scholarly journals Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study

10.2196/28953 ◽  
2022 ◽  
Vol 24 (1) ◽  
pp. e28953
Author(s):  
Siyang Zeng ◽  
Mehrdad Arjomandi ◽  
Yao Tong ◽  
Zachary C Liao ◽  
Gang Luo
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
High Risk ◽  
Pulmonary Disease ◽  
Care Management ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Copd Exacerbations ◽  
Machine Learning Model ◽  
Severe Copd

Background Chronic obstructive pulmonary disease (COPD) poses a large burden on health care. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause an irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target patients at high risk for preventive care management to reduce severe COPD exacerbations and improve outcomes. Objective The aim of this study is to develop a more accurate model to predict severe COPD exacerbations. Methods We examined all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019 and identified 278 candidate features. By performing secondary analysis on 43,576 University of Washington Medicine data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD. Results The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 9.99% (752/7529) of the patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6801/7529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6698/7347). Conclusions Our model provided a more accurate prediction of severe COPD exacerbations in the next year compared with prior published models. After further improvement of its performance measures (eg, by adding features extracted from clinical notes), our model could be used in a decision support tool to guide the identification of patients with COPD and at high risk for care management to improve outcomes. International Registered Report Identifier (IRRID) RR2-10.2196/13783

scholarly journals Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study (Preprint)

2021 ◽  
Author(s):  
Siyang Zeng ◽  
Mehrdad Arjomandi ◽  
Yao Tong ◽  
Zachary C Liao ◽  
Gang Luo
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
High Risk ◽  
Pulmonary Disease ◽  
Care Management ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Copd Exacerbations ◽  
Machine Learning Model ◽  
Severe Copd

BACKGROUND Chronic obstructive pulmonary disease (COPD) poses a large burden on health care. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause an irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target patients at high risk for preventive care management to reduce severe COPD exacerbations and improve outcomes. OBJECTIVE The aim of this study is to develop a more accurate model to predict severe COPD exacerbations. METHODS We examined all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019 and identified 278 candidate features. By performing secondary analysis on 43,576 University of Washington Medicine data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD. RESULTS The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 9.99% (752/7529) of the patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6801/7529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6698/7347). CONCLUSIONS Our model provided a more accurate prediction of severe COPD exacerbations in the next year compared with prior published models. After further improvement of its performance measures (eg, by adding features extracted from clinical notes), our model could be used in a decision support tool to guide the identification of patients with COPD and at high risk for care management to improve outcomes. INTERNATIONAL REGISTERED REPORT RR2-10.2196/13783

Control of chronic obstructive pulmonary disease exacerbations frequency in association with ENT organs abnormalities

2020 ◽  
Vol 29 (6) ◽  
pp. 716-724
Author(s):  
D. G. Pavlush ◽  
V. A. Nevzorova ◽  
E. A. Gilifanov ◽  
V. B. Shumatov ◽  
I. M. Martynenko
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
High Risk ◽  
Pulmonary Disease ◽  
Treatment Plan ◽  
Control Group ◽  
Chronic Obstructive ◽  
Copd Exacerbation ◽  
Exacerbation Rate ◽  
Obstructive Pulmonary Disease ◽  
Copd Exacerbations

Chronic obstructive pulmonary disease (COPD) is a disease holding a stable position in morbidity and mortality structure in patients aged over 40 years.The aim of the study was to evaluate the condition of otorhinolaryngological (ENT) organs in patients with the COPD at different disease periods with subsequent analysis of COPD exacerbation rate based on the results of therapy regimen change according to the established comorbidity.Materials and Methods. Examination of ENT organs was performed in patients with COPD (n = 99) Patients from group 1 (n = 50) were treated at Pulmonary Department of the Regional State Budgetary Health Institution "Vladivostok Clinical Hospital No.1" for disease exacerbation; outpatients from group 2 (n = 49) had stable COPD course. Control group (n = 50) included patients without history of smoking and without respiratory and hearing disorders. All patients were matched by age and sex. Repeated examination was conducted in patients (n = 72) with stable COPD after 6 months.Results. It was observed that patients from groups 1 and 2 had different severity of disease symptoms, but equally high (> 2) risk of COPD exacerbation within 1 year. 50.0 and 42.9% of patients actively complained about the ENT organ-related conditions during the periods of COPD exacerbation and stable course, respectively. Among ENT organ diseases the most frequent were laryngeal diseases reported in 84.0 and 73.5% of patients with COPD exacerbation and stable course, respectively. The chronic catarrhal rhinitis and pharyngitis were revealed in 26 and 30% of patients with COPD exacerbation (p < 0.01). According to the data of 6-month study, the number of COPD exacerbations in high-risk patients with COPD using personal treatment plan for ENT-organ diseases was reduced by half, which had a positive effect on the condition of ENT-organs.Conclusion. The study showed that patients with COPD often ENT-organ-related complaints – in the exacerbation period about 50% of patients, and at stable course – 43%. Patients most often complain on glottic incompetence with the most pronounced symptoms at COPD exacerbation. Decreased number of COPD exacerbations by 2 times in patients with high risk of their occurrence and improvement of ENT organ condition were noted if ENT diseases were timely treated. ENT specialist consultation should be provided at dispensary observation organization for patients with COPD in order to personalize the treatment plan depending on the clinical situation.

CHARACTERISTICS OF 24-HOUR BLOOD PRESSURE INDICATORS IN PATIENTS WITH HYPERTENSION AND CHRONIC OBSTRUCTIVE PULMONARY DISEASE

2020 ◽  
pp. 31-41
Author(s):  
M.A. Bubnova ◽  
O.N. Kryuchkova
Keyword(s):  
Blood Pressure ◽  
Chronic Obstructive Pulmonary Disease ◽  
Mean Arterial Pressure ◽  
High Risk ◽  
Arterial Pressure ◽  
Pulmonary Disease ◽  
Comparison Group ◽  
Cardiovascular Complications ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease

Patients with hypertension (HT) and chronic obstructive pulmonary disease (COPD) have a high risk of cardiovascular complications. Up to now, there is no optimal strategy for combined antihypertensive therapy. Still, the data of 24-hour blood pressure monitoring (BPM) are important while choosing treatment tactics. The aim of the paper is to study the features of indicators in patients with arterial hypertension (AH) and COPD. Materials and methods. 130 patients with HT were included in the study. The main group (n=90) included comorbid patients with HT and COPD, their average age was 61.30±1.01; the comparison group (n=40) consisted of patients with HT, their average age was 59.10±1.53. All patients underwent 24-hour BPM. Results. Comorbid patients revealed an increase in the mean 24-hour and night systolic and mean arterial pressure values as well as a significant increase in the load index of systolic, diastolic and mean arterial pressure. Also, comorbid patients demonstrated higher blood pressure in contrast to the patients of the comparison group. They had increased systolic, diastolic and mean blood pressure variability and a quicker rate of morning blood pressure rise. According to 24-hour blood pressure dynamics, pathological types of the 24-hour blood pressure curve, a higher frequency of the night-peaker profile dominated in patients with COPD if compared to patients with HT. Conclusion. The obtained data indicated a high risk of cardiovascular complications in comorbid patients, early target organ damage and an unfavorable disease prognosis. It means that both further study of hypertension clinical course in such patients and personalization of antihypertensive therapy are relevant. Keywords: hypertension, chronic obstructive pulmonary disease, 24-hour monitoring, blood pressure. Пациенты с артериальной гипертензией (АГ) и хронической обструктивной болезнью легких (ХОБЛ) имеют высокий риск возникновения кардиоваскулярных осложнений. В настоящее время в лечении не определена наиболее оптимальная стратегия комбинированной антигипертензивной терапии. Для выбора тактики терапии важную роль играют показатели суточного мониторирования артериального давления (СМАД). Цель. Изучить особенности показателей СМАД у пациентов с АГ на фоне ХОБЛ. Материалы и методы. В исследование включено 130 пациентов с АГ. В основную группу (n=90) вошли пациенты с АГ и ХОБЛ (средний возраст – 61,30±1,01 года), в группу сравнения (n=40) – больные только АГ (средний возраст – 59,10±1,53 года). Всем пациентам проведено СМАД. Результаты. У пациентов с коморбидностью выявлены следующие особенности суточных показателей артериального давления: увеличение значений среднесуточных и средненочных показателей систолического и среднего артериального давления; существенное повышение индекса нагрузки систолическим, диастолическим и средним артериальным давлением. Также эти больные отличались от пациентов группы сравнения более высокими значениями пульсового давления, имели повышенную вариабельность систолического, диастолического и среднего артериального давления, у них наблюдалось увеличение скорости утреннего подъема артериального давления. Суточная динамика артериального давления у пациентов с ХОБЛ характеризовалась преобладанием патологических типов суточной кривой АД, более высокой частотой профиля night-peaker по сравнению с больными только АГ. Выводы. Выявленные особенности свидетельствуют о высоком риске сердечно-сосудистых осложнений у пациентов с коморбидностью, раннем поражении органов-мишеней и неблагоприятном прогнозе заболевания, что требует дальнейшего изучения особенностей клинического течения АГ у таких больных и индивидуализации антигипертензивной терапии. Ключевые слова: артериальная гипертензия, хроническая обструктивная болезнь легких, суточное мониторирование, артериальное давление.

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
Sign in / Sign up

Export Citation Format

Share Document