Search

BackgroundMedication nonadherence is a critical problem with severe implications in individuals at risk for atherosclerotic cardiovascular disease. Many studies have attempted to predict medication adherence in this population, but few, if any, have been effective in prediction, sug-gesting that essential risk factors remain unidentified.ObjectiveThis study's objective was to (1) establish an accurate prediction model of medi-cation adherence in individuals at risk for atherosclerotic cardiovascular disease and (2) identify significant contributing factors to the predictive accuracy of medication adherence. In particular, we aimed to use only the baseline questionnaire data to assess medication adherence prediction feasibility.MethodsA sample of 40 individuals at risk for atherosclerotic cardiovascular disease was recruited for an eight-week feasibility study. After collecting baseline data, we recorded data from a pillbox that sent events to a cloud-based server. Health measures and medication use events were analyzed using machine learning algorithms to identify variables that best predict medication adherence.ResultsOur adherence prediction model, based on only the ten most relevant variables, achieved an average error rate of 12.9%. Medication adherence was closely correlated with being encouraged to play an active role in their treatment, having confidence about what to do in an emergency, knowledge about their medications, and having a special person in their life.ConclusionsOur results showed the significance of clinical and psychosocial factors for predicting medication adherence in people at risk for atherosclerotic cardiovascular diseases. Clini-cians and researchers can use these factors to stratify individuals to make evidence-based decisions to reduce the risks.

Generative adversarial networks have become a de facto approach to generate synthetic data points that resemble their real counterparts. We tackle the situation where the realism of individual samples is not the sole criterion for synthetic data generation. Additional constraints such as privacy preservation, distribution realism, and diversity promotion may also be essential to optimize. To address this challenge, we introduce HydraGAN, a multi-agent network that performs multi-objective synthetic data generation. We theoretically verify that training the HydraGAN system, containing a single generator and an arbitrary number of discriminators, leads to a Nash equilibrium. Experimental results for six datasets indicate that HydraGAN consistently outperforms prior methods in maximizing the Area under the Radar Chart, balancing a combination of cooperative or competitive data generation goals. [ABSTRACT FROM AUTHOR]

Background: This study examined associations of device‐measured physical activity and sedentary time with quality of life (QOL) and fatigue in newly diagnosed breast cancer patients in the Alberta Moving Beyond Breast Cancer (AMBER) cohort study. Methods: After diagnosis, 1409 participants completed the SF‐36 version 2 and the Fatigue Scale, wore an ActiGraph device on their right hip to measure physical activity, and an activPAL device on their thigh to measure sedentary time (sitting/lying) and steps. ActiGraph data was analyzed using a hybrid machine learning method (R Sojourn package, Soj3x) and activPAL data were analyzed using activPAL algorithms (PAL Software version 8). Quantile regression was used to examine cross‐sectional associations of QOL and fatigue with steps, physical activity, and sedentary hours at the 25th, 50th, and 75th percentiles of the QOL and fatigue distributions. Results: Total daily moderate and vigorous physical activity (MVPA) hours was positively associated with better physical QOL at the 25th (β = 2.14, p = <.001), 50th (β = 1.98, p = <.001), and 75th percentiles (β = 1.25, p =.003); better mental QOL at the 25th (β = 1.73, p =.05) and 50th percentiles (β = 1.07, p =.03); and less fatigue at the 25th (β = 4.44, p <.001), 50th (β = 3.08, p = <.001), and 75th percentiles (β = 1.51, p = <.001). Similar patterns of associations were observed for daily steps. Total sedentary hours was associated with worse fatigue at the 25th (β = −0.58, p =.05), 50th (β = −0.39, p =.06), and 75th percentiles (β = −0.24, p =.02). Sedentary hours were not associated with physical or mental QOL. Conclusions: MVPA and steps were associated with better physical and mental QOL and less fatigue in newly diagnosed breast cancer patients. Higher sedentary time was associated with greater fatigue symptoms. Consistent and significant associations emerged between device‐measured physical activity, quality of life, and fatigue outcomes in this large cohort of newly diagnosed breast cancer patients. These results may be used to inform clinical practice and policies about incorporating physical activity and reducing sedentary time as adjuvant therapy for newly diagnosed breast cancer patients starting treatment. [ABSTRACT FROM AUTHOR]

We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes limitations of the oracle into account when selecting sensor data for annotation by the oracle. Our approach is inspired by human-beings’ limited capacity to respond to prompts on their mobile device. This capacity constraint is manifested not only in the number of queries that a person can respond to in a given time-frame but also in the time lag between the query issuance and the oracle response. We introduce the notion of mindful active learning and propose a computational framework, called EMMA, to maximize the active learning performance taking informativeness of sensor data, query budget, and human memory into account. We formulate this optimization problem, propose an approach to model memory retention, discuss the complexity of the problem, and propose a greedy heuristic to solve the optimization problem. Additionally, we design an approach to perform mindful active learning in batch where multiple sensor observations are selected simultaneously for querying the oracle. We demonstrate the effectiveness of our approach using three publicly available activity datasets and by simulating oracles with various memory strengths. We show that the activity recognition accuracy ranges from 21 to 97 percent depending on memory strength, query budget, and difficulty of the machine learning task. Our results also indicate that EMMA achieves an accuracy level that is, on average, 13.5 percent higher than the case when only informativeness of the sensor data is considered for active learning. Moreover, we show that the performance of our approach is at most 20 percent less than the experimental upper-bound and up to 80 percent higher than the experimental lower-bound. To evaluate the performance of EMMA for batch active learning, we design two instantiations of EMMA to perform active learning in batch mode. We show that these algorithms improve the algorithm training time at the cost of a reduced accuracy in performance. Another finding in our work is that integrating clustering into the process of selecting sensor observations for batch active learning improves the activity learning performance by 11.1 percent on average, mainly due to reducing the redundancy among the selected sensor observations. We observe that mindful active learning is most beneficial when the query budget is small and/or the oracle’s memory is weak. This observation emphasizes advantages of utilizing mindful active learning strategies in mobile health settings that involve interaction with older adults and other populations with cognitive impairments. [ABSTRACT FROM AUTHOR]

Activity recognizers are challenging to design for continuous, in-home settings. However, they are notoriously difficult to create when there is more than one resident in the home. Despite recent efforts, there remains a need for an algorithm that can estimate the number of residents in the house, split a time series stream into separate substreams, and accurately identify each resident's activities. To address this challenge, we introduce Gamut. This novel unsupervised method jointly estimates the number of residents and associates sensor readings with those residents, based on a multi-target Gaussian mixture probability hypothesis density filter. We hypothesize that the proposed method will offer robust recognition for homes with two or more residents. In experiments with labeled data collected from 50 single-resident and 11 multi-resident homes, we observe that Gamut outperforms previous unsupervised and supervised methods, offering a robust strategy to track behavioral routines in complex settings.