Wearable Device Design for Cattle Behavior Classification Using IoT and Machine Learning

2021 ◽  
pp. 235-248
Author(s):  
Fatema Ahmed ◽  
Bholanath Roy ◽  
Saritha Khetawat
Keyword(s):  
Machine Learning ◽  
Wearable Device ◽  
Device Design

Diagnosis of Atrial Fibrillation Using Machine Learning with Wearable Devices after Cardiac Surgery (Preprint)

2021 ◽  
Author(s):  
Daisuke Hiraoka ◽  
Tomohiko Inui ◽  
Eiryo Kawakami ◽  
Megumi Oya ◽  
Ayumu Tsuji ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Cardiac Surgery ◽  
Early Detection ◽  
Pulse Rate ◽  
Paroxysmal Atrial Fibrillation ◽  
Wearable Device ◽  
Strongly Correlated ◽  
Cross Correlation Analysis ◽  
Data Output

BACKGROUND Some attempts have been made to detect atrial fibrillation with a wearable device equipped with photoelectric volumetric pulse wave technology, and it is expected to be applied under real clinical conditions. OBJECTIVE This study is the second part of a two-phase study aimed at developing a method for immediate detection of paroxysmal atrial fibrillation (AF) using a wearable device with built-in PPG. The objective of this study is to develop an algorithm to immediately diagnose atrial fibrillation by wearing an Apple Watch equipped with a photoplethysmography (PPG) sensor on patients undergoing cardiac surgery and using machine learning of the pulse data output from the device. METHODS A total of 80 subjects who underwent cardiac surgery at a single institution between June 2020 and March 2021 were monitored for postoperative atrial fibrillation using telemetry monitored ECG and Apple Watch. Atrial fibrillation was diagnosed by qualified physicians from telemetry-monitored ECGs and 12-lead ECGs; a diagnostic algorithm was developed using machine learning on pulse rate data output from the Apple Watch. RESULTS One of the 80 patients was excluded from the analysis due to redness of the Apple Watch wearer. 27 (34.2%) of the 79 patients developed AF, and 199 events of AF, including brief AF, were observed. 18 events of AF lasting longer than 1 hour were observed, and Cross-correlation analysis (CCF) showed that pulse rate measured by Apple Watch was strongly correlated (CCF 0.6-0.8) with 8 events and very strongly correlated (CCF >0.8) with 3 events. The diagnostic accuracy by machine learning was 0.7952 (sensitivity 0.6312, specificity 0.8605 at the point closest to the top-left) for the AUC of the ROC curve. CONCLUSIONS We were able to safely monitor pulse rate in patients after cardiac surgery by wearing an Apple Watch. Although the pulse rate from the PPG sensor does not follow the heart rate of the telemetry monitoring ECG in some parts, which may reduce the accuracy of the diagnosis of atrial fibrillation by machine learning, we have shown the possibility of clinical application of early detection of atrial fibrillation using only the pulse rate collected by the PPG sensor. CLINICALTRIAL The use of wristband type continuous pulse measurement device with artificial intelligence for early detection of paroxysmal atrial fibrillation Clinical Research Protocol No. jRCTs032200032 https://jrct.niph.go.jp/latest-detail/jRCTs032200032

scholarly journals Dear Watch, Should I get a COVID Test? Designing deployable machine learning for wearables

2021 ◽  
Author(s):  
Anna Goldenberg ◽  
Bret Nestor ◽  
Jaryd Hunter ◽  
Raghu Kainkaryam ◽  
Erik Drysdale ◽  
...  
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Real World ◽  
False Positive Rate ◽  
Wearable Devices ◽  
Classification Performance ◽  
Wearable Device ◽  
Screening Tools ◽  
Machine Learning Model ◽  
Positive Rate

Abstract Commercial wearable devices are surfacing as an appealing mechanism to detect COVID-19 and potentially other public health threats, due to their widespread use. To assess the validity of wearable devices as population health screening tools, it is essential to evaluate predictive methodologies based on wearable devices by mimicking their real-world deployment. Several points must be addressed to transition from statistically significant differences between infected and uninfected cohorts to COVID-19 inferences on individuals. We demonstrate the strengths and shortcomings of existing approaches on a cohort of 32,198 individuals who experience influenza like illness (ILI), 204 of which report testing positive for COVID-19. We show that, despite commonly made design mistakes resulting in overestimation of performance, when properly designed wearables can be effectively used as a part of the detection pipeline. For example, knowing the week of year, combined with naive randomised test set generation leads to substantial overestimation of COVID-19 classification performance at 0.73 AUROC. However, an average AUROC of only 0.55 +/- 0.02 would be attainable in a simulation of real-world deployment, due to the shifting prevalence of COVID-19 and non-COVID-19 ILI to trigger further testing. In this work we show how to train a machine learning model to differentiate ILI days from healthy days, followed by a survey to differentiate COVID-19 from influenza and unspecified ILI based on symptoms. In a forthcoming week, models can expect a sensitivity of 0.50 (0-0.74, 95% CI), while utilising the wearable device to reduce the burden of surveys by 35%. The corresponding false positive rate is 0.22 (0.02-0.47, 95% CI). In the future, serious consideration must be given to the design, evaluation, and reporting of wearable device interventions if they are to be relied upon as part of frequent COVID-19 or other public health threat testing infrastructures.

scholarly journals Machine Learning Models Predicting the Survival of Abrupt Heart Attack in Cardiac Sarcoidosis Disease using the Wearable Device

2020 ◽  
Vol 9 (5) ◽  
pp. 9-13
Keyword(s):  
Machine Learning ◽  
Ventricular Tachycardia ◽  
Ventricular Fibrillation ◽  
Heart Attack ◽  
Cardiac Sarcoidosis ◽  
Wearable Device ◽  
Cardioverter Defibrillator ◽  
Wearable Cardioverter Defibrillator ◽  
Positive Rate ◽  
Machine Learning Models

Wearable technology has countless prospects of remodelling healthcare establishment and also medical education. Cardiac sarcoidosis disease (CS) is a sporadic illness in which white blood cells (WBC) clusters known as granulomas, form as heart tissue. Cardiac sarcoidosis disease (CS) Patients are at high threat of ventricular tachycardia or ventricular fibrillation (VT/VF). Wearable cardioverter defibrillator device is introduced which helps to alleviate the abrupt heart attack risk amid patients of cardiac sarcoidosis. A reflective evaluation of the commercial record acknowledged patients of cardiac sarcoidosis disease who sported the wearable cardioverter defibrillator (WCD). ML models are applied to get accurate predictions to motivate WCD wear ability. The wearable device cardioverter defibrillator (WCD) was worn by forty six patients of cardiac sarcoidosis disease in which 22(48%) female, male 24 (52%). The wearable cardioverter defibrillator (WCD) was sported hours about 23.6 median daily. Nearby eleven ventricular tachycardia or ventricular fibrillation (VT/VF) incidents occur in ten patients (22%). Ventricular tachycardia or ventricular fibrillation (VT/VF) happened over a series of (1-79) days, median of twenty-four days. 1st- heart attack success for ventricular tachycardia or ventricular fibrillation (VT/VF) conversion was hundred percent. Survival of Patient in twenty four hours after treatment of attack was hundred percent. To regulate the discontinuing cause for wearable device cardioverter defibrillator (WCD) use specified that among seven attacked patients received ICD, one patient was died two weeks later discontinuing the use of wearable cardioverter defibrillator device (WCD), and two patients were absent to track. Sixteen were not attacked patients, who obtained an implantable cardioverter defibrillator (ICD) while seven of them attained and improved left ventricular ejection fraction (LVEF). Abrupt heart attack (HA) management amongst patients of cardiac sarcoidosis disease (CS) was assisted by wearable device cardioverter defibrillator (WCD) ensuing in positive ventricular tachycardia or ventricular fibrillation (VT/VF) termination upon attack delivery. In this paper, the dataset is retrieved from google dataset search and evaluated on various ML models to predict the survival of the patients Receiving ICD while wearing WCD as well as evaluating the developed model performance and to identify the best applicable model. Dataset is primarily processed and nursed to many machine learning classifiers like KNN, SVM, Perceptron, Random Forest, Decision Trees (DT), Logistic Expression, SGD, and Naïve Basis. Cross-validation is smeared, training is performed so that new machine learning models are established and verified. The outcomes found are assessed on many factors such as Accuracy, Misclassification Rate, True Positive Rate, True Negative Rate, Precision, Prevalence, False Positive rate taken to build the model. Result analysis reveals that among all the classifiers SVM and KNN best model acquiescent high and precise outcomes.

Sign in / Sign up

Export Citation Format

Share Document