Improved screening of fall risk using free-living based accelerometer data

Ecological Fall Prediction Sensitivity, Specificity, and Accuracy in Patients with Mild Cognitive Impairment at a High Risk of Falls

While falls among patients with mild cognitive impairment (MCI) have been closely associated with an increased postural sway during ecological activities of daily living, there is a dearth of postural sway detection (PSD) research in ecological environments. The present study aimed to investigate the fall sensitivity, specificity, and accuracy of our PSD system. Forty healthy young and older adults with MCI at a high risk of falls underwent the sensitivity, specificity, and accuracy tests for PSD by simultaneously recording the Berg Balance Scale and Timed Up and Go in ecological environments, and the data were analyzed using the receiver operating characteristic curve and area under the curve. The fall prediction sensitivity ranged from 0.82 to 0.99, specificity ranged from 0.69 to 0.90, and accuracy ranged from 0.53 to 0.81. The PSD system's fall prediction sensitivity, specificity, and accuracy data suggest a reasonable discriminative capacity for distinguishing between fallers and non-fallers as well as predicting falls in older adults with MCI in ecological testing environments.

Detection of Fall Risk in Multiple Sclerosis by Gait Analysis-An Innovative Approach Using Feature Selection Ensemble and Machine Learning Algorithms

One of the common causes of falls in people with Multiple Sclerosis (pwMS) is walking impairment. Therefore, assessment of gait is of importance in MS. Gait analysis and fall detection can take place in the clinical context using a wide variety of available methods. However, combining these methods while using machine learning algorithms for detecting falls has not been performed. Our objective was to determine the most relevant method for determining fall risk by analyzing eleven different gait data sets with machine learning algorithms. In addition, we examined the most important features of fall detection. A new feature selection ensemble (FS-Ensemble) and four classification models (Gaussian Naive Bayes, Decision Tree, k-Nearest Neighbor, Support Vector Machine) were used. The FS-Ensemble consisted of four filter methods: Chi-square test, information gain, Minimum Redundancy Maximum Relevance and RelieF. Various thresholds (50%, 25% and 10%) and combination methods (Union, Union 2, Union 3 and Intersection) were examined. Patient-reported outcomes using specialized walking questionnaires such as the 12-item Multiple Sclerosis Walking Scale (MSWS-12) and the Early Mobility Impairment Questionnaire (EMIQ) achieved the best performances with an F1 score of 0.54 for detecting falls. A combination of selected features of MSWS-12 and EMIQ, including the estimation of walking, running and stair climbing ability, the subjective effort as well as necessary concentration and walking fluency during walking, the frequency of stumbling and the indication of avoidance of social activity achieved the best recall of 75%. The Gaussian Naive Bayes was the best classification model for detecting falls with almost all data sets. FS-Ensemble improved the classification models and is an appropriate technique for reducing data sets with a large number of features. Future research on other risk factors, such as fear of falling, could provide further insights.