Vital sign monitoring using wearable devices in a Vietnamese intensive care unit

Van, Hoang Minh Tu; Hảo, Nguyễn Văn; Quoc, Khanh Phan Nguyen; Hai, Ho Bich; Le, Dan; Yen, Lam Minh; Nhat, Phung Tran Huy; Duong, Ha Thi Hai; Thuy, Duong Bich; Zhu, Tingting; Greeff, Heloise; Clifton, David A.; Thwaites, C. Louise

doi:10.1136/bmjinnov-2021-000707

Cited by 15 publications

(27 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors demonstrated that vital sign measurements from a wireless wearable device are reliable and accurate compared to those obtained by an experienced nurse. Our previous work has also shown that the wearable devices are reliable and robust, and can be used as a surrogate for bedside monitors [ 27 ]. However, no previous attempt has been made to design automatic prediction algorithms based on wearable data in LMICs.…”

Section: Related Workmentioning

confidence: 99%

Sepsis Mortality Prediction Using Wearable Monitoring in Low–Middle Income Countries

Ghiasi

Zhu

Lü

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Sepsis is associated with high mortality—particularly in low–middle income countries (LMICs). Critical care management of sepsis is challenging in LMICs due to the lack of care providers and the high cost of bedside monitors. Recent advances in wearable sensor technology and machine learning (ML) models in healthcare promise to deliver new ways of digital monitoring integrated with automated decision systems to reduce the mortality risk in sepsis. In this study, firstly, we aim to assess the feasibility of using wearable sensors instead of traditional bedside monitors in the sepsis care management of hospital admitted patients, and secondly, to introduce automated prediction models for the mortality prediction of sepsis patients. To this end, we continuously monitored 50 sepsis patients for nearly 24 h after their admission to the Hospital for Tropical Diseases in Vietnam. We then compared the performance and interepretability of state-of-the-art ML models for the task of mortality prediction of sepsis using the heart rate variability (HRV) signal from wearable sensors and vital signs from bedside monitors. Our results show that all ML models trained on wearable data outperformed ML models trained on data gathered from the bedside monitors for the task of mortality prediction with the highest performance (area under the precision recall curve = 0.83) achieved using time-varying features of HRV and recurrent neural networks. Our results demonstrate that the integration of automated ML prediction models with wearable technology is well suited for helping clinicians who manage sepsis patients in LMICs to reduce the mortality risk of sepsis.

show abstract

Section: Related Workmentioning

confidence: 99%

Sepsis Mortality Prediction Using Wearable Monitoring in Low–Middle Income Countries

Ghiasi

Zhu

Lü

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In most low-resource settings this means admission to high-dependency or intensive care units (ICUs) as these are the only places with sufficient staff and equipment to do this. This large burden of additional cases results in suboptimal use of already scare resources and likely worsens outcomes for those who do require ICU level care [9] [10] [11]. Additionally in countries like Vietnam where many patients pay for care outof-pocket, the extra costs of ICU care, compared to normal ward care, are significant.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally in countries like Vietnam where many patients pay for care outof-pocket, the extra costs of ICU care, compared to normal ward care, are significant. There are the information about direct medical costs of tetanus, dengue, and sepsis patients in an ICU in Vietnam from previous research [9] [10] [11]. If patients do not require mechanical ventilation, the median total ICU cost per patient varied between US$64.…”

Section: Introductionmentioning

confidence: 99%

“…In high-income countries, complex continuous monitoring systems and high staff-to-patient ratios facilitate improved the tetanus outcomes [11]. However, in LMICs, inexperienced staff, lack of equipment with limited time are commonly cited impediments to providing high quality care for patients with tetanus.…”

Section: Introductionmentioning

confidence: 99%

“…The wearable sensors are small, lightweight and wireless. They can continuously monitor vital signs in real-time, in order to help in the early identification of patient deterioration [12] [11]. One challenge of utilizing low-cost wearable sensors is that the recorded continuous physiological data can be less precise, due to the large amount of noise (caused by muscle movement and the monitors electrical source) and missing data [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Classification of Tetanus Severity for Patients in Low-Middle Income Countries Wearing ECG Sensors by Using a CNN-Transformer Network

Lü

Wang

Hagenah

et al. 2023

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Tetanus is a life-threatening infectious disease, which is still common in low-and middle-income countries, including in Vietnam. This disease is characterized by muscle spasm and in severe cases is complicated by autonomic dysfunction. Ideally continuous vital sign monitoring using bedside monitors allows the prompt detection of the onset of autonomic nervous system dysfunction or avoiding rapid deterioration. Detection can be improved using heart rate variability analysis from ECG signals. Recently, characteristic ECG and heart rate variability features have been shown to be of value in classifying tetanus severity. However, conventional manual analysis of ECG is time-consuming. The traditional convolutional neural network (CNN) has limitations in extracting the global context information, due to its fixed-sized kernel filters. In this work, we propose a novel hybrid CNN-Transformer model to automatically classify tetanus severity using tetanus monitoring from low-cost wearable sensors. This model can capture the local features from the CNN and the global features from the Transformer. The time series imaging -spectrogram -is transformed from one-dimensional ECG signal and input to the proposed model. The CNN-Transformer model outperforms state-of-the-art methods in tetanus classification, achieves results with a F1 score of 0.82 ± 0.03, precision of 0.94 ± 0.03, recall of 0.73 ± 0.07, specificity of 0.97 ± 0.02, accuracy of 0.88 ± 0.01 and AUC of 0.85 ± 0.03. In addition, we found that Random Forest with enough manually selected features can be comparable with the proposed CNN-Transformer model.

show abstract

Introduction to cardiovascular signals and automated systems

Pachori,

Dash,

Tripathy

et al. 2024

Signal Processing Driven Machine Learning Techniques for Cardiovascular Data Processing

View full text Add to dashboard Cite

Vital sign monitoring using wearable devices in a Vietnamese intensive care unit

Cited by 15 publications

References 30 publications

Sepsis Mortality Prediction Using Wearable Monitoring in Low–Middle Income Countries

Sepsis Mortality Prediction Using Wearable Monitoring in Low–Middle Income Countries

Improving Classification of Tetanus Severity for Patients in Low-Middle Income Countries Wearing ECG Sensors by Using a CNN-Transformer Network

Introduction to cardiovascular signals and automated systems

Contact Info

Product

Resources

About