Developments in Wearable-Based Health Monitoring and AI-Driven Disease Detection

The field of health monitoring and disease detection is rapidly advancing, with a growing focus on wearable-based technologies and AI-driven approaches. Recent research has explored the use of smartwatches and other wearables to detect intoxication levels, antidepressant use, and other health metrics. Additionally, there has been significant progress in the development of AI models for disease detection, including epilepsy, Alzheimer's disease, and depression. These models often leverage multimodal data, such as EEG signals, speech, and text, to improve detection accuracy. Notable papers in this area include: Advancing Intoxication Detection, which introduced a smartwatch-based approach to detecting intoxication levels. Transformer Model Detects Antidepressant Use From a Single Night of Sleep, which presented a noninvasive biomarker for detecting antidepressant intake. DistilCLIP-EEG, which proposed a multimodal model for epilepsy detection that integrates EEG signals and text descriptions. TRI-DEP, which conducted a trimodal comparative study for depression detection using speech, text, and EEG.

Sources

Advancing Intoxication Detection: A Smartwatch-Based Approach

Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker

Event-Aware Prompt Learning for Dynamic Graphs

DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation

T3former: Temporal Graph Classification with Topological Machine Learning

A Robust Classification Method using Hybrid Word Embedding for Early Diagnosis of Alzheimer's Disease

TRI-DEP: A Trimodal Comparative Study for Depression Detection Using Speech, Text, and EEG

Built with on top of