Real-time Patient Monitoring System Research Articles

IoT Based Patient Health Monitoring using ESP8266 and Arduino

Internet of Things is a technological paradigm which can be incorporated in real time patient monitoring system. The review and implementation of real time monitoring of patients using biomedical sensors and microcontroller is presented where physiological parameters like heart-rate, body temperature is measured. This IoT prototype could read the pulse rate and measure the body temperature updates them to things peak an IoT platform.

Prospective Pilot Study of Telehealth As Domiciliary Follow-up after Hematopoietic Cell Transplantation during the COVID19 Pandemic

IntroductionAn increased risk of mortality has been documented in transplanted patients affected by Coronavirus Disease 2019 (COVID19) with an estimated mortality rate between 20-40%. Multiple efforts are ongoing to control COVID19 pandemic, and clinical practice is being adapted at the same time as the pandemic progresses around the world. To reduce unnecessary in-person appointments has become crucial to minimize hospital exposition. Digital technologies allow us to perform real-time monitoring of patients' clinical status. A real-time patient monitoring system through the use of a smartphone application and wearable devices was implemented at our Center during the COVID19 pandemic.MethodsSince March 2020, a real time patient monitoring system was implemented at our HCT program. All consecutive adults patients transplanted between April 2020 and July 2020 were considered for the study. Vital signs and relevant clinical information were reported during 14 consecutive days after being discharged, through the online platform provided by Trilema Fundation (saludencasa.trilema.org, Fundación Trilema, Valencia, Spain). Vital signs (cardiac frequency, blood pressure, oxygen saturation) were measured with validated oxymeters (Onyx II®, Nonin Inc, Plymouth MN USA) and blood pressure monitors (iHealth Track®, Mountain View, CA USA). Temperature was measured through domiciliary thermometers. Patients were educated to measure their respiratory frequency. A checklist of clinical symptoms was filled daily. An analogue visual scale (0-10) to detect potential cases of anxiety or depressive disorders was reported daily. Scores of >6 were evaluated by a psycho-oncologist through videoconference. All the data were reported to the online platform using a smartphone app compatible with iPhone and Android systems. A direct chat between patients and physician was available through the app. Clinical information was daily supervised by an experienced HCT hematologist. Clinical interventions were arranged if significant clinical abnormalities were documented. A hematologist with experience in HCT patients revised all the patients’ data daily. Programmed alarms were set in case of any of the following situations: fever >38 oC; oxygen saturation <92%; tachicardia >125/bpm, hypotension (sytolic<90 mmHg, diastolic > 60 mmHg; altered mental status; persistent emesis or diarrhea). Patient´s satisfaction questionnaires were evaluated individually after finalizing the 14-days clinical monitoring.ResultsDuring the study period, 21 adults underwent HCT and 16 were s were eligible to be recruited into the study (80% feasibility) with team effort and without additional costs. Reasons for not being enrolled were: language incompatibility (1 patient), no consent (1 patient), not compatible smartphone (3 patients). Of the 16 enrolled patients, median age was 50 (range 22-70 years), 37% were female and 94% had lymphoid diseases. Thirty-eight percent of HCTs were autologous and 62% allogeneic.Of the 16 enrolled patients, 25% were not able to adequately use the app due to inability in using smartphone applications. Of the remaining 12 patients, adherence in reporting study data (number of days reported of the planned 14 days study period) was as follows (average):temperature 89%, oxygen saturation 90%, respiratory frequency 70%, cardiac frequency 85%, blood pressure 89%, symptoms reporting 65%, emotional distress 71%.Automatic alarms were activated only 3 times: twice for the presence of clinical symptoms and once, for emotional distress. A videoconference with the psycho-oncologist was requested by one patient only. The chat service to communicate with hospital personnel was used in 4 patients. Data collected with the digital system helped the clinician to early recognize arterial hypertension (1 patient) and acute cutaneous GVHD grade 1 (1 patient).Only two patients of the whole cohort were readmitted within 14 days from discharge due to grade 4 odynophagia due to HSV1/2 reactivation.Patients´ experiences with telehealth systems are reported in table 1.ConclusionTelehealth monitoring can potentially improve patient's follow-up in terms of both physical and psychological outcomes. Technological problems still represent a barrier to a wider application of telehealth monitoring systems in the medical setting.DisclosuresMussetti:Novartis, Gilead: Honoraria, Research Funding. Sureda Balari:Incyte: Consultancy; Janssen: Consultancy, Honoraria; Celgene/Bristol-Myers Squibb: Consultancy, Honoraria; Novartis: Consultancy, Honoraria; Celgene: Consultancy, Honoraria; BMS: Speakers Bureau; Roche: Honoraria; Takeda: Consultancy, Honoraria, Speakers Bureau; Sanofi: Consultancy, Honoraria; Gilead/Kite: Consultancy, Honoraria; Merck Sharpe and Dohme: Consultancy, Honoraria, Speakers Bureau.

I see it in your eyes: Training the shallowest-possible CNN to recognise emotions and pain from muted web-assisted in-the-wild video-chats in real-time

A robust value- and time-continuous emotion recognition has enormous potential benefits within healthcare. For example, within mental health, a real-time patient monitoring system capable of accurately inferring a patient’s emotional state could help doctors make an appropriate diagnosis and treatment plan. Such interventions could be vital in terms of ensuring a higher quality of life for the patient involved. To make such tools a reality, the associated machine learning systems need to be fast, robust and generalisable. In this regard, we present herein, a novel emotion recognition system consisting of the shallowest realisable Convolutional Neural Network (CNN) architecture. We draw insights from visualisations of the trained filter weights and the facial action unit (FAU) activations, i. e. the inputs to the model, of the participants featured in the in-the-wild, spontaneous video-chat sessions of the SEWA corpus. Further, we demonstrate the generalisablity of this approach on the German, Hungarian, and Chinese cultures available in this corpus. The obtained cross-cultural performance is a testimony to the universality of FAUs in expression and understanding of the human affective behaviours. These learnings were moderately consistent with the human perception of emotional expression. The practicality of the proposed approach is also demonstrated in another key healthcare applications; pain intensity prediction. Key results from these experiments highlight the transparency of the shallow CNN structure. As FAU can be extracted in near real-time, and because the models we developed are exceptionally shallow, this study paves the way for a robust, cross-cultural, end-to-end, in-the-wild, explainable real-time affect and pain prediction, that is value- and time-continuous.

Epileptic seizure prediction by the detection of seizure waveform from the pre-ictal phase of EEG signal

Epilepsy is a significant burden on our society till now, due to appropriate healthcare treatment, cost of therapy, the spontaneous and unpredictable occurrence of seizures. There is a need for a fast and integrated neural investigation process that could help epileptologist to determine and diagnose the patients as soon as possible. Electroencephalogram (EEG) has been commonly used to diagnose patients by investigating the brain's electrical activity that might be related to epilepsy. The proposed framework consists of several algorithms of feature extraction (current maxima, lower threshold, and target point selection), pattern matching (segment and domain matching) and post-processing with power, energy features. Maxima, homogeneity, power, energy and physiological field features have been used in this proposed model. Moreover, specific brain regions (lobes) inside the brain, where the seizure occurs, has been identified by the domain matching algorithm. There exist no such seizure detection system which provides warning message from the pre-ictal phase. This proposed model can be efficiently used as a real-time patient monitoring system which can send a warning message to the patient before the occurrence of seizure. This ultimately helps doctors for taking necessary actions. True positive rate (TPR) of 91.07% and 97.36% has been recorded for seizure and normal classes respectively. The accuracy and F1 score of the proposed model are 92.66% and 94.86%, respectively.

Heart Disease Detection by Using Machine Learning Algorithms and a Real-Time Cardiovascular Health Monitoring System

Cardiovascular diseases are the most common cause of death worldwide over the last few decades in the developed as well as underdeveloped and developing countries. Early detection of cardiac diseases and continuous supervision of clinicians can reduce the mortality rate. However, accurate detection of heart diseases in all cases and consultation of a patient for 24 hours by a doctor is not available since it requires more sapience, time and expertise. In this study, a tentative design of a cloud-based heart disease prediction system had been proposed to detect impending heart disease using Machine learning techniques. For the accurate detection of the heart disease, an efficient machine learning technique should be used which had been derived from a distinctive analysis among several machine learning algorithms in a Java Based Open Access Data Mining Platform, WEKA. The proposed algorithm was validated using two widely used open-access database, where 10-fold cross-validation is applied in order to analyze the performance of heart disease detection. An accuracy level of 97.53% accuracy was found from the SVM algorithm along with sensitivity and specificity of 97.50% and 94.94%respectively. Moreover, to monitor the heart disease patient round-the-clock by his/her caretaker/doctor, a real-time patient monitoring system was developed and presented using Arduino, capable of sensing some real-time parameters such as body temperature, blood pressure, humidity, heartbeat. The developed system can transmit the recorded data to a central server which are updated every 10 seconds. As a result, the doctors can visualize the patient’s real-time sensor data by using the application and start live video streaming if instant medication is required. Another important feature of the proposed system was that as soon as any real-time parameter of the patient exceeds the threshold, the prescribed doctor is notified at once through GSM technology.

Design and Development of Real Time Patient Monitoring System with GSM Technology

Technology keeps evolving every second. Humans receive all the essential information with just one touch. Be it the weather forecast or ordering any grocery or communicating with one's peers, everything happens so easily and efficiently. It is undoubtedly user friendly. When the same technology associates itself with the medical equipment it becomes easier to fetch and process the patient's data in real time. It also helps to make several life-saving, spontaneous decisions for the critical care. This paper talks about the patient monitoring system. The physiological parameters of the patient are continuously monitored in real time using sensors. The data that is obtained from the sensor is then sent to an Arduino Uno microcontroller where it is analyzed. If the patient's data differs from the required threshold values, an emergency message is sent to the assigned doctor's mobile. This is done using the GSM module which is interfaced with the microcontroller. Verifying the system in software is done using Proteus.

Cluster-based real-time analysis of mobile healthcare application for prediction of physiological data

In recent years, interest in medical healthcare applications using Wireless Body Sensor Network (WBSN) has grown considerably. A WBSN can be used to develop a patient monitoring system, which offers flexibility and mobility to monitor patient’s health condition. When the value of the physiological signal reaches threshold, the system raises an alarm. However, earlier patient monitoring systems may not be accurate all the time and do not support mobility which lead to false positive prediction. This paper presents, a data mining algorithm to predict the health risk of the patient in real time with 96% accuracy using historical medical records. Proposed Online Distribution Resource Aware (ODRA) algorithm gives accurate condition of the patients so as to inform the status to physician whenever immediate attention is required. The worst health conditions are predicted by risk components which are extracted using signal windows of the vital signal. The proposed algorithm of real-time patient monitoring system uses online signals to monitor the patient’s physiological data with increased mobility even in the ubiquitous environment. HR, SpO2, and Blood Pressure signals of 64 patients with different illness have been tested and verified. Results confirmed that the proposed algorithm gives better accuracy and reduce False Positive Rate (FPR) for predicting risk status of the patient compared to Resource Aware High-Quality Clustering (RAH).

A Real Time Patient Monitoring System based on Artificial Neural Fuzzy Inference System (ANFIS)

A Real Time Patient Monitoring System based on Artificial Neural Fuzzy Inference System (ANFIS)

RELIABLE TRANSMISSION PROTOCAL FOR GSM AND HTTP BASED ON WIRELESS PATIENT MONITORING

The main focus of the paper is to implement a prototype model for the real time patient monitoring system. The proposed is used to measure the physical parameters like body temperature, heartbeat, ECG, blood sugar, and oxygen level monitoring with the help of biosensors. Conventionally there are number of techniques available for the ICU patient's health monitoring system with wired communication technology. In the novel system the patient health is continuously monitored and the acquired data is transmitted to an ARM server using zigbee wireless sensor networks. Embedded processor supports for analyzing the input from the patient and the results of all the parameters are stored in the database. If any abnormality felt by the patient automatic alarm sound will arrive and the message will send to the doctor mobile automatically by using GSM module. The implementation of the system is achieved by the advanced processor and simulation results are obtained by Keil c software.

Optimal gateway selection in sensor–cloud framework for health monitoring

Sensor-cloud computing is envisioned to be one of the key enabling technologies for remote health monitoring. Integration of sensed data into cloud applications in sensor-cloud will help in real-time monitoring of patients over geographically distributed locations. In this study, the authors study the optimal gateway selection problem in sensor-cloud framework for real-time patient monitoring system by using a zero-sum game model. In the proposed model, a gateway acts as the first player, and chooses the strategy based on the available bandwidth, whereas a user request acts as the second player, and follows the strategy chosen by the first player. The authors evaluate the execution time for selecting the optimal gateway through which the sensed data will be fetched to the cloud platform. In addition, the authors show how user requests are serviced by the gateways to access data from cloud platform optimally. The authors also show that by using the proposed approach, the execution time decreases, thereby helping in forming a reliable, efficient and real-time architecture for health monitoring.

SU‐E‐T‐267: Preliminary Study of Development of the Respiratory Training System by Using the MEMS Acceleration Sensor for the Radiation Therapy

Purpose: In this study, we developed and estimated the home‐made patient‐respiration‐training‐system (PRTS) by using the micro‐electromechanical‐system (MEMS) which can help to avoid the problems for the limitation of the RGRT applicable patient cases. Methods: We compared the response of the PRTS with period of real movement and commercially introduced real time patient monitoring (RPM) system. We measured the response of the PRTS by using the respiratory gating platform (RGP) for a 2.5, 3.0 and 3.5 second of the period and a 20, 30, 40 mm of the amplitude. Under the same condition, we measured the response of the RPM system by using the RGP. Results: The period error from the PRST was measured as 0.6∼6.0% compared with period of real movement. Considering the overall shape of the graphs, the uncertainty of the signal of the RPM system measured about 1% in an amplitude for each interval, on the other hand, MEMS signals had 3∼11% of the error in amplitude. Conclusion: In term of simplicity and convenience, we found the possibility of PRTS as the patient training system and we expect more detail of study for more realistic situation can be established, in near future.

Study of the Respiratory Monitoring System by Using the MEMS Acceleration Sensor

In this study, we developed and evaluated the patient respiration training method which can help to avoid the problems for the limitation of RGRT applicable patient cases. By using the MEMS (micro-electro-mechanical- system) acceleration sensor, we measured movement of motion phantom. We had compared the response of MEMS with commercially introduced real time patient monitoring (RPM) system. We measured the response of the MEMS with 1 dimensional motion phantom movement for 2.5, 3.0, 3.5 second of period and the 2.0, 3.0, 4.0 cm of the amplitudes. The measured period error of the MEMS system was 0.6∼6.0% compared with measured period using RPM system. We found that the shape of MEMS signals were similar with RPM system. From this study, we found the possibility of MEMS as patient training system.

Remote monitoring of post-operative patients using wireless sensor networks

Patients recovering from surgery are at risk of complications due to reduced mobility as a result of post-operative pain. The ability to monitor the recovery of this group of patients and identify those at risk of developing complications is, therefore, clinically desirable and may result in an early intervention to prevent adverse outcomes. We have developed a real-time patient monitoring system that integrates a vital signs sensor, a sensor network, electronic patient records and web portal technology to allow remote monitoring of post-operative patient status in the hospital and homecare conditions and to alert medical personnel when life-threatening events occur. This system will facilitate communication among patients, medical professionals at local hospitals and specialists available for consultation from distant places through a secured web server. The most valued features of this system are to prevent the patient from re-hospitalisation and to avoid possible critical events, thus reducing global healthcare costs.