Abstract: Disability is associated with lower quality of life and premature death in older people. Therefore, prevention and intervention targeting older people living with a disability is important. Frailty can be considered a major predictor of disability. In this study, we aimed to develop nomograms with items of the Tilburg Frailty Indicator (TFI) as predictors by using cross-sectional and longitudinal data (follow-up of five and nine years), focusing on the prediction of total disability, disability in activities of daily living (ADL), and disability in instrumental activities of daily living (IADL). At baseline, 479 Dutch community-dwelling people aged 75 years participated. They completed a questionnaire that included the TFI and the Groningen Activity Restriction Scale to assess the three disability variables. We showed that the TFI items scored different points, especially over time. Therefore, not every item was equally important in predicting disability. ‘Difficulty in walking’ and ‘unexplained weight loss’ appeared to be important predictors of disability. Healthcare professionals need to focus on these two items to prevent disability. We also conclude that the points given to frailty items differed between total, ADL, and IADL disability and also differed regarding years of follow-up. Creating one monogram that does justice to this seems impossible.
DOCUMENT
Background: Modern modeling techniques may potentially provide more accurate predictions of dichotomous outcomes than classical techniques. Objective: In this study, we aimed to examine the predictive performance of eight modeling techniques to predict mortality by frailty. Methods: We performed a longitudinal study with a 7-year follow-up. The sample consisted of 479 Dutch community-dwelling people, aged 75 years and older. Frailty was assessed with the Tilburg Frailty Indicator (TFI), a self-report questionnaire. This questionnaire consists of eight physical, four psychological, and three social frailty components. The municipality of Roosendaal, a city in the Netherlands, provided the mortality dates. We compared modeling techniques, such as support vector machine (SVM), neural network (NN), random forest, and least absolute shrinkage and selection operator, as well as classical techniques, such as logistic regression, two Bayesian networks, and recursive partitioning (RP). The area under the receiver operating characteristic curve (AUROC) indicated the performance of the models. The models were validated using bootstrapping. Results: We found that the NN model had the best validated performance (AUROC=0.812), followed by the SVM model (AUROC=0.705). The other models had validated AUROC values below 0.700. The RP model had the lowest validated AUROC (0.605). The NN model had the highest optimism (0.156). The predictor variable “difficulty in walking” was important for all models. Conclusions: Because of the high optimism of the NN model, we prefer the SVM model for predicting mortality among community-dwelling older people using the TFI, with the addition of “gender” and “age” variables. External validation is a necessary step before applying the prediction models in a new setting.
DOCUMENT
The task of risk assessment is a central feature of probation work and a core activity of probation officers. Risk assessment forms the basis for subsequent interventions and management of offenders so that the likelihood of reoffending is reduced. A primary difficulty for probation workers is the ability to predict the risk of probation violations which could facilitate prevention. The main objective of the present study was to investigate the value of the 61-item Dutch diagnostic and risk assessment tool Recidivism Assessment Scales (RISc) with respect to predicting probation supervision violations of male probationers (N = 14,363). Because all RISc assessments included in the study were completed before the start of the supervision period, they could not have been influenced by behavior of the offenders or other circumstances during this period. It was found that the predictive accuracy of the RISc, with regard to supervision violation, was supported. All RISc subscales and the total score significantly predicted probation supervision violation. The AUC demonstrating the strength of the relationship of the RISc total score (AUC = .70) is satisfactory. Logistic regression analyses resulted in a fitting model, demonstrating that a selection of only 17 items from the total of 61 RISc items was sufficient to predict probation violation while preserving predictive accuracy (AUC = .73). For one of the possible cut-off sum scores used to select groups at high risk for probation violation, it was shown that is possible to double the percentage of correctly identified future violators when compared to the base rate of probation violation.
LINK
Study designCross-sectional study.ObjectivesThe aims of this study were (1) to validate the two recently developed SCI-specific REE equations; (2) to develop new prediction equations to predict REE in a general population with SCI.SettingUniversity, the Netherlands.MethodsForty-eight community-dwelling men and women with SCI were recruited (age: 18–75 years, time since injury: ≥12 months). Body composition was measured by dual-energy X-ray absorptiometry (DXA), single-frequency bioelectrical impedance analysis (SF-BIA) and skinfold thickness. REE was measured by indirect calorimetry. Personal and lesion characteristics were collected. SCI-specific REE equations by Chun et al. [1] and by Nightingale and Gorgey [2] were validated. New equations for predicting REE were developed using multivariate regression analysis.ResultsPrediction equations by Chun et al. [1] and by Nightingale and Gorgey [2] significantly underestimated REE (Chun et al.: −11%; Nightingale and Gorgey: −11%). New equations were developed for predicting REE in the general population of people with SCI using FFM measured by SF-BIA and Goosey-Tolfrey et al. skinfold equation (R2 = 0.45–0.47; SEE = 200 kcal/day). The new equations showed proportional bias (p < 0.001) and wide limits of agreement (LoA, ±23%).ConclusionsPrediction equations by Chun et al. [1] and by Nightingale and Gorgey [2] significantly underestimated REE and showed large individual variations in a general population with SCI. The newly developed REE equations showed proportional bias and a wide LoA (±23%) which limit the predictive power and accuracy to predict REE in the general population with SCI. Alternative methods for measuring REE need to be investigated.
DOCUMENT
Individuals with autism increasingly enroll in universities, but little is known about predictors for their success. This study developed predictive models for the academic success of autistic bachelor students (N=101) in comparison to students with other health conditions (N=2465) and students with no health conditions (N=25,077). We applied propensity score weighting to balance outcomes. The research showed that autistic students’ academic success was predictable, and these predictions were more accurate than predictions of their peers’ success. For first-year success, study choice issues were the most important predictors (parallel program and application timing). Issues with participation in pre-education (missingness of grades in pre-educational records) and delays at the beginning of autistic students’ studies (reflected in age) were the most influential predictors for the second-year success and delays in the second and final year of their bachelor’s program. In addition, academic performance (average grades) was the strongest predictor for degree completion in 3 years. These insights can enable universities to develop tailored support for autistic students. Using early warning signals from administrative data, institutions can lower dropout risk and increase degree completion for autistic students.
DOCUMENT
Since the European Union wants to reduce the oil dependence of the transportation system, the uptake of alternative vehicle technologies are stimulated in the member states. In the Netherlands, stimulation is already largely implemented in the form of a comprehensive charging infrastructure. This infrastructure is widely used by the electric vehicle drivers and thus there may occur a form of competition for the charging points. In this paper we address this problem by predicting the short-term availability of charging points at a given location and time by using the historical charging data in a space-time series model. The model shows better accuracy with respect to a naive method for short term predictions up to one day. This will allow charging point operators to provide customers with the service of looking up estimated charging point availability in the nearby future.
DOCUMENT
We investigate the experiential factors predicting the short-termimpact of a museum visit. Two recently developed frameworks wereused: the Dimensions of Visitor Experience (DoVE) framework byPacker et al. (2018) and the experience impact framework by Duerdenet al. (2018). We employ a survey method, collecting data from 523respondents over a year. The results of a SEM analysis reveal thatreflection and joy significantly enhance memorable impacts of thevisit, while sociability plays a smaller, yet still significant role. Reflectionalone significantly and largely influences perceived meaningfulness,and both sociability and reflection significantly contribute to transfor-mative impacts. This research provides valuable insights for museumsto design experiences that enhance their impact on visitors, therebydemonstrating their value to stakeholders and supporting museums’financial sustainability.
LINK
This study investigates factors predicting hospitality management students’ intention to enter employment in the hospitality industry upon graduation. Survey data were collected from 591 hospitality management students in a hotel management school in the Netherlands. Results of multiple regression analyses showed that study progress negatively predicted, while preferences for large organisations, engaging work content and growth opportunities positively predicted students’ intention to enter the hospitality industry. Supplementary analyses further revealed that among higher study year students, growth opportunity was the most crucial predictor for intention to enter the industry. Theoretical and practical implications were discussed.
LINK
Ambient activity monitoring systems produce large amounts of data, which can be used for health monitoring. The problem is that patterns in this data reflecting health status are not identified yet. In this paper the possibility is explored of predicting the functional health status (the motor score of AMPS = Assessment of Motor and Process Skills) of a person from data of binary ambient sensors. Data is collected of five independently living elderly people. Based on expert knowledge, features are extracted from the sensor data and several subsets are selected. We use standard linear regression and Gaussian processes for mapping the features to the functional status and predict the status of a test person using a leave-oneperson-out cross validation. The results show that Gaussian processes perform better than the linear regression model, and that both models perform better with the basic feature set than with location or transition based features. Some suggestions are provided for better feature extraction and selection for the purpose of health monitoring. These results indicate that automated functional health assessment is possible, but some challenges lie ahead. The most important challenge is eliciting expert knowledge and translating that into quantifiable features.
DOCUMENT
Study orientation tools are frequently grounded in the notion that achieving person-environment (PE) fit is key to academic success. Nevertheless, the literature reveals two notable gaps: the focus on predictive rather than explanatory role of PE fit within a broader set of variables, and its varying impact on outcomes across study programmes. This study aimed to address these gaps by investigating the relative importance of PE fit within a comprehensive set of pre-enrolment predictors to predict programme-specific persistence. We analysed data from 1305 prospective first-year students across five study programmes, with at least 200 students per programme. Data analysis included propensity score weighting and logistic LASSO regressions with cross-validation. The results indicated prediction accuracy in each programme ranging from 67% to 77% in the training data, which reduced to 50–75% in the test data, reflecting good prediction of persistence but challenges in predicting dropout. Inspection of the retained predictors revealed varying predictors across study programmes, with interest and skill fit variables representing the largest effects. This study underscores the necessity of programme-specific predictions to understand the relationship between PE fit and first-year persistence. The findings lay the groundwork for more personalised feedback in study orientation tools.
DOCUMENT
