scholarly journals An attempt to construct the individual model of daily facial skin temperature using variational autoencoder

2021 ◽  
Author(s):  
Ayaka Masaki ◽  
Kent Nagumo ◽  
Yuki Iwashita ◽  
Kosuke Oiwa ◽  
Akio Nozawa
Keyword(s):  
Skin Temperature ◽  
Normal State ◽  
Roc Analysis ◽  
Daily Life ◽  
Area Under The Curve ◽  
Facial Skin ◽  
Individual Model ◽  
Variational Autoencoder ◽  
Auc Value ◽  
The Individual

AbstractFacial skin temperature (FST) has also gained prominence as an indicator for detecting anomalies such as fever due to the COVID-19. When FST is used for engineering applications, it is enough to be able to recognize normal. We are also focusing on research to detect some anomaly in FST. In a previous study, it was confirmed that abnormal and normal conditions could be separated based on FST by using a variational autoencoder (VAE), a deep generative model. However, the simulations so far have been a far cry from reality. In this study, normal FST with a diurnal variation component was defined as a normal state, and a model of normal FST in daily life was individually reconstructed using VAE. Using the constructed model, the anomaly detection performance was evaluated by applying the Hotelling theory. As a result, the area under the curve (AUC) value in ROC analysis was confirmed to be 0.89 to 1.00 in two subjects.

scholarly journals Predictive value of relative fat mass algorithm for incident hypertension: a 6-year prospective study in Chinese population

BMJ Open ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. e038420
Author(s):  
Peng Yu ◽  
Teng Huang ◽  
Senlin Hu ◽  
Xuefeng Yu
Keyword(s):  
Prospective Study ◽  
Fat Mass ◽  
Chinese Population ◽  
Predictive Power ◽  
Roc Analysis ◽  
Statistical Significance ◽  
Area Under The Curve ◽  
Predictive Ability ◽  
Incident Hypertension ◽  
Auc Value

ObjectivesIndividuals with obesity especially excessive visceral adiposity have high risk for incident hypertension. Recently, a new algorithm named relative fat mass (RFM) was introduced to define obesity. Our aim was to investigate whether it can predict hypertension in Chinese population and to compare its predictive power with traditional indices including body mass index (BMI), waist circumference (WC) and waist-to-height ratio (WHtR).DesignA 6-year prospective study.SettingNine provinces (Hei Long Jiang, Liao Ning, Jiang Su, Shan Dong, He Nan, Hu Bei, Hu Nan, Guang Xi and Gui Zhou) in China.ParticipantsThose without hypertension in 2009 survey and respond in 2015 survey.InterventionLogistic regression were performed to investigate the association between RFM and incident hypertension. Receiver operating characteristic (ROC) analysis was performed to compare the predictive ability of these indices and define their optimal cut-off values.Main outcome measuresIncident hypertension in 2015.ResultsThe prevalence of incident hypertension in 2015 based on RFM quartiles were 14.8%, 21.2%, 26.8% and 35.2%, respectively (p for trend <0.001). In overall population, the OR for the highest quartile compared with the lowest quartile for RFM was 2.032 (1.567–2.634) in the fully adjusted model. In ROC analysis, RFM and WHtR had the highest area under the curve (AUC) value in both sexes but did not show statistical significance when compared with AUC value of BMI and WC in men and AUC value of WC in women. The performance of the prediction model based on RFM was comparable to that of BMI, WC or WHtR.ConclusionsRFM can be a powerful indictor for predicting incident hypertension in Chinese population, but it does not show superiority over BMI, WC and WHtR in predictive power.

scholarly journals Anomaly detection in facial skin temperature using variational autoencoder

2020 ◽  
Author(s):  
Ayaka Masaki ◽  
Kent Nagumo ◽  
Bikash Lamsal ◽  
Kosuke Oiwa ◽  
Akio Nozawa
Keyword(s):  
Anomaly Detection ◽  
Skin Temperature ◽  
Facial Skin ◽  
Autonomic Nervous System Activity ◽  
New Approach ◽  
Thermal Images ◽  
Psychological States ◽  
Detection Model ◽  
Nervous System Activity ◽  
Variational Autoencoder

Abstract Facial skin temperature is a physiological index that varies with skin blood flow controlled by autonomic nervous system activity. The facial skin temperature can be remotely measured using infrared thermography, and it has recently attracted attention as a remote biomarker. For example, studies have been reported to estimate human emotions, drowsiness, and mental stress on facial skin temperature. However, it is impossible to make a machine that can discriminate all infinite physiological and psychological states. Considering the practicality of skin temperature, a machine that can determine the normal state of facial skin temperature may be sufficient. In this study, we propose a completely new approach to incorporate the concept of anomaly detection into the analysis of physiological and psychological states by facial skin temperature. In this paper, the method for separating normal and anomaly facial thermal images using an anomaly detection model was investigated to evaluate the applicability of variational autoencoder (VAE) to facial thermal images.

scholarly journals Development of a New Triage Method to Prioritize Patients Arriving at the Emergency Room

2019 ◽  
Vol 34 (s1) ◽  
pp. s118-s119
Author(s):  
Tomoaki Natsukawa ◽  
Ryo Deguchi ◽  
Naoki Akita ◽  
Sadayori Uemori ◽  
Toyokazu Miki ◽  
...  
Keyword(s):  
Emergency Room ◽  
Roc Analysis ◽  
Area Under The Curve ◽  
Triage Category ◽  
Number Of Patients ◽  
Calculated Risk ◽  
The Many ◽  
The Individual ◽  
Christian Hospital ◽  
Provision Of Care

Introduction:By prioritizing emergency patients, triage facilitates the timely provision of care to the largest possible number of patients arriving at an emergency room (ER). Previous triage methods include the Canadian and Japan Triage and Acuity Scales. Since these methods sort patients into five categories, multiple patients are often categorized into the same category. Furthermore, since these scales adopt original complex algorithms to determine the triage category, triage personnel need to be very familiar with the algorithm. Hence, a simple triage method is needed to prioritize ER patients.Aim:To develop a new triage method to prioritize patients arriving at the ER.Methods:Patients aged ≥13 years who arrived at the ER of Yodogawa Christian Hospital without being transported by ambulance between January 2016 and October 2018 were assessed. We analyzed correlations between the items included in the triage sheet and admission. We calculated risk ratios (RRs) of the items that were significantly related to admission. The RR of an item was considered its score, and the triage score was calculated by summing the individual RR scores for each patient. We performed receiver operating characteristic (ROC) analysis of admission and triage scores.Results:Among 20992 patients, 2030 patients (9.7%) were admitted to the hospital. The triage scores of all the patients ranged from 26.5 to 62.3. According to the ROC analysis, the area under the curve was 0.791 and the optimal cutoff value for the triage score was 32.7 (sensitivity: 0.74, specificity: 0.70).Discussion:Since this research was based on data from a Japanese secondary level emergency hospital in an urban area, our triage method can be adapted to the many ERs in Japan that share a similar background. The method used to develop this triage method can also be used to develop triage methods for ERs with different backgrounds.

scholarly journals Clinical performance and utility of a NNMT-based urine test for bladder cancer

2017 ◽  
Vol 33 (1) ◽  
pp. 94-101 ◽  
Author(s):  
Valentina Pozzi ◽  
Giulia Di Ruscio ◽  
Davide Sartini ◽  
Roberto Campagna ◽  
Riccardo Seta ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Diagnostic Accuracy ◽  
Roc Analysis ◽  
Clinical Performance ◽  
Histological Grade ◽  
Area Under The Curve ◽  
Inverse Correlation ◽  
Cutoff Value ◽  
Healthy Donors ◽  
Auc Value

Background: Bladder cancer (BC) represents the most common neoplasm of the urinary tract. Although cystoscopy and urine cytology represent the gold standard methods to monitor BC, both procedures have limitations. Therefore, the identification of reliable biomarkers for early and noninvasive detection of BC is urgently required. Methods: In this study, we analyzed nicotinamide N-methyltransferase (NNMT) expression in urine samples from 55 BC patients and 107 controls, using real-time polymerase chain reaction (PCR). Receiver operating characteristic (ROC) analysis was used to identify the best cutoff value to discriminate BC patients from healthy donors, and to evaluate the diagnostic accuracy of a urine-based NNMT test. Results: The results demonstrated that urinary NNMT expression was significantly (p<0.05) higher in BC patients. Moreover, a significant (p<0.05) inverse correlation was found between NNMT expression and histological grade. The ROC analysis revealed that a ΔCq of 13.3 was the best cutoff value, since it was associated with the highest combination of sensitivity and specificity. Moreover, the area under the curve (AUC) value was 0.913 (p<0.05), indicating the excellent diagnostic accuracy of a urine-based NNMT test. Conclusions: Our data indicate that NNMT is a promising biomarker that could be used to support the early and noninvasive diagnosis of BC.

scholarly journals The effect of troponin values on prognosis in acute pulmonary embolism

2020 ◽  
Vol 7 (4) ◽  
pp. 229
Author(s):  
Gulay Dasdemir Ilkhan ◽  
Hakan Celikhisar
Keyword(s):  
Pulmonary Embolism ◽  
Sensitivity And Specificity ◽  
Significant Relationship ◽  
Roc Analysis ◽  
Operating Characteristic ◽  
Area Under The Curve ◽  
Survivor Group ◽  
Acute Pulmonary Thromboembolism ◽  
Auc Value ◽  
Low Sensitivity

<p class="abstract"><strong>Background:</strong> The objective of this study is to evaluate the clinical usefulness of cardiac troponin levels in acute pulmonary thromboembolism (PTE) prognosis.</p><p class="abstract"><strong>Methods:</strong> Thorax computed tomography (CT) angiography was performed and reported by the radiologist as pulmonary embolism and 193 patients older than 18 years of age who were considered PTE by the physician of chest diseases were included in the study. Patients diagnosed with PTE were divided into two groups as those who died within 30 days and did not die within 30 days. As a result of the statistically significant relationship between troponin and mortality, receiver operating characteristic (ROC) analysis was performed to determine the prognosis level of troponin and appropriate sensitivity and specificity cut-off values were determined.</p><p class="abstract"><strong>Results:</strong> We determined that troponin levels of patients diagnosed with PTE in the emergency department were statistically significantly higher in the group with mortality (p=0.031). Since the area under the curve (AUC) value was calculated as 0.636, troponin value was found to have a weak-medium significance in terms of predicting 30-day mortality.</p><p class="abstract"><strong>Conclusions: </strong>Troponin values are statistically significantly higher in patients with a one-month period than the survivor group in this period. However, we concluded that troponin values are not clinically usable as mortality markers due to their low sensitivity and specificity rates. However, due to its significant relationship with increased mortality, patients with PTE with high troponin values should be hospitalized and monitored closely.</p>

Secretary leukocyte peptide inhibitor (SLPI) in pleural fluid is useful as a diagnostic marker of malignant pleural mesothelioma.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e23098-e23098
Author(s):  
Nobukazu Fujimoto ◽  
Yoko Kojima ◽  
Takumi Kishimoto
Keyword(s):  
Pleural Fluid ◽  
Malignant Pleural Mesothelioma ◽  
Roc Analysis ◽  
Diagnostic Marker ◽  
Area Under The Curve ◽  
Peptide Inhibitor ◽  
Pleural Mesothelioma ◽  
Exploratory Research ◽  
Operating Characteristics ◽  
Auc Value

e23098 Background: There is no established diagnostic marker for malignant pleural mesothelioma (MPM). In particular, the differentiation from benign asbestos pleural effusion (BAPE) is challenging. Secretary leukocyte peptide inhibitor (SLPI) is an enzyme encoded by SLPI gene. SLPI gene is reported to be overexpressed in MPM cells. Methods: SLPI in pleural fluid was determined using Quantikine ELISA Human SLPI kit (R&D Systems). Results: Exploratory research revealed that SLPI value in pleural fluid of patients with MPM (n = 52) were significantly higher than those in lung cancer (LC) (n = 69) and BAPE (n = 50) ( P= 0.000). Prospective validation study included 12 pts of MPM, 24 pts of LC, 26 pts of BAPE. Median values of SLPI in MPM, LC, and BAPE were 159 .6 ng/ml, 90.5 ng/ml, and 43.2 ng/ml, respectively. SLPI value in patients with MPM were significantly higher than those in other groups ( P= 0.000). Receiver operating characteristics ROC) analysis was performed to examine the usefulness of differentiation of MPM and other diseases, and demonstrated that area under the curve (AUC) value was 0.758. With the cut of value of 88.6 ng/ml, the sensitivity was 83.3% and the specificity was 59.8%. Concerning the differentiation between MPM and BAPE, AUC value was 0.904 and with the cut of value of 81.8 ng/ml, the sensitivity was 83.3% and the specificity was 92.3%. Conclusions: Pleural fluid SLPI is a useful biomarker for the diagnosis of MPM, in particular, for the differentiation from BAPE.

Measuring Facial Skin Temperature Changes Caused by Mental Work-Load with Infrared Thermography

2016 ◽  
Vol 136 (11) ◽  
pp. 1581-1585 ◽  
Author(s):  
Tota Mizuno ◽  
Takeru Sakai ◽  
Shunsuke Kawazura ◽  
Hirotoshi Asano ◽  
Kota Akehi ◽  
...  
Keyword(s):  
Skin Temperature ◽  
Infrared Thermography ◽  
Work Load ◽  
Facial Skin ◽  
Mental Work ◽  
Temperature Changes ◽  
Mental Work Load

scholarly journals Serum Extracellular Vesicle-Derived circHIPK3 and circSMARCA5 Are Two Novel Diagnostic Biomarkers for Glioblastoma Multiforme

2021 ◽  
Vol 14 (7) ◽  
pp. 618
Author(s):  
Michele Stella ◽  
Luca Falzone ◽  
Angela Caponnetto ◽  
Giuseppe Gattuso ◽  
Cristina Barbagallo ◽  
...  
Keyword(s):  
Glioblastoma Multiforme ◽  
Roc Analysis ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Digital Pcr ◽  
Extracellular Vesicle ◽  
Size Exclusion ◽  
Circular Rnas ◽  
Diagnostic Biomarkers ◽  
Exclusion Chromatography

Glioblastoma multiforme (GBM) is the most frequent and deadly human brain cancer. Early diagnosis through non-invasive biomarkers may render GBM more easily treatable, improving the prognosis of this currently incurable disease. We suggest the use of serum extracellular vesicle (sEV)-derived circular RNAs (circRNAs) as highly stable minimally invasive diagnostic biomarkers for GBM diagnosis. EVs were isolated by size exclusion chromatography from sera of 23 GBM and 5 grade 3 glioma (GIII) patients, and 10 unaffected controls (UC). The expression of two candidate circRNAs (circSMARCA5 and circHIPK3) was assayed by droplet digital PCR. CircSMARCA5 and circHIPK3 were significantly less abundant in sEVs from GBM patients with respect to UC (fold-change (FC) of −2.15 and −1.92, respectively) and GIII (FC of −1.75 and −1.4, respectively). Receiver operating characteristic curve (ROC) analysis, based on the expression of sEV-derived circSMARCA5 and circHIPK3, allowed us to distinguish GBM from UC (area under the curve (AUC) 0.823 (0.667–0.979) and 0.855 (0.704 to 1.000), with a 95% confidence interval (CI), respectively). Multivariable ROC analysis, performed by combining the expression of sEV-derived circSMARCA5 and circHIPK3 with preoperative neutrophil to lymphocyte (NLR), platelet to lymphocyte (PLR) and lymphocyte to monocyte (LMR) ratios, three known diagnostic and prognostic GBM markers, allowed an improvement in the GBM diagnostic accuracy (AUC 0.901 (0.7912 to 1.000), 95% CI). Our data suggest sEV-derived circSMARCA5 and circHIPK3 as good diagnostic biomarkers for GBM, especially when associated with preoperative NLR, PLR and LMR.

scholarly journals Wearable robotic exoskeletons: A socio-philosophical perspective on Duchenne muscular dystrophy research

2020 ◽  
Vol 11 (1) ◽  
pp. 404-413
Author(s):  
Alexandra Kapeller ◽  
Michael H. Nagenborg ◽  
Kostas Nizamis
Keyword(s):  
Duchenne Muscular Dystrophy ◽  
Muscular Dystrophy ◽  
Disability Studies ◽  
Philosophy Of Technology ◽  
Research Projects ◽  
Philosophical Perspective ◽  
Individual Model ◽  
Engineering Sciences ◽  
The Social ◽  
The Individual

AbstractRecently, several research projects in the Netherlands have focused on the development of wearable robotic exoskeletons (WREs) for individuals with Duchenne muscular dystrophy (DMD). Such research on WREs is often treated solely within the disciplines of biomedical and mechanical engineering, overlooking insights from disability studies and philosophy of technology. We argue that mainly two such insights should receive attention: the problematization of the ableism connected to the individual model of disability and the stigmatization by assistive technology. While disability studies have largely rejected the individual model of disability, the engineering sciences seem to still locate disability in an individual’s body, not questioning their own problematization of disability. Additionally, philosophy of technology has argued that technologies are not neutral instruments but shape users’ actions and perceptions. The design of WREs may convey a message about the understanding of disability, which can be comprehended as a challenge and an opportunity: stigmatization needs to be avoided and positive views on disability can be evoked. This article aims to highlight the benefits of considering these socio-philosophical perspectives by examining the case of WREs for people with DMD and proposing design principles for WREs. These principles may enhance acceptability of WREs, not only by individuals with DMD but also by other users, and help engineers to better place their work in the social context.

Sign in / Sign up

Export Citation Format

Share Document