University of Bristol Researchers Detail New Studies and Findings in the Area of Machine Learning (Exacerbation predictive modelling using real-world data from the myCOPD app)
University of Bristol Researchers Detail New Studies and Findings in the Area of Machine Learning (Exacerbation predictive modelling using real-world data from the myCOPD app)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on artificial in telligence have been published. According to news reporting from Bristol, United Kingdom, by NewsRx journalists, research stated, “Acute exacerbations of COPD ( AECOPD) are episodes of breathlessness, cough and sputum which are associated wi th the risk of hospitalisation, progressive lung function decline and death. The y are often missed or diagnosed late.” The news editors obtained a quote from the research from University of Bristol: “Accurate timely intervention can improve these poor outcomes. Digital tools can be used to capture symptoms and other clinical data in COPD. This study aims to apply machine learning to the largest available real-world digital dataset to d evelop AECOPD Prediction tools which could be used to support early intervention and improve clinical outcomes. To create and validate a machine learning predic tive model that forecasts exacerbations of COPD 1-8 days in advance. The model i s based on routine patient-entered data from myCOPD self-management app. Adaptat ions of the AdaBoost algorithm were employed as machine learning approaches. The dataset included 506 patients users between 2017 and 2021. 55,066 app records w ere available for stable COPD event labels and 1263 records of AECOPD event labe ls. The data used for training the model included COPD assessment test (CAT) sco res, symptom scores, smoking history, and previous exacerbation frequency. All e xacerbation records used in the model were confined to the 1-8 days preceding a self-reported exacerbation event. TheEasyEnsemble Classifier resulted in a Sensi tivity of 67.0 % and a Specificity of 65 % with a po sitive predictive value (PPV) of 5.0 % and a negative predictive v alue (NPV) of 98.9 %. An AdaBoost model with a cost-sensitive decis ion tree resulted in a a Sensitivity of 35.0 % and a Specificity o f 89.0 % with a PPV of 7.08 % and NPV of 98.3 % .”
Key words
University of Bristol/Bristol/United K ingdom/Europe/Cyborgs/Emerging Technologies/Machine Learning
NETL
NSTL