ABSTRACT
Chronic disease management and follow-up are vital for realizing sustained patient well-being and optimal health outcomes. Recent advancements in wearable technologies, particularly wrist-worn devices, offer promising solutions for longitudinal patient monitoring, replacing subjective, intermittent self-reporting with objective, continuous monitoring. However, collecting and analyzing data from wearables presents several challenges, such as data entry errors, non-wear periods, missing data, and wearable artifacts. In this work, we explore these data analysis challenges using two real-world datasets (mBrain21 and ETRI lifelog2020). We introduce practical countermeasures, including participant compliance visualizations, interaction-triggered questionnaires to assess personal bias, and an optimized pipeline for detecting non-wear periods. Additionally, we propose a visualization-oriented approach to validate processing pipelines using scalable tools such as tsflex and Plotly-Resampler. Lastly, we present a bootstrapping methodology to evaluate the variability of wearable-derived features in the presence of partially missing data segments. Prioritizing transparency and reproducibility, we provide open access to our detailed code examples, facilitating adaptation in future wearable research. In conclusion, our contributions provide actionable approaches for improving wearable data collection and analysis.
Subject(s)
Data Accuracy , Monitoring, Ambulatory , Wearable Electronic Devices , Wrist , Humans , Monitoring, Ambulatory/instrumentation , Monitoring, Ambulatory/methods , Female , Male , Reproducibility of Results , Adult , Surveys and QuestionnairesABSTRACT
BACKGROUND: In healthcare, an increasing collaboration can be noticed between different caregivers, especially considering the shift to homecare. To provide optimal patient care, efficient coordination of data and workflows between these different stakeholders is required. To achieve this, data should be exposed in a machine-interpretable, reusable manner. In addition, there is a need for smart, dynamic, personalized and performant services provided on top of this data. Flexible workflows should be defined that realize their desired functionality, adhere to use case specific quality constraints and improve coordination across stakeholders. User interfaces should allow configuring all of this in an easy, user-friendly way. METHODS: A distributed, generic, cascading reasoning reference architecture can solve the presented challenges. It can be instantiated with existing tools built upon Semantic Web technologies that provide data-driven semantic services and constructing cross-organizational workflows. These tools include RMLStreamer to generate Linked Data, DIVIDE to adaptively manage contextually relevant local queries, Streaming MASSIF to deploy reusable services, AMADEUS to compose semantic workflows, and RMLEditor and Matey to configure rules to generate Linked Data. RESULTS: A use case demonstrator is built on a scenario that focuses on personalized smart monitoring and cross-organizational treatment planning. The performance and usability of the demonstrator's implementation is evaluated. The former shows that the monitoring pipeline efficiently processes a stream of 14 observations per second: RMLStreamer maps JSON observations to RDF in 13.5 ms, a C-SPARQL query to generate fever alarms is executed on a window of 5 s in 26.4 ms, and Streaming MASSIF generates a smart notification for fever alarms based on severity and urgency in 1539.5 ms. DIVIDE derives the C-SPARQL queries in 7249.5 ms, while AMADEUS constructs a colon cancer treatment plan and performs conflict detection with it in 190.8 ms and 1335.7 ms, respectively. CONCLUSIONS: Existing tools built upon Semantic Web technologies can be leveraged to optimize continuous care provisioning. The evaluation of the building blocks on a realistic homecare monitoring use case demonstrates their applicability, usability and good performance. Further extending the available user interfaces for some tools is required to increase their adoption.
Subject(s)
Home Care Services , Workflow , Semantics , HumansABSTRACT
The detection of Activities of Daily Living (ADL) holds significant importance in a range of applications, including elderly care and health monitoring. Our research focuses on the relevance of ADL detection in elderly care, highlighting the importance of accurate and unobtrusive monitoring. In this paper, we present a novel approach that that leverages smartphone data as the primary source for detecting ADLs. Additionally, we investigate the possibilities offered by ambient sensors installed in smart home environments to complement the smartphone data and optimize the ADL detection. Our approach uses a Long Short-Term Memory (LSTM) model. One of the key contributions of our work is defining ADL detection as a multilabeling problem, allowing us to detect different activities that occur simultaneously. This is particularly valuable since in real-world scenarios, individuals can perform multiple activities concurrently, such as cooking while watching TV. We also made use of unlabeled data to further enhance the accuracy of our model. Performance is evaluated on a real-world collected dataset, strengthening reliability of our findings. We also made the dataset openly available for further research and analysis. Results show that utilizing smartphone data alone already yields satisfactory results, above 50% true positive rate and balanced accuracy for all activities, providing a convenient and non-intrusive method for ADL detection. However, by incorporating ambient sensors, as an additional data source, one can improve the balanced accuracy of the ADL detection by 7% and 8% of balanced accuracy and true positive rate respectively, on average.
Subject(s)
Activities of Daily Living , Smartphone , Humans , Reproducibility of Results , Cooking , Memory, Long-TermABSTRACT
OBJECTIVE: To investigate the changes in activity energy expenditure (AEE) throughout daytime cluster headache (CH) attacks in patients with chronic CH and to evaluate the usefulness of actigraphy as a digital biomarker of CH attacks. BACKGROUND: CH is a primary headache disorder characterized by attacks of severe to very severe unilateral pain (orbital, supraorbital, temporal, or in any combination of these sites), with ipsilateral cranial autonomic symptoms and/or a sense of restlessness or agitation. We hypothesized increased AEE from hyperactivity during attacks measured by actigraphy. METHODS: An observational study including patients with chronic CH was conducted. During 21 days, patients wore an actigraphy device on the nondominant wrist and recorded CH attack-related data in a dedicated smartphone application. Accelerometer data were used for the calculation of AEE before and during daytime CH attacks that occurred in ambulatory settings, and without restrictions on acute and preventive headache treatment. We compared the activity and movements during the pre-ictal, ictal, and postictal phases with data from wrist-worn actigraphy with time-concordant intervals during non-headache periods. RESULTS: Four patients provided 34 attacks, of which 15 attacks met the eligibility criteria for further analysis. In contrast with the initial hypothesis of increased energy expenditure during CH attacks, a decrease in movement was observed during the pre-ictal phase (30 min before onset to onset) and during the headache phase. A significant decrease (p < .01) in the proportion of high-intensity movement during headache attacks, of which the majority were oxygen-treated, was observed. This trend was less present for low-intensity movements. CONCLUSION: The unexpected decrease in AEE during the pre-ictal and headache phase of daytime CH attacks in patients with chronic CH under acute and preventive treatment in ambulatory settings has important implications for future research on wrist actigraphy in CH.
Subject(s)
Cluster Headache , Humans , Cluster Headache/diagnosis , Cluster Headache/therapy , Wrist , Actigraphy , Pain , HeadacheABSTRACT
Human activity recognition (HAR) algorithms today are designed and evaluated on data collected in controlled settings, providing limited insights into their performance in real-world situations with noisy and missing sensor data and natural human activities. We present a real-world HAR open dataset compiled from a wristband equipped with a triaxial accelerometer. During data collection, participants had autonomy in their daily life activities, and the process remained unobserved and uncontrolled. A general convolutional neural network model was trained on this dataset, achieving a mean balanced accuracy (MBA) of 80%. Personalizing the general model through transfer learning can yield comparable and even superior results using fewer data, with the MBA improving to 85%. To emphasize the issue of insufficient real-world training data, we conducted training of the model using the public MHEALTH dataset, resulting in 100% MBA. However, upon evaluating the MHEALTH-trained model on our real-world dataset, the MBA drops to 62%. After personalizing the model with real-world data, an improvement of 17% in the MBA is achieved. This paper showcases the potential of transfer learning to make HAR models trained in different contexts (lab vs. real-world) and on different participants perform well for new individuals with limited real-world labeled data available.
Subject(s)
Algorithms , Human Activities , Humans , Data Collection , Learning , Neural Networks, ComputerABSTRACT
BACKGROUND: Atrial Fibrillation (AF) is the most common arrhythmia in the intensive care unit (ICU) and is associated with increased morbidity and mortality. Identification of patients at risk for AF is not routinely performed as AF prediction models are almost solely developed for the general population or for particular ICU populations. However, early AF risk identification could help to take targeted preemptive actions and possibly reduce morbidity and mortality. Predictive models need to be validated across hospitals with different standards of care and convey their predictions in a clinically useful manner. Therefore, we designed AF risk models for ICU patients using uncertainty quantification to provide a risk score and evaluated them on multiple ICU datasets. METHODS: Three CatBoost models, utilizing feature windows comprising data 1.5-13.5, 6-18, or 12-24 hours before AF occurrence, were built using 2-repeat-10-fold cross-validation on AmsterdamUMCdb, the first freely available European ICU database. Furthermore, AF Patients were matched with no-AF patients for training. Transferability was validated using a direct and a recalibration evaluation on two independent external datasets, MIMIC-IV and GUH. The calibration of the predicted probability, used as an AF risk score, was measured using the Expected Calibration Error (ECE) and the presented Expected Signed Calibration Error (ESCE). Additionally, all models were evaluated across time during the ICU stay. RESULTS: The model performance reached Areas Under the Curve (AUCs) of 0.81 at internal validation. Direct external validation showed partial generalizability with AUCs reaching 0.77. However, recalibration resulted in performances matching or exceeding that of the internal validation. All models furthermore showed calibration capabilities demonstrating adequate risk prediction competence. CONCLUSION: Ultimately, recalibrating models reduces the challenge of generalization to unseen datasets. Moreover, utilizing the patient-matching methodology together with the assessment of uncertainty calibration can serve as a step toward the development of clinical AF prediction models.
Subject(s)
Atrial Fibrillation , Humans , Atrial Fibrillation/diagnosis , Atrial Fibrillation/epidemiology , Risk Factors , Critical Care , Intensive Care Units , Machine LearningABSTRACT
BACKGROUND: Several studies have indicated that commonly used piperacillin-tazobactam (TZP) and meropenem (MEM) dosing regimens lead to suboptimal plasma concentrations for a range of pharmacokinetic/pharmacodynamic (PK/PD) targets in intensive care unit (ICU) patients. These targets are often based on a hypothetical worst-case scenario, possibly overestimating the percentage of suboptimal concentrations. We aimed to evaluate the pathogen-based clinically relevant target attainment (CRTA) and therapeutic range attainment (TRA) of optimized continuous infusion dosing regimens of TZP and MEM in surgical ICU patients. METHODS: A single center prospective observational study was conducted between March 2016 and April 2019. Free plasma concentrations were calculated by correcting total plasma concentrations, determined on remnants of blood gas samples by ultra-performance liquid chromatography with tandem mass spectrometry, for their protein binding. Break points (BP) of identified pathogens were derived from epidemiological cut-off values. CRTA was defined as a corrected measured total serum concentration above the BP and calculated for increasing BP multiplications up to 6 × BP. The upper limit of the therapeutic range was set at 157.2 mg/L for TZP and 45 mg/L for MEM. As a worst-case scenario, a BP of 16 mg/L for TZP and 2 mg/L for MEM was used. RESULTS: 781 unique patients were included with 1036 distinctive beta-lactam antimicrobial prescriptions (731 TZP, 305 MEM) for 1003 unique infections/prophylactic regimens (750 TZP, 323 MEM). 2810 samples were available (1892 TZP, 918 MEM). The median corrected plasma concentration for TZP was 86.4 mg/L [IQR 56.2-148] and 16.2 mg/L [10.2-25.5] for MEM. CRTA and TRA was consistently higher for the pathogen-based scenario than for the worst-case scenario, but nonetheless, a substantial proportion of samples did not attain commonly used PK/PD targets. CONCLUSION: Despite these pathogen-based data demonstrating that CRTA and TRA is higher than in the often-used theoretical worst-case scenario, a substantial proportion of samples did not attain commonly used PK/PD targets when using optimised continuous infusion dosing regimens. Therefore, more dosing optimization research seems warranted. At the same time, a 'pathogen-based analysis' approach might prove to be more sensible than a worst-case scenario approach when evaluating target attainment and linked clinical outcomes.
ABSTRACT
A healthy and safe indoor environment is an important part of containing the coronavirus disease 2019 (COVID-19) pandemic. Therefore, this work presents a real-time Internet of things (IoT) software architecture to automatically calculate and visualize a COVID-19 aerosol transmission risk estimation. This risk estimation is based on indoor climate sensor data, such as carbon dioxide (CO2) and temperature, which is fed into Streaming MASSIF, a semantic stream processing platform, to perform the computations. The results are visualized on a dynamic dashboard that automatically suggests appropriate visualizations based on the semantics of the data. To evaluate the complete architecture, the indoor climate during the student examination periods of January 2020 (pre-COVID) and January 2021 (mid-COVID) was analyzed. When compared to each other, we observe that the COVID-19 measures in 2021 resulted in a safer indoor environment.
Subject(s)
Air Pollution, Indoor , COVID-19 , Humans , Air Pollution, Indoor/analysis , Respiratory Aerosols and Droplets , Software , TemperatureABSTRACT
Traditionally, neural networks are viewed from the perspective of connected neuron layers represented as matrix multiplications. We propose to compose these weight matrices from a set of orthogonal basis matrices by approaching them as elements of the real matrices vector space under addition and multiplication. Making use of the Kronecker product for vectors, this composition is unified with the singular value decomposition (SVD) of the weight matrix. The orthogonal components of this SVD are trained with a descent curve on the Stiefel manifold using the Cayley transform. Next, update equations for the singular values and initialization routines are derived. Finally, acceleration for stochastic gradient descent optimization using this formulation is discussed. Our proposed method allows more parameter-efficient representations of weight matrices in neural networks. These decomposed weight matrices achieve maximal performance in both standard and more complicated neural architectures. Furthermore, the more parameter-efficient decomposed layers are shown to be less dependent on optimization and better conditioned. As a tradeoff, training time is increased up to a factor of 2. These observations are consequently attributed to the properties of the method and choice of optimization over the manifold of orthogonal matrices.
ABSTRACT
BACKGROUND: Insomnia, eating disorders, heart problems and even strokes are just some of the illnesses that reveal the negative impact of stress overload on health and well-being. Early detection of stress is therefore of utmost importance. Whereas the gold-standard for detecting stress is by means of questionnaires, more recent work uses wearable sensors to find continuous and qualitative physical markers of stress. As some physiological stress responses, e.g. increased heart rate or sweating and chills, might also occur when doing sports, a more profound approach is needed for stress detection than purely considering physiological data. METHODS: In this paper, we analyse the added value of context information during stress detection from wearable data. We do so by comparing the performance of models trained purely on physiological data and models trained on physiological and context data. We consider the user's activity and hours of sleep as context information, where we compare the influence of user-given context versus machine learning derived context. RESULTS: Context-aware models reach higher accuracy and lower standard deviations in comparison to the baseline (physiological) models. We also observe higher accuracy and improved weighted F1 score when incorporating machine learning predicted, instead of user-given, activities as context information. CONCLUSIONS: In this paper we show that considering context information when performing stress detection from wearables leads to better performance. We also show that it is possible to move away from human labeling and rely only on the wearables for both physiology and context.
Subject(s)
Wearable Electronic Devices , Awareness , Humans , Machine LearningABSTRACT
BACKGROUND: Anxiety disorders are highly prevalent in mental health problems. The lives of people suffering from an anxiety disorder can be severely impaired. Virtual Reality Exposure Therapy (VRET) is an effective treatment, which immerses patients in a controlled Virtual Environment (VE). This creates the opportunity to confront feared stimuli and learn how to deal with them, which may result in the reduction of anxiety. The configuration of these VEs requires extensive effort to maximise the potential of Virtual Reality (VR) and the effectiveness of the therapy. Manual configuration becomes infeasible when the number of possible virtual stimuli combinations is infinite. Due to the growing complexity, acquiring the skills to truly master a VR system is difficult and it increases the threshold for psychotherapists to use such useful systems. We therefore developed a prototype of a supportive algorithm to facilitate the use of VRET in a clinical setting. This automatised system assists psychotherapists to use the wide range of functionalities without burdening them with technical challenges. Thus, psychotherapists can focus their attention on the patient. METHODS: In this paper both the prototype of the algorithm and a first proof of concept are described. The algorithm suggests environment configurations for VRET, tailored to the individual therapeutic needs of each patient. The system aims to maximise learning during exposure therapy for different combinations of stimuli by using the Rescorla-Wagner model as a predictor for learning. In a first proof of concept, the VE configurations suggested by the algorithm for three anonymised clinical vignettes were compared with prior manual configurations by two psychotherapists. RESULTS: The prototype of the algorithm and a first proof of concept are described. The first proof of concept demonstrated the relevance and potential of the proposed system, as it managed to propose similar configurations for the clinical vignettes compared to those made by therapists. Nonetheless, because of the exploratory nature of the study, no claims can yet be made about its efficacy. CONCLUSIONS: With the increasing ubiquity of immersive technologies, this technology for assisted configuration of VEs could make VRET a valuable tool for psychotherapists.
Subject(s)
Virtual Reality Exposure Therapy , Virtual Reality , Algorithms , Anxiety/psychology , Anxiety Disorders/therapy , HumansABSTRACT
BACKGROUND: Beta-lactam antimicrobial concentrations are frequently suboptimal in critically ill patients. Population pharmacokinetic (PopPK) modeling is the golden standard to predict drug concentrations. However, currently available PopPK models often lack predictive accuracy, making them less suited to guide dosing regimen adaptations. Furthermore, many currently developed models for clinical applications often lack uncertainty quantification. We, therefore, aimed to develop machine learning (ML) models for the prediction of piperacillin plasma concentrations while also providing uncertainty quantification with the aim of clinical practice. METHODS: Blood samples for piperacillin analysis were prospectively collected from critically ill patients receiving continuous infusion of piperacillin/tazobactam. Interpretable ML models for the prediction of piperacillin concentrations were designed using CatBoost and Gaussian processes. Distribution-based Uncertainty Quantification was added to the CatBoost model using a proposed Quantile Ensemble method, useable for any model optimizing a quantile function. These models are subsequently evaluated using the distribution coverage error, a proposed interpretable uncertainty quantification calibration metric. Development and internal evaluation of the ML models were performed on the Ghent University Hospital database (752 piperacillin concentrations from 282 patients). Ensuing, ML models were compared with a published PopPK model on a database from the University Medical Centre of Groningen where a different dosing regimen is used (46 piperacillin concentrations from 15 patients.). RESULTS: The best performing model was the Catboost model with an RMSE and [Formula: see text] of 31.94-0.64 and 33.53-0.60 for internal evaluation with and without previous concentration. Furthermore, the results prove the added value of the proposed Quantile Ensemble model in providing clinically useful individualized uncertainty predictions and show the limits of homoscedastic methods like Gaussian Processes in clinical applications. CONCLUSIONS: Our results show that ML models can consistently estimate piperacillin concentrations with acceptable and high predictive accuracy when identical dosing regimens as in the training data are used while providing highly relevant uncertainty predictions. However, generalization capabilities to other dosing schemes are limited. Notwithstanding, incorporating ML models in therapeutic drug monitoring programs seems definitely promising and the current work provides a basis for validating the model in clinical practice.
Subject(s)
Critical Illness , Piperacillin , Anti-Bacterial Agents/pharmacokinetics , Anti-Bacterial Agents/therapeutic use , Humans , Machine Learning , Piperacillin/pharmacokinetics , Piperacillin/therapeutic use , Piperacillin, Tazobactam Drug Combination , UncertaintyABSTRACT
In today's data landscape, data streams are well represented. This is mainly due to the rise of data-intensive domains such as the Internet of Things (IoT), Smart Industries, Pervasive Health, and Social Media. To extract meaningful insights from these streams, they should be processed in real time, while solving an integration problem as these streams need to be combined with more static data and their domain knowledge. Ontologies are ideal for modeling this domain knowledge and facilitate the integration of heterogeneous data within data-intensive domains such as the IoT. Expressive reasoning techniques, such as OWL2 DL reasoning, are needed to completely interpret the domain knowledge and for the extraction of meaningful decisions. Expressive reasoning techniques have mainly focused on static data environments, as it tends to become slow with growing datasets. There is thus a mismatch between expressive reasoning and the real-time requirements of data-intensive domains. In this paper, we take a first step towards bridging the gap between expressivity and efficiency while reasoning over high-velocity IoT data streams for the task of event enrichment. We present a structural caching technique that eliminates reoccurring reasoning steps by exploiting the characteristics of most IoT streams, i.e., streams typically produce events that are similar in structure and size. Our caching technique speeds up reasoning time up to thousands of times for fully fledged OWL2 DL reasoners and even tenths and hundreds of times for less expressive OWL2 RL and OWL2 EL reasoners.
ABSTRACT
BACKGROUND: The diagnosis of headache disorders relies on the correct classification of individual headache attacks. Currently, this is mainly done by clinicians in a clinical setting, which is dependent on subjective self-reported input from patients. Existing classification apps also rely on self-reported information and lack validation. Therefore, the exploratory mBrain study investigates moving to continuous, semi-autonomous and objective follow-up and classification based on both self-reported and objective physiological and contextual data. METHODS: The data collection set-up of the observational, longitudinal mBrain study involved physiological data from the Empatica E4 wearable, data-driven machine learning (ML) algorithms detecting activity, stress and sleep events from the wearables' data modalities, and a custom-made application to interact with these events and keep a diary of contextual and headache-specific data. A knowledge-based classification system for individual headache attacks was designed, focusing on migraine, cluster headache (CH) and tension-type headache (TTH) attacks, by using the classification criteria of ICHD-3. To show how headache and physiological data can be linked, a basic knowledge-based system for headache trigger detection is presented. RESULTS: In two waves, 14 migraine and 4 CH patients participated (mean duration 22.3 days). 133 headache attacks were registered (98 by migraine, 35 by CH patients). Strictly applying ICHD-3 criteria leads to 8/98 migraine without aura and 0/35 CH classifications. Adapted versions yield 28/98 migraine without aura and 17/35 CH classifications, with 12/18 participants having mostly diagnosis classifications when episodic TTH classifications (57/98 and 32/35) are ignored. CONCLUSIONS: Strictly applying the ICHD-3 criteria on individual attacks does not yield good classification results. Adapted versions yield better results, with the mostly classified phenotype (migraine without aura vs. CH) matching the diagnosis for 12/18 patients. The absolute number of migraine without aura and CH classifications is, however, rather low. Example cases can be identified where activity and stress events explain patient-reported headache triggers. Continuous improvement of the data collection protocol, ML algorithms, and headache classification criteria (including the investigation of integrating physiological data), will further improve future headache follow-up, classification and trigger detection. Trial registration This trial was retrospectively registered with number NCT04949204 on 24 June 2021 at www. CLINICALTRIALS: gov .
Subject(s)
Headache Disorders , Migraine Disorders , Follow-Up Studies , Headache , Headache Disorders/diagnosis , Humans , Migraine Disorders/diagnosis , Self ReportABSTRACT
In the time series classification domain, shapelets are subsequences that are discriminative of a certain class. It has been shown that classifiers are able to achieve state-of-the-art results by taking the distances from the input time series to different discriminative shapelets as the input. Additionally, these shapelets can be visualized and thus possess an interpretable characteristic, making them appealing in critical domains, where longitudinal data are ubiquitous. In this study, a new paradigm for shapelet discovery is proposed, which is based on evolutionary computation. The advantages of the proposed approach are that: (i) it is gradient-free, which could allow escaping from local optima more easily and supports non-differentiable objectives; (ii) no brute-force search is required, making the algorithm scalable; (iii) the total amount of shapelets and the length of each of these shapelets are evolved jointly with the shapelets themselves, alleviating the need to specify this beforehand; (iv) entire sets are evaluated at once as opposed to single shapelets, which results in smaller final sets with fewer similar shapelets that result in similar predictive performances; and (v) the discovered shapelets do not need to be a subsequence of the input time series. We present the results of the experiments, which validate the enumerated advantages.
ABSTRACT
Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource, called the Term/Preterm Electrohysterogram database. However, we argue that these results are overly optimistic due to a methodological flaw being made. In this work, we focus on one specific type of methodological flaw: applying over-sampling before partitioning the data into mutually exclusive training and testing sets. We show how this causes the results to be biased using two artificial datasets and reproduce results of studies in which this flaw was identified. Moreover, we evaluate the actual impact of over-sampling on predictive performance, when applied prior to data partitioning, using the same methodologies of related studies, to provide a realistic view of these methodologies' generalization capabilities. We make our research reproducible by providing all the code under an open license.
Subject(s)
Premature Birth , Databases, Factual , Female , Humans , Infant, Newborn , PregnancyABSTRACT
BACKGROUND: Leveraging graphs for machine learning tasks can result in more expressive power as extra information is added to the data by explicitly encoding relations between entities. Knowledge graphs are multi-relational, directed graph representations of domain knowledge. Recently, deep learning-based techniques have been gaining a lot of popularity. They can directly process these type of graphs or learn a low-dimensional numerical representation. While it has been shown empirically that these techniques achieve excellent predictive performances, they lack interpretability. This is of vital importance in applications situated in critical domains, such as health care. METHODS: We present a technique that mines interpretable walks from knowledge graphs that are very informative for a certain classification problem. The walks themselves are of a specific format to allow for the creation of data structures that result in very efficient mining. We combine this mining algorithm with three different approaches in order to classify nodes within a graph. Each of these approaches excels on different dimensions such as explainability, predictive performance and computational runtime. RESULTS: We compare our techniques to well-known state-of-the-art black-box alternatives on four benchmark knowledge graph data sets. Results show that our three presented approaches in combination with the proposed mining algorithm are at least competitive to the black-box alternatives, even often outperforming them, while being interpretable. CONCLUSIONS: The mining of walks is an interesting alternative for node classification in knowledge graphs. Opposed to the current state-of-the-art that uses deep learning techniques, it results in inherently interpretable or transparent models without a sacrifice in terms of predictive performance.
Subject(s)
Algorithms , Pattern Recognition, Automated , Humans , Knowledge , Machine LearningABSTRACT
This paper contributes to the pursuit of leveraging unstructured medical notes to structured clinical decision making. In particular, we present a pipeline for clinical information extraction from medical notes related to preterm birth, and discuss the main challenges as well as its potential for clinical practice. A large collection of medical notes, created by staff during hospitalizations of patients who were at risk of delivering preterm, was gathered and analyzed. Based on an annotated collection of notes, we trained and evaluated information extraction components to discover clinical entities such as symptoms, events, anatomical sites and procedures, as well as attributes linked to these clinical entities. In a retrospective study, we show that these are highly informative for clinical decision support models that are trained to predict whether delivery is likely to occur within specific time windows, in combination with structured information from electronic health records.
Subject(s)
Premature Birth , Data Mining , Electronic Health Records , Female , Humans , Infant, Newborn , Pregnancy , Premature Birth/epidemiology , Retrospective StudiesABSTRACT
Autism Spectrum Disorder (ASD) is characterized by social interaction difficulties and communication difficulties. Moreover, children with ASD often suffer from other co-morbidities, such as anxiety and depression. Finding appropriate treatment can be difficult as symptoms of ASD and co-morbidities often overlap. Due to these challenges, parents of children with ASD often suffer from higher levels of stress. This research aims to investigate the feasibility of empowering children with ASD and their parents through the use of a serious game to reduce stress and anxiety and a supporting parent application. The New Horizon game and the SpaceControl application were developed together with therapists and according to guidelines for e-health patient empowerment. The game incorporates two mini-games with relaxation techniques. The performance of the game was analyzed and usability studies with three families were conducted. Parents and children were asked to fill in the Spence's Children Anxiety Scale (SCAS) and Spence Children Anxiety Scale-Parents (SCAS-P) anxiety scale. The game shows potential for stress and anxiety reduction in children with ASD.
Subject(s)
Anxiety/pathology , Autism Spectrum Disorder/psychology , Empowerment , Parents/psychology , Stress, Psychological , Video Games , Autism Spectrum Disorder/therapy , Child , Cognitive Behavioral Therapy , Humans , Quality of Life , TelemedicineABSTRACT
In industry, dashboards are often used to monitor fleets of assets, such as trains, machines or buildings. In such industrial fleets, the vast amount of sensors evolves continuously, new sensor data exchange protocols and data formats are introduced, new visualization types may need to be introduced and existing dashboard visualizations may need to be updated in terms of displayed sensors. These requirements motivate the development of dynamic dashboarding applications. These, as opposed to fixed-structure dashboard applications, allow users to create visualizations at will and do not have hard-coded sensor bindings. The state-of-the-art in dynamic dashboarding does not cope well with the frequent additions and removals of sensors that must be monitored-these changes must still be configured in the implementation or at runtime by a user. Also, the user is presented with an overload of sensors, aggregations and visualizations to select from, which may sometimes even lead to the creation of dashboard widgets that do not make sense. In this paper, we present a dynamic dashboard that overcomes these problems. Sensors, visualizations and aggregations can be discovered automatically, since they are provided as RESTful Web Things on a Web Thing Model compliant gateway. The gateway also provides semantic annotations of the Web Things, describing what their abilities are. A semantic reasoner can derive visualization suggestions, given the Thing annotations, logic rules and a custom dashboard ontology. The resulting dashboarding application automatically presents the available sensors, visualizations and aggregations that can be used, without requiring sensor configuration, and assists the user in building dashboards that make sense. This way, the user can concentrate on interpreting the sensor data and detecting and solving operational problems early.