Validation of the LEOSound Cough Detection Algorithm

2019 ◽  
Author(s):  
Volker Gross ◽  
Patrick Fischer ◽  
Andreas Weissflog ◽  
Olaf Hildebrandt ◽  
Ulrich Koehler ◽  
...  
Keyword(s):  
Respiratory Symptom ◽  
Contingency Table ◽  
Detection Algorithm ◽  
Monitoring Systems ◽  
Lung Sound ◽  
Predictive Values ◽  
Reliable Detection ◽  
Movement Artifacts ◽  
Sensitivity Specificity ◽  
Lung Sound Monitoring

Abstract Background Cough is an important respiratory symptom being of great interest to many researchers. Up to now, most knowledge about cough has been collected through standardized questionnaires. Objective, and reliable detection of cough assessed by automated lung sound monitoring are becoming increasingly important. The aim of this study is to validate the LEOSound lung sound monitor by using previously determined and investigated COPD datasets (1,2). Methods Based on multiple recordings of 48 patients with stable COPD II-IV, we validated the cough detection algorithm of LEOSound by using a contingency table. Sensitivity, specificity, positive and negative predictive values were used as quantitative measures. Results We found the overall accuracy to be 87.3% with sensitivity and specificity of 98.7% and 80.2%, respectively. Major reasons for midsections in descending order were throat cleaning, snoring and movement artifacts. Conclusion In comparison to other full-automated cough monitoring systems, the LEOSound performs the best in sensitivity, but shows slightly poor specificity. Misdetections were mainly caused due to morphological similar noises and can be withdrawn while scanning through the recording manually.

scholarly journals Wheezing Characteristics and Predicting Reactivity to Inhaled β2-Agonist in Children for Home Medical Care

2021 ◽  
Vol 9 ◽  
Author(s):  
Chizu Habukawa ◽  
Naoto Ohgami ◽  
Takahiro Arai ◽  
Haruyuki Makata ◽  
Tomoki Nishikido ◽  
...  
Keyword(s):  
Lung Sounds ◽  
Lung Sound ◽  
Tidal Breathing ◽  
Sound Analysis ◽  
Predictive Values ◽  
Before And After ◽  
Number Frequency ◽  
Sensitivity Specificity ◽  
Β2 Agonist ◽  
Β2 Agonists

Background: Given that wheezing is treated with inhaled β2-agonists, their effect should be reviewed before the condition becomes severe; however, few methods can currently predict reactivity to inhaled β2-agonists. We investigated whether preinhalation wheezing characteristics identified by lung sound analysis can predict reactivity to inhaled β2-agonists.Methods: In 202 children aged 10–153 months, wheezing was identified by auscultation. Lung sounds were recorded for 30 s in the chest region on the chest wall during tidal breathing. We analyzed the wheezing before and after β2-agonist inhalation. Wheezing was displayed as horizontal bars of intensity defined as a wheeze power band, and the wheezing characteristics (number, frequency, and maximum intensity frequency) were evaluated by lung sound analysis. The participants were divided into two groups: non-disappears (wheezing did not disappear after inhalation) and disappears (wheezing disappeared after inhalation). Wheezing characteristics before β2-agonist inhalation were compared between the two groups.The characteristics of wheezing were not affected by body size. The number of wheeze power bands of the non-responder group was significantly higher than those of the responder group (P < 0.001). The number of wheeze power bands was a predictor of reactivity to inhaled β2-agonists, with a cutoff of 11.1. The 95% confidence intervals of sensitivity, specificity, and positive and negative predictive values were 88.8, 42, 44, and 81.1% (P < 0.001), respectively.Conclusions: The number of preinhalation wheeze power bands shown by lung sound analysis was a useful indicator before treatment. This indicator could be a beneficial index for managing wheezing in young children.

Discriminating Malignancy in Thyroid Nodules: The Nomogram Versus the Kwak and ACR TI-RADS

2020 ◽  
Vol 163 (6) ◽  
pp. 1156-1165
Author(s):  
Juan Xiao ◽  
Qiang Xiao ◽  
Wei Cong ◽  
Ting Li ◽  
Shouluan Ding ◽  
...  
Keyword(s):  
Thyroid Nodules ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Diagnostic Study ◽  
Diagnostic Efficiency ◽  
Training Set ◽  
Multivariable Logistic Regression Model ◽  
Predictive Values ◽  
Validation Set ◽  
Sensitivity Specificity

Objective To develop an easy-to-use nomogram for discrimination of malignant thyroid nodules and to compare diagnostic efficiency with the Kwak and American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Study Design Retrospective diagnostic study. Setting The Second Hospital of Shandong University. Subjects and Methods From March 2017 to April 2019, 792 patients with 1940 thyroid nodules were included into the training set; from May 2019 to December 2019, 174 patients with 389 nodules were included into the validation set. Multivariable logistic regression model was used to develop a nomogram for discriminating malignant nodules. To compare the diagnostic performance of the nomogram with the Kwak and ACR TI-RADS, the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values were calculated. Results The nomogram consisted of 7 factors: composition, orientation, echogenicity, border, margin, extrathyroidal extension, and calcification. In the training set, for all nodules, the area under the curve (AUC) for the nomogram was 0.844, which was higher than the Kwak TI-RADS (0.826, P = .008) and the ACR TI-RADS (0.810, P < .001). For the 822 nodules >1 cm, the AUC of the nomogram was 0.891, which was higher than the Kwak TI-RADS (0.852, P < .001) and the ACR TI-RADS (0.853, P < .001). In the validation set, the AUC of the nomogram was also higher than the Kwak and ACR TI-RADS ( P < .05), each in the whole series and separately for nodules >1 or ≤1 cm. Conclusions When compared with the Kwak and ACR TI-RADS, the nomogram had a better performance in discriminating malignant thyroid nodules.

scholarly journals The Impact of Narrow-band Imaging on the Pre- and Intra- operative Assessments of Neoplastic and Preneoplastic Laryngeal Lesions. A Systematic Review

2020 ◽  
Author(s):  
Carmelo Saraniti ◽  
Enzo Chianetta ◽  
Giuseppe Greco ◽  
Norhafiza Mat Lazim ◽  
Barbara Verro
Keyword(s):  
White Light ◽  
Diagnostic Tool ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Resection Margins ◽  
Predictive Values ◽  
White Light Endoscopy ◽  
Laryngeal Lesions ◽  
Sensitivity Specificity ◽  
The Impact

Introduction Narrow-band imaging is an endoscopic diagnostic tool that, focusing on superficial vascular changes, is useful to detect suspicious laryngeal lesions, enabling their complete excision with safe and tailored resection margins. Objectives To analyze the applications and benefits of narrow-band imaging in detecting premalignant and malignant laryngeal lesions through a comparison with white-light endoscopy. Data Synthesis A literature search was performed in the PubMed, Scopus and Web of Science databases using strict keywords. Then, two authors independently analyzed the articles, read the titles and abstracts, and read completely only the relevant studies according to certain eligibility criteria. In total, 14 articles have been included in the present review; the sensitivity, specificity, positive and negative predictive values, and accuracy of pre- and/or intraoperative narrow-band imaging were analyzed. The analysis showed that narrow-band imaging is better than white-light endoscopy in terms of sensitivity, specificity, positive and negative predictive values, and accuracy regarding the ability to identify cancer and/or precancerous laryngeal lesions. Moreover, the intraoperative performance of narrow-band imaging resulted more effective than the in-office performance. Conclusion Narrow-band imaging is an effective diagnostic tool to detect premalignant and malignant laryngeal lesions and to define proper resection margins. Moreover, narrow-band imaging is useful in cases of leukoplakia that may cover a possible malignant lesion and that cannot be easily assessed with white-light endoscopy. Finally, a shared, simple and practical classification of laryngeal lesions, such as that of the European Laryngological Society, is required to identify a shared lesion management strategy. Key Points

scholarly journals Predicting youth diabetes risk using NHANES data and machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nita Vangeepuram ◽  
Bian Liu ◽  
Po-hsiang Chiu ◽  
Linhua Wang ◽  
Gaurav Pandey
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Clinical Guideline ◽  
Diabetes Risk ◽  
Screening Tools ◽  
Clinical Screening ◽  
Predictive Values ◽  
Screening Guideline ◽  
Demographic Subgroups ◽  
Sensitivity Specificity

AbstractPrediabetes and diabetes mellitus (preDM/DM) have become alarmingly prevalent among youth in recent years. However, simple questionnaire-based screening tools to reliably assess diabetes risk are only available for adults, not youth. As a first step in developing such a tool, we used a large-scale dataset from the National Health and Nutritional Examination Survey (NHANES) to examine the performance of a published pediatric clinical screening guideline in identifying youth with preDM/DM based on American Diabetes Association diagnostic biomarkers. We assessed the agreement between the clinical guideline and biomarker criteria using established evaluation measures (sensitivity, specificity, positive/negative predictive value, F-measure for the positive/negative preDM/DM classes, and Kappa). We also compared the performance of the guideline to those of machine learning (ML) based preDM/DM classifiers derived from the NHANES dataset. Approximately 29% of the 2858 youth in our study population had preDM/DM based on biomarker criteria. The clinical guideline had a sensitivity of 43.1% and specificity of 67.6%, positive/negative predictive values of 35.2%/74.5%, positive/negative F-measures of 38.8%/70.9%, and Kappa of 0.1 (95%CI: 0.06–0.14). The performance of the guideline varied across demographic subgroups. Some ML-based classifiers performed comparably to or better than the screening guideline, especially in identifying preDM/DM youth (p = 5.23 × 10−5).We demonstrated that a recommended pediatric clinical screening guideline did not perform well in identifying preDM/DM status among youth. Additional work is needed to develop a simple yet accurate screener for youth diabetes risk, potentially by using advanced ML methods and a wider range of clinical and behavioral health data.

scholarly journals COVID-19 Seroprevalence among Healthcare Workers of a Large COVID-19 Hospital in Rome Reveals Strengths and Limits of Two Different Serological Tests

2021 ◽  
Vol 18 (5) ◽  
pp. 2650
Author(s):  
Giuseppe Vetrugno ◽  
Daniele Ignazio La Milia ◽  
Floriana D’Ambrosio ◽  
Marcello Di Pumpo ◽  
Roberta Pastorino ◽  
...  
Keyword(s):  
Blood Test ◽  
Healthcare Workers ◽  
Point Of Care ◽  
Venous Blood ◽  
Administrative Staff ◽  
Serological Tests ◽  
Predictive Values ◽  
Work From Home ◽  
Significant Difference ◽  
Sensitivity Specificity

Healthcare workers are at the forefront against COVID-19, worldwide. Since Fondazione Policlinico Universitario A. Gemelli (FPG) IRCCS was enlisted as a COVID-19 hospital, the healthcare workers deployed to COVID-19 wards were separated from those with limited/no exposure, whereas the administrative staff were designated to work from home. Between 4 June and 3 July 2020, an investigation was conducted to evaluate the seroprevalence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) immunoglobulin (IgG) antibodies among the employees of the FPG using point-of-care (POC) and venous blood tests. Sensitivity, specificity, and predictive values were determined with reverse-transcription polymerase chain reaction on nasal/oropharyngeal swabs as the diagnostic gold standard. The participants enrolled amounted to 4777. Seroprevalence was 3.66% using the POC test and 1.19% using the venous blood test, with a significant difference (p < 0.05). The POC test sensitivity and specificity were, respectively, 63.64% (95% confidence interval (CI): 62.20% to 65.04%) and 96.64% (95% CI: 96.05% to 97.13%), while those of the venous blood test were, respectively, 78.79% (95% CI: 77.58% to 79.94%) and 99.36% (95% CI: 99.07% to 99.55%). Among the low-risk populations, the POC test’s predictive values were 58.33% (positive) and 98.23% (negative), whereas those of the venous blood test were 92.86% (positive) and 98.53% (negative). According to our study, these serological tests cannot be a valid alternative to diagnose COVID-19 infection in progress.

scholarly journals Accuracy of the fluorescence-aided identification technique (FIT) for detecting tooth-colored restorations utilizing different fluorescence-inducing devices: an ex vivo comparative study

2021 ◽  
Author(s):  
W. Leontiev ◽  
E. Magni ◽  
C. Dettwiler ◽  
C. Meller ◽  
R. Weiger ◽  
...  
Keyword(s):  
Multivariate Analysis ◽  
Ex Vivo ◽  
Predictive Values ◽  
Composite Restorations ◽  
Significant Difference ◽  
Identification Technique ◽  
Illumination Method ◽  
Sensitivity Specificity ◽  
Entire Procedure ◽  
Higher Sensitivity

Abstract Objectives The aim of the present study was to compare the accuracy of the conventional illumination method (CONV) and the fluorescence-aided identification technique (FIT) for distinguishing between composite restorations and intact teeth using different fluorescence-inducing devices commonly used for FIT. Materials and methods Six groups of six dentists equipped with one of six different FIT systems each independently attempted to identify composite restorations and intact teeth on a full-mouth model with 22 composite restorations using CONV and, 1 h later, FIT. The entire procedure was repeated 1 week later. Sensitivity, specificity, and positive (PPV) and negative (NPV) predictive values, including 95% confidence intervals (CI), were calculated for CONV and FIT overall and for each device. The influence of examiner age, method, and device on each parameter was assessed by multivariate analysis of variance. Results The sensitivity (84%, CI 81–86%), specificity (94%, CI 93–96%), PPV (92%, CI 90–94%), and NPV (90%, CI 88–91%) of FIT was significantly higher than that of CONV (47%, CI 44–50%; 82%, CI 79–84%; 66%, CI 62–69%, and 69%, CI 68–71%, respectively; p<0.001). The differences between CONV and FIT were significant for all parameters and FIT systems except VistaCam, which achieved no significant difference in specificity. Examiners younger than 40 years attained significantly higher sensitivity and negative predictive values than older examiners. Conclusions FIT is more reliable for detecting composite restorations than the conventional illumination method. Clinical relevance FIT can be considered an additional or alternative tool for improving the detection of composite restorations.

scholarly journals Comparison of saliva with healthcare workers- and patient-collected swabs in the diagnosis of COVID-19 in a large cohort

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Mitnala Sasikala ◽  
Yelamanchili Sadhana ◽  
Ketavarapu Vijayasarathy ◽  
Anand Gupta ◽  
Sarala Kumari Daram ◽  
...  
Keyword(s):  
Healthcare Workers ◽  
Early Stage ◽  
Cost Effective ◽  
Hospitalized Patients ◽  
Detection Sensitivity ◽  
Nasopharyngeal Swab ◽  
Predictive Values ◽  
Qrt Pcr ◽  
Asymptomatic Patients ◽  
Sensitivity Specificity

Abstract Background A considerable amount of evidence demonstrates the potential of saliva in the diagnosis of COVID-19. Our aim was to determine the sensitivity of saliva versus swabs collected by healthcare workers (HCWs) and patients themselves to assess whether saliva detection can be offered as a cost-effective, risk-free method of SARS-CoV-2 detection. Methods This study was conducted in a hospital involving outpatients and hospitalized patients. A total of 3018 outpatients were tested. Of these, 200 qRT-PCR-confirmed SARS-CoV-2-positive patients were recruited for further study. In addition, 101 SARS-CoV-2-positive hospitalized patients with symptoms were also enrolled in the study. From outpatients, HCWs collected nasopharyngeal swabs (NPS), saliva were obtained. From inpatients, HCWs collected swabs, patient-collected swabs, and saliva were obtained. qRT-PCR was performed to detect SARS-CoV-2 by TAQPATH assay to determine the sensitivity of saliva detection. Sensitivity, specificity and positive/negative predictive values (PPV, NPV) of detecting SARS-CoV-2 were calculated using MedCalc. Results Of 3018 outpatients (asymptomatic: 2683, symptomatic: 335) tested by qRT-PCR, 200 were positive (males: 140, females: 60; aged 37.9 ± 12.8 years; (81 asymptomatic, 119 symptomatic). Of these, saliva was positive in 128 (64%); 39 of 81 asymptomatic (47%),89 of 119 symptomatic patients (74.8%). Sensitivity of detection was 60.9% (55.4–66.3%, CI 95%), with a negative predictive value of 36%(32.9–39.2%, CI 95%).Among 101 hospitalized patients (males:65, females: 36; aged 53.48 ± 15.6 years), with HCW collected NPS as comparator, sensitivity of saliva was 56.1% (47.5–64.5, CI 95%), specificity 63.5%(50.4–75.3, CI95%) with PPV of 77.2% and NPV of 39.6% and that of self-swab was 52.3%(44–60.5%, CI95%), specificity 56.6% (42.3–70.2%, CI95%) with PPV 77.2% and NPV29.7%. Comparison of positivity with the onset of symptoms revealed highest detection in saliva on day 3 after onset of symptoms. Additionally, only saliva was positive in 13 (12.8%) hospitalized patients. Conclusion Saliva which is easier to collect than nasopharyngeal swab is a viable alternate to detect SARS-COV-2 in symptomatic patients in the early stage of onset of symptoms. Although saliva is currently not recommended for screening asymptomatic patients, optimization of collection and uniform timing of sampling might improve the sensitivity enabling its use as a screening tool at community level.

scholarly journals Development of Machine Learning Models to Predict Probabilities and Types of Stroke at Prehospital Stage: the Japan Urgent Stroke Triage Score Using Machine Learning (JUST-ML)

2021 ◽  
Author(s):  
Kazutaka Uchida ◽  
Junichi Kouno ◽  
Shinichi Yoshimura ◽  
Norito Kinjo ◽  
Fumihiro Sakakibara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forests ◽  
Prediction Models ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Vessel Occlusion ◽  
Predictive Values ◽  
Training Cohort ◽  
Sensitivity Specificity

AbstractIn conjunction with recent advancements in machine learning (ML), such technologies have been applied in various fields owing to their high predictive performance. We tried to develop prehospital stroke scale with ML. We conducted multi-center retrospective and prospective cohort study. The training cohort had eight centers in Japan from June 2015 to March 2018, and the test cohort had 13 centers from April 2019 to March 2020. We use the three different ML algorithms (logistic regression, random forests, XGBoost) to develop models. Main outcomes were large vessel occlusion (LVO), intracranial hemorrhage (ICH), subarachnoid hemorrhage (SAH), and cerebral infarction (CI) other than LVO. The predictive abilities were validated in the test cohort with accuracy, positive predictive value, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and F score. The training cohort included 3178 patients with 337 LVO, 487 ICH, 131 SAH, and 676 CI cases, and the test cohort included 3127 patients with 183 LVO, 372 ICH, 90 SAH, and 577 CI cases. The overall accuracies were 0.65, and the positive predictive values, sensitivities, specificities, AUCs, and F scores were stable in the test cohort. The classification abilities were also fair for all ML models. The AUCs for LVO of logistic regression, random forests, and XGBoost were 0.89, 0.89, and 0.88, respectively, in the test cohort, and these values were higher than the previously reported prediction models for LVO. The ML models developed to predict the probability and types of stroke at the prehospital stage had superior predictive abilities.

scholarly journals Evaluation of HiCrome KPC Agar for the Screening of Carbapenem-Resistant Enterobacterales Colonization in the ICU Setting of a Tertiary Care Hospital

2021 ◽  
Author(s):  
Ashoka Mahapatra ◽  
K Nikitha ◽  
Sutapa Rath ◽  
Bijayini Behera ◽  
Kavita Gupta
Keyword(s):  
Tertiary Care ◽  
High Sensitivity ◽  
Care Hospital ◽  
Predictive Values ◽  
Klebsiella Pneumoniae Carbapenemase ◽  
Carbapenem Resistant ◽  
Rectal Swabs ◽  
Control And Prevention ◽  
Indian Setting ◽  
Sensitivity Specificity

Abstract Background Spread of carbapenem-resistant Enterobacterales (CRE) is a significant concern in intensive care unit (ICU) settings. Approaches to routine screening for CRE colonization in all ICU patients vary depending on institutional epidemiology and resources. The present study was aimed to evaluate the performance of HiCrome Klebsiella pneumoniae carbapenemase (KPC) agar for the detection of CRE colonization in ICU settings taking the Centers for Disease Control and Prevention (CDC) recommended method as reference. Methods Two-hundred and eighty rectal swabs (duplicate) from 140 patients were subjected to CRE detection in HiCrome KPC agar and MacConkey agar (CDC criteria). Results Using CDC method, total 41 CRE isolates were recovered comprising of 29 E scherichia coli, 11 Klebsiella, and 1 Enterobacter spp. On the other hand, 49 isolates of CRE recovered from 140 rectal swabs using HiCrome KPC agar, out of which 33 were E. coli, 15 Klebsiella, and 1 Enterobacter sp. Statistical Analysis Sensitivity, specificity, negative, and positive predictive values of CRE screening by HiCrome KPC agar were found to be 100% (91.4–100), 91.9% (84.8–95.8), 83.6% (70.9–91.4), and 100% (95.9–100), respectively, taking the CDC recommended method as reference. Conclusion HiCrome KPC agar has high sensitivity in screening CRE colonization. Further studies are needed to establish its applicability for detecting the predominant circulating carbapenemases in the Indian setting.

scholarly journals Validation of a rapid antigen test as a screening tool for SARS-CoV-2 infection in asymptomatic populations. Sensitivity, specificity and predictive values

2021 ◽  
pp. 100954
Author(s):  
Alejandro Fernandez-Montero ◽  
Josepmaria Argemi ◽  
José Antonio Rodríguez ◽  
Arturo H. Ariño ◽  
Laura Moreno-Galarraga
Keyword(s):  
Screening Tool ◽  
Antigen Test ◽  
Predictive Values ◽  
Sensitivity Specificity
Sign in / Sign up

Export Citation Format

Share Document