Complication Prediction after Esophagectomy with Machine Learning.

Esophageal cancer can be treated effectively with esophagectomy; however, the postoperative complication rate is high. In this paper, we study to what extent machine learning methods can predict anastomotic leakage and pneumonia up to two days in advance. We use a dataset with 417 patients who underwent esophagectomy between 2011 and 2021. The dataset contains multimodal temporal information, specifically, laboratory results, vital signs, thorax images, and preoperative patient characteristics. The best models scored mean test set AUROCs of 0.87 and 0.82 for leakage 1 and 2 days ahead, respectively. For pneumonia, this was 0.74 and 0.61 for 1 and 2 days ahead, respectively. We conclude that machine learning models can effectively predict anastomotic leakage and pneumonia after esophagectomy.

Database of lower limb kinematics and electromyography during gait-related activities in able-bodied subjects.

This data descriptor describes the Roessingh Research & Development-MyLeg database for activity prediction (MyPredict), containing three data sets. These data sets contain data from 55 able-bodied subjects, mean age 24 ± 2 years, measured in 85 measurement sessions. Measurement sessions consisted of trials containing sitting, standing, overground walking, stair ascent, stair descent, ramp ascent, ramp descent, walking on uneven terrain and walking in simulated confined spaces. Subjects were measured using eight inertial measurement units in combination with different types of sEMG. Recorded kinematics consisted of joint angles, sensor accelerations, angular velocity, orientation and virtual marker positions. sEMG was recorded using bipolar sEMG, multi-array sEMG or a combination of both. All data showed excellent correlation with other online available data sets. The data reported in this descriptor forms a solid basis for research into myoelectric pattern recognition, myoelectric control development and electromyography to be used in data-driven applications.

Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes.

BACKGROUND: Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making. OBJECTIVE: This study investigates to what extent different machine learning methods, applied to two different PROMs datasets, can predict outcomes among patients with non-specific neck and/or low back pain. METHODS: Using two datasets consisting of PROMs from (1) care-seeking low back pain patients in primary care who participated in a randomized controlled trial, and (2) patients with neck and/or low back pain referred to multidisciplinary biopsychosocial rehabilitation, we present data science methods for data prepossessing and evaluate selected regression and classification methods for predicting patient outcomes. RESULTS: The results show that there is a potential for machine learning to predict and classify PROMs. The prediction models based on baseline measurements perform well, and the number of predictors can be reduced, which is an advantage for implementation in decision support scenarios. The classification task shows that the dataset does not contain all necessary predictors for the care type classification. Overall, the work presents generalizable machine learning pipelines that can be adapted to other PROMs datasets. CONCLUSION: This study demonstrates the potential of PROMs in predicting short-term patient outcomes. Our results indicate that machine learning methods can be used to exploit the predictive value of PROMs and thereby support clinical decision making, given that the PROMs hold enough predictive power.

Adaptive Lower Limb Pattern Recognition for Multi-Day Control.

Pattern recognition in EMG-based control systems suffer from increase in error rate over time, which could lead to unwanted behavior. This so-called concept drift in myoelectric control systems could be caused by fatigue, sensor replacement and varying skin conditions. To circumvent concept drift, adaptation strategies could be used to retrain a pattern recognition system, which could lead to comparable error rates over multiple days. In this study, we investigated the error rate development over one week and compared three adaptation strategies to reduce the error rate increase. The three adaptation strategies were based on entropy, on backward prediction and a combination of backward prediction and entropy. Ten able-bodied subjects were measured on four measurement days while performing gait-related activities. During the measurement electromyography and kinematics were recorded. The three adaptation strategies were implemented and compared against the baseline error rate and against adaptation using the ground truth labels. It can be concluded that without adaptation the baseline error rate increases significantly from day 1 to 2, but plateaus on day 2, 3 and 7. Of the three tested adaptation strategies, entropy based adaptation showed the smallest increase in error rate over time. It can be concluded that entropy based adaptation is simple to implement and can be considered a feasible adaptation strategy for lower limb pattern recognition.

Perceived Mental Workload Classification Using Intermediate Fusion Multimodal Deep Learning.

A lot of research has been done on the detection of mental workload (MWL) using various bio-signals. Recently, deep learning has allowed for novel methods and results. A plethora of measurement modalities have proven to be valuable in this task, yet studies currently often only use a single modality to classify MWL. The goal of this research was to classify perceived mental workload (PMWL) using a deep neural network (DNN) that flexibly makes use of multiple modalities, in order to allow for feature sharing between modalities. To achieve this goal, an experiment was conducted in which MWL was simulated with the help of verbal logic puzzles. The puzzles came in five levels of difficulty and were presented in a random order. Participants had 1 h to solve as many puzzles as they could. Between puzzles, they gave a difficulty rating between 1 and 7, seven being the highest difficulty. Galvanic skin response, photoplethysmograms, functional near-infrared spectrograms and eye movements were collected simultaneously using LabStreamingLayer (LSL). Marker information from the puzzles was also streamed on LSL. We designed and evaluated a novel intermediate fusion multimodal DNN for the classification of PMWL using the aforementioned four modalities. Two main criteria that guided the design and implementation of our DNN are modularity and generalisability. We were able to classify PMWL within-level accurate (0.985 levels) on a seven-level workload scale using the aforementioned modalities. The model architecture allows for easy addition and removal of modalities without major structural implications because of the modular nature of the design. Furthermore, we showed that our neural network performed better when using multiple modalities, as opposed to a single modality. The dataset and code used in this paper are openly available.

Time Coherent Full-Body Poses Estimated Using Only Five Inertial Sensors: Deep versus Shallow Learning.

Full-body motion capture typically requires sensors/markers to be placed on each rigid body segment, which results in long setup times and is obtrusive. The number of sensors/markers can be reduced using deep learning or offline methods. However, this requires large training datasets and/or sufficient computational resources. Therefore, we investigate the following research question: "What is the performance of a shallow approach, compared to a deep learning one, for estimating time coherent full-body poses using only five inertial sensors?". We propose to incorporate past/future inertial sensor information into a stacked input vector, which is fed to a shallow neural network for estimating full-body poses. Shallow and deep learning approaches are compared using the same input vector configurations. Additionally, the inclusion of acceleration input is evaluated. The results show that a shallow learning approach can estimate full-body poses with a similar accuracy (~6 cm) to that of a deep learning approach (~7 cm). However, the jerk errors are smaller using the deep learning approach, which can be the effect of explicit recurrent modelling. Furthermore, it is shown that the delay using a shallow learning approach (72 ms) is smaller than that of a deep learning approach (117 ms).

Evaluation of three machine learning models for self-referral decision support on low back pain in primary care.

BACKGROUND: Most people experience low back pain (LBP) at least once in their life and for some patients this evolves into a chronic condition. One way to prevent acute LBP from transiting into chronic LBP, is to ensure that patients receive the right interventions at the right moment. We started research in the design of a clinical decision support system (CDSS) to support patients with LBP in their self-referral to primary care. For this, we explored the possibilities of using supervised machine learning. We compared the performances of the three classification models - i.e. 1. decision tree, 2. random forest, and 3. boosted tree - to get insight in which model performs best and whether it is already acceptable to use this model in real practice. METHODS: The three models were generated by means of supervised machine learning with 70% of a training dataset (1288 cases with 65% GP, 33% physio, 2% self-care cases). The cases in the training dataset were fictive cases on low back pain collected during a vignette study with primary healthcare professionals. We also wanted to know the performance of the models on real-life low back pain cases that were not used to train the models. Therefore we also collected real-life cases on low back pain as test dataset. These cases were collected with the help of patients and healthcare professionals in primary care. For each model, the performance was measured during model validation - with 30% of the training dataset -as well as during model testing - with the test dataset containing real-life cases. The total observed accuracy as well as the kappa, and the sensitivity, specificity, and precision were used as performance measures to compare the models. RESULTS: For the training dataset, the total observed accuracies of the decision tree, the random forest and boosted tree model were 70%, 69%, and 72% respectively. For the test dataset, the total observed accuracies were 71%, 53%, and 71% respectively. The boosted tree appeared to be the best for predicting a referral advice with a fair accuracy (Kappa between 0.2 and 0.4). Next to this, the measured evaluation measures show that all models provided a referral advice better than just a random guess. This means that all models learned some implicit knowledge of the provided referral advices in the training dataset. CONCLUSIONS: The study showed promising results on the possibility of using machine learning in the design of our CDSS. The boosted tree model performed best on the classification of low back pain cases, but still has to be improved. Therefore, new cases have to be collected, especially cases that are classified as self-care cases. This to be sure that also the self-care advice can be predicted well by the model.

Opening the Black Box of Electronic Health: Collecting, Analyzing, and Interpreting Log Data.

In electronic health (eHealth) research, limited insight has been obtained on process outcomes or how the use of technology has contributed to the users' ability to have a healthier life, improved well-being, or activate new attitudes in their daily tasks. As a result, eHealth is often perceived as a black box. To open this black box of eHealth, methodologies must extend beyond the classic effect evaluations. The analyses of log data (anonymous records of real-time actions performed by each user) can provide continuous and objective insights into the actual usage of the technology. However, the possibilities of log data in eHealth research have not been exploited to their fullest extent. The aim of this paper is to describe how log data can be used to improve the evaluation and understand the use of eHealth technology with a broader approach than only descriptive statistics. This paper serves as a starting point for using log data analysis in eHealth research. Here, we describe what log data is and provide an overview of research questions to evaluate the system, the context, the users of a technology, as well as the underpinning theoretical constructs. We also explain the requirements for log data, the starting points for the data preparation, and methods for data collection. Finally, we describe methods for data analysis and draw a conclusion regarding the importance of the results for both scientific and practical applications. The analysis of log data can be of great value for opening the black box of eHealth. A deliberate log data analysis can give new insights into how the usage of the technology contributes to found effects and can thereby help to improve the persuasiveness and effectiveness of eHealth technology and the underpinning behavioral models.

Online decoding of object-based attention using real-time fMRI.

Visual attention is used to selectively filter relevant information depending on current task demands and goals. Visual attention is called object-based attention when it is directed to coherent forms or objects in the visual field. This study used real-time functional magnetic resonance imaging for moment-to-moment decoding of attention to spatially overlapped objects belonging to two different object categories. First, a whole-brain classifier was trained on pictures of faces and places. Subjects then saw transparently overlapped pictures of a face and a place, and attended to only one of them while ignoring the other. The category of the attended object, face or place, was decoded on a scan-by-scan basis using the previously trained decoder. The decoder performed at 77.6% accuracy indicating that despite competing bottom-up sensory input, object-based visual attention biased neural patterns towards that of the attended object. Furthermore, a comparison between different classification approaches indicated that the representation of faces and places is distributed rather than focal. This implies that real-time decoding of object-based attention requires a multivariate decoding approach that can detect these distributed patterns of cortical activity.

Comparison of feature and classifier algorithms for online automatic sleep staging based on a single EEG signal.

Automatic sleep staging on an online basis has recently emerged as a research topic motivated by fundamental sleep research. The aim of this paper is to find optimal signal processing methods and machine learning algorithms to achieve online sleep staging on the basis of a single EEG signal. The classification performance obtained using six different EEG signals and various signal processing feature sets is compared using the kappa statistic which has very recently become popular in sleep staging research. A variable duration of the EEG segment (or epoch) to decide on the sleep stage is also analyzed. Spectral-domain, time-domain, linear, and nonlinear features are compared in terms of performance and two types of machine learning approaches (random forests and support vector machines) are assessed. We have determined that frontal EEG signals, with spectral linear features, epoch durations between 18 and 30 seconds, and a random forest classifier lead to optimal classification performance while ensuring real-time online operation.

How much control is enough? Influence of unreliable input on user experience.

Brain­computer interfaces (BCI) provide a valuable new input modality within human­computer interaction systems. However, like other body-based inputs such as gesture or gaze based systems, the system recognition of input commands is still far from perfect. This raises important questions, such as what level of control should such an interface be able to provide. What is the relationship between actual and perceived control? And in the case of applications for entertainment in which fun is an important part of user experience, should we even aim for the highest level of control, or is the optimum elsewhere? In this paper, we evaluate whether we can modulate the amount of control and if a game can be fun with less than perfect control. In the experiment users (n = 158) played a simple game in which a hamster has to be guided to the exit of a maze. The amount of control the user has over the hamster is varied. The variation of control through confusion matrices makes it possible to simulate the experience of using a BCI, while using the traditional keyboard for input. After each session the user completed a short questionnaire on user experience and perceived control. Analysis of the data showed that the perceived control of the user could largely be explained by the amount of control in the respective session. As expected, user frustration decreases with increasing control. Moreover, the results indicate that the relation between fun and control is not linear. Although at lower levels of control fun does increase with improved control, the level of fun drops just before perfect control is reached (with an optimum around 96%). This poses new insights for developers of games who want to incorporate some form of BCI or other modality with unreliable input in their game: for creating a fun game, unreliable input can be used to create a challenge for the user.

The impact of loss of control on movement BCIs.

Brain-computer interfaces (BCIs) are known to suffer from spontaneous changes in the brain activity. If changes in the mental state of the user are reflected in the brain signals used for control, the behavior of a BCI is directly influenced by these states. We investigate the influence of a state of loss of control in a variant of Pacman on the performance of BCIs based on motor control. To study the effect a temporal loss of control has on the BCI performance, BCI classifiers were trained on electroencephalography (EEG) recorded during the normal control condition, and the classification performance on segments of EEG from the normal and loss of control condition was compared. Classifiers based on event-related desynchronization unexpectedly performed significantly better during the loss of control condition; for the event-related potential classifiers there was no significant difference in performance.

A subject-independent brain-computer interface based on smoothed, second-order baselining.

A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session.