Fall Detection System for the Elderly Based on the Classification of Shimmer Sensor Prototype Data / 대한의료정보학회지

OBJECTIVES: Falling in the elderly is considered a major cause of death. In recent years, ambient and wireless sensor platforms have been extensively used in developed countries for the detection of falls in the elderly. However, we believe extra efforts are required to address this issue in developing countries, such as Pakistan, where most deaths due to falls are not even reported. Considering this, in this paper, we propose a fall detection system prototype that s based on the classification on real time shimmer sensor data. METHODS: We first developed a data set, ‘SMotion’ of certain postures that could lead to falls in the elderly by using a body area network of Shimmer sensors and categorized the items in this data set into age and weight groups. We developed a feature selection and classification system using three classifiers, namely, support vector machine (SVM), K-nearest neighbor (KNN), and neural network (NN). Finally, a prototype was fabricated to generate alerts to caregivers, health experts, or emergency services in case of fall. RESULTS: To evaluate the proposed system, SVM, KNN, and NN were used. The results of this study identified KNN as the most accurate classifier with maximum accuracy of 96% for age groups and 93% for weight groups. CONCLUSIONS: In this paper, a classification-based fall detection system is proposed. For this purpose, the SMotion data set was developed and categorized into two groups (age and weight groups). The proposed fall detection system for the elderly is implemented through a body area sensor network using third-generation sensors. The evaluation results demonstrate the reasonable performance of the proposed fall detection prototype system in the tested scenarios.

Significance of sonographic characterization and fnac of small size thyroid nodules

The purpose of this study is to determine the accuracy of various ultrasound characteristics of small size thyroid nodules in the predication of malignancy and the usefulness of ultrasound guided FNAC of these nodules. Experimental / analytic study. This study was carried out at Radiology Department Services Hospital, Lahore from October 2011 to September 2012. This study was conducted on 70 patients, in whom 76 thyroid nodules 4mm to 10mm in size were biopsied. Diagnostic ultrasound was performed with high frequency linear probe for the evaluation of following ultrasound characteristics, internal structure, echogenicity, margins, posterior acoustic shadowing, height to width ratio, halo around the nodules, calcifications and vascular flow on Doppler scan. Each character was correlated with the results of FNAC to determine the accuracy of the feature in the prediction of malignancy. Out of 76 FNACs of 4mm to 10mm size thyroid nodules 8 [10.5%] biopsies did not yield significant cytological specimen. Another 8 [10.5%] specimen were classified as indeterminate so no further analysis was done. The rate of malignancy among nodules on final diagnosis was 20%. The most accurate sonographic features associated with malignancy were posterior acoustic shadowing [88.3%], taller than wider [83%], Halo around the nodule [80%] and calcification [70%]. Small size thyroid nodules are associated with significant risk of malignancy. Certain sonographic characteristics can be used to measure the risk of malignancy. FNAC of these nodules can be safely and accurately performed with high diagnostic rate