Abstract-Accurate identification of physical activity types has been achieved in laboratory conditions using single-site accelerometers and classification algorithms. This methodology is then applied to free-living subjects to determine activity behaviour. This study aimed at analysing the reproducibility of the accuracy of laboratory-trained classification algorithms in free-living subjects during daily life. A support vector machine (SVM), a feed-forward neural network (NN) and a decision tree (DT) were trained with data collected by a waist-mounted accelerometer during a laboratory trial. The reproducibility of the classification performance was tested on data collected in daily life using a multiple-site accelerometer (IDEEA) augmented with an activity diary for 20 healthy subjects (age: 30 ± 9; BMI: 23.0 ± 2.6 kg/m 2 ). Leave-one-subject-out cross-validation of the training data showed accuracies of 95.1 ± 4.3%, 91.4 ± 6.7% and 92.2 ± 6.6% for the SVM, NN and DT, respectively. All algorithms showed a significantly decreased accuracy in daily life as compared to the reference truth represented by the IDEEA and diary classifications (75.6 ± 10.4%, 74.8 ± 9.7%, and 72.2 ± 10.3%; p<0.05). In conclusion, cross-validation of training data overestimates the accuracy of the classification algorithms in daily life.Index Terms-Assessment of daily physical activity, classification algorithms, IDEEA, physical activity, triaxial accelerometer

BackgroundHeart Failure (HF) is a common reason for hospitalization. Admissions might be prevented by early detection of and intervention for decompensation. Conventionally, changes in weight, a possible measure of fluid accumulation, have been used to detect deterioration. Transthoracic impedance may be a more sensitive and accurate measure of fluid accumulation.ObjectiveIn this study, we review previously proposed predictive algorithms using body weight and noninvasive transthoracic bio-impedance (NITTI) to predict HF decompensations.MethodsWe monitored 91 patients with chronic HF for an average of 10 months using a weight scale and a wearable bio-impedance vest. Three algorithms were tested using either simple rule-of-thumb differences (RoT), moving averages (MACD), or cumulative sums (CUSUM).ResultsAlgorithms using NITTI in the 2 weeks preceding decompensation predicted events (P<.001); however, using weight alone did not. Cross-validation showed that NITTI improved sensitivity of all algorithms tested and that trend algorithms provided the best performance for either measurement (Weight-MACD: 33%, NITTI-CUSUM: 60%) in contrast to the simpler rules-of-thumb (Weight-RoT: 20%, NITTI-RoT: 33%) as proposed in HF guidelines.ConclusionsNITTI measurements decrease before decompensations, and combined with trend algorithms, improve the detection of HF decompensation over current guideline rules; however, many alerts are not associated with clinically overt decompensation.

Blood pressure (BP) and heart rate (HR) are often captured in conjunction with weight in telemonitoring systems, but the additional prognostic potential of daily measurements of BP and HR in providing information on upcoming hospitalizations for worsening heart failure (HFH) have not been explored thoroughly. We retrospectively analyzed 267 daily home-telemonitored heart failure (HF) subjects. We extracted those episodes of HFHs that had sufficient data entries in the days leading up to hospitalization and tested the prognostic potential of 48 trend features based on weight, systolic BP, diastolic BP, pulse pressure (PP) and HR with a Naïve Bayesian model. The single best-performing trend feature-with a cross-validated estimate of 0.64 for the area under the curve (AUC) with a standard deviation (SD) of 0.01-is based on a 2-day weight trend. The best multivariate feature set (cross-validated AUC=0.70, SD=0.01) comprises of 2-day trend features based on weight, systolic BP, and HR. There were large variations in the weight trends preceding hospitalizations and weight-change alone had a modest predictive ability. Readily interpretable features capturing trends in BP and HR provided additional prognostic information and can be used for improving classification.