@InProceedings{Xie2013,
  Title                    = {Prediction of Chronic Obstructive Pulmonary Disease (COPD) Exacerbation Using Physiological Time Series Patterns},
  Author                   = {Xie, Y. and Redmond, S. J. and Mohktar, M. S. and Shany, T. and Basilakis, J. and Hession, M. and Lovell, N. H.},
  Booktitle                = {Proceedings of the International Conference of the IEEE Engineering in Medicine and Biology Society},
  Year                     = {2013},

  Abstract                 = {COPD is a complex disease that has been acknowledged as one of the top five leading causes of deaths. Recent clinical research has indicated a strong association between physiological homeostasis and the onset of COPD exacerbation. Thus the manipulation of these variables may eventually yield an effective means of predicting the risk of occurrence of an exacerbation event in the near future. However, the accuracy of existing prediction methods based on statistical analysis of periodic snapshots of certain physiological variables is still far from satisfactory, due to lack of the study in long-term and interactive effects of the physiological variables. Therefore, developing a relatively accurate method for predicting COPD exacerbation is an outstanding challenge. In this paper, a regression-based machine learning technique was developed, using trend pattern variables extracted from COPD patients' longitudinal physiological records, to classify subjects into ��low-ris�� and ��high-risk�� categories, indicating their risk of suffering a COPD exacerbation event. Experiment results from cross validation of the classifier model show an average accuracy of 79.27% using this method.},
  Keywords                 = {EMBC2013},
  Review                   = {Research shows an association between HR, SpO2, BP and body temperature physioloigcal parameters on onset of COPD exacerbation, which increases COPD morbidity. Patterns have been derived from statistical analysis based on weekly or monthly snapshots. A trend detection technique was developed to see if we can use long term longtiudinal data to predict COPD events. 

7 COPD patients were examined. Tracked daily weight, diastolic blood pressure, systolic blood pressure, HR, SpO2 and temperature for a year. Standard health questionnaires were applied to assess illness progress and mood of patient. Piecewise regression was employed to fit the time series data. Breakpoints in the fit are found by removing breakpoints that gives the least increase in MSE, under some MSE threshold. Data is added "online" and several metrics, such as the slope and sandard deviation, was calculated. 

Sections in the data were labelled "low-risk" or "high-risk" based on patient status, and a logistic regression classifier was used to predict if some data sequence would fall into the low-risk or high-risk section. They then determined which metric combination works best at predicting COPD events.},
  Timestamp                = {2013.07.30}
}

{"_id":"cEyaeFRs7zRcxiuBx","bibbaseid":"xie-redmond-mohktar-shany-basilakis-hession-lovell-predictionofchronicobstructivepulmonarydiseasecopdexacerbationusingphysiologicaltimeseriespatterns-2013","downloads":0,"creationDate":"2017-09-14T16:34:37.239Z","title":"Prediction of Chronic Obstructive Pulmonary Disease (COPD) Exacerbation Using Physiological Time Series Patterns","author_short":["Xie, Y.","Redmond, S. J.","Mohktar, M. S.","Shany, T.","Basilakis, J.","Hession, M.","Lovell, N. H."],"year":2013,"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/jfslin/jfslin.github.io/master/jf2lin.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Prediction of Chronic Obstructive Pulmonary Disease (COPD) Exacerbation Using Physiological Time Series Patterns","author":[{"propositions":[],"lastnames":["Xie"],"firstnames":["Y."],"suffixes":[]},{"propositions":[],"lastnames":["Redmond"],"firstnames":["S.","J."],"suffixes":[]},{"propositions":[],"lastnames":["Mohktar"],"firstnames":["M.","S."],"suffixes":[]},{"propositions":[],"lastnames":["Shany"],"firstnames":["T."],"suffixes":[]},{"propositions":[],"lastnames":["Basilakis"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Hession"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Lovell"],"firstnames":["N.","H."],"suffixes":[]}],"booktitle":"Proceedings of the International Conference of the IEEE Engineering in Medicine and Biology Society","year":"2013","abstract":"COPD is a complex disease that has been acknowledged as one of the top five leading causes of deaths. Recent clinical research has indicated a strong association between physiological homeostasis and the onset of COPD exacerbation. Thus the manipulation of these variables may eventually yield an effective means of predicting the risk of occurrence of an exacerbation event in the near future. However, the accuracy of existing prediction methods based on statistical analysis of periodic snapshots of certain physiological variables is still far from satisfactory, due to lack of the study in long-term and interactive effects of the physiological variables. Therefore, developing a relatively accurate method for predicting COPD exacerbation is an outstanding challenge. In this paper, a regression-based machine learning technique was developed, using trend pattern variables extracted from COPD patients' longitudinal physiological records, to classify subjects into ��low-ris�� and ��high-risk�� categories, indicating their risk of suffering a COPD exacerbation event. Experiment results from cross validation of the classifier model show an average accuracy of 79.27% using this method.","keywords":"EMBC2013","review":"Research shows an association between HR, SpO2, BP and body temperature physioloigcal parameters on onset of COPD exacerbation, which increases COPD morbidity. Patterns have been derived from statistical analysis based on weekly or monthly snapshots. A trend detection technique was developed to see if we can use long term longtiudinal data to predict COPD events. 7 COPD patients were examined. Tracked daily weight, diastolic blood pressure, systolic blood pressure, HR, SpO2 and temperature for a year. Standard health questionnaires were applied to assess illness progress and mood of patient. Piecewise regression was employed to fit the time series data. Breakpoints in the fit are found by removing breakpoints that gives the least increase in MSE, under some MSE threshold. Data is added \"online\" and several metrics, such as the slope and sandard deviation, was calculated. Sections in the data were labelled \"low-risk\" or \"high-risk\" based on patient status, and a logistic regression classifier was used to predict if some data sequence would fall into the low-risk or high-risk section. They then determined which metric combination works best at predicting COPD events.","timestamp":"2013.07.30","bibtex":"@InProceedings{Xie2013,\n Title = {Prediction of Chronic Obstructive Pulmonary Disease (COPD) Exacerbation Using Physiological Time Series Patterns},\n Author = {Xie, Y. and Redmond, S. J. and Mohktar, M. S. and Shany, T. and Basilakis, J. and Hession, M. and Lovell, N. H.},\n Booktitle = {Proceedings of the International Conference of the IEEE Engineering in Medicine and Biology Society},\n Year = {2013},\n\n Abstract = {COPD is a complex disease that has been acknowledged as one of the top five leading causes of deaths. Recent clinical research has indicated a strong association between physiological homeostasis and the onset of COPD exacerbation. Thus the manipulation of these variables may eventually yield an effective means of predicting the risk of occurrence of an exacerbation event in the near future. However, the accuracy of existing prediction methods based on statistical analysis of periodic snapshots of certain physiological variables is still far from satisfactory, due to lack of the study in long-term and interactive effects of the physiological variables. Therefore, developing a relatively accurate method for predicting COPD exacerbation is an outstanding challenge. In this paper, a regression-based machine learning technique was developed, using trend pattern variables extracted from COPD patients' longitudinal physiological records, to classify subjects into ��low-ris�� and ��high-risk�� categories, indicating their risk of suffering a COPD exacerbation event. Experiment results from cross validation of the classifier model show an average accuracy of 79.27% using this method.},\n Keywords = {EMBC2013},\n Review = {Research shows an association between HR, SpO2, BP and body temperature physioloigcal parameters on onset of COPD exacerbation, which increases COPD morbidity. Patterns have been derived from statistical analysis based on weekly or monthly snapshots. A trend detection technique was developed to see if we can use long term longtiudinal data to predict COPD events. \n\n7 COPD patients were examined. Tracked daily weight, diastolic blood pressure, systolic blood pressure, HR, SpO2 and temperature for a year. Standard health questionnaires were applied to assess illness progress and mood of patient. Piecewise regression was employed to fit the time series data. Breakpoints in the fit are found by removing breakpoints that gives the least increase in MSE, under some MSE threshold. Data is added \"online\" and several metrics, such as the slope and sandard deviation, was calculated. \n\nSections in the data were labelled \"low-risk\" or \"high-risk\" based on patient status, and a logistic regression classifier was used to predict if some data sequence would fall into the low-risk or high-risk section. They then determined which metric combination works best at predicting COPD events.},\n Timestamp = {2013.07.30}\n}\n\n","author_short":["Xie, Y.","Redmond, S. J.","Mohktar, M. S.","Shany, T.","Basilakis, J.","Hession, M.","Lovell, N. H."],"key":"Xie2013","id":"Xie2013","bibbaseid":"xie-redmond-mohktar-shany-basilakis-hession-lovell-predictionofchronicobstructivepulmonarydiseasecopdexacerbationusingphysiologicaltimeseriespatterns-2013","role":"author","urls":{},"keyword":["EMBC2013"],"downloads":0},"search_terms":["prediction","chronic","obstructive","pulmonary","disease","copd","exacerbation","using","physiological","time","series","patterns","xie","redmond","mohktar","shany","basilakis","hession","lovell"],"keywords":["embc2013"],"authorIDs":[],"dataSources":["iCsmKnycRmHPxmhBd"]}