State-of-the-art sleep arousal detection evaluated on a comprehensive clinical dataset

Aiming to apply automatic arousal detection to support sleep laboratories, we evaluated an optimized, state-of-the-art approach using data from daily work in our university hospital sleep laboratory. Therefore, a machine learning algorithm was trained and evaluated on 3423 polysomnograms of people with various sleep disorders. The model architecture is a U-net that accepts 50 Hz signals as input. We compared this algorithm with models trained on publicly available datasets, and evaluated these models using our clinical dataset, particularly with regard to the effects of different sleep disorders. In an effort to evaluate clinical relevance, we designed a metric based on the error of the predicted arousal index. Our models achieve an area under the precision recall curve (AUPRC) of up to 0.83 and F1 scores of up to 0.81. The model trained on our data showed no age or gender bias and no significant negative effect regarding sleep disorders on model performance compared to healthy sleep. In contrast, models trained on public datasets showed a small to moderate negative effect (calculated using Cohen's d) of sleep disorders on model performance. Therefore, we conclude that state-of-the-art arousal detection on our clinical data is possible with our model architecture. Thus, our results support the general recommendation to use a clinical dataset for training if the model is to be applied to clinical data.

Using machine learning algorithms to detect fear of falling in people with multiple sclerosis in standardized gait analysis

INTRODUCTION

Multiple sclerosis (MS) is the most common chronic inflammatory disease of the central nervous system. The progressive impairment of gait is one of the most important pathognomic symptoms which are associated with falls and fear of falling (FOF) in people with MS (pwMS). 60 % of pwMS show a FOF, which leads to restrictions in mobility as well as physical activity and reduces the quality of life in general. Therefore, early detection of FOF is crucial because it enables early implementation of rehabilitation strategies as well as clinical decision-making to reduce progression. Qualitative and quantitative evaluation of gait pattern is an essential aspect of disease assessment and can provide valuable insights for personalized treatment decisions in pwMS. Our objective was to identify the most appropriate clinical gait analysis methods to identify FOF in pwMS and to detect the optimal machine learning (ML) algorithms to predict FOF using the complex multidimensional data from gait analysis.

METHODS

Data of 1240 pwMS was recorded at the MS Centre of the University Hospital Dresden between November 2020 and September 2021. Patients performed a multidimensional gait analysis with pressure and motion sensors, as well as patient-reported outcomes (PROs), according to a standardized protocol. A feature selection ensemble (FS-Ensemble) was developed to improve the classification performance. The FS-Ensemble consisted of four filtering methods: Chi-square test, information gain, minimum redundancy maximum relevance and ReliefF. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) were used to identify FOF.

RESULTS

The descriptive analysis showed that 37 % of the 1240 pwMS had a FOF (n = 458; age: 51 ± 16 years, 76 % women, median EDSS: 4.0). The FS-Ensemble improved classification performance in most cases. The SVM showed the best performance of the four classification models in detecting FOF. The PROs showed the best F1 scores (Early Mobility Impairment Questionnaire F1 = 0.81 ± 0.00 and 12-item Multiple Sclerosis Scale F1 = 0.80 ± 0.00).

CONCLUSION

FOF is an important psychological risk factor associated with an increased risk of falls. To integrate a functional early warning system for fall detection into MS management and progression monitoring, it is necessary to detect the relevant gait parameters as well as assessment methods. In this context, ML strategies allow the integration of gait parameters from clinical routine to support the initiation of early rehabilitation measures and adaptation of course-modifying therapeutics. The results of this study confirm that patients' self-assessments play an important role in disease management.

xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

Novel Metric for Non-Invasive Beat-to-Beat Blood Pressure Measurements Demonstrates Physiological Blood Pressure Fluctuations during Pregnancy

Beat-to-beat (B2B) variability in biomedical signals has been shown to have high diagnostic power in the treatment of various cardiovascular and autonomic disorders. In recent years, new techniques and devices have been developed to enable non-invasive blood pressure (BP) measurements. In this work, we aim to establish the concept of two-dimensional signal warping, an approved method from ECG signal processing, for non-invasive continuous BP signals. To this end, we introduce a novel BP-specific beat annotation algorithm and a B2B-BP fluctuation (B2B-BPF) metric novel for BP measurements that considers the entire BP waveform. In addition to careful validation with synthetic data, we applied the generated analysis pipeline to non-invasive continuous BP signals of 44 healthy pregnant women (30.9 ± 5.7 years) between the 21st and 30th week of gestation (WOG). In line with established variability metrics, a significant increase (p < 0.05) in B2B-BPF can be observed with advancing WOGs. Our processing pipeline enables robust extraction of B2B-BPF, demonstrates the influence of various factors such as increasing WOG or exercise on blood pressure during pregnancy, and indicates the potential of novel non-invasive biosignal sensing techniques in diagnostics. The results represent B2B-BP changes in healthy pregnant women and allow for future comparison with those signals acquired from women with hypertensive disorders.

Torsobarography: Intra-Observer Reliability Study of a Novel Posture Analysis Based on Pressure Distribution

Postural deformities often manifest themselves in a sagittal imbalance and an asymmetric morphology of the torso. As a novel topographic method, torsobarography assesses the morphology of the back by analysing pressure distribution along the torso in a lying position. At torsobarography's core is a capacitive pressure sensor array. To evaluate its feasibility as a diagnostic tool, the reproducibility of the system and extracted anatomical associated parameters were evaluated on 40 subjects. Landmarks and reference distances were identified within the pressure images. The examined parameters describe the shape of the spine, various structures of the trunk symmetry, such as the scapulae, and the pelvic posture. The results showed that the localisation of the different structures performs with a good (ICC > 0.75) to excellent (ICC > 0.90) reliability. In particular, parameters for approximating the sagittal spine shape were reliably reproduced (ICC > 0.83). Lower reliability was observed for asymmetry parameters, which can be related to the low variability within the subject group. Nonetheless, the reliability levels of selected parameters are comparable to commercial systems. This study demonstrates the substantial potential of torsobarography at its current stage for reliable posture analysis and may pave the way as an early detection system for postural deformities.

Assessment of the human response to acute mental stress-An overview and a multimodal study

Numerous vital signs are reported in association with stress response assessment, but their application varies widely. This work provides an overview over methods for stress induction and strain assessment, and presents a multimodal experimental study to identify the most important vital signs for effective assessment of the response to acute mental stress. We induced acute mental stress in 65 healthy participants with the Mannheim Multicomponent Stress Test and acquired self-assessment measures (Likert scale, Self-Assessment Manikin), salivary α-amylase and cortisol concentrations as well as 60 vital signs from biosignals, such as heart rate variability parameters, QT variability parameters, skin conductance level, and breath rate. By means of statistical testing and a self-optimizing logistic regression, we identified the most important biosignal vital signs. Fifteen biosignal vital signs related to ventricular repolarization variability, blood pressure, skin conductance, and respiration showed significant results. The logistic regression converged with QT variability index, left ventricular work index, earlobe pulse arrival time, skin conductance level, rise time and number of skin conductance responses, breath rate, and breath rate variability (F1 = 0.82). Self-assessment measures indicated successful stress induction. α-amylase and cortisol showed effect sizes of -0.78 and 0.55, respectively. In summary, the hypothalamic-pituitary-adrenocortical axis and sympathetic nervous system were successfully activated. Our findings facilitate a coherent and integrative understanding of the assessment of the stress response and help to align applications and future research concerning acute mental stress.

Approach for Non-Intrusive Detection of the Fit of Orthopaedic Devices Based on Vibrational Data

The soft tissues of residual limb amputees are subject to large volume fluctuations over the course of a day. Volume fluctuations in residual limbs can lead to local pressure marks, causing discomfort, pain and rejection of prostheses. Existing methods for measuring interface stress encounter several limitations. A major problem is that the measurement instrumentation is applied in the sensitive interface between the prosthesis and residual limb. This paper presents the principle investigation of a non-intrusive technique to evaluate the fit of orthopaedic prosthesis sockets in transfemoral amputees based on experimentally obtained vibrational data. The proposed approach is based on changes in the dynamical behaviour detectable at the outer surface of prostheses; thus, the described interface is not affected. Based on the experimental investigations shown and the derived results, it can be concluded that structural dynamic measurements are a promising non-intrusive technique to evaluate the fit of orthopaedic prosthesis sockets in transfemoral amputee patients. The obtained resonance frequency changes of 2% are a good indicator of successful applicabilityas these changes can be detected without the need for complex measurement devices.

Controllability and Robustness of Functional and Structural Connectomic Networks in Glioma Patients

Previous studies suggest that the topological properties of structural and functional neural networks in glioma patients are altered beyond the tumor location. These alterations are due to the dynamic interactions with large-scale neural circuits. Understanding and describing these interactions may be an important step towards deciphering glioma disease evolution. In this study, we analyze structural and functional brain networks in terms of determining the correlation between network robustness and topological features regarding the default-mode network (DMN), comparing prognostically differing patient groups to healthy controls. We determine the driver nodes of these networks, which are receptive to outside signals, and the critical nodes as the most important elements for controllability since their removal will dramatically affect network controllability. Our results suggest that network controllability and robustness of the DMN is decreased in glioma patients. We found losses of driver and critical nodes in patients, especially in the prognostically less favorable IDH wildtype (IDHwt) patients, which might reflect lesion-induced network disintegration. On the other hand, topological shifts of driver and critical nodes, and even increases in the number of critical nodes, were observed mainly in IDH mutated (IDHmut) patients, which might relate to varying degrees of network plasticity accompanying the chronic disease course in some of the patients, depending on tumor growth dynamics. We hereby implement a novel approach for further exploring disease evolution in brain cancer under the aspects of neural network controllability and robustness in glioma patients.

A Wireless Rowing Measurement System for Improving the Rowing Performance of Athletes

The rowing technique is a key factor in the overall rowing performance. Nowadays the athletes' performance is so advanced that even small differences in technique can have an impact on sport competitions. To further improve the athletes' performance, individualized rowing is necessary. This can be achieved by intelligent measurement technology that provides direct feedback. To address this issue, we developed a novel wireless rowing measurement system (WiRMS) that acquires rowing movement and measures muscle activity using electromyography (EMG). Our measurement system is able to measure several parameters simultaneously: the rowing forces, the pressure distribution on the scull, the oar angles, the seat displacement and the boat acceleration. WiRMS was evaluated in a proof-of-concept study with seven experienced athletes performing a training on water. Evaluation results showed that WiRMS is able to assess the rower's performance by recording the rower's movement and force applied to the scull. We found significant correlations (p < 0.001) between stroke rate and drive-to-recovery ratio. By incorporating EMG data, a precise temporal assignment of the activated muscles and their contribution to the rowing motion was possible. Furthermore, we were able to show that the rower applies the force to the scull mainly with the index and middle fingers.

Detection of Fall Risk in Multiple Sclerosis by Gait Analysis-An Innovative Approach Using Feature Selection Ensemble and Machine Learning Algorithms

One of the common causes of falls in people with Multiple Sclerosis (pwMS) is walking impairment. Therefore, assessment of gait is of importance in MS. Gait analysis and fall detection can take place in the clinical context using a wide variety of available methods. However, combining these methods while using machine learning algorithms for detecting falls has not been performed. Our objective was to determine the most relevant method for determining fall risk by analyzing eleven different gait data sets with machine learning algorithms. In addition, we examined the most important features of fall detection. A new feature selection ensemble (FS-Ensemble) and four classification models (Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, Support Vector Machine) were used. The FS-Ensemble consisted of four filter methods: Chi-square test, information gain, Minimum Redundancy Maximum Relevance and RelieF. Various thresholds (50%, 25% and 10%) and combination methods (Union, Union 2, Union 3 and Intersection) were examined. Patient-reported outcomes using specialized walking questionnaires such as the 12-item Multiple Sclerosis Walking Scale (MSWS-12) and the Early Mobility Impairment Questionnaire (EMIQ) achieved the best performances with an F1 score of 0.54 for detecting falls. A combination of selected features of MSWS-12 and EMIQ, including the estimation of walking, running and stair climbing ability, the subjective effort as well as necessary concentration and walking fluency during walking, the frequency of stumbling and the indication of avoidance of social activity achieved the best recall of 75%. The Gaussian Naive Bayes was the best classification model for detecting falls with almost all data sets. FS-Ensemble improved the classification models and is an appropriate technique for reducing data sets with a large number of features. Future research on other risk factors, such as fear of falling, could provide further insights.

Investigation of muscle fatigue during on-water rowing using surface EMG

In this work, four different algorithms (fast Fourier transform FFT, short-time Fourier transform STFT, continuous wavelet transform CWT, and instantaneous frequency IF) for calculating median frequency (MDF) from surface EMG signals were investigated for studying muscle fatigue during a on-water rowing training. The study protocol included 5 consecutive parts with increasing stroke rate. Six athletes participated in the study aged 36.6+-14.6 years and a rowing experience of 6 to 35 years. We considered eight muscles: biceps brachii right, biceps brachii left, latissimus dorsi right, latissimus dorsi left, erector spinae right, erector spinae left, rectus femoris and biceps femoris. By applying Friedmann test, we found a significant difference in MDF behavior between algorithms in assessing muscle fatigue . Correlation analyses showed significant correlations between muscle activity duration t_act and MDF, which differs for the four considered algorithms and should be taken into account in further experiments. With CWT showing the smallest correlation to t_act it might be more robust against time window variations. Our study provides a basis for the development of improved methods for more robust, non-invasive, and continuous detection of muscle fatigue in experiments with dynamic on-water rowing study designs.

Camera-based assessment of cutaneous perfusion strength in a clinical setting

Objective. After skin flap transplants, perfusion strength monitoring is essential for the early detection of tissue perfusion disorders and thus to ensure the survival of skin flaps. Camera-based photoplethysmography (cbPPG) is a non-contact measurement method, using video cameras and ambient light, which provides spatially resolved information about tissue perfusion. It has not been researched yet whether the measurement depth of cbPPG, which is limited by the penetration depth of ambient light, is sufficient to reach pulsatile vessels and thus to measure the perfusion strength in regions that are relevant for skin flap transplants.Approach. We applied constant negative pressure (compared to ambient pressure) to the anterior thighs of 40 healthy subjects. Seven measurements (two before and five up to 90 minutes after the intervention) were acquired using an RGB video camera and photospectrometry simultaneously. We investigated the performance of different algorithmic approaches for perfusion strength assessment, including the signal-to-noise ratio (SNR), its logarithmic components logS and logN, amplitude maps, and the amplitude height of alternating and direct signal components.Main results. We found strong correlations of up tor=0.694 (p<0.001) between photospectrometric measurements and all cbPPG parameters except SNR when using the green color channel. The transfer of cbPPG signals to POS, CHROM, and O3C did not lead to systematic improvements. However, for direct signal components, the transformation to O3C led to correlations of up tor=0.744 (p<0.001) with photospectrometric measurements.Significance. Our results indicate that a camera-based perfusion strength assessment in tissue with deep-seated pulsatile vessels is possible.

Hyperspectral Imaging during Normothermic Machine Perfusion—A Functional Classification of Ex Vivo Kidneys Based on Convolutional Neural Networks

Facing an ongoing organ shortage in transplant medicine, strategies to increase the use of organs from marginal donors by objective organ assessment are being fostered. In this context, normothermic machine perfusion provides a platform for ex vivo organ evaluation during preservation. Consequently, analytical tools are emerging to determine organ quality. In this study, hyperspectral imaging (HSI) in the wavelength range of 550–995 nm was applied. Classification of 26 kidneys based on HSI was established using KidneyResNet, a convolutional neural network (CNN) based on the ResNet-18 architecture, to predict inulin clearance behavior. HSI preprocessing steps were implemented, including automated region of interest (ROI) selection, before executing the KidneyResNet algorithm. Training parameters and augmentation methods were investigated concerning their influence on the prediction. When classifying individual ROIs, the optimized KidneyResNet model achieved 84% and 62% accuracy in the validation and test set, respectively. With a majority decision on all ROIs of a kidney, the accuracy increased to 96% (validation set) and 100% (test set). These results demonstrate the feasibility of HSI in combination with KidneyResNet for non-invasive prediction of ex vivo kidney function. This knowledge of preoperative renal quality may support the organ acceptance decision.

Pulse Arrival Time - A Sensitive Vital Parameter for the Detection of Mental Stress

Mental stress triggers positive inotropic and chronotropic effects as well as peripheral vasoconstriction. This alters the pulse arrival time (PAT), the duration between electrical excitation of the ventricles and arrival of the pulse wave in the periphery. We conducted a study to examine PAT during five rest blocks and under mental stress utilizing the Mannheim Multicomponent Stress Test. Electrocardiograms as well as finger and earlobe photoplethysmograms were recorded. PAT was calculated for over 135,000 heartbeats from 42 healthy volunteers as the time duration between the R peak in the electrocardiogram and the following pulse onset in the respective photoplethysmogram. To identify the effect of mental stress, block-wise PAT means were statistically analyzed with repeated measures ANOVA. The analyses showed significant differences between the block means for both PAT measures (p < 0.001). Post-hoc tests revealed significantly reduced PAT during the stress block compared to all rest blocks for both PAT measures (p < 0.001). We found no significant differences between the rest blocks. Our results support that PAT is a sensitive vital parameter for the detection of mental stress in healthy volunteers. This holds true for both measurement positions, the finger and the earlobe.

Using Machine Learning Algorithms for Identifying Gait Parameters Suitable to Evaluate Subtle Changes in Gait in People with Multiple Sclerosis

In multiple sclerosis (MS), gait impairment is one of the most prominent symptoms. For a sensitive assessment of pathological gait patterns, a comprehensive analysis and processing of several gait analysis systems is necessary. The objective of this work was to determine the best diagnostic gait system (DIERS pedogait, GAITRite system, and Mobility Lab) using six machine learning algorithms for the differentiation between people with multiple sclerosis (pwMS) and healthy controls, between pwMS with and without fatigue and between pwMS with mild and moderate impairment. The data of the three gait systems were assessed on 54 pwMS and 38 healthy controls. Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, and Support Vector Machines (SVM) with linear, radial basis function (rbf) and polynomial kernel were applied for the detection of subtle walking changes. The best performance for a healthy-sick classification was achieved on the DIERS data with a SVM rbf kernel (κ = 0.49 ± 0.11). For differentiating between pwMS with mild and moderate disability, the GAITRite data with the SVM linear kernel (κ = 0.61 ± 0.06) showed the best performance. This study demonstrates that machine learning methods are suitable for identifying pathologic gait patterns in early MS.

Comparison of different spectral cameras for image-guided organ transplantation

SIGNIFICANCE

Hyperspectral and multispectral imaging (HMSI) in medical applications provides information about the physiology, morphology, and composition of tissues and organs. The use of these technologies enables the evaluation of biological objects and can potentially be applied as an objective assessment tool for medical professionals.

AIM

Our study investigates HMSI systems for their usability in medical applications.

APPROACH

Four HMSI systems (one hyperspectral pushbroom camera and three multispectral snapshot cameras) were examined and a spectrometer was used as a reference system, which was initially validated with a standardized color chart. The spectral accuracy of the cameras reproducing chemical properties of different biological objects (porcine blood, physiological porcine tissue, and pathological porcine tissue) was analyzed using the Pearson correlation coefficient.

RESULTS

All the HMSI cameras examined were able to provide the characteristic spectral properties of blood and tissues. A pushbroom camera and two snapshot systems achieve Pearson coefficients of at least 0.97 compared to the ground truth, indicating a very high positive correlation. Only one snapshot camera performs moderately to high positive correlation (0.59 to 0.85).

CONCLUSION

The knowledge of the suitability of HMSI cameras for accurate measurement of chemical properties of biological objects offers a good opportunity for the selection of the optimal imaging tool for specific medical applications, such as organ transplantation.

Instantaneous Cardiac Baroreflex Sensitivity: xBRS Method Quantifies Heart Rate Blood Pressure Variability Ratio at Rest and During Slow Breathing

Spontaneous baroreflex sensitivity (BRS) is a widely used tool for the quantification of the cardiovascular regulation. Numerous groups use the xBRS method, which calculates the cross-correlation between the systolic beat-to-beat blood pressure and the R-R interval (resampled at 1 Hz) in a 10 s sliding window, with 0-5 s delays for the interval. The delay with the highest correlation is selected and, if significant, the quotient of the standard deviations of the R-R intervals and the systolic blood pressures is recorded as the corresponding xBRS value. In this paper we test the hypothesis that the xBRS method quantifies the causal interactions of spontaneous BRS from non-invasive measurements at rest. We use the term spontaneous BRS in the sense of the sensitivity curve is calculated from non-interventional, i.e., spontaneous, baroreceptor activity. This study includes retrospective analysis of 1828 measurements containing ECG as well as continues blood pressure under resting conditions. Our results show a high correlation between the heart rate - systolic blood pressure variability (HRV/BPV) quotient and the xBRS (r = 0.94, p < 0.001). For a deeper understanding we conducted two surrogate analyses by substituting the systolic blood pressure by its reversed time series. These showed that the xBRS method was not able to quantify causal relationships between the two signals. It was not possible to distinguish between random and baroreflex controlled sequences. It appears xBRS rather determines the HRV/BPV quotient. We conclude that the xBRS method has a potentially large bias in characterizing the capacity of the arterial baroreflex under resting conditions. During slow breathing, estimates for xBRS are significantly increased, which clearly shows that measurements at rest only involve limited baroreflex activity, but does neither challenge, nor show the full range of the arterial baroreflex regulatory capacity. We show that xBRS is exclusively dominated by the heart rate to systolic blood pressure ratio (r = 0.965, p < 0.001). Further investigations should focus on additional autonomous testing procedures such as slow breathing or orthostatic testing to provide a basis for a non-invasive evaluation of baroreflex sensitivity.

Neighborhood Optimization for Therapy Decision Support

This work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm and a metric learning approach are investigated. Both adapt similarity functions to the underlying data in order to determine the neighborhood incorporated into the filtering process. The implemented approaches are evaluated regarding the accuracy of the outcome estimations. The metric learning approach can outperform the Relief-based algorithms. It is, however, inferior regarding explainability of the generated recommendations.

Predicting sepsis with a recurrent neural network using the MIMIC III database

OBJECTIVE

Predicting sepsis onset with a recurrent neural network and performance comparison with InSight - a previously proposed algorithm for the prediction of sepsis onset.

METHODOLOGY

A retrospective analysis of adult patients admitted to the intensive care unit (from the MIMIC III database) who did not fall under the definition of sepsis at the time of admission. The area under the receiver operating characteristic (AUROC) measures the performance of the prediction task. We examine the sequence length given to the machine learning algorithms for different points in time before sepsis onset concerning the prediction performance. Additionally, the impact of sepsis onset's definition is investigated. We evaluate the model with a relatively large and thus more representative patient population compared to related works in the field.

RESULTS

For a prediction 3 h prior to sepsis onset, our network achieves an AUROC of 0.81 (95% CI: 0.78-0.84). The InSight algorithm achieves an AUROC of 0.72 (95% CI: 0.69-0.75). For a fixed sensitivity of 90% our network reaches a specificity of 47.0% (95% CI: 43.1%-50.8%) compared to 31.1% (95% CI: 24.8%-37.5%) for InSight. In addition, we compare the performance for 6 and 12 h prediction time for both approaches.

CONCLUSION

Our findings demonstrate that a recurrent neural network is superior to InSight considering the prediction performance. Most probably, the improvement results from the network's ability of revealing time dependencies. We show that the length of the look back has a significant impact on the performance of the classifier. We also demonstrate that for the correct detection of sepsis onset for a retrospective analysis, further research is necessary.

The FED-Method (Fixation, Elongation, Derotation) - a Machine-supported Treatment Approach to Patients with Idiopathic Scoliosis - Systematic Review

BACKGROUND

The FED method (Fixation, Elongation, Derotation) is a treatment method approach to Patients with scoliosis. The FED method is especially established in Spain and Poland, whereby in Germany it is less well-known. Nevertheless the FED method is within the scope of a research project (Project Number: 19200 BR/3). The purpose of the paper is to characterize the FED method and to highlight the specificities in contrast to the Schroth method, which is international established and especially in Germany.

METHODS

This systematic literature research was conducted in Nov 2017-Jan 2018. Therefore common medical and physiotherapeutic databases were used. Furthermore there was a hand search in selected scientific journals. Only a small number of relevant references were identified. That is why the respective authors were asked to provide the full-texts of their papers and to recommend further references.

RESULTS

A total of 378 references were identified. After removing duplicates and the content-related selection, 19 references were deemed to be relevant. Based on the analysis of this relevant literature, the FED method was comprehensively characterized. First of all the general structure of the FED method and the scientific evidence for its effectiveness was described. And as a result of the literature research, the operating principles of the FED method were pointed out. Then these operating principles were discussed in comparison with the Schroth method. The Schroth method based on sensomotoric and kinesthetic principles and the correction of the pathologic posture was performed by selective muscle activation and breathing-pattern. Thus, the posture correction will be performed by the patients (auto correction). Compared to the Schroth method, the FED method implements the posture correction by the FED-device. This correction is influenced by mechanical forces with a comparatively high strength and intensity. The repetitive mechanical correction stimulates the sensomotoric system. And due to trophic/biochemical adaptations, the physiological bone growth will be stimulated.

CONCLUSION

In total the authors want to clarify, that both treatment methods (Schroth method, FED method) supposed to be applied in consideration of the preconditions of the patients and the pursue of the different treatment goals. Thus, the implementation of treatment methods should be used according to the individual treatment demand and on different stages in the treatment process.

Algorithms for mapping kidney tissue oxygenation during normothermic machine perfusion using hyperspectral imaging

The lack of donor grafts is a severe problem in transplantation medicine. Hence, the improved preservation of existing and the usage of organs that were deemed untransplantable is as urgent as ever. The development of novel preservation techniques has come into focus. A promising alternative to traditional cold storage is normothermic machine perfusion (NMP), which provides the benefit of improving the organs' viability and of assessing the organs' status under physiological conditions. For this purpose, methods for evaluating organ parameters have yet to be developed. In a previous study, we determined the tissue oxygen saturation (StO2) of kidneys during NMP with hyperspectral imaging (HSI) based on a discrete wavelength (DW) algorithm. The aim of the current study was to identify a more accurate algorithm for StO2 calculation. A literature search revealed three candidates to test: a DW algorithm and two full spectral algorithms - area under a curve and partial least square regression (PLSR). After obtaining suitable calibration data to train each algorithm, they were evaluated during NMP. The wavelength range from 590 to 800 nm was found to be appropriate for analyzing StO2 of kidneys during NMP. The PLSR method shows good results in analyzing the tissues' oxygen status in perfusion experiments.

Cardiovascular assessment by imaging photoplethysmography - a review

Over the last few years, the contactless acquisition of cardiovascular parameters using cameras has gained immense attention. The technique provides an optical means to acquire cardiovascular information in a very convenient way. This review provides an overview on the technique's background and current realizations. Besides giving detailed information on the most widespread application of the technique, namely the contactless acquisition of heart rate, we outline further concepts and we critically discuss the current state.