Challenges and recommendations for wearable devices in digital health: Data quality, interoperability, health equity, fairness

Canali, Stefano; Schiaffonati, Viola; Aliverti, Andréa

doi:10.1371/journal.pdig.0000104

Cited by 87 publications

(29 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, some challenges exist with other types of sensors used in remote patient monitoring systems. For instance, wearable devices, which often use a variety of sensors, have been associated with issues such as data quality, interoperability, health equity, and fairness [ 23 ]. Additionally, the reliability of data from some remote patient monitoring tools has been questioned, with error margins up to 25 percent reported for some popular fitness wearables [ 24 ].…”

Section: Discussionmentioning

confidence: 99%

Non-Contact Thermal and Acoustic Sensors with Embedded Artificial Intelligence for Point-of-Care Diagnostics

Rodríguez-Cobo,

Reyes-Gonzalez,

Algorri

et al. 2023

Sensors

View full text Add to dashboard Cite

This work involves exploring non-invasive sensor technologies for data collection and preprocessing, specifically focusing on novel thermal calibration methods and assessing low-cost infrared radiation sensors for facial temperature analysis. Additionally, it investigates innovative approaches to analyzing acoustic signals for quantifying coughing episodes. The research integrates diverse data capture technologies to analyze them collectively, considering their temporal evolution and physical attributes, aiming to extract statistically significant relationships among various variables for valuable insights. The study delineates two distinct aspects: cough detection employing a microphone and a neural network, and thermal sensors employing a calibration curve to refine their output values, reducing errors within a specified temperature range. Regarding control units, the initial implementation with an ESP32 transitioned to a Raspberry Pi model 3B+ due to neural network integration issues. A comprehensive testing is conducted for both fever and cough detection, ensuring robustness and accuracy in each scenario. The subsequent work involves practical experimentation and interoperability tests, validating the proof of concept for each system component. Furthermore, this work assesses the technical specifications of the prototype developed in the preceding tasks. Real-time testing is performed for each symptom to evaluate the system’s effectiveness. This research contributes to the advancement of non-invasive sensor technologies, with implications for healthcare applications such as remote health monitoring and early disease detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Non-Contact Thermal and Acoustic Sensors with Embedded Artificial Intelligence for Point-of-Care Diagnostics

Rodríguez-Cobo,

Reyes-Gonzalez,

Algorri

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Previous studies have shown the ability of DL models to detect hyperkalemia, but they also found that as the number of input leads decreased, the overall performance deteriorated 14 . Furthermore, the efficacy of algorithms specifically designed for wearable devices like the Apple Watch, where the signal-to-noise ratio is typically lower, had not been extensively tested 30 . Nevertheless, we adopted several approaches to enhance single-lead Kardio-Net performance as cited in previous literature, including a moving window average prediction from 5-s ECG 31 , and noise detection and removal 32 .…”

Section: Deep Learning Models Have Previously Shown Proficiency In De...mentioning

confidence: 99%

Serum Potassium Monitoring using AI-enabled Smart Watch Electrocardiograms

Chiu,

Wu,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background Hyperkalemia poses a significant risk of sudden cardiac death, especially for those with end-stage renal diseases (ESRD). Smartwatches with ECG capabilities offer a promising solution for continuous, non-invasive monitoring using AI. Objectives To develop an AI-ECG algorithm to predict serum potassium level in ESRD patient with smartwatch generated ECG waveforms. Methods A cohort of 152,508 patients with 293,557 ECGs paired serum potassium levels obtained within one hour at Cedars Sinai Medical Center (CSMC) was used to train an AI-ECG model (Kardio-Net) to predict serum potassium level. The model was further fine-tuned on 4,337 ECGs from 1,463 patients with ESRD using inputs from 12-lead and single-lead ECGs. Kardio-Net was evaluated in held-out test cohorts from CSMC and Stanford Healthcare (SHC) as well as a prospective international cohort of 40 ESRD patients with smartwatch ECGs at Chang Gung Memorial Hospital (CGMH). Results The Kardio-Net, when applied to 12-lead ECGs, identified severe hyperkalemia with an AUC of 0.852 and a mean absolute error (MAE) of 0.527 mEq/L. In external validation at SHC, the model achieved an AUC of 0.849 and an MAE of 0.599 mEq/L. For single-lead ECGs, Kardio-Net detected hyperkalemia with an AUC of 0.876 and had an MAE of 0.575 mEq/L in the CSMC test cohort. Using prospectively obtained smartwatch data, the AUC was 0.831, with an MAE of 0.580 mEq/L. Conclusions We validate a deep learning model to predict serum potassium levels from both 12-lead ECGs and single-lead smartwatch data, demonstrating its utility for remote monitoring of hyperkalemia.

show abstract

“…Data bias and discrimination can occur if datasets are not representative of diverse populations or if algorithms are trained on biased data, leading to disparities in healthcare outcomes and exacerbating health inequities. To address these concerns, healthcare organizations must strive to collect inclusive and representative data, promote diversity in research and development efforts, and mitigate bias in data analysis and decision-making processes (Canali, et al, 2022;Rajkomar, et al ., 2018). In conclusion, ethical considerations are paramount in healthcare data solutions, encompassing privacy concerns, data security, and the fair and ethical use of data.…”

Section: Regulatory Framework Shaping Healthcare Data Solutionsmentioning

confidence: 99%

Advancing Healthcare Data Solutions: Comparative Analysis of Business and Research Models in the U.S

Arenike Patricia Adekugbe,

Chidera Victoria Ibeh

2024

imsrj

View full text Add to dashboard Cite

In the dynamic landscape of healthcare, data-driven solutions play a pivotal role in enhancing patient outcomes, optimizing processes, and steering strategic decision-making. This review presents a comprehensive comparative analysis of the business and research models underpinning healthcare data solutions in the United States. By examining the distinctive characteristics, challenges, and advancements within these models, this study aims to elucidate critical insights for stakeholders navigating the complex intersection of healthcare and data analytics. The American healthcare ecosystem is marked by a diverse array of entities engaged in harnessing data for various purposes, ranging from improving patient care to driving operational efficiencies. This analysis delves into the contrasting approaches adopted by businesses and research institutions in leveraging healthcare data. Businesses predominantly focus on profit-driven initiatives, emphasizing efficiency, scalability, and commercial viability. In contrast, research models prioritize scientific rigor, innovation, and academic collaboration, often with a primary focus on advancing medical knowledge. Key components of the comparative analysis include examining the regulatory frameworks governing healthcare data, the utilization of cutting-edge technologies such as artificial intelligence and machine learning, and the ethical considerations surrounding data privacy and security. Furthermore, this study investigates the impact of socioeconomic factors, such as disparities in access to healthcare and disparities in data availability, on the development and implementation of data solutions. The comparative analysis also highlights notable case studies and best practices from both business and research sectors, illustrating successful approaches to overcoming common challenges and driving innovation in healthcare data solutions. Additionally, emerging trends, such as the integration of wearables and Internet of Things (IoT) devices, are explored for their potential to revolutionize data collection and analysis in healthcare settings. Ultimately, this review underscores the imperative for collaborative efforts between business entities and research institutions to harness the full potential of healthcare data solutions, fostering advancements that benefit patients, providers, and society at large. Keywords: Healthcare Data Solutions, Comparative Analysis, Business Models, Research Models, United States, Innovation.

show abstract

Challenges and recommendations for wearable devices in digital health: Data quality, interoperability, health equity, fairness

Cited by 87 publications

References 59 publications

Non-Contact Thermal and Acoustic Sensors with Embedded Artificial Intelligence for Point-of-Care Diagnostics

Non-Contact Thermal and Acoustic Sensors with Embedded Artificial Intelligence for Point-of-Care Diagnostics

Serum Potassium Monitoring using AI-enabled Smart Watch Electrocardiograms

Advancing Healthcare Data Solutions: Comparative Analysis of Business and Research Models in the U.S

Contact Info

Product

Resources

About