Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatiotemporal Forecasting.

Graph neural networks (GNNs), especially dynamic GNNs, have become a research hotspot in spatiotemporal forecasting problems. While many dynamic graph construction methods have been developed, relatively few of them explore the causal relationship between neighbor nodes. Thus, the resulting models lack strong explainability for the causal relationship between the neighbor nodes of the dynamically generated graphs, which can easily lead to a risk in subsequent decisions. Moreover, few of them consider the uncertainty and noise of dynamic graphs based on the time series datasets, which are ubiquitous in real-world graph structure networks. In this article, we propose a novel dynamic diffusion-variational GNN (DVGNN) for spatiotemporal forecasting. For dynamic graph construction, an unsupervised generative model is devised. Two layers of graph convolutional network (GCN) are applied to calculate the posterior distribution of the latent node embeddings in the encoder stage. Then, a diffusion model is used to infer the dynamic link probability and reconstruct causal graphs (CGs) in the decoder stage adaptively. The new loss function is derived theoretically, and the reparameterization trick is adopted in estimating the probability distribution of the dynamic graphs by evidence lower bound (ELBO) during the backpropagation period. After obtaining the generated graphs, dynamic GCN and temporal attention are applied to predict future states. Experiments are conducted on four real-world datasets of different graph structures in different domains. The results demonstrate that the proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding root mean square error (RMSE) results while exhibiting higher robustness. Also, by F1-score and probability distribution analysis, we demonstrate that DVGNN better reflects the causal relationship and uncertainty of dynamic graphs. The website of the code is https://github.com/gorgen2020/DVGNN.

Exploring classical machine learning for identification of pathological lung auscultations.

The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

Semi-Supervised Learning for Forklift Activity Recognition from Controller Area Network (CAN) Signals.

Machine Activity Recognition (MAR) can be used to monitor manufacturing processes and find bottlenecks and potential for improvement in production. Several interesting results on MAR techniques have been produced in the last decade, but mostly on construction equipment. Forklift trucks, which are ubiquitous and highly important industrial machines, have been missing from the MAR research. This paper presents a data-driven method for forklift activity recognition that uses Controller Area Network (CAN) signals and semi-supervised learning (SSL). The SSL enables the utilization of large quantities of unlabeled operation data to build better classifiers; after a two-step post-processing, the recognition results achieve balanced accuracy of 88% for driving activities and 95% for load-handling activities on a hold-out data set. In terms of the Matthews correlation coefficient for five activity classes, the final score is 0.82, which is equal to the recognition results of two non-domain experts who use videos of the activities. A particular success is that context can be used to capture the transport of small weight loads that are not detected by the forklift's built-in weight sensor.

Attention Horizon as a Predictor for the Fuel Consumption Rate of Drivers.

Understanding the operation of complex assets such heavy-duty vehicles is essential for improving the efficiency, sustainability, and safety of future industry. Specifically, reducing energy consumption of transportation is crucially important for fleet operators, due to the impact it has on decreasing energy costs and lowering greenhouse gas emissions. Drivers have a high influence on fuel usage. However, reliably estimating driver performance is challenging. This is a key component of many eco-driving tools used to train drivers. Some key aspects of good, or efficient, drivers include being more aware of the surroundings, adapting to the road situations, and anticipating likely developments of the traffic conditions. With the development of IoT technologies and possibility of collecting high-precision and high-frequency data, even such vague concepts can be qualitatively measured, or at least approximated. In this paper, we demonstrate how the driver's degree of attention to the road can be automatically extracted from onboard sensor data. More specifically, our main contribution is introduction of a new metric, called attention horizon (AH); it can, fully automatically and based on readily-available IoT data, capture, differentiate, and evaluate a driver's behavior as the vehicle approaches a red traffic light. We suggest that our measure encapsulates complex concepts such as driver's "awareness" and "carefulness" in itself. This metric is extracted from the pedal positions in a 150 m trajectory just before stopping. We demonstrate that this metric is correlated with normalized fuel consumption rate (FCR) in the long term, making it a suitable tool for ranking and evaluating drivers. For example, over weekly periods we found a negative median correlation between AH and FCR with the absolute value of 0.156; while using monthly data, the value was 0.402.

Improving Medication Adherence Through Adaptive Digital Interventions (iMedA) in Patients With Hypertension: Protocol for an Interrupted Time Series Study.

BACKGROUND: There is a strong need to improve medication adherence (MA) for individuals with hypertension in order to reduce long-term hospitalization costs. We believe this can be achieved through an artificial intelligence agent that helps the patient in understanding key individual adherence risk factors and designing an appropriate intervention plan. The incidence of hypertension in Sweden is estimated at approximately 27%. Although blood pressure control has increased in Sweden, barely half of the treated patients achieved adequate blood pressure levels. It is a major risk factor for coronary heart disease and stroke as well as heart failure. MA is a key factor for good clinical outcomes in persons with hypertension. OBJECTIVE: The overall aim of this study is to design, develop, test, and evaluate an adaptive digital intervention called iMedA, delivered via a mobile app to improve MA, self-care management, and blood pressure control for persons with hypertension. METHODS: The study design is an interrupted time series. We will collect data on a daily basis, 14 days before, during 6 months of delivering digital interventions through the mobile app, and 14 days after. The effect will be analyzed using segmented regression analysis. The participants will be recruited in Region Halland, Sweden. The design of the digital interventions follows the just-in-time adaptive intervention framework. The primary (distal) outcome is MA, and the secondary outcome is blood pressure. The design of the digital intervention is developed based on a needs assessment process including a systematic review, focus group interviews, and a pilot study, before conducting the longitudinal interrupted time series study. RESULTS: The focus groups of persons with hypertension have been conducted to perform the needs assessment in a Swedish context. The design and development of digital interventions are in progress, and the interventions are planned to be ready in November 2020. Then, the 2-week pilot study for usability evaluation will start, and the interrupted time series study, which we plan to start in February 2021, will follow it. CONCLUSIONS: We hypothesize that iMedA will improve medication adherence and self-care management. This study could illustrate how self-care management tools can be an additional (digital) treatment support to a clinical one without increasing burden on health care staff. TRIAL REGISTRATION: ClinicalTrials.gov NCT04413500; https://clinicaltrials.gov/ct2/show/NCT04413500. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/24494.

Parallel orthogonal deep neural network.

Ensemble learning methods combine multiple models to improve performance by exploiting their diversity. The success of these approaches relies heavily on the dissimilarity of the base models forming the ensemble. This diversity can be achieved in many ways, with well-known examples including bagging and boosting. It is the diversity of the models within an ensemble that allows the ensemble to correct the errors made by its members, and consequently leads to higher classification or regression performance. A mistake made by a base model can only be rectified if other members behave differently on that particular instance, and provide the aggregator with enough information to make an informed decision. On the contrary, lack of diversity not only lowers model performance, but also wastes computational resources. Nevertheless, in the current state of the art ensemble approaches, there is no guarantee on the level of diversity achieved, and no mechanism ensuring that each member will learn a different decision boundary from the others. In this paper, we propose a parallel orthogonal deep learning architecture in which diversity is enforced by design, through imposing an orthogonality constraint. Multiple deep neural networks are created, parallel to each other. At each parallel layer, the outputs of different base models are subject to Gram-Schmidt orthogonalization. We demonstrate that this approach leads to a high level of diversity from two perspectives. First, the models make different errors on different parts of feature space, and second, they exhibit different levels of uncertainty in their decisions. Experimental results confirm the benefits of the proposed method, compared to standard deep learning models and well-known ensemble methods, in terms of diversity and, as a result, classification performance.

How Behavior Change Strategies are Used to Design Digital Interventions to Improve Medication Adherence and Blood Pressure Among Patients With Hypertension: Systematic Review.

BACKGROUND: Information on how behavior change strategies have been used to design digital interventions (DIs) to improve blood pressure (BP) control or medication adherence (MA) for patients with hypertension is currently limited. OBJECTIVE: Hypertension is a major modifiable risk factor for cardiovascular diseases and can be controlled with appropriate medication. Many interventions that target MA to improve BP are increasingly using modern digital technologies. This systematic review was conducted to discover how DIs have been designed to improve MA and BP control among patients with hypertension in the recent 10 years. Results were mapped into a matrix of change objectives using the Intervention Mapping framework to guide future development of technologies to improve MA and BP control. METHODS: We included all the studies regarding DI development to improve MA or BP control for patients with hypertension published in PubMed from 2008 to 2018. All the DI components were mapped into a matrix of change objectives using the Intervention Mapping technique by eliciting the key determinant factors (from patient and health care team and system levels) and targeted patient behaviors. RESULTS: The analysis included 54 eligible studies. The determinants were considered at two levels: patient and health care team and system. The most commonly described determinants at the patient level were lack of education, lack of self-awareness, lack of self-efficacy, and forgetfulness. Clinical inertia and an inadequate health workforce were the most commonly targeted determinants at the health care team and system level. Taking medication, interactive patient-provider communication, self-measurement, and lifestyle management were the most cited patient behaviors at both levels. Most of the DIs did not include support from peers or family members, despite its reported effectiveness and the rate of social media penetration. CONCLUSIONS: This review highlights the need to design a multifaceted DI that can be personalized according to patient behavior(s) that need to be changed to overcome the key determinant(s) of low adherence to medication or uncontrolled BP among patients with hypertension, considering different levels including patient and healthcare team and system involvement.

Pitfalls of medication adherence approximation through EHR and pharmacy records: Definitions, data and computation.

BACKGROUND AND PURPOSE: Patients' adherence to medication is a complex, multidimensional phenomenon. Dispensation data and electronic health records are used to approximate medication-taking through refill adherence. In-depth discussions on the adverse effects of data quality and computational differences are rare. The purpose of this article is to evaluate the impact of common pitfalls when computing medication adherence using electronic health records. PROCEDURES: We point out common pitfalls associated with the data and operationalization of adherence measures. We provide operational definitions of refill adherence and conduct experiments to determine the effect of the pitfalls on adherence estimations. We performed statistical significance testing on the impact of common pitfalls using a baseline scenario as reference. FINDINGS: Slight changes in definition can significantly skew refill adherence estimates. Pickup patterns cause significant disagreement between measures and the commonly used proportion of days covered. Common data related issues had a small but statistically significant (p < 0.05) impact on population-level and significant effect on individual cases. CONCLUSION: Data-related issues encountered in real-world administrative databases, which affect various operational definitions of refill adherence differently, can significantly skew refill adherence values, leading to false conclusions about adherence, particularly when estimating adherence for individuals.

Prediction and pattern analysis of medication refill adherence through electronic health records and dispensation data.

BACKGROUND AND PURPOSE: Low adherence to medication in chronic disease patients leads to increased morbidity, mortality, and healthcare costs. The widespread adoption of electronic prescription and dispensation records allows a more comprehensive overview of medication utilization. In combination with electronic health records (EHR), such data provides new opportunities for identifying patients at risk of nonadherence and provide more targeted and effective interventions. The purpose of this article is to study the predictability of medication adherence for a cohort of hypertensive patients, focusing on healthcare utilization factors under various predictive scenarios. Furthermore, we discover common proportion of days covered patterns (PDC-patterns) for patients with index prescriptions and simulate medication-taking behaviours that might explain observed patterns. PROCEDURES: We predict refill adherence focusing on factors of healthcare utilization, such as visits, prescription information and demographics of patient and prescriber. We train models with machine learning algorithms, using four different data splits: stratified random, patient, temporal forward prediction with and without index patients. We extract frequent, two-year long PDC-patterns using K-means clustering and investigate five simple models of medication-taking that can generate such PDC-patterns. FINDINGS: Model performance varies between data splits (AUC test set: 0.77-0.89). Including historical information increases the performance slightly in most cases (approx. 1-2% absolute AUC uplift). Models show low predictive performance (AUC test set: 0.56-0.66) on index-prescriptions and patients with sudden drops in PDC (Recall: 0.58-0.63). We find 21 distinct two-year PDC-patterns, ranging from good adherence to intermittent gaps and early discontinuation in the first or second year. Simulations show that observed PDC-patterns can only be explained by specific medication consumption behaviours. CONCLUSIONS: Prediction models developed using EHR exhibit bias towards patients with high healthcare utilization. Even though actual medication-taking is not observable, consumption patterns may not be as arbitrary, provided that medication refilling and consumption is linked.

Readmission prediction using deep learning on electronic health records.

Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, F1-measure) and cost-savings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; F1: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients.