scholarly journals Improving prediction of risk of hospital admission in chronic obstructive pulmonary disease: application of machine learning to telemonitoring data (Preprint)

2017 ◽  
Author(s):  
Peter Orchard ◽  
Anna Agakova ◽  
Hilary Pinnock ◽  
Christopher David Burton ◽  
Christophe Sarran ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Hospital Admissions ◽  
Learning Algorithm ◽  
Weather Data ◽  
Chronic Obstructive ◽  
Machine Learning Algorithm ◽  
Obstructive Pulmonary Disease ◽  
Positive Rate

BACKGROUND Telemonitoring of symptoms and physiological signs has been suggested as a means of early detection of exacerbations of chronic obstructive pulmonary disease (COPD) with a view to instituting timely treatment. However, current algorithms to identify exacerbations result in frequent false positive results and increased workload. Machine learning, when applied to predictive modelling, can determine patterns of risk factors useful for improving quality of predictions. OBJECTIVE To establish if machine learning techniques applied to telemonitoring datasets improve prediction of hospital admissions, decisions to start steroids, and to determine if the addition of weather data further improves such predictions. METHODS We used daily symptoms, physiological measures and medication data, with baseline demography, COPD severity, quality of life, and hospital admissions from a pilot and large randomised controlled trial of telemonitoring in COPD. In addition, we linked weather data from the UK Meteorological Office. We used feature selection and extraction techniques for time-series to construct up to 153 predictive patterns (features) from symptom, medication, and physiological measurements. The resulting variables were used for the construction of predictive models fitted to training sets of patients and compared to common algorithms. RESULTS We had a mean 363 days of telemonitoring data from 135 patients. The two most practical traditional score-counting algorithms, restricted to cases with complete data resulted in AUC estimates of 0.60 [CI 95% 0.51, 0.69] and 0.58 [0.50, 0.67] for predicting admissions based on a single day’s readings. However, in a real-world scenario allowing for missing data, with greater numbers of patient daily data and hospitalisations (N = 57,150, N+=17), the performance of all the traditional algorithms fell, including those based on two days data. One of the most frequently used algorithms performed no better than chance. Machine learning models demonstrated significant improvements; the best machine learning algorithm based on 57,150 episodes resulted in an aggregated AUC = 0.73 [0.67, 0.79]. Addition of weather data measurements resulted in a negligible improvement in the predictive performance of the best model (AUC = 0.74 [0.69, 0.79]). In order to achieve an 80% true positive rate (sensitivity), the traditional algorithms were associated with an 80% false positive rate: our algorithm halved this rate to approximately 40% (specificity approximately 60%). The machine learning algorithm was moderately superior to the best standard algorithm (AUC = 0.77 [0.74, 0.79] v AUC = 0.66 [0.63, 0.68]) at predicting the need for steroids. CONCLUSIONS The early detection and management of COPD remains an important goal given the huge personal and economic costs of the condition. Machine learning approaches, which can be tailored to an individual’s baseline profile and can learn from experience of the individual patient are superior to existing predictive algorithms show promise in achieving this goal. CLINICALTRIAL NA

scholarly journals Improving Prediction of Risk of Hospital Admission in Chronic Obstructive Pulmonary Disease: Application of Machine Learning to Telemonitoring Data

2018 ◽  
Vol 20 (9) ◽  
pp. e263 ◽  
Author(s):  
Peter Orchard ◽  
Anna Agakova ◽  
Hilary Pinnock ◽  
Christopher David Burton ◽  
Christophe Sarran ◽  
...  
Keyword(s):  
Machine Learning ◽  
Hospital Admissions ◽  
Learning Algorithm ◽  
Controlled Trial ◽  
Weather Data ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Randomized Controlled ◽  
Positive Rate ◽  
Counting Algorithms

Background Telemonitoring of symptoms and physiological signs has been suggested as a means of early detection of chronic obstructive pulmonary disease (COPD) exacerbations, with a view to instituting timely treatment. However, algorithms to identify exacerbations result in frequent false-positive results and increased workload. Machine learning, when applied to predictive modelling, can determine patterns of risk factors useful for improving prediction quality. Objective Our objectives were to (1) establish whether machine learning techniques applied to telemonitoring datasets improve prediction of hospital admissions and decisions to start corticosteroids, and (2) determine whether the addition of weather data further improves such predictions. Methods We used daily symptoms, physiological measures, and medication data, with baseline demography, COPD severity, quality of life, and hospital admissions from a pilot and large randomized controlled trial of telemonitoring in COPD. We linked weather data from the United Kingdom meteorological service. We used feature selection and extraction techniques for time series to construct up to 153 predictive patterns (features) from symptom, medication, and physiological measurements. We used the resulting variables to construct predictive models fitted to training sets of patients and compared them with common symptom-counting algorithms. Results We had a mean 363 days of telemonitoring data from 135 patients. The two most practical traditional score-counting algorithms, restricted to cases with complete data, resulted in area under the receiver operating characteristic curve (AUC) estimates of 0.60 (95% CI 0.51-0.69) and 0.58 (95% CI 0.50-0.67) for predicting admissions based on a single day’s readings. However, in a real-world scenario allowing for missing data, with greater numbers of patient daily data and hospitalizations (N=57,150, N+=55, respectively), the performance of all the traditional algorithms fell, including those based on 2 days’ data. One of the most frequently used algorithms performed no better than chance. All considered machine learning models demonstrated significant improvements; the best machine learning algorithm based on 57,150 episodes resulted in an aggregated AUC of 0.74 (95% CI 0.67-0.80). Adding weather data measurements did not improve the predictive performance of the best model (AUC 0.74, 95% CI 0.69-0.79). To achieve an 80% true-positive rate (sensitivity), the traditional algorithms were associated with an 80% false-positive rate: our algorithm halved this rate to approximately 40% (specificity approximately 60%). The machine learning algorithm was moderately superior to the best symptom-counting algorithm (AUC 0.77, 95% CI 0.74-0.79 vs AUC 0.66, 95% CI 0.63-0.68) at predicting the need for corticosteroids. Conclusions Early detection and management of COPD remains an important goal given its huge personal and economic costs. Machine learning approaches, which can be tailored to an individual’s baseline profile and can learn from experience of the individual patient, are superior to existing predictive algorithms and show promise in achieving this goal. Trial Registration International Standard Randomized Controlled Trial Number ISRCTN96634935; http://www.isrctn.com/ISRCTN96634935 (Archived by WebCite at http://www.webcitation.org/722YkuhAz)

scholarly journals Factors Associated with Hospital Admission in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease in a Teaching Hospital

2018 ◽  
Vol 28 (2) ◽  
pp. 52-57
Author(s):  
Md Nure Alom Siddiqui ◽  
Shahnaj Sultana ◽  
MMR Khan ◽  
PM Basak
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Hospital Admissions ◽  
Forced Expiratory Volume ◽  
Chronic Obstructive ◽  
Related Factors ◽  
Obstructive Pulmonary Disease ◽  
Factors Associated ◽  
Acute Exacerbations

Background: Acute exacerbations of chronic obstructive pulmonary disease (AE-COPD) impair quality of life (QOL), accelerate the decline in lung function and often require hospitalization, and thus, leading to increased healthcare burden. By identifying factors that may be associated with AE-COPD and managing them rationally, not only the hospital admissions could be avoided but progression of the disease may also be slowed.Objective. The aim of the present study was to determine the factors associated with hospital admissions among adults with AE-COPD.Methods. Seventy-three patients admitted with AE-COPD were administered a structured questionnaire during their hospital stay. Data on body mass index (BMI), smoking, symptoms, co-morbidities course of the disease, spirometry management and outcomes during the hospitalisation were obtained. Factors associated with hospital admissions were analyzed.Results. The hospitalization due to AE-COPD was significantly associated with the reduced forced expiratory volume in one second (FEV1), and peak expiratory flow rates, increasing sputum purulence, number of hospitalizations during previous year for COPD and presence of co-morbidities.Conclusions. The study shows that both disease and healthcare-related factors are predictors for hospitalisation. Identification of risk factors and appropriate management may reduce hospitalisation due to AE-COPD.TAJ 2015; 28(2): 52-57

scholarly journals Protocol for an observational study to identify potential predictors of an acute exacerbation in patients with chronic obstructive pulmonary disease (the PACE Study)

BMJ Open ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. e043014
Author(s):  
Klaus Kenn ◽  
Rainer Gloeckl ◽  
Daniela Leitl ◽  
Tessa Schneeberger ◽  
Inga Jarosch ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Acute Exacerbation ◽  
Hospital Admissions ◽  
Negative Impact ◽  
Chronic Obstructive ◽  
Detailed Knowledge ◽  
Obstructive Pulmonary Disease

IntroductionAcute exacerbations of chronic obstructive pulmonary disease (AECOPD) are the most critical events for patients with COPD that have a negative impact on patients’ quality of life, accelerate disease progression, and can result in hospital admissions and death. Although there is no distinct definition or detailed knowledge about AECOPD, it is commonly used as primary outcome in clinical studies. Furthermore, it may be difficult in clinical practice to differentiate the worsening of symptoms due to an AECOPD or to the development of heart failure. Therefore, it is of major clinical importance to investigate the underlying pathophysiology, and if possible, predictors of an AECOPD and thus to identify patients who are at high risk for developing an acute exacerbation.Methods and analysisIn total, 355 patients with COPD will be included prospectively to this study during a 3-week inpatient pulmonary rehabilitation programme at the Schoen Klinik Berchtesgadener Land, Schoenau am Koenigssee (Germany). All patients will be closely monitored from admission to discharge. Lung function, exercise tests, clinical parameters, quality of life, physical activity and symptoms will be recorded, and blood samples and exhaled air will be collected. If a patient develops an AECOPD, there will be additional comprehensive diagnostic assessments to differentiate between cardiac, pulmonary or cardiopulmonary causes of worsening. Follow-up measures will be performed at 6, 12 and 24 months.Exploratory data analyses methods will be used for the primary research question (screening and identification of possible factors to predict an AECOPD). Regression analyses and a generalised linear model with a binomial outcome (AECOPD) will be applied to test if predictors are significant.Ethics and disseminationThis study has been approved by the Ethical Committee of the Philipps University Marburg, Germany (No. 61/19). The results will be presented in conferences and published in a peer-reviewed journal.Trial registration numberNCT04140097.

scholarly journals Features of the clinical course of chronic obstructive pulmonary disease and quality of life in patients with coexisting metabolic syndrome

2016 ◽  
Vol 97 (5) ◽  
pp. 681-686
Author(s):  
S A Kozhevnikova ◽  
A V Budnevskiy
Keyword(s):  
Quality Of Life ◽  
Chronic Obstructive Pulmonary Disease ◽  
Metabolic Syndrome ◽  
Pulmonary Disease ◽  
Hospital Admissions ◽  
Clinical Course ◽  
Life Assessment ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease

Aim. To study the clinical course of chronic obstructive pulmonary disease in patients with metabolic syndrome and analyze the degree of influence of the metabolic syndrome components on chronic obstructive pulmonary disease and patients’ quality of life.Methods. 100 patients with chronic obstructive pulmonary disease were examined: 30 patients without metabolic syndrome (the first group) and 70 patients with metabolic syndrome (the second group). Anthropometric measurements (weight, height, body mass index, waist circumference), laboratory tests (levels of triglycerides, cholesterol, low- and high-density lipoproteins, fasting blood glucose, the oral glucose tolerance test), physical examination, quality of life assessment were performed.Results.Patients of the second group had statistically significant differences in the studied parameters in comparison with the first group. The number of exacerbations, calls to ambulance service, hospital admissions were 1.4; 1.3 and 1.5 times higher, respectively. Dyspnea intensity, cough and sputum score were 1.6; 1.7 and 1.6 times higher respectively as compared with the first group (pConclusion. Metabolic syndrome is associated with a more severe course of chronic obstructive pulmonary disease, which results in a higher frequency of exacerbations, hospital admissions, more severe clinical manifestations, greater influence of dyspnea on the physical activity limitation of patients, more severe airflow obstruction, low exercise tolerance with worse performance of everyday activities, emotional perception of the disease, worse psychosocial adaptation of patients.

scholarly journals Trends in Hospital Admissions for Chronic Obstructive Pulmonary Disease in Men and Women in SPAIN, 1998 to 2018

2021 ◽  
Vol 10 (7) ◽  
pp. 1529
Author(s):  
Domingo Orozco-Beltrán ◽  
Juan Manuel Arriero-Marin ◽  
Concepción Carratalá-Munuera ◽  
Juan J. Soler-Cataluña ◽  
Adriana Lopez-Pineda ◽  
...  
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Hospital Admissions ◽  
Chronic Obstructive ◽  
Annual Percent Change ◽  
Data Set ◽  
Obstructive Pulmonary Disease ◽  
Men And Women ◽  
Admission Rates ◽  
Percent Change

The prevalence of chronic obstructive pulmonary disease (COPD) is rising faster in women in some countries. An observational time trends study was performed to assess the evolution of hospital admissions for COPD in men and women in Spain from 1998 to 2018. ICD-9 diagnostic codes (490–492, 496) from the minimum basic data set of hospital discharges were used. Age-standardised admission rates were calculated using the European Standard Population. Joinpoint regression models were fitted to estimate the annual percent change (APC). In 2018, the age-standardised admission rate per 100,000 population/year for COPD was five times higher in men (384.8, 95% CI: 381.7, 387.9) than in women (78.6, 95% CI: 77.4, 79.9). The average annual percent change (AAPC) was negative over the whole study period in men (−1.7%/year, 95% CI: −3.1, −0.2) but positive from 2010 to 2018 (1.1%/year, 95% CI: −0.8, 2.9). In women, the APC was −6.0% (95%CI: −7.1, −4.9) from 1998 to 2010, but the trend reversed direction in the 2010–2018 period (7.8%/year, 95% CI: 5.5, 10.2). Thus, admission rates for COPD decreased from 1998 to 2010 in both men and women but started rising again until 2018, modestly in men and sharply in women.

Sign in / Sign up

Export Citation Format

Share Document