Improving the Accuracy of Continuous Blood Glucose Measurement Using Personalized Calibration and Machine Learning.

Despite tremendous developments in continuous blood glucose measurement (CBGM) sensors, they are still not accurate for all patients with diabetes. As glucose concentration in the blood is <1% of the total blood volume, it is challenging to accurately measure glucose levels in the interstitial fluid using CBGM sensors due to within-patient and between-patient variations. To address this issue, we developed a novel data-driven approach to accurately predict CBGM values using personalized calibration and machine learning. First, we scientifically divided measured blood glucose into smaller groups, namely, hypoglycemia (<80 mg/dL), nondiabetic (81-115 mg/dL), prediabetes (116-150 mg/dL), diabetes (151-181 mg/dL), severe diabetes (181-250 mg/dL), and critical diabetes (>250 mg/dL). Second, we separately trained each group using different machine learning models based on patients' personalized parameters, such as physical activity, posture, heart rate, breath rate, skin temperature, and food intake. Lastly, we used multilayer perceptron (MLP) for the D1NAMO dataset (training to test ratio: 70:30) and grid search for hyperparameter optimization to predict accurate blood glucose concentrations. We successfully applied our proposed approach in nine patients with type 1 diabetes and observed that the mean absolute relative difference (MARD) decreased from 17.8% to 8.3%.

Effect of Perceptual Training with Sound-Guided and Kinesthetic Feedback on Human 3D Sound Localization Capabilities.

In this paper, we experimentally investigate how the 3D sound localization capabilities of the blind can improve through perceptual training. To this end, we develop a novel perceptual training method with sound-guided feedback and kinesthetic assistance to evaluate its effectiveness compared to conventional training methods. In perceptual training, we exclude visual perception by blindfolding the subjects to apply the proposed method to the visually impaired. Subjects used a specially designed pointing stick to generate a sound at the tip, indicating localization error and tip position. The proposed perceptual training aims to evaluate the training effect on 3D sound localization, including variations in azimuth, elevation, and distance. The six days of training based on six subjects resulted in the following outcomes: (1) In general, accuracy in full 3D sound localization can be improved based on training. (2) Training based on relative error feedback is more effective than absolute error feedback. (3) Subjects tend to underestimate distance when the sound source is near, less than 1000 mm, or larger than 15° to the left, and overestimate the elevation when the sound source is near or in the center, and within ±15° in azimuth estimations.

Effectiveness of Faradic and Russian currents on plantar flexor muscle spasticity, ankle motor recovery, and functional gait in stroke patients.

BACKGROUND AND PURPOSE: Spasticity is a major disabling symptom in patients post stroke. Though studies have demonstrated that electrical stimulation (ES) can reduce spasticity and improve passive ankle range of motion (ROM), not many studies have evaluated the effectiveness of ES on active ankle ROM. The purpose of this study was to determine the effectiveness of Faradic and Russian currents in the reduction of ankle plantar-flexor spasticity and improving motor recovery in patients post stroke. METHODS: Eighty-three patients (29 females and 54 males; mean age of 57.12 years) were randomly assigned to Group 1 (task-oriented exercises), Group 2 (Faradic current for 10 min and task-oriented exercises), and Group 3 (Russian current for 10 min and task-oriented exercises) for a period of 5 sessions per week for 6 weeks. All patients were assessed for soleus and gastrocnemius muscles spasticity measured by modified modified Ashworth scale; active and passive range ROM measured by goniometer; and functional ambulation measured by modified Emory Functional Ambulation Profile at the time of recruitment to study and after 6 weeks. RESULTS: Both the types of stimulation and exercises were not associated with improvements in modified Emory Functional Ambulation Profile (p > 0.05). The results showed that all the groups are effective in improving passive ankle ROM (p < 0.05) and reducing soleus and gastrocnemius muscles spasticity (p < 0.05). Though all the groups were effective in improving active ankle ROM, no group was found to be superior to another after treatment CONCLUSION: Adding ES to exercises are associated with low to medium effect sizes (<0.5) in reducing spasticity and improving ankle ROM.