Detecting Epileptic Seizures Using Hand-Crafted and Automatically Constructed EEG Features.

Epileptic seizure detection aims to replace unreliable seizure diaries by a model that automatically detects seizures based on electroencephalography (EEG) sensors. However, developing such a model is difficult and time consuming as it requires manually searching for relevant features from complex EEG data. Domain experts may have a partial understanding of the EEG characteristics that indicate seizures, but this knowledge is often not sufficient to exhaustively enumerate all relevant features. To address this challenge, we investigate how automated feature construction may complement hand-crafted features for epileptic seizure detection. By means of an empirical comparison on a real-world seizure detection dataset, we evaluate the ability of automated feature construction to come up with new relevant features. We show that combining hand-crafted and automated features results in more accurate models compared to using hand-crafted features alone. Our findings suggest that future studies on developing EEG-based seizure detection models may benefit from features constructed using a combination of hand-crafted and automated feature engineering.

Machine-learned-based prediction of lower extremity overuse injuries using pressure plates.

Although running has many benefits for both the physical and mental health, it also involves the risk of injuries which results in negative physical, psychological and economical consequences. Those injuries are often linked to specific running biomechanical parameters such as the pressure pattern of the foot while running, and they could potentially be indicative for future injuries. Previous studies focus solely on some specific type of running injury and are often only applicable to a gender or running-experience specific population. The purpose of this study is, for both male and female, first-year students, (i) to predict the development of a lower extremity overuse injury in the next 6 months based on foot pressure measurements from a pressure plate and (ii) to identify the predictive loading features. For the first objective, we developed a machine learning pipeline that analyzes foot pressure measurements and predicts whether a lower extremity overuse injury is likely to occur with an AUC of 0.639 and a Brier score of 0.201. For the second objective, we found that the higher pressures exerted on the forefoot are the most predictive for lower extremity overuse injuries and that foot areas from both the lateral and the medial side are needed. Furthermore, there are two kinds of predictive features: the angle of the FFT coefficients and the coefficients of the autoregressive AR process. However, these features are not interpretable in terms of the running biomechanics, limiting its practical use for injury prevention.

Can the Output of a Learned Classification Model Monitor a Person's Functional Recovery Status Post-Total Knee Arthroplasty?

Osteoarthritis is a common musculoskeletal disorder. Classification models can discriminate an osteoarthritic gait pattern from that of control subjects. However, whether the output of learned models (probability of belonging to a class) is usable for monitoring a person's functional recovery status post-total knee arthroplasty (TKA) is largely unexplored. The research question is two-fold: (I) Can a learned classification model's output be used to monitor a person's recovery status post-TKA? (II) Is the output related to patient-reported functioning? We constructed a logistic regression model based on (1) pre-operative IMU-data of level walking, ascending, and descending stairs and (2) 6-week post-operative data of walking, ascending-, and descending stairs. Trained models were deployed on subjects at three, six, and 12 months post-TKA. Patient-reported functioning was assessed by the KOOS-ADL section. We found that the model trained on 6-weeks post-TKA walking data showed a decrease in the probability of belonging to the TKA class over time, with moderate to strong correlations between the model's output and patient-reported functioning. Thus, the LR-model's output can be used as a screening tool to follow-up a person's recovery status post-TKA. Person-specific relationships between the probabilities and patient-reported functioning show that the recovery process varies, favouring individual approaches in rehabilitation.

Joint kinematics alone can distinguish hip or knee osteoarthritis patients from asymptomatic controls with high accuracy.

Osteoarthritis (OA) is one of the leading musculoskeletal disabilities worldwide, and several interventions intend to change the gait pattern in OA patients to more healthy patterns. However, an accessible way to follow up the biomechanical changes in a clinical setting is still missing. Therefore, this study aims to evaluate whether we can use biomechanical data collected from a specific activity of daily living to help distinguish hip OA patients from controls and knee OA patients from controls using features that potentially could be measured in a clinical setting. To achieve this goal, we considered three different classes of statistical models with different levels of data complexity. Class 1 is kinematics based only (clinically applicable), class 2 includes joint kinetics (semi-applicable under the condition of access to a force plate or prediction models), and class 3 uses data from advanced musculoskeletal modeling (not clinically applicable). We used a machine learning pipeline to determine which classification model was best. We found 100% classification accuracy for KneeOA-vs-Asymptomatic and 93.9% for HipOA-vs-Asymptomatic using seven features derived from the lumbar spine and hip kinematics collected during ascending stairs. These results indicate that kinematical data alone can distinguish hip or knee OA patients from asymptomatic controls. However, to enable clinical use, we need to validate if the classifier also works with sensor-based kinematical data and whether the probabilistic outcome of the logistic regression model can be used in the follow-up of patients with OA.

Towards the Monitoring of Functional Status in a Free-Living Environment for People with Hip or Knee Osteoarthritis: Design and Evaluation of the JOLO Blended Care App.

(1) Background: Joint loading is an important parameter in patients with osteoarthritis (OA). However, calculating joint loading relies on the performance of an extensive biomechanical analysis, which is not possible to do in a free-living situation. We propose the concept and design of a novel blended-care app called JOLO (Joint Load) that combines free-living information on activity with lab-based measures of joint loading in order to estimate a subject's functional status. (2) Method: We used an iterative design process to evaluate the usability of the JOLO app through questionnaires. The user interfaces that resulted from the iterations are described and provide a concept for feedback on functional status. (3) Results: In total, 44 people (20 people with OA and 24 health-care providers) participated in the testing of the JOLO app. OA patients rated the latest version of the JOLO app as moderately useful. Therapists were predominantly positive; however, their intention to use JOLO was low due to technological issues. (4) Conclusion: We can conclude that JOLO is promising, but further technological improvements concerning activity recognition, the development of personalized joint loading predictions and a more comfortable means to carry the device are needed to facilitate its integration as a blended-care program.

A Machine Learning Approach to Estimate Hip and Knee Joint Loading Using a Mobile Phone-Embedded IMU.

Hip osteoarthritis patients exhibit changes in kinematics and kinetics that affect joint loading. Monitoring this load can provide valuable information to clinicians. For example, a patient's joint loading measured across different activities can be used to determine the amount of exercise that the patient needs to complete each day. Unfortunately, current methods for measuring joint loading require a lab environment which most clinicians do not have access to. This study explores employing machine learning to construct a model that can estimate joint loading based on sensor data obtained solely from a mobile phone. In order to learn such a model, we collected a dataset from 10 patients with hip osteoarthritis who performed multiple repetitions of nine different exercises. During each repetition, we simultaneously recorded 3D motion capture data, ground reaction force data, and the inertial measurement unit data from a mobile phone attached to the patient's hip. The 3D motion and ground reaction force data were used to compute the ground truth joint loading using musculoskeletal modeling. Our goal is to estimate the ground truth loading value using only the data captured by the sensors of the mobile phone. We propose a machine learning pipeline for learning such a model based on the recordings of a phone's accelerometer and gyroscope. When evaluated for an unseen patient, the proposed pipeline achieves a mean absolute error of 29% for the left hip and 36% for the right hip. While our approach is a step in the direction of using a minimal number of sensors to estimate joint loading outside the lab, developing a tool that is accurate enough to be applicable in a clinical context still remains an open challenge. It may be necessary to use sensors at more than one location in order to obtain better estimates.

Data fusion of body-worn accelerometers and heart rate to predict VO2max during submaximal running.

Maximal oxygen uptake (VO2max) is often used to assess an individual's cardiorespiratory fitness. However, measuring this variable requires an athlete to perform a maximal exercise test which may be impractical, since this test requires trained staff and specialized equipment, and may be hard to incorporate regularly into training programs. The aim of this study is to develop a new model for predicting VO2max by exploiting its relationship to heart rate and accelerometer features extracted during submaximal running. To do so, we analyzed data collected from 31 recreational runners (15 men and 16 women) aged 19-26 years who performed a maximal incremental test on a treadmill. During this test, the subjects' heart rate and acceleration at three locations (the upper back, the lower back and the tibia) were continuously measured. We extracted a wide variety of features from the measurements of the warm-up and the first three stages of the test and employed a data-driven approach to select the most relevant ones. Furthermore, we evaluated the utility of combining different types of features. Empirically, we found that combining heart rate and accelerometer features resulted in the best model with a mean absolute error of 2.33 ml ⋅ kg-1 ⋅ min-1 and a mean absolute percentage error of 4.92%. The model includes four features: gender, body mass, the inverse of the average heart rate and the inverse of the variance of the total tibia acceleration during the warm-up stage of the treadmill test. Our model provides a practical tool for recreational runners in the same age range to estimate their VO2max from submaximal running on a treadmill. It requires two body-worn sensors: a heart rate monitor and an accelerometer positioned on the tibia.