Smartphone-Based Bioelectric Coherence Index for Mental Health Diagnostics: A Digital Twin Study
Munro, G.
Show abstract
BackgroundMental health disorders affect over 1 billion people globally, with circadian rhythm disruption emerging as a key pathophysiological mechanism. Digital biomarkers offer potential for scalable assessment, but validation remains limited. ObjectiveTo develop and validate a Bioelectric Coherence Index (BCI) using smartphone sensors for circadian dysfunction assessment across 50 mental health conditions through digital twin simulation. MethodsWe developed a BCI using smartphone sensors (light exposure, sleep patterns, pupillometry) with the formula: BCI(t) = {middle dot}{Phi}(t) + {beta}{middle dot}{Delta}(t) - {gamma}{middle dot}{Psi}(t), integrating phase alignment, circadian amplitude, and temporal variability components. We simulated 1,000 virtual subjects (20 per condition) across 50 mental health conditions over 365 days, stratified by circadian impact tier. ResultsDigital twin validation achieved 71.2% diagnostic accuracy (95% CI: 68.8-73.6%) across all 50 conditions. Performance varied by circadian impact tier: Core Circadian conditions (87.3%), High Circadian (76.5%), Moderate Circadian (65.2%), and Lower Circadian (52.8%). Cross-validation demonstrated robust performance with minimal overfitting. External benchmarking against published chronotherapy literature showed strong correlations (r = 0.84, p < 0.001). ConclusionsThis digital twin validation provides preliminary computational evidence for smartphone-based circadian assessment utility across diverse mental health conditions. The tier-based performance hierarchy aligns with circadian biology principles. Clinical validation through prospective trials remains essential before clinical application.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Longitudinal Physiological Data from a Wearable Device Identifies SARS-CoV-2 Infection and Symptoms and Predicts COVID-19 Diagnosis 94%
- Circadian Rhythm Analysis Using Wearable Device Data: A Novel Penalized Machine Learning Approach 92%
- Uncovering social states in healthy and clinical populations using digital phenotyping and Hidden Markov Models 92%
Similar papers in this journal
- Quantifying Sleep-Wake Rhythms in the Hospital Environment with Digital Technologies 94%
- Passive Detection of COVID-19 with Wearable Sensors and Explainable Machine Learning Algorithms 94%
- The menstrual cycle through the lens of a wearable device: insights into physiology, sleep, and cycle variability 92%
Similar papers in this journal
- Assessing the Effects of Behavioral Circadian Rhythm Disruption in Shift-Working Police Academy Trainees 94%
- dlmoR: An open-source R package for the dim-light melatonin onset (DLMO) hockey-stick method 90%
- The combination of topological data analysis and mathematical modeling improves sleep stage prediction from consumer-grade wearables 89%
Similar papers in this journal
- Longitudinally Tracking Personal Physiomes for Precision Management of Childhood Epilepsy 92%
- Feasibility characteristics of wrist-worn fitness trackers in health status monitoring for post-COVID patients in remote and rural areas 91%
- Feasibility of Continuous Distal Body Temperature for Passive, Early Pregnancy Detection 91%
Similar papers in this journal
- Within-subjects ultra-short sleep-wake protocol for characterising circadian variations in retinal function 95%
- A clinical trial to evaluate the dayzz smartphone app on employee sleep, health, and productivity at a large US employer 93%
- Discrimination of sleep and wake periods from a hip-worn raw acceleration sensor using recurrent neural networks 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.