39] on heart disease prediction, used Heart Disease Data Set from UCI machine learning repository.…”

Section: Discussionmentioning

confidence: 97%

“…The prediction of lung diseases such as COPD and Asthma through classifier techniques. Study by Spathis and Vlamos [29] predicted Asthma and Chronic Obstructive Pulmonary Disease (COPD). Dataset consist of 132 subjects and the study reported that Random Forest outperforms other algorithms with precision rate of 97.7% for COPD and 80.3% for asthma.…”

Section: Asthma Copdmentioning

confidence: 99%

Medical Big Data Analytics Using Machine Learning Algorithms

Moorthy,

Gandhi*

2019

IJITEE

View full text Add to dashboard Cite

Artificial intelligence and expert systems plays a key role in modern medicine sciences for disease prediction, surveillance interventions, cost efficiency and better quality of life etc. With the arrival of new web-based data sources and systematic data collection through surveys and medical reporting, there is a need of the hour to develop effective recommendation systems which can support practitioners in better decision-making process. Machine Learning Algorithms (MLA) is a powerful tool which enables computers to learn from data. While many novel developed MLA constantly evolves, there is need to develop more systematic, robust algorithm which can interpret with highest possible accuracy, sensitivity and specificity. The study reviews previously published series on different algorithms their advantages and limitations which shall help make future recommendations for researchers and experts seeking to develop an effective algorithm for predicting the likelihood of various diseases.

show abstract

“…China has a high incidence of COPD, and with an increasing population, environment deterioration and prominent aging problem, the number of COPD patients complicated with pneumonia has also shown a growing trend ( 9 ). Alveolar lavage using antibiotics based on the bronchoscope technique has been widely applied in clinic to remove the lung mucus and control inflammation, which can effectively increase the treatment effective rate of COPD patients complicated with pneumonia, and reduce the inflammatory response ( 10 ). Fortún et al ( 11 ) treated the COPD patients complicated with type II respiratory failure using alveolar lavage combined with mechanical ventilation, and the results showed that CRP declined and blood gas analysis were significantly improved.…”

Section: Discussionmentioning

confidence: 99%

Analysis of curative effect of adjuvant therapy with bronchoalveolar lavage on COPD patients complicated with pneumonia

Zhao

Liu

et al. 2018

Exp Ther Med

View full text Add to dashboard Cite

Clinical effect of adjuvant therapy with bronchoalveolar lavage on chronic obstructive pulmonary disease (COPD) patients complicated with pneumonia and its influence on the expression levels of inflammatory factors were studied. One hundred and twenty mild-moderate COPD patients complicated with pneumonia treated in the Department of Respiratory Medicine, The Sixth People's Hospital of Nantong from February 2016 to February 2017 were selected and randomly divided into three groups: One-time lavage group (n=40), two-time lavage group (n=40) and control group (n=40). Fasting peripheral blood was collected from all the patients in the morning. The lung function and blood gas analyses, and the detection of peripheral white blood cells (WBC), procalcitonin (PCT) and C-reactive protein (CRP) were performed. Moreover, the messenger RNA (mRNA) levels of interleukin-6 (IL-6), IL-8, tumor necrosis factor-α (TNF-α) and leukotriene B4 (LTB4) in lavage fluid were detected via reverse transcription-quantitative polymerase chain reaction. The lung functions of patients in the two-time lavage group were significantly improved compared with that in the one-time lavage group (p<0.01). pH and PaO2 in two-time lavage group were higher than those in the one-time lavage group (p<0.01). Peripheral WBC, PCT and CRP levels in the two-time lavage group were lower than those in the one-time lavage group (p<0.05). The mRNA levels of IL-6, IL-8, TNF-α and LTB4 in lavage fluid in two-time lavage group were lower than those in one-time lavage group (p<0.01). IL-6, IL-8, TNF-α and LTB4 expression levels in lavage fluid in two-time lavage group were lower than those in one-time lavage group (p<0.01). In conclusion, the adjuvant therapy with bronchoalveolar lavage improves the therapeutic effect on COPD patients complicated with pneumonia, which can significantly reduce the expression levels of inflammatory factors, and facilitate the control of pulmonary infection and recovery of lung function.

show abstract

Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

Cited by 94 publications

References 21 publications

Using machine learning approaches to predict high-cost chronic obstructive pulmonary disease patients in China

Using machine learning approaches to predict high-cost chronic obstructive pulmonary disease patients in China

Medical Big Data Analytics Using Machine Learning Algorithms

Analysis of curative effect of adjuvant therapy with bronchoalveolar lavage on COPD patients complicated with pneumonia

Contact Info

Product

Resources

About