1,721,101 research outputs found
Dimensionality reduction for the quantitative evaluation of a smartphone-based Timed Up and Go test
No full textThe Timed Up and Go is a clinical test to assess mobility in the elderly and in Parkinson's disease. Lately instrumented versions of the test are being considered, where inertial sensors assess motion. To improve the pervasiveness, ease of use, and cost, we consider a smartphone's accelerometer as the measurement system. Several parameters (usually highly correlated) can be computed from the signals recorded during the test. To avoid redundancy and obtain the features that are most sensitive to the locomotor performance, a dimensionality reduction was performed through principal component analysis (PCA). Forty-nine healthy subjects of different ages were tested. PCA was performed to extract new features (principal components) which are not redundant combinations of the original parameters and account for most of the data variability. They can be useful for exploratory analysis and outlier detection. Then, a reduced set of the original parameters was selected through correlation analysis with the principal components. This set could be recommended for studies based on healthy adults. The proposed procedure could be used as a first-level feature selection in classification studies (i.e. healthy-Parkinson's disease, fallers-non fallers) and could allow, in the future, a complete system for movement analysis to be incorporated in a smartphone
Sensor-based assessment of mobility-related behavior in dementia: Feasibility and relevance in a hospital context
Full text linkBackground: The assessment of patients' motor behavior is a key challenge in dementia care. Common geriatric assessment questionnaires or actigraphy measurements often lack methodological quality and are unsuitable to individually tailor interventions. Hence, there is a need for developing objective tools to assess patterns of motor behavior. Therefore, the feasibility of a sensor-based assessment of mobility-related behavior in patients with dementia is investigated. Methods: A cross-sectional investigation on three dementia care wards in a psychiatric hospital was conducted. Forty-five patients with stages of dementia were included. Hybrid motion sensors, recording the sequence of body-postures, were attached on the patients' lower back for 72 consecutive hours. Results: Eighty-nine percent of the assessment periods were completed. On average patients spent 10.9 h/day lying (45%), 9.7 h/day sedentary while sitting or standing (41%), 1.7 h/day active while sitting or standing (7%), 1.7 h/day walking (7%), and reached on average 8,829 steps per day (SD = 7,428). Though overall activity levels were low, the results indicate a wide spectrum of activity patterns - ranging from almost inactive to highly active with general restlessness and wandering behavior. Conclusion: The excellent adherence to the assessment protocol compared to wrist-worn actigraphy and the consistency of the sensor-derived analyses with clinical observations are pivotal findings of this study. These results show that it is possible to acquire objective data on individual motor behavior of patients suffering from dementia. This information is essential for tailoring the therapeutic management of these patients in a hospital context
Physical activity classification meets daily life: Review on existing methodologies and open challenges
No full textRecent advances in the MEMS devices make it happen to wirelessly integrate miniature motion capturing devices with Smartphones and to use them in personal health care and physical activity monitoring in daily life. There is no ground truth, though, to measure the physical activity (PA) in daily life and because of this, there is no common validation procedure adapted by the researchers for benchmarking the performance of algorithms for PA classification. The major issue in the existing studies for PA classification is the utilization of structured protocol in a controlled setting or simulated daily environment, which limits their implementation in real life conditions where activities are unplanned and unstructured, both in occurrence and in duration. This study provides a critical review on the validation procedures used for PA classification, types of activities classified and limitations in the exiting studies to implement them in daily life settings. Only those studies are considered which classify PA based on wearable accelerometers as an objective measure. The pros and cons of existing methodologies are highlighted and future possibilities are addressed for the development of a robust PA classification system which is feasible under real life conditions
Mobility in Old Age: Capacity Is Not Performance
Full text linkBackground. Outcomes of laboratory-based tests for mobility are often used to infer about older adults' performance in real life; however, it is unclear whether such association exists. We hypothesized that mobility capacity, as measured in the laboratory, and mobility performance, as measured in real life, would be poorly linked. Methods. The sample consisted of 84 older adults 72.5 +/- 5.9 years). Capacity was assessed via the iTUG and standard gait parameters stride length, stride velocity, and cadence). Performance was assessed in real life over a period of 6.95 +/- 1.99 days using smartphone technology to calculate following parameters: active and gait time, number of steps, life-space, mean action-range, and maximum action-range. Correlation analyses and stepwise multiple regression analyses were applied. Results. All laboratory measures demonstrated significant associations with the real-life-measures between r =.229 and r =.461). The multiple regression analyses indicated that the laboratory measures accounted for a significant but very low proportion of variance between 5% and 21%) in real-life measures. Conclusion. In older adults without mobility impairments, capacity-related measures of mobility bear little significance for predicting real-life performance. Hence, other factors play a role in how older people manage their daily-life mobility. This should be considered for diagnosis and treatment of mobility deficits in older people
Tecnologie indossabili per il monitoraggio e la prevenzione delle cadute nell'anziano
No full textSe si prende in considerazione uno dei cosiddetti giganti geriatrici, appare evidente come le cadute costituiscano un pesante onere economico e sociale, determinando una significativa riduzione della qualità di vita nella popolazione anziana e/o patologica. Nel solo 2009, le cadute hanno determinato costi che variano tra lo 0,85 e lo 1,5 per cento delle spese sanitarie totali negli Stati Uniti, Australia, UE e Regno Unito (Heinrich et al., 2009). Le cadute hanno anche un impatto notevole sulle condizioni di salute generali di uno stato, dato che lo 81-98% delle fratture sono causate da cadute (Tinetti, 2003), e queste sono la principale causa di accessi al pronto soccorso in USA (Fuller, 2000).
Il rischio di una caduta aumenta con l'età (Mathers e Weiss, 1998); le cadute rappresentano l'eziologia primaria di morte accidentale in soggetti con più di 65 anni, e anche il tasso di mortalità associato aumenta notevolmente con l'età, con picchi pari al 70% delle morti accidentali nelle persone di 75 anni di età (Fuller, 2000). I principali costi associati tendono quindi a verificarsi in gruppi di età più avanzata e a seguito di fratture (si veda il capitolo di Luca Cristofolini in questo volume), un problema che si aggrava ulteriormente con l’invecchiamento della popolazione (Hamacher et al., 2011).
Risulta quindi chiaro l’interesse nell’individuazione di metodi efficaci, che consentano di identificare i soggetti a rischio e di mettere a punto interventi clinici/riabilitativi capaci di ridurre tale rischio. Purtroppo, però, questo risulta tutt’altro che semplice dato che, in base alle valutazioni epidemiologiche, il rischio di caduta ha una natura multifattoriale e può essere il risultato di quadri clinici e condizioni ambientali molto diversi da un soggetto all’altro. Sia la stabilità posturale che quella motoria sono il risultato dell’azione concorrente di diverse risorse funzionali
The improvement of turning ability is a key objective for fall-risk reduction in individuals with impaired dynamic stability
No full textTurning difficulty is a sign of balance instability and may be indicative of elevated fall risk. Features extracted from the 90° turn suggest that this turn type is the most unstable type of turn in older adults with compromised balance control. Since the 90° turn is also the most common type of turn executed during activities of daily living, we recommend targeting movement strategies specific to 90° turning during therapeutic intervention. Specific neuro-rehabilitation strategies to improve/optimize turning ability in individuals with compromised stability may significantly contribute to fall-risk reduction. The adoption of quantitative tools for the assessment and monitoring of turning quality is advisable
Position paper: Extending Credibility Assessment of In Silico Medicine Predictors to Machine Learning Predictors
No full textThere are several situations where it would be convenient if a quantity of interest essential to support a medical or regulatory decision could be predicted as a function of other measurable quantities rather than measured experimentally. To do so, we need to ensure that in all practical cases, the predicted value does not differ from what we would measure experimentally by more than an acceptable threshold, defined by the context in which that quantity of interest is used in the decision-making process. This is called Credibility Assessment. Initial work, which guided the elaboration of the first technical standard on the topic (ASME VV-40:2018), focused on predictive models built from available mechanistic knowledge of the phenomenon of interest. For this class of predictive models, sometimes called biophysical models, a credibility assessment practice based on the so-called verification, Validation, Uncertainty, Quantification and Applicability (VVUQA) analysis is accepted. Through theoretical considerations, this position paper aims to summarise a complex debate on whether such an approach can be extended to predictive models built without any mechanistic knowledge (machine learning (ML) predictors). We conclude that the VVUQA can be extended to ML-based predictors; however, since there is no certainty that the features used to predict the quantity of interest are necessary and sufficient, according to the VVUQA framework, such credibility assessment is limited to the test sets used for the validation studies. This calls for a Total Product Life Cycle approach, where periodic retesting of ML-based predictors is part of post-marketing surveillance to ensure that no “unknown bias” may play a role
Real-time use of audio-biofeedback can improve postural sway in patients with degenerative ataxia
Full text linkAbstract
Objective
Cerebellar ataxia essentially includes deficient postural control. It remains unclear whether augmented sensory information might help cerebellar patients, as the cerebellum underlies processing of various sensory modalities for postural control. Here, we hypothesized that patients with cerebellar degeneration can still exploit audio‐biofeedback (ABF) of trunk acceleration as a real‐time assistive signal to compensate for deficient postural control.
Methods
Effects on postural sway during stance were assessed in an ABF intervention group versus a no‐ABF disease control group (23 vs. 17 cerebellar patients) in a clinico‐experimental study. A single‐session ABF paradigm of standing plus short exergaming under ABF was applied. Postural sway with eyes open and eyes closed was quantified prior to ABF, under ABF, and post ABF.
Results
Postural sway in the eyes closed condition was significantly reduced under ABF. Both benefit of ABF and benefit of vision correlated with the extent of postural sway at baseline, and both types of sensory benefits correlated with each other. Patients with strongest postural sway exhibited reduced postural sway also with eyes open, thus benefitting from both vision and ABF. No changes were observed in the no‐ABF control group.
Interpretation
Our findings provide proof‐of‐principle evidence that subjects with cerebellar degeneration are still able to integrate additional sensory modalities to compensate for deficient postural control: They can use auditory cues functionally similar to vision in the absence of vision, and additive to vision in the presence of vision (in case of pronounced postural sway). These findings might inform future assistive strategies for cerebellar ataxia
Position paper: Extending Credibility Assessment of In Silico Medicine Predictors to Machine Learning Predictors
Full text linkThere are several situations where it would be convenient if a quantity of interest essential to support a medical or regulatory decision could be predicted as a function of other measurable quantities rather than measured experimentally. To do so, we need to ensure that in all practical cases, the predicted value does not differ from what we would measure experimentally by more than an acceptable threshold, defined by the context in which that quantity of interest is used in the decision-making process. This is called Credibility Assessment. Initial work, which guided the elaboration of the first technical standard on the topic (ASME VV-40:2018), focused on predictive models built from available mechanistic knowledge of the phenomenon of interest. For this class of predictive models, sometimes called biophysical models, a credibility assessment practice based on the so-called verification, Validation, Uncertainty, Quantification and Applicability (VVUQA) analysis is accepted. Through theoretical considerations, this position paper aims to summarise a complex debate on whether such an approach can be extended to predictive models built without any mechanistic knowledge (machine learning (ML) predictors). We conclude that the VVUQA can be extended to ML-based predictors; however, since there is no certainty that the features used to predict the quantity of interest are necessary and sufficient, according to the VVUQA framework, such credibility assessment is limited to the test sets used for the validation studies. This calls for a Total Product Life Cycle approach, where periodic retesting of ML-based predictors is part of post-marketing surveillance to ensure that no "unknown bias"may play a role
- …
