Using Gated Recurrent Unit Networks for the Prediction of Hemodynamic and Pulmonary Decompensation.

This paper presents a new medical severity scoring system, used to assess the risk of hemodynamic and pulmonary decompensation for patients being treated in intensive care units. The score presented here includes drug circulatory support and ventilation mode data for the evaluation of the patient's biosignals and laboratory values. It is shown that Gated Recurrent Unit-based neural networks are able to predict the maximal severity class within a 24 hour prediction time-frame (hemodynamic: 0.85 AUROC / pulmonary: 0.9 AUROC), and can estimate the underlying decompensation score for prediction times of up to 24 hours with mean errors of 6.3% of the maximal possible pulmonary, and 9.6% of the hemodynamic score. These results are based on 60h observation period. Clinical Relevance- Hemodynamic and pulmonary decom-pensation are life threatening dynamic events that can lead to death of patients. Early detection of these incidents is essential in order to intervene therapeutically and to improve survival chances. In everyday intensive care physicians are confronted with a vast number of laboratory values and vital parameters. There is a risk that early stages of hemodynamic and pulmonary decompensation are misjudged. The implementation of robust warning systems could support physicians in detecting these critical events and initiate therapeutical intervention in time which would achieve significant reduction of patient mortality.

Artificial intelligence supporting cancer patients across Europe-The ASCAPE project.

INTRODUCTION: Breast and prostate cancer survivors can experience impaired quality of life (QoL) in several QoL domains. The current strategy to support cancer survivors with impaired QoL is suboptimal, leading to unmet patient needs. ASCAPE aims to provide personalized- and artificial intelligence (AI)-based predictions for QoL issues in breast- and prostate cancer patients as well as to suggest potential interventions to their physicians to offer a more modern and holistic approach on cancer rehabilitation. METHODS AND ANALYSES: An AI-based platform aiming to predict QoL issues and suggest appropriate interventions to clinicians will be built based on patient data gathered through medical records, questionnaires, apps, and wearables. This platform will be prospectively evaluated through a longitudinal study where breast and prostate cancer survivors from four different study sites across the Europe will be enrolled. The evaluation of the AI-based follow-up strategy through the ASCAPE platform will be based on patients' experience, engagement, and potential improvement in QoL during the study as well as on clinicians' view on how ASCAPE platform impacts their clinical practice and doctor-patient relationship, and their experience in using the platform. ETHICS AND DISSEMINATION: ASCAPE is the first research project that will prospectively investigate an AI-based approach for an individualized follow-up strategy for patients with breast- or prostate cancer focusing on patients' QoL issues. ASCAPE represents a paradigm shift both in terms of a more individualized approach for follow-up based on QoL issues, which is an unmet need for cancer survivors, and in terms of how to use Big Data in cancer care through democratizing the knowledge and the access to AI and Big Data related innovations. TRIAL REGISTRATION: Trial Registration on clinicaltrials.gov: NCT04879563.

[Recognition and classification of posture and gait patterns of rollator users by distance measurements-a comparison between clinical assessment and automatic classification]. / Erkennung und Klassifikation von Haltungs- und Gangmustern am Rollator durch Abstandsmessungen ­ ein Vergleich zwischen klinischer Beurteilung und maschineller Klassifikation.

BACKGROUND: This article describes the development of an add-on module for wheeled walkers dedicated to sensor-based posture and gait pattern recognition with the goal to develop an everyday aid for fall prevention. The core contribution is a clinical study that compared single gait parameter assessments coming from medical staff to those obtained from an automatic classification algorithm, i. e. the Mahalanobis distance over time series of sensor measurements. METHODS: The walker-module described here extends an off-the-shelf wheeled walker by two depth cameras that observe the torso, pelvic, region and legs of the user. From the stream of depth images, distance measurements to eight relevant feature points on the body surface (shoulders, iliac crests, upper and lower legs) are combined to time series that describe the individual gait cycles. For automatic classification of gait cycle descriptions 14 safety-relevant gait parameters (gait width, height, length, symmetry, variability; flection of torso, knees (l/r), hips (l/r); position, distance to walker; 2­value, 5­value gait patterns [While the two-value gait pattern differentiates a gait cycle into physiological and pathological, the five-value gait pattern distinguishes between antalgic, atactic, paretic, protective, and physiological gait]), single classifier algorithms were trained using machine learning techniques based on the mathematical concept of the Mahalanobis distance (distance of individual gait cycles to class averages and corresponding covariance matrices). For this purpose, training and test datasets were gathered in a clinical setting from 29 subjects. Here, the assessment of gait properties given by medical experts served for the labelling of sensorial gait cycle descriptions of the training and test datasets. In order to evaluate the quality of the automated classification in the add-on module a final comparison between human and automatic gait parameter assessment is given. RESULTS: The gait assessment conducted by trained medical staff served as a comparator for the machine learning gait assessment and showed a relatively uniform class distribution of gait parameters over the group of probands, e. g. 57% showed an increased and 43% a normal distance to the walker. Of the subjects 51% positioned themselves central to the walker, while 41% took a left deviating, and 8% a right deviating position. A further 12 gait parameters were differentiated and evaluated in 2-5 classes. In the following, single gait cycle descriptions of each subject were assessed by trained classification algorithms. The best automatic classification rates over all subjects were given by the distance to walker (99.4%), and the 2-value gait pattern (99.2%). Gait variability (94.6%) and position to walker (94.2%) showed the poorest classification rates. Over all gait parameters and subjects, 96.9% of all gait cycle descriptions were correctly classified. DISCUSSION/OUTLOOK: With an average classification rate of 96.9%, the described gait classification approach is well suited for a patient-oriented training correction system that informs the user about false posture during every day walker use. A second application scenario is the use in a clinical setting for objectifying the gait assessment of patients. To reach these ambitious goals requires more future research. It includes the replacement of depth cameras by small size distance sensors (1D Lidar), the design and implementation of a suitable walker-user interface, and the evaluation of the proposed classification algorithm by contrasting it to results of modern deep convolutional neural network output.

CrowdHEALTH: Big Data Analytics and Holistic Health Records.

The aim of this paper is to present examples of big data techniques that can be applied on Holistic Health Records (HHR) in the context of the CrowdHEALTH project. Real-time big data analytics can be performed on the stored data (i.e. HHRs) enabling correlations and extraction of situational factors between laboratory exams, physical activities, biosignals, medical data patterns, and clinical assessment. Based on the outcomes of different analytics (e.g. risk analysis, pathways mining, forecasting and causal analysis) on the aforementioned HHRs datasets, actionable information can be obtained for the development of efficient health plans and public health policies.

The CrowdHEALTH project and the Hollistic Health Records: Collective Wisdom Driving Public Health Policies.

INTRODUCTION: With the expansion of available Information and Communication Technology (ICT) services, a plethora of data sources provide structured and unstructured data used to detect certain health conditions or indicators of disease. Data is spread across various settings, stored and managed in different systems. Due to the lack of technology interoperability and the large amounts of health-related data, data exploitation has not reached its full potential yet. AIM: The aim of the CrowdHEALTH approach, is to introduce a new paradigm of Holistic Health Records (HHRs) that include all health determinants defining health status by using big data management mechanisms. METHODS: HHRs are transformed into HHRs clusters capturing the clinical, social and human context with the aim to benefit from the collective knowledge. The presented approach integrates big data technologies, providing Data as a Service (DaaS) to healthcare professionals and policy makers towards a "health in all policies" approach. A toolkit, on top of the DaaS, providing mechanisms for causal and risk analysis, and for the compilation of predictions is developed. RESULTS: CrowdHEALTH platform is based on three main pillars: Data & structures, Health analytics, and Policies. CONCLUSIONS: A holistic approach for capturing all health determinants in the proposed HHRs, while creating clusters of them to exploit collective knowledge with the aim of the provision of insight for different population segments according to different factors (e.g. location, occupation, medication status, emerging risks, etc) was presented. The aforementioned approach is under evaluation through different scenarios with heterogeneous data from multiple sources.

CrowdHEALTH: Holistic Health Records and Big Data Analytics for Health Policy Making and Personalized Health.

Today's rich digital information environment is characterized by the multitude of data sources providing information that has not yet reached its full potential in eHealth. The aim of the presented approach, namely CrowdHEALTH, is to introduce a new paradigm of Holistic Health Records (HHRs) that include all health determinants. HHRs are transformed into HHRs clusters capturing the clinical, social and human context of population segments and as a result collective knowledge for different factors. The proposed approach also seamlessly integrates big data technologies across the complete data path, providing of Data as a Service (DaaS) to the health ecosystem stakeholders, as well as to policy makers towards a "health in all policies" approach. Cross-domain co-creation of policies is feasible through a rich toolkit, being provided on top of the DaaS, incorporating mechanisms for causal and risk analysis, and for the compilation of predictions.