Vital Signs Prediction and Early Warning Score Calculation Based on Continuous Monitoring of Hospitalised Patients Using Wearable Technology

In this prospective, interventional, international study, we investigate continuous monitoring of hospitalised patients’ vital signs using wearable technology as a basis for real-time early warning scores (EWS) estimation and vital signs time-series prediction. The collected continuous monitored vital signs are heart rate, blood pressure, respiration rate, and oxygen saturation of a heterogeneous patient population hospitalised in cardiology, postsurgical, and dialysis wards. Two aspects are elaborated in this study. The first is the high-rate (every minute) estimation of the statistical values (e.g., minimum and mean) of the vital signs components of the EWS for one-minute segments in contrast with the conventional routine of 2 to 3 times per day. The second aspect explores the use of a hybrid machine learning algorithm of kNN-LS-SVM for predicting future values of monitored vital signs. It is demonstrated that a real-time implementation of EWS in clinical practice is possible. Furthermore, we showed a promising prediction performance of vital signs compared to the most recent state of the art of a boosted approach of LSTM. The reported mean absolute percentage errors of predicting one-hour averaged heart rate are 4.1, 4.5, and 5% for the upcoming one, two, and three hours respectively for cardiology patients. The obtained results in this study show the potential of using wearable technology to continuously monitor the vital signs of hospitalised patients as the real-time estimation of EWS in addition to a reliable prediction of the future values of these vital signs is presented. Ultimately, both approaches of high-rate EWS computation and vital signs time-series prediction is promising to provide efficient cost-utility, ease of mobility and portability, streaming analytics, and early warning for vital signs deterioration.

Download Full-text

Safety Monitoring and Warning System for Subway Construction Workers using Wearable Technology

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813666191127111248 ◽

2019 ◽

Vol 13 ◽

Author(s):

Jun-hua Chen ◽

Da-hu Wang ◽

Cun-yuan Sun

Keyword(s):

Real Time ◽

Video Surveillance ◽

Early Warning ◽

Warning System ◽

Safety Monitoring ◽

Wearable Technology ◽

Construction Workers ◽

Great Success ◽

Subway Construction ◽

Monitoring And Early Warning

Objective: This study focused on the application of wearable technology in the safety monitoring and early warning for subway construction workers. Methods: With the help of real-time video surveillance and RFID positioning which was applied in the construction has realized the real-time monitoring and early warning of on-site construction to a certain extent, but there are still some problems. Real-time video surveillance technology relies on monitoring equipment, while the location of the equipment is fixed, so it is difficult to meet the full coverage of the construction site. However, wearable technologies can solve this problem, they have outstanding performance in collecting workers’ information, especially physiological state data and positioning data. Meanwhile, wearable technology has no impact on work and is not subject to the inference of dynamic environment. Results and conclusion: The first time the system applied to subway construction was a great success. During the construction of the station, the number of occurrences of safety warnings was 43 times, but the number of occurrences of safety accidents was 0, which showed that the safety monitoring and early warning system played a significant role and worked out perfectly.

Download Full-text

Development of A Pharmaceutical Early Warning Scoring Model for Cardiac Arrest Using Deep Learning: Retrospective Cohort Study (Preprint)

10.2196/preprints.21720 ◽

2020 ◽

Author(s):

Hsiao-Ko Chang ◽

Hui-Chih Wang ◽

Chih-Fen Huang ◽

Feipei Lai

Keyword(s):

Time Series ◽

Cardiac Arrest ◽

Early Warning ◽

Time Series Data ◽

Predictive Accuracy ◽

Vital Signs ◽

Sliding Window ◽

Early Warning Score ◽

Series Data ◽

Dynamic Time

BACKGROUND In most of Taiwan’s medical institutions, congestion is a serious problem for emergency departments. Due to a lack of beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest (CA). OBJECTIVE We seek to develop a pharmaceutical early warning model to predict cardiac arrest in emergency departments via drug classification and medical expert suggestion. METHODS We propose a new early warning score model for detecting cardiac arrest via pharmaceutical classification and by using a sliding window; we apply learning-based algorithms to time-series data for a Pharmaceutical Early Warning Scoring Model (PEWSM). By treating pharmaceutical features as a dynamic time-series factor for cardiopulmonary resuscitation (CPR) patients, we increase sensitivity, reduce false alarm rates and mortality, and increase the model’s accuracy. To evaluate the proposed model we use the area under the receiver operating characteristic curve (AUROC). RESULTS Four important findings are as follows: (1) We identify the most important drug predictors: bits, and replenishers and regulators of water and electrolytes. The best AUROC of bits is 85%; that of replenishers and regulators of water and electrolytes is 86%. These two features are the most influential of the drug features in the task. (2) We verify feature selection, in which accounting for drugs improve the accuracy: In Task 1, the best AUROC of vital signs is 77%, and that of all features is 86%. In Task 2, the best AUROC of all features is 85%, which demonstrates that thus accounting for the drugs significantly affects prediction. (3) We use a better model: For traditional machine learning, this study adds a new AI technology: the long short-term memory (LSTM) model with the best time-series accuracy, comparable to the traditional random forest (RF) model; the two AUROC measures are 85%. (4) We determine whether the event can be predicted beforehand: The best classifier is still an RF model, in which the observational starting time is 4 hours before the CPR event. Although the accuracy is impaired, the predictive accuracy still reaches 70%. Therefore, we believe that CPR events can be predicted four hours before the event. CONCLUSIONS This paper uses a sliding window to account for dynamic time-series data consisting of the patient’s vital signs and drug injections. In a comparison with NEWS, we improve predictive accuracy via feature selection, which includes drugs as features. In addition, LSTM yields better performance with time-series data. The proposed PEWSM, which offers 4-hour predictions, is better than the National Early Warning Score (NEWS) in the literature. This also confirms that the doctor’s heuristic rules are consistent with the results found by machine learning algorithms.

Download Full-text

Development of A Drug Early Warning System Model for Cardiac Arrest Using Deep Learning: Retrospective Cohort Study (Preprint)

10.2196/preprints.26783 ◽

2020 ◽

Author(s):

Hsiao-Ko Chang ◽

Hui-Chih Wang ◽

Chih-Fen Huang ◽

Feipei Lai

Keyword(s):

Machine Learning ◽

Time Series ◽

Cardiac Arrest ◽

Early Warning ◽

Time Series Data ◽

Predictive Accuracy ◽

Vital Signs ◽

Warning System ◽

Series Data ◽

Dynamic Time

BACKGROUND In most of Taiwan’s medical institutions, congestion is a serious problem for emergency departments. Due to a lack of beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest (CA). OBJECTIVE We seek to develop a Drug Early Warning System Model (DEWSM), it included drug injections and vital signs as this research important features. We use it to predict cardiac arrest in emergency departments via drug classification and medical expert suggestion. METHODS We propose this new model for detecting cardiac arrest via drug classification and by using a sliding window; we apply learning-based algorithms to time-series data for a DEWSM. By treating drug features as a dynamic time-series factor for cardiopulmonary resuscitation (CPR) patients, we increase sensitivity, reduce false alarm rates and mortality, and increase the model’s accuracy. To evaluate the proposed model, we use the area under the receiver operating characteristic curve (AUROC). RESULTS Four important findings are as follows: (1) We identify the most important drug predictors: bits (intravenous therapy), and replenishers and regulators of water and electrolytes (fluid and electrolyte supplement). The best AUROC of bits is 85%, it means the medical expert suggest the drug features: bits, it will affect the vital signs, and then the evaluate this model correctly classified patients with CPR reach 85%; that of replenishers and regulators of water and electrolytes is 86%. These two features are the most influential of the drug features in the task. (2) We verify feature selection, in which accounting for drugs improve the accuracy: In Task 1, the best AUROC of vital signs is 77%, and that of all features is 86%. In Task 2, the best AUROC of all features is 85%, which demonstrates that thus accounting for the drugs significantly affects prediction. (3) We use a better model: For traditional machine learning, this study adds a new AI technology: the long short-term memory (LSTM) model with the best time-series accuracy, comparable to the traditional random forest (RF) model; the two AUROC measures are 85%. It can be seen that the use of new AI technology will achieve better results, currently comparable to the accuracy of traditional common RF, and the LSTM model can be adjusted in the future to obtain better results. (4) We determine whether the event can be predicted beforehand: The best classifier is still an RF model, in which the observational starting time is 4 hours before the CPR event. Although the accuracy is impaired, the predictive accuracy still reaches 70%. Therefore, we believe that CPR events can be predicted four hours before the event. CONCLUSIONS This paper uses a sliding window to account for dynamic time-series data consisting of the patient’s vital signs and drug injections. The National Early Warning Score (NEWS) only focuses on the score of vital signs, and does not include factors related to drug injections. In this study, the experimental results of adding the drug injections are better than only vital signs. In a comparison with NEWS, we improve predictive accuracy via feature selection, which includes drugs as features. In addition, we use traditional machine learning methods and deep learning (using LSTM method as the main processing time series data) as the basis for comparison of this research. The proposed DEWSM, which offers 4-hour predictions, is better than the NEWS in the literature. This also confirms that the doctor’s heuristic rules are consistent with the results found by machine learning algorithms.

Download Full-text

Heart Rate monitor based on IP networking

MATEC Web of Conferences ◽

10.1051/matecconf/201821001006 ◽

2018 ◽

Vol 210 ◽

pp. 01006

Author(s):

Miguel G. Molina ◽

Priscila E. Garzón ◽

Carolina J. Molina ◽

Juan X. Nicola

Keyword(s):

Heart Rate ◽

Real Time ◽

Electronic Devices ◽

Vital Signs ◽

Well Being ◽

Heart Rate Monitor ◽

Ip Address ◽

Health Concept ◽

New Applications ◽

Threat Situation

With the uprising of Internet of Things (IoT) networks, new applications have taken advantage of this new concept. Having all devices and all people connected 24/7 have several advantages in a variated amount of disciplines. One of them is medicine and the e-health concept. The possibility of having a real time lecture of the vital signs of people can prevent a live threat situation. This paper describes the realization of a device capable of measuring the heart rate of a person and checking for abnormalities that may negatively affect the patient’s well-being. This project will make use of electronic devices known as microcontrollers, specifically from the Arduino family, enabling us to capture data, and, with the help of a network card and a RJ-45 cable, transfer it to a PC and visualize the heart rate in real time over its assigned IP address.

Download Full-text

Non-intrusive vital sign monitoring using an intelligent pillow based on a piezoelectric ceramic sensor

Journal of Engineered Fibers and Fabrics ◽

10.1177/1558925020977268 ◽

2020 ◽

Vol 15 ◽

pp. 155892502097726

Author(s):

Wei Wang ◽

Zhiqiang Pang ◽

Ling Peng ◽

Fei Hu

Keyword(s):

Heart Rate ◽

Real Time ◽

Piezoelectric Ceramic ◽

Low Cost ◽

Body Movement ◽

Vital Signs ◽

High Heart Rate ◽

Detection Accuracy ◽

Processing Unit ◽

Real Time Monitoring

Performing real-time monitoring for human vital signs during sleep at home is of vital importance to achieve timely detection and rescue. However, the existing smart equipment for monitoring human vital signs suffers the drawbacks of high complexity, high cost, and intrusiveness, or low accuracy. Thus, it is of great need to develop a simplified, nonintrusive, comfortable and low cost real-time monitoring system during sleep. In this study, a novel intelligent pillow was developed based on a low-cost piezoelectric ceramic sensor. It was manufactured by locating a smart system (consisting of a sensing unit i.e. a piezoelectric ceramic sensor, a data processing unit and a GPRS communication module) in the cavity of the pillow made of shape memory foam. The sampling frequency of the intelligent pillow was set at 1000 Hz to capture the signals more accurately, and vital signs including heart rate, respiratory rate and body movement were derived through series of well established algorithms, which were sent to the user’s app. Validation experimental results demonstrate that high heart-rate detection accuracy (i.e. 99.18%) was achieved in using the intelligent pillow. Besides, human tests were conducted by detecting vital signs of six elder participants at their home, and results showed that the detected vital signs may well predicate their health conditions. In addition, no contact discomfort was reported by the participants. With further studies in terms of validity of the intelligent pillow and large-scale human trials, the proposed intelligent pillow was expected to play an important role in daily sleep monitoring.

Download Full-text

A Linear Time Series Analysis of Fetal Heart Rate to Detect the Variability

Handbook of Research on Recent Developments in Intelligent Communication Application - Advances in Wireless Technologies and Telecommunication ◽

10.4018/978-1-5225-1785-6.ch018 ◽

2017 ◽

pp. 471-495 ◽

Cited By ~ 4

Author(s):

Sahana Das ◽

Kaushik Roy ◽

Chanchal Kumar Saha

Keyword(s):

Heart Rate ◽

Time Series ◽

Feature Extraction ◽

Time Series Analysis ◽

Real Time ◽

Fetal Heart Rate ◽

Fetal Heart ◽

Linear Time ◽

Automated Diagnosis ◽

Real Time Analysis

Real time analysis and interpretation of fetal heart rate (FHR) is the challenge posed to every clinician. Different algorithms had been developed, tried and subsequently incorporated into Cardiotocograph (CTG) machines for automated diagnosis. Feature extraction and accurate detection of baseline and its variability has been the focus of this chapter. Algorithms by Dawes and Redman and Ayres-de-Campos have been discussed in this chapter. The authors are pleased to propose an algorithm for extracting the variability of fetal heart. The algorithm's accuracy and degree of agreement with clinician's diagnosis had been established by various statistical methods. This algorithm has been compared with an algorithm proposed by Nidhal and the new algorithm is found to be better at detecting variability in both ante-partum and intra-partum period.

Download Full-text

Longitudinal Analysis of Continuous Pulse Oximetry as Prognostic Factor in Neonatal Respiratory Distress

American Journal of Perinatology ◽

10.1055/s-0040-1718877 ◽

2020 ◽

Author(s):

Gonzalo Solís-García ◽

Elena Maderuelo-Rodríguez ◽

Teresa Perez-Pérez ◽

Laura Torres-Soblechero ◽

Ana Gutiérrez-Vélez ◽

...

Keyword(s):

Heart Rate ◽

Intensive Care ◽

Respiratory Distress ◽

Oxygen Saturation ◽

Continuous Monitoring ◽

Vital Signs ◽

Epidemiological Data ◽

Monitoring Data ◽

Joint Models ◽

Neonatal Icu

Objective Analysis of longitudinal data can provide neonatologists with tools that can help predict clinical deterioration and improve outcomes. The aim of this study is to analyze continuous monitoring data in newborns, using vital signs to develop predictive models for intensive care admission and time to discharge. Study Design We conducted a retrospective cohort study, including term and preterm newborns with respiratory distress patients admitted to the neonatal ward. Clinical and epidemiological data, as well as mean heart rate and saturation, at every minute for the first 12 hours of admission were collected. Multivariate mixed, survival and joint models were developed. Results A total of 56,377 heart rate and 56,412 oxygen saturation data were analyzed from 80 admitted patients. Of them, 73 were discharged home and 7 required transfer to the intensive care unit (ICU). Longitudinal evolution of heart rate (p < 0.01) and oxygen saturation (p = 0.01) were associated with time to discharge, as well as birth weight (p < 0.01) and type of delivery (p < 0.01). Longitudinal heart rate evolution (p < 0.01) and fraction of inspired oxygen at admission at the ward (p < 0.01) predicted neonatal ICU (NICU) admission. Conclusion Longitudinal evolution of heart rate can help predict time to transfer to intensive care, and both heart rate and oxygen saturation can help predict time to discharge. Analysis of continuous monitoring data in patients admitted to neonatal wards provides useful tools to stratify risks and helps in taking medical decisions. Key Points

Download Full-text