Femke Ongenae

A probabilistic ontology-based platform for self-learning context-aware healthcare applications

Context-aware platforms consist of dynamic algorithms that take the context information into account to adapt the behavior of the applications. The relevant context information is modeled in a context model. Recently, a trend has emerged towards capturing the context in an ontology, which formally models the concepts within a certain domain, their relations and properties. Although much research has been done on the subject, the adoption of context-aware services in healthcare is lagging behind what could be expected. The main complaint made by users is that they had to signicantly alter workow patterns to accommodate the system. When new technology is introduced, the behavior of the users changes to adapt to it. Moreover, small dierences in user requirements often occur between dierent

An ontology-based nurse call management system (oNCS) with probabilistic priority assessment

BackgroundThe current, place-oriented nurse call systems are very static. A patient can only make calls with a button which is fixed to a wall of a room. Moreover, the system does not take into account various factors specific to a situation. In the future, there will be an evolution to a mobile button for each patient so that they can walk around freely and still make calls. The system would become person-oriented and the available context information should be taken into account to assign the correct nurse to a call.The aim of this research is (1) the design of a software platform that supports the transition to mobile and wireless nurse call buttons in hospitals and residential care and (2) the design of a sophisticated nurse call algorithm. This algorithm dynamically adapts to the situation at hand by taking the profile information of staff members and patients into account. Additionally, the priority of a call probabilistically depends on the risk factors, assigned to a patient.MethodsThe ontology-based Nurse Call System (oNCS) was developed as an extension of a Context-Aware Service Platform. An ontology is used to manage the profile information. Rules implement the novel nurse call algorithm that takes all this information into account. Probabilistic reasoning algorithms are designed to determine the priority of a call based on the risk factors of the patient.ResultsThe oNCS system is evaluated through a prototype implementation and simulations, based on a detailed dataset obtained from Ghent University Hospital. The arrival times of nurses at the location of a call, the workload distribution of calls amongst nurses and the assignment of priorities to calls are compared for the oNCSsystem and the current, place-oriented nurse call system. Additionally, the performance of the system is discussed.ConclusionsThe execution time of the nurse call algorithm is on average 50.333 ms. Moreover, the oNCS system significantly improves the assignment of nurses to calls. Calls generally have a nurse present faster and the workload-distribution amongst the nurses improves.

Towards a social and context-aware multi-sensor fall detection and risk assessment platform

For elderly people fall incidents are life-changing events that lead to degradation or even loss of autonomy. Current fall detection systems are not integrated and often associated with undetected falls and/or false alarms. In this paper, a social- and context-aware multi-sensor platform is presented, which integrates information gathered by a plethora of fall detection systems and sensors at the home of the elderly, by using a cloud-based solution, making use of an ontology. Within the ontology, both static and dynamic information is captured to model the situation of a specific patient and his/her (in)formal caregivers. This integrated contextual information allows to automatically and continuously assess the fall risk of the elderly, to more accurately detect falls and identify false alarms and to automatically notify the appropriate caregiver, e.g., based on location or their current task. The main advantage of the proposed platform is that multiple fall detection systems and sensors can be integrated, as they can be easily plugged in, this can be done based on the specific needs of the patient. The combination of several systems and sensors leads to a more reliable system, with better accuracy. The proof of concept was tested with the use of the visualizer, which enables a better way to analyze the data flow within the back-end and with the use of the portable testbed, which is equipped with several different sensors.

Novel Applications Integrate Location and Context Information

New applications and services aim to adapt themselves to the users context and thus require platforms that can collect, distribute, and exchange contextual information. The Context-Aware Service Platform (CASP) can help, as exemplified here in three different use cases.

Towards computerizing intensive care sedation guidelines: design of a rule-based architecture for automated execution of clinical guidelines

BackgroundComputerized ICUs rely on software services to convey the medical condition of their patients as well as assisting the staff in taking treatment decisions. Such services are useful for following clinical guidelines quickly and accurately. However, the development of services is often time-consuming and error-prone. Consequently, many care-related activities are still conducted based on manually constructed guidelines. These are often ambiguous, which leads to unnecessary variations in treatments and costs.The goal of this paper is to present a semi-automatic verification and translation framework capable of turning manually constructed diagrams into ready-to-use programs. This framework combines the strengths of the manual and service-oriented approaches while decreasing their disadvantages. The aim is to close the gap in communication between the IT and the medical domain. This leads to a less time-consuming and error-prone development phase and a shorter clinical evaluation phase.MethodsA framework is proposed that semi-automatically translates a clinical guideline, expressed as an XML-based flow chart, into a Drools Rule Flow by employing semantic technologies such as ontologies and SWRL. An overview of the architecture is given and all the technology choices are thoroughly motivated. Finally, it is shown how this framework can be integrated into a service-oriented architecture (SOA).ResultsThe applicability of the Drools Rule language to express clinical guidelines is evaluated by translating an example guideline, namely the sedation protocol used for the anaesthetization of patients, to a Drools Rule Flow and executing and deploying this Rule-based application as a part of a SOA. The results show that the performance of Drools is comparable to other technologies such as Web Services and increases with the number of decision nodes present in the Rule Flow. Most delays are introduced by loading the Rule Flows.ConclusionsThe framework is an effective solution for computerizing clinical guidelines as it allows for quick development, evaluation and human-readable visualization of the Rules and has a good performance. By monitoring the parameters of the patient to automatically detect exceptional situations and problems and by notifying the medical staff of tasks that need to be performed, the computerized sedation guideline improves the execution of the guideline.

Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores

INTRODUCTION The length of stay of critically ill patients in the intensive care unit (ICU) is an indication of patient ICU resource usage and varies considerably. Planning of postoperative ICU admissions is important as ICUs often have no nonoccupied beds available. PROBLEM STATEMENT Estimation of the ICU bed availability for the next coming days is entirely based on clinical judgement by intensivists and therefore too inaccurate. For this reason, predictive models have much potential for improving planning for ICU patient admission. OBJECTIVE Our goal is to develop and optimize models for patient survival and ICU length of stay (LOS) based on monitored ICU patient data. Furthermore, these models are compared on their use of sequential organ failure (SOFA) scores as well as underlying raw data as input features. METHODOLOGY Different machine learning techniques are trained, using a 14,480 patient dataset, both on SOFA scores as well as their underlying raw data values from the first five days after admission, in order to predict (i) the patient LOS, and (ii) the patient mortality. Furthermore, to help physicians in assessing the prediction credibility, a probabilistic model is tailored to the output of our best-performing model, assigning a belief to each patient status prediction. A two-by-two grid is built, using the classification outputs of the mortality and prolonged stay predictors to improve the patient LOS regression models. RESULTS For predicting patient mortality and a prolonged stay, the best performing model is a support vector machine (SVM) with GA,D=65.9% (area under the curve (AUC) of 0.77) and GS,L=73.2% (AUC of 0.82). In terms of LOS regression, the best performing model is support vector regression, achieving a mean absolute error of 1.79 days and a median absolute error of 1.22 days for those patients surviving a nonprolonged stay. CONCLUSION Using a classification grid based on the predicted patient mortality and prolonged stay, allows more accurate modeling of the patient LOS. The detailed models allow to support the decisions made by physicians in an ICU setting.

Time series classification for the prediction of dialysis in critically ill patients using echo statenetworks

Objective: Time series often appear in medical databases, but only few machine learning methods exist that process this kind of data properly. Most modeling techniques have been designed with a static data model in mind and are not suitable for coping with the dynamic nature of time series. Recurrent neural networks (RNNs) are often used to process time series, but only a few training algorithms exist for RNNs which are complex and often yield poor results. Therefore, researchers often turn to traditional machine learning approaches, such as support vector machines (SVMs), which can easily be set up and trained and combine them with feature extraction (FE) and selection (FS) to process the high-dimensional temporal data. Recently, a new approach, called echo state networks (ESNs), has been developed to simplify the training process of RNNs. This approach allows modeling the dynamics of a system based on time series data in a straightforwardway. The objective of this study is to explore the advantages of using ESN instead of other traditional classifiers combined with FE and FS in classification problems in the intensive care unit (ICU) when the input data consists of time series. While ESNs have mostly been used to predict the future course of a time series, we use the ESN model for classification instead. Although time series often appear in medical data, little medical applications of ESNs have been studiedyet. Methods and material: ESN is used to predict the need for dialysis between the fifth and tenth day after admission in the ICU. The input time series consist of measured diuresis and creatinine values during the first 3days after admission. Data about 830 patients was used for the study, of which 82 needed dialysis between the fifth and tenth day after admission. ESN is compared to traditional classifiers, a sophisticated and a simple one, namely support vector machines and the naive Bayes (NB) classifier. Prior to the use of the SVM and NB classifier, FE and FS is required to reduce the number of input features and thus alleviate the curse dimensionality. Extensive feature extraction was applied to capture both the overall properties of the time series and the correlation between the different measurements in the time series. The feature selection method consists of a greedy hybrid filter-wrapper method using a NB classifier, which selects in each iteration the feature that improves prediction the best and shows little multicollinearity with the already selected set. Least squares regression with noise was used to train the linear readout function of the ESN to mitigate sensitivity to noise and overfitting. Fisher labeling was used to deal with the unbalanced data set. Parameter sweeps were performed to determine the optimal parameter values for the different classifiers. The area under the curve (AUC) and maximum balanced accuracy are used as performance measures. The required execution time was also measured. Results: The classification performance of the ESN shows significant difference at the 5% level compared to the performance of the SVM or the NB classifier combined with FE and FS. The NB+FE+FS, with an average AUC of 0.874, has the best classification performance. This classifier is followed by the ESN, which has an average AUC of 0.849. The SVM+FE+FS has the worst performance with an average AUC of 0.838. The computation time needed to pre-process the data and to train and test the classifier is significantly less for the ESN compared to the SVM andNB. Conclusion: It can be concluded that the use of ESN has an added value in predicting the need for dialysis through the analysis of time series data. The ESN requires significantly less processing time, needs no domain knowledge, is easy to implement, and can be configured using rules ofthumb.

OTAGen: A Tunable Ontology Generator for Benchmarking Ontology-Based Agent Collaboration

On the one hand, agent-based software platforms are commonly used these days, while on the other hand Semantic Web technologies are also maturing. It is obvious that the combination of these two technologies can bring added value through the creation of Semantic Agent-based frameworks. However, it is also known that these Semantic Web technologies, and the reasoning on ontologies in particular, can rapidly become resource intensive. In order to get a clear view on this problem, we have developed OTAGen, a highly tunable tool to generate customized ontologies and corresponding queries. The generated ontologies can then be used to evaluate at design-time the performance of the Semantic Agent-based platform as a function of the number of ontologies, users and queries.

Ontology Based and Context-Aware Hospital Nurse Call Optimization

In this paper, the focus is on how context information can be efficiently modeled with an ontology. This ontology can than be used by reasoning algorithms which are based on this context information. This is illustrated with a use case which studies the evolution from a place oriented to a person oriented nurse call system. An ontology was designed which holds the necessary context information. A nurse call algorithm that uses this information was constructed. The CASP Context framework was extended to implement the use case. This framework is bases on an OSGi framework. Rules are formulated to implement the algorithm. OWL was applied to integrate the ontology into the framework. A Web service interface was designed which allows to insert new information into the knowledge base or extract information from it. At last a simulation was set up to show the advantages of the person oriented approach. The results of a performance study are shown as well.

Design of a semantic person-oriented nurse call management system

Context information is becoming increasingly important in a world with more and more wireless devices that have to be in touch with the environment around them. In this paper, we focus on how this context information can be efficiently modelled by employing an ontology. This ontology can then be used by reasoning algorithms (e.g., Rules) which are based on this context information. This way, the algorithm is more sensitive to the varying conditions of the environment. This is illustrated with a use case which studies the transition from a place-oriented to a person-oriented nurse call system. The Context-aware Service Platform (CASP) context framework (Strobbe et al., 2007; 2006) was extended to implement the use case. A web service interface was designed which allows the insertion or extraction of new information into the Knowledge Base. Finally, a simulation was set up to illustrate the advantages and the performance of the new person-oriented approach.