Background: Advanced statistical modeling techniques may help predict health outcomes. However, it is not the case that these modeling techniques always outperform traditional techniques such as regression techniques. In this study, external validation was carried out for five modeling strategies for the prediction of the disability of community-dwelling older people in the Netherlands. Methods: We analyzed data from five studies consisting of community-dwelling older people in the Netherlands. For the prediction of the total disability score as measured with the Groningen Activity Restriction Scale (GARS), we used fourteen predictors as measured with the Tilburg Frailty Indicator (TFI). Both the TFI and the GARS are self-report questionnaires. For the modeling, five statistical modeling techniques were evaluated: general linear model (GLM), support vector machine (SVM), neural net (NN), recursive partitioning (RP), and random forest (RF). Each model was developed on one of the five data sets and then applied to each of the four remaining data sets. We assessed the performance of the models with calibration characteristics, the correlation coefficient, and the root of the mean squared error. Results: The models GLM, SVM, RP, and RF showed satisfactory performance characteristics when validated on the validation data sets. All models showed poor performance characteristics for the deviating data set both for development and validation due to the deviating baseline characteristics compared to those of the other data sets. Conclusion: The performance of four models (GLM, SVM, RP, RF) on the development data sets was satisfactory. This was also the case for the validation data sets, except when these models were developed on the deviating data set. The NN models showed a much worse performance on the validation data sets than on the development data sets.
DOCUMENT
Background To gain insight into the role of plantar intrinsic foot muscles in fall-related gait parameters in older adults, it is fundamental to assess foot muscles separately. Ultrasonography is considered a promising instrument to quantify the strength capacity of individual muscles by assessing their morphology. The main goal of this study was to investigate the intra-assessor reliability and measurement error for ultrasound measures for the morphology of selected foot muscles and the plantar fascia in older adults using a tablet-based device. The secondary aim was to compare the measurement error between older and younger adults and between two different ultrasound machines. Methods Ultrasound images of selected foot muscles and the plantar fascia were collected in younger and older adults by a single operator, intensively trained in scanning the foot muscles, on two occasions, 1–8 days apart, using a tablet-based and a mainframe system. The intra-assessor reliability and standard error of measurement for the cross-sectional area and/or thickness were assessed by analysis of variance. The error variance was statistically compared across age groups and machines. Results Eighteen physically active older adults (mean age 73.8 (SD: 4.9) years) and ten younger adults (mean age 21.9 (SD: 1.8) years) participated in the study. In older adults, the standard error of measurement ranged from 2.8 to 11.9%. The ICC ranged from 0.57 to 0.97, but was excellent in most cases. The error variance for six morphology measures was statistically smaller in younger adults, but was small in older adults as well. When different error variances were observed across machines, overall, the tablet-based device showed superior repeatability. Conclusions This intra-assessor reliability study showed that a tablet-based ultrasound machine can be reliably used to assess the morphology of selected foot muscles in older adults, with the exception of plantar fascia thickness. Although the measurement errors were sometimes smaller in younger adults, they seem adequate in older adults to detect group mean hypertrophy as a response to training. A tablet-based ultrasound device seems to be a reliable alternative to a mainframe system. This advocates its use when foot muscle morphology in older adults is of interest.
MULTIFILE
Abstract Background: COVID-19 was first identified in December 2019 in the city of Wuhan, China. The virus quickly spread and was declared a pandemic on March 11, 2020. After infection, symptoms such as fever, a (dry) cough, nasal congestion, and fatigue can develop. In some cases, the virus causes severe complications such as pneumonia and dyspnea and could result in death. The virus also spread rapidly in the Netherlands, a small and densely populated country with an aging population. Health care in the Netherlands is of a high standard, but there were nevertheless problems with hospital capacity, such as the number of available beds and staff. There were also regions and municipalities that were hit harder than others. In the Netherlands, there are important data sources available for daily COVID-19 numbers and information about municipalities. Objective: We aimed to predict the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands, using a data set with the properties of 355 municipalities in the Netherlands and advanced modeling techniques. Methods: We collected relevant static data per municipality from data sources that were available in the Dutch public domain and merged these data with the dynamic daily number of infections from January 1, 2020, to May 9, 2021, resulting in a data set with 355 municipalities in the Netherlands and variables grouped into 20 topics. The modeling techniques random forest and multiple fractional polynomials were used to construct a prediction model for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants per municipality in the Netherlands. Results: The final prediction model had an R2 of 0.63. Important properties for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality in the Netherlands were exposure to particulate matter with diameters <10 μm (PM10) in the air, the percentage of Labour party voters, and the number of children in a household. Conclusions: Data about municipality properties in relation to the cumulative number of confirmed infections in a municipality in the Netherlands can give insight into the most important properties of a municipality for predicting the cumulative number of confirmed COVID-19 infections per 10,000 inhabitants in a municipality. This insight can provide policy makers with tools to cope with COVID-19 and may also be of value in the event of a future pandemic, so that municipalities are better prepared.
LINK
Recent research has indicated an increase in the likelihood and impact of tree failure. The potential for trees to fail relates to various biomechanical and physical factors. Strikingly, there seems to be an absence of tree risk assessment methods supported by observations, despite an increasing availability of variables and parameters measured by scientists, arborists and practitioners. Current urban tree risk assessments vary due to differences in experience, training, and personal opinions of assessors. This stresses the need for a more objective method to assess the hazardousness of urban trees. The aim of this study is to provide an overview of factors that influence tree failure including stem failure, root failure and branch failure. A systematic literature review according to the PRISMA guidelines has been performed in databases, supported by backward referencing: 161 articles were reviewed revealing 142 different factors which influenced tree failure. A meta-analysis of effect sizes and p-values was executed on those factors which were associated directly with any type of tree failure. Bayes Factor was calculated to assess the likelihood that the selected factors appear in case of tree failure. Publication bias was analysed visually by funnel plots and results by regression tests. The results provide evidence that the factors Height and Stem weight positively relate to stem failure, followed by Age, DBH, DBH squared times H, and Cubed DBH (DBH3) and Tree weight. Stem weight and Tree weight were found to relate positively to root failure. For branch failure no relating factors were found. We recommend that arborists collect further data on these factors. From this review it can further be concluded that there is no commonly shared understanding, model or function available that considers all factors which can explain the different types of tree failure. This complicates risk estimations that include the failure potential of urban trees.
MULTIFILE
Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and metereological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be GatedRecurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
MULTIFILE
Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and meteorological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be Gated Recurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.
DOCUMENT
In sports, inertial measurement units are often used to measure the orientation of human body segments. A Madgwick (MW) filter can be used to obtain accurate inertial measurement unit (IMU) orientation estimates. This filter combines two different orientation estimates by applying a correction of the (1) gyroscope-based estimate in the direction of the (2) earth frame-based estimate. However, in sports situations that are characterized by relatively large linear accelerations and/or close magnetic sources, such as wheelchair sports, obtaining accurate IMU orientation estimates is challenging. In these situations, applying the MW filter in the regular way, i.e., with the same magnitude of correction at all time frames, may lead to estimation errors. Therefore, in this study, the MW filter was extended with machine learning to distinguish instances in which a small correction magnitude is beneficial from instances in which a large correction magnitude is beneficial, to eventually arrive at accurate body segment orientations in IMU-challenging sports situations. A machine learning algorithm was trained to make this distinction based on raw IMU data. Experiments on wheelchair sports were performed to assess the validity of the extended MW filter, and to compare the extended MW filter with the original MW filter based on comparisons with a motion capture-based reference system. Results indicate that the extended MW filter performs better than the original MW filter in assessing instantaneous trunk inclination (7.6 vs. 11.7◦ root-mean-squared error, RMSE), especially during the dynamic, IMU-challenging situations with moving athlete and wheelchair. Improvements of up to 45% RMSE were obtained for the extended MW filter compared with the original MW filter. To conclude, the machine learning-based extended MW filter has an acceptable accuracy and performs better than the original MW filter for the assessment of body segment orientation in IMU-challenging sports situations.
DOCUMENT
Objective: To examine the underlying factor structure and psychometric properties of the Assessment of Self-management in Anxiety and Depression (ASAD) questionnaire, which was specifically designed for patients with (chronic) anxiety and depressive disorders. Moreover, this study assesses whether the number of items in the ASAD can be reduced without significantly reducing its precision. Methods: The ASAD questionnaire was completed by 171 participants across two samples: one sample comprised patients with residual anxiety or depressive symptoms, while the other consisted of patients who have been formally diagnosed with a chronic anxiety or depressive disorder. All participants had previously undergone treatment. Both exploratory (EFA) and confirmatory factor analyses (CFA) were conducted. Internal consistency and test–retest reliability were also assessed. Results: Both EFA and CFA indicated three solid factors: Seeking support, Daily life strategies and Taking ownership [Comparative Fit Index = 0.80, Tucker Lewis Index = 0.78, Root Mean Square Error of Approximation = 0.09 (CI 0.08–1.00), Standardized Root Mean Square Residual = 0.09 ($2 = 439.35, df = 168)]. The ASAD was thus reduced from 45 items to 21 items, which resulted in the ASAD-Short Form (SF). All sub-scales had a high level of internal consistency (> a = 0.75) and test–retest reliability (ICC > 0.75). Discussion: The first statistical evaluation of the ASAD indicated a high level of internal consistency and test–retest reliability, and identified three distinctive factors. This could aid patients and professionals’ assessment of types of self-management used by the patient. Given that this study indicated that the 21-item ASAD-SF is appropriate, this version should be further explored and validated among a sample of patients with (chronic or partially remitted) anxiety and depressive disorders. Alongside this, to increase generalizability, more studies are required to examine the English version of the ASAD within other settings and countries.
DOCUMENT
Accurate assessment of rolling resistance is important for wheelchair propulsion analyses. However, the commonly used drag and deceleration tests are reported to underestimate rolling resistance up to 6% due to the (neglected) influence of trunk motion. The first aim of this study was to investigate the accuracy of using trunk and wheelchair kinematics to predict the intra-cyclical load distribution, more particularly front wheel loading, during hand-rim wheelchair propulsion. Secondly, the study compared the accuracy of rolling resistance determined from the predicted load distribution with the accuracy of drag test-based rolling resistance. Twenty-five able-bodied participants performed hand-rim wheelchair propulsion on a large motor-driven treadmill. During the treadmill sessions, front wheel load was assessed with load pins to determine the load distribution between the front and rear wheels. Accordingly, a machine learning model was trained to predict front wheel load from kinematic data. Based on two inertial sensors (attached to the trunk and wheelchair) and the machine learning model, front wheel load was predicted with a mean absolute error (MAE) of 3.8% (or 1.8 kg). Rolling resistance determined from the predicted load distribution (MAE: 0.9%, mean error (ME): 0.1%) was more accurate than drag test-based rolling resistance (MAE: 2.5%, ME: −1.3%).
DOCUMENT
In wheelchair sports, the use of Inertial Measurement Units (IMUs) has proven to be one of the most accessible ways for ambulatory measurement of wheelchair kinematics. A three-IMU configuration, with one IMU attached to the wheelchair frame and two IMUs on each wheel axle, has previously shown accurate results and is considered optimal for accuracy. Configurations with fewer sensors reduce costs and could enhance usability, but may be less accurate. The aim of this study was to quantify the decline in accuracy for measuring wheelchair kinematics with a stepwise sensor reduction. Ten differently skilled participants performed a series of wheelchair sport specific tests while their performance was simultaneously measured with IMUs and an optical motion capture system which served as reference. Subsequently, both a one-IMU and a two-IMU configuration were validated and the accuracy of the two approaches was compared for linear and angular wheelchair velocity. Results revealed that the one-IMU approach show a mean absolute error (MAE) of 0.10 m/s for absolute linear velocity and a MAE of 8.1◦/s for wheelchair angular velocity when compared with the reference system. The twoIMU approach showed similar differences for absolute linear wheelchair velocity (MAE 0.10 m/s), and smaller differences for angular velocity (MAE 3.0◦/s). Overall, a lower number of IMUs used in the configuration resulted in a lower accuracy of wheelchair kinematics. Based on the results of this study, choices regarding the number of IMUs can be made depending on the aim, required accuracy and resources available.
DOCUMENT
