It is well established that exercise improves cardiovascular and all-cause mortality, although an ideal dose of exercise is not known. The physical activity guidelines currently recommend 150 minutes per week of moderate-intensity exercise or 75 minutes of vigorous-intensity activity. Most individuals do not engage in adequate exercise, although a safe upper limit does not exist and a too much exercise hypothesis has recently emerged. This review of the literature analyzes studies that have evaluated exercise dose response on all-cause and cardiovascular mortality for the purpose of determining safe and effective exercise prescriptions. Searches were performed in PubMed and CINAHL between 2010 and 2018 to identify six studies that met inclusion criteria. Moderate-intensity exercise reduced all-cause mortality in five of six studies, whereas low-dose exercise most effectively improved all-cause mortality in three studies, and cardiovascular mortality in one study. Vigorous-intensity exercise or extreme doses demonstrated variable outcomes and remain controversial; two studies found vigorous-intensity exercise beneficial to improve health, two studies discouraged vigorous exercise, and two studies had less conclusive outcomes. It is not surprising that any amount of exercise improves health compared with none at all, with the greatest benefits observed when sedentary individuals began exercising. Low-dose exercise should be recommended to everyone with a goal of meeting the minimal requirements according to guidelines for decreased all-cause and cardiovascular mortality. Additional research to more thoroughly understand exercise dose response and motivate individuals to improve exercise engagement is currently warranted.

Context: Respiratory morbidity is a leading cause of children’s consultations with general practitioners. Auscultation, the act of listening to breath sounds, is a crucial diagnostic method for respiratory system diseases. Problem: Parents and caregivers often lack the necessary knowledge and experience to identify subtle differences in children’s breath sounds. Furthermore, obtaining reliable feedback from young children about their physical condition is challenging. Methods: The use of a human–artificial intelligence (AI) tool is an essential component for screening and monitoring young children’s respiratory diseases. Using clinical data to design and validate the proposed approaches, we propose novel methods for recognizing and classifying children’s breath sounds. Different breath sound signals were analyzed in the time domain, frequency domain, and using spectrogram representations. Breath sound detection and segmentation were performed using digital signal processing techniques. Multiple features—including Mel–Frequency Cepstral Coefficients (MFCCs), Linear Prediction Coefficients (LPCs), Linear Prediction Cepstral Coefficients (LPCCs), spectral entropy, and Dynamic Linear Prediction Coefficients (DLPCs)—were extracted to capture both time and frequency characteristics. These features were then fed into various classifiers, including K-Nearest Neighbor (KNN), artificial neural networks (ANNs), hidden Markov models (HMMs), logistic regression, and decision trees, for recognition and classification. Main Findings: Experimental results from across 120 infants and preschoolers (2 months to 6 years) with respiratory disease (30 asthma, 30 croup, 30 pneumonia, and 30 normal) verified the performance of the proposed approaches. Conclusions: The proposed AI system provides a real-time diagnostic platform to improve clinical respiratory management and outcomes in young children, thereby reducing healthcare costs. Future work exploring additional respiratory diseases is warranted.

Assessment of personal exposure in the external environment commonly relies on global positioning system (GPS) measurements. However, it has been challenging to determine exposures accurately due to missing data in GPS trajectories. In environmental health research using GPS, missing data are often discarded or are typically imputed based on the last known location or linear interpolation. Imputation is said to mitigate bias in exposure measures, but methods used are hardly evaluated against ground truth. Widely used imputation methods assume that a person is either stationary or constantly moving during the missing interval. Relaxing this assumption, we propose a method for imputing locations as a function of a person’s likely movement state (stop, move) during the missing interval. We then evaluate the proposed method in terms of the accuracy of imputed location, movement state, and daily mobility measures such as the number of trips and time spent on places visited. Experiments based on real data collected by participants (n=59) show that the proposed approach outperforms existing methods. Imputation to the last known location can lead to large deviation from the actual location when gap distance is large. Linear interpolation is shown to result in large errors in mobility measures. Researchers should be aware that the different treatment of missing data can affect the spatiotemporal accuracy of GPS-based exposure assessments.