Mas S Mohktar1, Stephen J Redmond2, Nick C Antoniades3, Peter D Rochford4, Jeffrey J Pretto5, Jim Basilakis6, Nigel H Lovell7, Christine F McDonald8. 1. Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. Electronic address: mas_dayana@um.edu.my. 2. Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia. Electronic address: s.redmond@unsw.edu.au. 3. Institute for Breathing and Sleep, Department of Respiratory Medicine, Austin Health, Heidelberg, Victoria 3081, Australia. Electronic address: nickantoniades@gmail.com. 4. Institute for Breathing and Sleep, Department of Respiratory Medicine, Austin Health, Heidelberg, Victoria 3081, Australia. Electronic address: peter.rochford@austin.org.au. 5. Department of Respiratory Medicine, John Hunter Hospital, Newcastle 2305, Australia. Electronic address: masdayana@gmail.com. 6. School of Computing and Mathematics, University of Western Sydney, Sydney, NSW 2751, Australia. Electronic address: j.basilakis@uws.edu.au. 7. Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia. Electronic address: n.lovell@unsw.edu.au. 8. Institute for Breathing and Sleep, Department of Respiratory Medicine, Austin Health, Heidelberg, Victoria 3081, Australia. Electronic address: christine.mcdonald@austin.org.au.
Abstract
BACKGROUND: The use of telehealth technologies to remotely monitor patients suffering chronic diseases may enable preemptive treatment of worsening health conditions before a significant deterioration in the subject's health status occurs, requiring hospital admission. OBJECTIVE: The objective of this study was to develop and validate a classification algorithm for the early identification of patients, with a background of chronic obstructive pulmonary disease (COPD), who appear to be at high risk of an imminent exacerbation event. The algorithm attempts to predict the patient's condition one day in advance, based on a comparison of their current physiological measurements against the distribution of their measurements over the previous month. METHOD: The proposed algorithm, which uses a classification and regression tree (CART), has been validated using telehealth measurement data recorded from patients with moderate/severe COPD living at home. The data were collected from February 2007 to January 2008, using a telehealth home monitoring unit. RESULTS: The CART algorithm can classify home telehealth measurement data into either a 'low risk' or 'high risk' category with 71.8% accuracy, 80.4% specificity and 61.1% sensitivity. The algorithm was able to detect a 'high risk' condition one day prior to patients actually being observed as having a worsening in their COPD condition, as defined by symptom and medication records. CONCLUSION: The CART analyses have shown that features extracted from three types of physiological measurements; forced expiratory volume in 1s (FEV1), arterial oxygen saturation (SPO2) and weight have the most predictive power in stratifying the patients condition. This CART algorithm for early detection could trigger the initiation of timely treatment, thereby potentially reducing exacerbation severity and recovery time and improving the patient's health. This study highlights the potential usefulness of automated analysis of home telehealth data in the early detection of exacerbation events among COPD patients.
BACKGROUND: The use of telehealth technologies to remotely monitor patients suffering chronic diseases may enable preemptive treatment of worsening health conditions before a significant deterioration in the subject's health status occurs, requiring hospital admission. OBJECTIVE: The objective of this study was to develop and validate a classification algorithm for the early identification of patients, with a background of chronic obstructive pulmonary disease (COPD), who appear to be at high risk of an imminent exacerbation event. The algorithm attempts to predict the patient's condition one day in advance, based on a comparison of their current physiological measurements against the distribution of their measurements over the previous month. METHOD: The proposed algorithm, which uses a classification and regression tree (CART), has been validated using telehealth measurement data recorded from patients with moderate/severe COPD living at home. The data were collected from February 2007 to January 2008, using a telehealth home monitoring unit. RESULTS: The CART algorithm can classify home telehealth measurement data into either a 'low risk' or 'high risk' category with 71.8% accuracy, 80.4% specificity and 61.1% sensitivity. The algorithm was able to detect a 'high risk' condition one day prior to patients actually being observed as having a worsening in their COPD condition, as defined by symptom and medication records. CONCLUSION: The CART analyses have shown that features extracted from three types of physiological measurements; forced expiratory volume in 1s (FEV1), arterial oxygen saturation (SPO2) and weight have the most predictive power in stratifying the patients condition. This CART algorithm for early detection could trigger the initiation of timely treatment, thereby potentially reducing exacerbation severity and recovery time and improving the patient's health. This study highlights the potential usefulness of automated analysis of home telehealth data in the early detection of exacerbation events among COPDpatients.
Authors: Grace Hawthorne; Matthew Richardson; Neil J Greening; Dale Esliger; Samuel Briggs-Price; Emma J Chaplin; Lisa Clinch; Michael C Steiner; Sally J Singh; Mark W Orme Journal: Respir Res Date: 2022-04-26
Authors: Kyoung Hee Cho; Young Sam Kim; Chung Mo Nam; Tae Hyun Kim; Sun Jung Kim; Kyu-Tae Han; Eun-Cheol Park Journal: BMJ Open Date: 2015-11-30 Impact factor: 2.692
Authors: Neele Jankrift; Christina Kellerer; Helgo Magnussen; Dennis Nowak; Rudolf A Jörres; Antonius Schneider Journal: J Thorac Dis Date: 2021-06 Impact factor: 2.895