Predicting the risk of exacerbation in patients with chronic obstructive pulmonary disease using home telehealth measurement data.

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.

Pilot study of remote telemonitoring in COPD.

BACKGROUND: Remote in-home monitoring (RM) of symptoms and physiological variables may allow early detection and treatment of exacerbations of chronic obstructive pulmonary disease (COPD). It is unclear whether RM improves patient outcomes or healthcare resource utilization. This study determined whether RM is feasible in patients with COPD and if RM reduces hospital admissions or length of stay (LOS) or improves health-related quality of life (HRQOL). SUBJECTS AND METHODS: Forty-four patients were randomized to standard best practice care (SBP) (n=22) or SBP+RM (n=22). RM involved daily recording of physiological variables, symptoms, and medication usage. RESULTS: There were no differences (mean±SD, SBP versus SBP+RM) in age (68±8 versus 70±9 years), gender (male:female 10:12 in both groups), or previous computer familiarity (59% versus 50%) between groups. The SBP group had a lower forced expiratory volume in 1 s (0.66±0.24 versus 0.91±0.34 L, p<0.01) and more current smokers (six versus none, p<0.05). There were no differences in number of COPD-related admissions/year (1.5±1.8 versus 1.3±1.7, p=0.76), COPD-related LOS days/year (15.6±19.4 versus 11.4±19.6, p=0.66), total admissions/year (2.2±2.1 versus 2.0±2.3, p=0.86), total LOS days/year (22.1±29.9 versus 21.6±30.4, p=0.88), or HRQOL between the two groups. CONCLUSIONS: The addition of RM to SBP was feasible but did not reduce healthcare utilization or improve quality of life in this group of patients already receiving comprehensive respiratory care.