Utilizing time series data embedded in electronic health records to develop continuous mortality risk prediction models using hidden Markov models: A sepsis case study.

Continuous mortality risk monitoring is instrumental to manage a patient's care and to efficiently utilize the limited hospital resources. Due to incompleteness and irregularities of electronic health records (EHR), developing continuous mortality risk prediction using EHR data is a challenge. In this study, we propose a framework to continuously monitor mortality risk, and apply it to the real-world EHR data. The proposed method employs hidden Markov models (temporal technique) that take account of both the previous state of patient's health and the current value of clinical signs. Following the Sepsis-3 definition, we selected 3898 encounters of patients with suspected infection to compare the performance of temporal and non-temporal methods (Decision Tree (DT), Logistic Regression (LR), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM)). The area under receiver operating characteristics (AUROC) curve, sensitivity, specificity and G-mean were used as performance measures. On the selected data, the AUROC of the proposed temporal framework (0.87) is 9-12% greater than the nontemporal methods (DT: 0.78, NB: 0.79, SVM: 0.79, LR: 0.80 and RF: 0.80). The results also show that our model (G-mean=0.78) provides a better balance between sensitivity and specificity compared to clinically acceptable bed-side criteria (G-mean=0.71). The proposed framework leverages the longitudinal data available in EHR and performs better than the non-temporal methods. The proposed method facilitates information related to the time of change of the patient's health that may help practitioners to plan early and develop effective treatment strategies.

Intercomparison of Small Unmanned Aircraft System (sUAS) Measurements for Atmospheric Science during the LAPSE-RATE Campaign.

Small unmanned aircraft systems (sUAS) are rapidly transforming atmospheric research. With the advancement of the development and application of these systems, improving knowledge of best practices for accurate measurement is critical for achieving scientific goals. We present results from an intercomparison of atmospheric measurement data from the Lower Atmospheric Process Studies at Elevation-a Remotely piloted Aircraft Team Experiment (LAPSE-RATE) field campaign. We evaluate a total of 38 individual sUAS with 23 unique sensor and platform configurations using a meteorological tower for reference measurements. We assess precision, bias, and time response of sUAS measurements of temperature, humidity, pressure, wind speed, and wind direction. Most sUAS measurements show broad agreement with the reference, particularly temperature and wind speed, with mean value differences of 1.6 ± 2 . 6 ∘ C and 0.22 ± 0 . 59 m/s for all sUAS, respectively. sUAS platform and sensor configurations were found to contribute significantly to measurement accuracy. Sensor configurations, which included proper aspiration and radiation shielding of sensors, were found to provide the most accurate thermodynamic measurements (temperature and relative humidity), whereas sonic anemometers on multirotor platforms provided the most accurate wind measurements (horizontal speed and direction). We contribute both a characterization and assessment of sUAS for measuring atmospheric parameters, and identify important challenges and opportunities for improving scientific measurements with sUAS.

Goal feedback from whom? A physical activity intervention using an N-of-1 RCT.

OBJECTIVE: Adolescents are not meeting the recommended guidelines for physical activity. Social support and self-regulatory skills are two factors known to impact physical activity and sedentary behaviour. The study sought to examine how targeting feedback as part of a self-regulatory process could increase physical activity, and the individual who should be providing the feedback. DESIGN: The study utilised an aggregated N-of-1 RCT which allows for an iterative process of intervention development, and examines variability within participants to answer the question for whom did the intervention work. Ten adolescents (ages 13-18) set a daily physical activity goal. Adolescents received a SMS text message providing feedback on goal attainment daily from a parent, peer, behavioural health specialist; or no text message (control). MAIN OUTCOME MEASURES: A bioharness heart rate monitor assessed heart rate as proxy for goal attainment. Adolescents also self-monitored their physical activity in the Calorie Counter and Diet Tracker by MyFitnessPalTM app (commercially available). RESULTS: Intervention demonstrated a significant effect for 30% of the sample in increasing MVPA (Mincrease = 52 min), with no significant effect on sedentary behaviour. CONCLUSION: A single occasion of text messaging from the right person can produce changes, however, careful consideration should be given to who provides the feedback.

Bidirectional Associations Between Psychological States and Physical Activity in Adolescents: A mHealth Pilot Study.

Objective: To understand the predictors and consequences of adolescent moderate-to-vigorous physical activity (MVPA) and sedentary behavior in nearly real-time. Methods: Participants were 26 adolescents ( M age = 15.96, SD = 1.56) who provided 80 self-reports of subjective states and continuous objective reports of MVPA and sedentary behavior over 20 days. Results: Random effects were observed for all of the models with affect and feeling variables predicting MVPA. There was a negative fixed effect for within-person positive affect and sedentary behavior and the inverse association for negative affect. Within-person MVPA was a significant positive predictor of positive affect and energy. There was a random effect for within-person MVPA and fatigue. There was a significant random effect for within-person sedentary behavior predicting positive affect. Within-person sedentary behavior was a significant negative predictor of energy. Conclusions: Findings highlight the importance of the intrapersonal nature of the associations among subjective states and physical activity.

The promise of wearable sensors and ecological momentary assessment measures for dynamical systems modeling in adolescents: a feasibility and acceptability study.

Intervention development can be accelerated by using wearable sensors and ecological momentary assessment (EMA) to study how behaviors change within a person. The purpose of this study was to determine the feasibility and acceptability of a novel, intensive EMA method for assessing physiology, behavior, and psychosocial variables utilizing two objective sensors and a mobile application (app). Adolescents (n = 20) enrolled in a 20-day EMA protocol. Participants wore a physiological monitor and an accelerometer that measured sleep and physical activity and completed four surveys per day on an app. Participants provided approximately 81 % of the expected survey data. Participants were compliant to the wrist-worn accelerometer (75.3 %), which is a feasible measurement of physical activity/sleep (74.1 % complete data). The data capture (47.8 %) and compliance (70.28 %) with the physiological monitor were lower than other study variables. The findings support the use of an intensive assessment protocol to study real-time relationships between biopsychosocial variables and health behaviors.

Controlling a robot with intention derived from motion.

We present a novel, sophisticated intention-based control system for a mobile robot built from an extremely inexpensive webcam and radio-controlled toy vehicle. The system visually observes humans participating in various playground games and infers their goals and intentions through analyzing their spatiotemporal activity in relation to itself and each other, and then builds a coherent narrative out of the succession of these intentional states. Starting from zero information about the room, the rules of the games, or even which vehicle it controls, it learns rich relationships between players, their goals and intentions, probing uncertain situations with its own behavior. The robot is able to watch people playing various playground games, learn the roles and rules that apply to specific games, and participate in the play. The narratives it constructs capture essential information about the observed social roles and types of activity. After watching play for a short while, the system is able to participate appropriately in the games. We demonstrate how the system acts appropriately in scenarios such as chasing, follow-the-leader, and variants of tag.

Apoptosis, neurogenesis, and information content in Hebbian networks.

The functional significance of alternate forms of plasticity in the brain (such as apoptosis and neurogenesis) is not easily observable with biological methods. Employing Hebbian dynamics for synaptic weight development, a three-layer neural network model of the hippocampus is used to simulate nonsupervised (autonomous) learning in the context of apoptosis and neurogenesis. This learning is applied to the characters of a pair of related alphabets, first the Roman and then the Greek, resulting in a set of encodings endogenously developed by the network. The learning performance takes the form of a U-shaped curve, showing that apoptosis and neurogenesis favorably inform memory development. We also discover that networks that converge very quickly on the Roman alphabet take much longer to handle the Greek, while networks which converge over an extended timeframe can then adapt very quickly to the new language. We find that the effect becomes increasingly pronounced as the number of neurons in the dentate gyrus layer decreases, and identify a strong correlation between cases where the Roman alphabet is quickly learned and cases where a few neurons saturate many of their weights almost immediately, minimizing participation of other neurons. Cases where learning the Roman alphabet requires more time lead to larger numbers of neurons participating with a larger diversity in synaptic weights. We present an information-theoretic argument about why this implies a better, more flexible learning system and why it leads to faster subsequent correlated Greek alphabet learning, and propose that the reason that apoptosis and neurogenesis work is that they promote this effect.