Feasibility of snapshot testing using wearable sensors to detect cardiorespiratory illness (COVID infection in India) DOI Creative Commons
Olivia K. Botonis,

Jonathan Mendley,

Shreya Aalla

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Oct. 19, 2024

The COVID-19 pandemic has challenged the current paradigm of clinical and community-based disease detection. We present a multimodal wearable sensor system paired with two-minute, movement-based activity sequence that successfully captures snapshot physiological data (including cardiac, respiratory, temperature, percent oxygen saturation). conducted large, multi-site trial this technology across India from June 2021 to April 2022 amidst (Clinical registry name: International Validation Wearable Sensor Monitor Like Signs Symptoms; NCT05334680; initial release: 04/15/2022). An Extreme Gradient Boosting algorithm was trained discriminate between infected individuals (n = 295) negative healthy controls 172) achieved an F1-Score 0.80 (95% CI [0.79, 0.81]). SHAP values were mapped visualize feature importance directionality, yielding engineered features core cough, lung sounds as highly important. results demonstrated potential for data-driven remote preliminary screening, highlighting fundamental pivot continuous monitoring cardiorespiratory illnesses.

Language: Английский

Survey and perspective on verification, validation, and uncertainty quantification of digital twins for precision medicine DOI Creative Commons
Kaan Sel, Andrea Hawkins‐Daarud,

Anirban Chaudhuri

et al.

npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)

Published: Jan. 17, 2025

Digital twins in precision medicine provide tailored health recommendations by simulating patient-specific trajectories and interventions. We examine the critical role of Verification, Validation, Uncertainty Quantification (VVUQ) for digital ensuring safety efficacy, with examples cardiology oncology. highlight challenges opportunities developing personalized trial methodologies, validation metrics, standardizing VVUQ processes. frameworks are essential integrating into clinical practice.

Language: Английский

Citations

1
Perspective on Harnessing Large Language Models to Uncover Insights in Diabetes Wearable Data DOI Open Access
Arash Alavi,

Kexin Cha,

Delara P Esfarjani

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 31, 2024

Abstract Large Language Models (LLMs) have gained significant attention and are increasingly used by researchers. Concurrently, publicly accessible datasets containing individual-level health information becoming more available. Some of these datasets, such as the recently released Artificial Intelligence Ready Equitable Atlas for Diabetes Insights (AI-READI) dataset, include data from digital wearable technologies. The application LLMs to gain insights about sensor specific diabetes is underexplored. This study presents a comprehensive evaluation multiple LLMs, including GPT-3.5, GPT-4, GPT-4o, Gemini, Gemini 1.5 Pro, Claude 3 Sonnet, on various research tasks using diverse prompting methods evaluate their performance new into glucose dysregulation. Notably, GPT-4o showed promising across with chain-of-thought prompt design (aggregate score 95.5%). Moreover, this model, we identified heightened sensitivity stress among diabetic participants during level fluctuations, which underscores complex interplay between metabolic psychological factors. These results demonstrate that can enhance pace discovery also enable automated interpretation users devices, both team individual wearing device. Meanwhile, emphasize critical limitations, privacy ethical risks dataset biases, must be resolved real-world in settings. highlights potential challenges integrating and, broadly, wearables, paving way future healthcare advancements, particularly disadvantaged communities.

Language: Английский

Citations

0
Digital health innovation and artificial intelligence in cardiovascular care: a case-based review DOI Creative Commons
Jelani Grant, Aamir Javaid, Richard Carrick

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 1(1)

Published: Oct. 17, 2024

Abstract This narrative review aims to equip clinicians with an understanding of how digital health innovations and artificial intelligence can be applied clinical care pathways for cardiovascular prevention. We describe a case that highlights augmentative AI the incidental detection coronary artery calcium, mobile application improve patient adherence/engagement, large language models enhance longitudinal communication care, limitations strategies successful adoption these technologies.

Language: Английский

Citations

0
Feasibility of snapshot testing using wearable sensors to detect cardiorespiratory illness (COVID infection in India) DOI Creative Commons
Olivia K. Botonis,

Jonathan Mendley,

Shreya Aalla

et al.

npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)

Published: Oct. 19, 2024

The COVID-19 pandemic has challenged the current paradigm of clinical and community-based disease detection. We present a multimodal wearable sensor system paired with two-minute, movement-based activity sequence that successfully captures snapshot physiological data (including cardiac, respiratory, temperature, percent oxygen saturation). conducted large, multi-site trial this technology across India from June 2021 to April 2022 amidst (Clinical registry name: International Validation Wearable Sensor Monitor Like Signs Symptoms; NCT05334680; initial release: 04/15/2022). An Extreme Gradient Boosting algorithm was trained discriminate between infected individuals (n = 295) negative healthy controls 172) achieved an F1-Score 0.80 (95% CI [0.79, 0.81]). SHAP values were mapped visualize feature importance directionality, yielding engineered features core cough, lung sounds as highly important. results demonstrated potential for data-driven remote preliminary screening, highlighting fundamental pivot continuous monitoring cardiorespiratory illnesses.

Language: Английский

Citations

0