Background and Objectives: Bone fracture risk assessment for osteopenia and osteoporotic patients is essential for the adoption of early countermeasures and avoiding discomfort and hospitalization. Currently employed ...
详细信息
Background and Objectives: Bone fracture risk assessment for osteopenia and osteoporotic patients is essential for the adoption of early countermeasures and avoiding discomfort and hospitalization. Currently employed methodologies, such as FRAX®, provides a risk assessment over a five to ten years period without showing the main variables influencing the prediction nor how they can be targeted in the short term. Thus, a lesser black-box approach where the fracture risk can be assessed in real-time from a commonly employed analysis, id est the dual-energy X-ray absorptiometry (2D-DXA), would be of help to clinicians and patients alike. Accordingly, this study presents three real-time machine learning (ML) assessment models, with distinct complexity, architectures, and performances, capable of predicting a binary fracture risk based on a femur head-hip joint 2D-DXA scan. Methods: A ~10,000 adult Korean gathered between 2017 and 2021 and composed of ~90% female and ~10% male ranging from 50 to 99 years of age was considered. 10% of the data is relevant to subjects who experienced skeletal fractures, among which 245 cases are femur fractures. The 2D-DXA analyses of the femur head-hip joint region carried out on patients allowed collecting 23 parameters, including the patient’s age, BMI, and gender, associated with one binary variable, defined in terms of non-fracture (NFX) or fracture (FX), to be employed as the training dataset for the three ML models employed and optimized in this research. The 2D-DXA results’ database (DB) was employed to train three ML classifiers with a binary (NFX/FX) output layer, namely the Extreme Gradient Boosting (XGB), the K-Nearest Neighbor (KNN), and Deep Neural Network (DNN). To avoid overfitting due to the higher number of NFX data with respect to FX one, two features augmentation techniques based on the Synthetic Minority Over-sampling Technique (SMOTE) and Oversample using Adaptive Synthetic (ADASYN) oversamplers were employed. For all
Attention deficit hyperactivity disorder (ADHD) is one of the most common psychological pathologies worldwide. Despite mostly occurring in childhood, it could lead to difficulties in adults, mainly on social relations...
详细信息
In this study, a rapid diagnosis platform was developed for the detection of Escherichia coli O157:H7. An electrical double layer (EDL)-gated field-effect transistor-based biosensor (BioFET) as a point-of-care testing...
详细信息
The purpose of this study was to develop a computerized classification method for molecular subtypes in low-grade gliomas (LGGs) with multi-scale 3D-attention branch networks analyzing multi-sequence brain MRI images....
详细信息
In this study, we investigated the effect of the presence or absence of fingernails on precision grasping using artificial anthropomimetic fingers. We hypothesized that fingernails improve precision grasping performan...
详细信息
Individuals who suffer in speaking and hearing are known as people with hearing and speech impairment. Sign language is used by them to communicate. Nevertheless, the general public does not fully comprehend sign lang...
详细信息
ISBN:
(纸本)9781665476515
Individuals who suffer in speaking and hearing are known as people with hearing and speech impairment. Sign language is used by them to communicate. Nevertheless, the general public does not fully comprehend sign language. In this study, assistive technology for the Indonesian Sign Language Interpretation System was developed to convert the alphabet sign into text. The system incorporates the usage of flex sensors, pressure sensor, and MPU6050 module. After the development, the evaluation for this interpreter is carried out. The classifier was able to identify 24 out of 26 alphabets with detection error frequently occurring in the letters N and R with an accuracy of 94% in the second experiment. By using a specific classification and including more test data, this study expected outcome can be heightened. The results show that the classification method, along with the tool, may be used effectively as a speech and hearing aid.
Although the average life expectancy in Japan has been increasing in recent years, the problem of the large gap between healthy and average life expectancy still needs to be solved. Among the factors that lead to the ...
A volatile organic compound (VOCs) classification system is developed for non-invasive biomarker screening tests. The developed system utilizes a preconcentrator, which contains an absorbent material for trapping VOCs...
详细信息
ISBN:
(数字)9798350381559
ISBN:
(纸本)9798350381566
A volatile organic compound (VOCs) classification system is developed for non-invasive biomarker screening tests. The developed system utilizes a preconcentrator, which contains an absorbent material for trapping VOCs at low temperatures and thermally desorbing at specific elevated temperatures. This system is especially useful for detection of odor mixture at low concentration and target VOCs biomarkers in the odor sample can also be measured with enhanced selectivity. All sensing processes, including a PID temperature controller for heating preconcentrator, odor sensor interface, and solenoid valve control, are performed using only a single embedded microcontroller. An odor mixture with low concentration is measured and classified in order to investigate the developed system. The result of the experiment and the principal component analysis (PCA) shows that the system with the preconcentrator can measure the VOCs mixture of odor sample in terms of sensitivity and selectivity. This system prototype is useful for screening tests of exhaled breath biomarker.
Designing biomimetic tissue models and developing scaffolds under cell-compatible protocols are a challenge in the field of tissue engineering. Cell encapsulation technique was selected with hydrogel fabrication due t...
详细信息
Current measurement techniques in the medical field, such as electrocardiography (ECG) and pulse oximetry, are critical for monitoring the cardiovascular health of newborns [1]. Although there are devices on the marke...
详细信息
ISBN:
(数字)9798350388572
ISBN:
(纸本)9798350388589
Current measurement techniques in the medical field, such as electrocardiography (ECG) and pulse oximetry, are critical for monitoring the cardiovascular health of newborns [1]. Although there are devices on the market capable of measuring these signals, they are often not designed for use with newborns. This study conducted a preliminary usability test of four cardiovascular monitors for use with a newborn model. The findings indicated that users prefer a simple, wireless device that can be securely attached to a child to minimize movement. Additionally, they value a guided process and straightforward, user-friendly software. Understanding user preferences can facilitate developing an affordable, at-home monitoring device tailored for newborns which in turn may enhance early detection and management of congenital heart diseases (CHDs).
暂无评论