Metabolic health tracking using Ultrahuman M1 continuous glucose monitoring platform in non- and pre-diabetic Indians: a multi-armed observational study.

Continuous glucose monitoring (CGM) device adoption in non- and pre-diabetics for preventive healthcare has uncovered a paucity of benchmarking data on glycemic control and insulin resistance for the high-risk Indian/South Asian demographic. Furthermore, the correlational efficacy between digital applications-derived health scores and glycemic indices lacks clear supportive evidence. In this study, we acquired glycemic variability (GV) using the Ultrahuman (UH) M1 CGM, and activity metrics via the Fitbit wearable for Indians/South Asians with normal glucose control (non-diabetics) and those with pre-diabetes (N = 53 non-diabetics, 52 pre-diabetics) for 14 days. We examined whether CGM metrics could differentiate between the two groups, assessed the relationship of the UH metabolic score (MetSc) with clinical biomarkers of dysglycemia (OGTT, HbA1c) and insulin resistance (HOMA-IR); and tested which GV metrics maximally correlated with inflammation (Hs-CRP), stress (cortisol), sleep, step count and heart rate. We found significant inter-group differences for mean glucose levels, restricted time in range (70-110 mg/dL), and GV-by-SD, all of which improved across days. Inflammation was strongly linked with specific GV metrics in pre-diabetics, while sleep and activity correlated modestly in non-diabetics. Finally, MetSc displayed strong inverse relationships with insulin resistance and dysglycemia markers. These findings present initial guidance GV data of non- and pre-diabetic Indians and indicate that digitally-derived metabolic scores can positively influence glucose management.

Detection of alcoholism using EEG signals and a CNN-LSTM-ATTN network.

Alcoholism is a serious disorder that poses a problem for modern society, but the detection of alcoholism has no widely accepted standard tests or procedures. If alcoholism goes undetected at its early stages, it can create havoc in the patient's life. An electroencephalography (EEG) is a method used to measure the brain's electrical activity and can detect alcoholism. EEG signals are complex and multi-channel and thus can be difficult to interpret manually. Several previous works have tried to classify a subject as alcoholic or control (non-alcoholic) based on EEG signals. Such works have mainly used machine learning or statistical techniques along with handcrafted features such as entropy, correlation dimension, Hurst exponent. With the growth in computational power and data volume worldwide, deep learning models have recently been gaining momentum in various fields. However, only a few studies are available on the application of deep learning models for the classification of alcoholism using EEG signals. This paper proposes a deep learning architecture that uses a combination of fast Fourier transform (FFT), a convolution neural network (CNN), long short-term memory (LSTM), and a recently proposed attention mechanism for extracting Spatio-temporal features from multi-channel EEG signals. The proposed architecture can classify a subject as an alcoholic or control with a high degree of accuracy by analyzing EEG signals of that subject and can be used for automating alcoholism detection. The analytical results using the proposed architecture show a 98.83% accuracy, making it better than most state-of-the-art algorithms.