scholarly journals Deep-Learning-Based Smartphone Application for Self-Diagnosis of Scleral Jaundice in Patients with Hepatobiliary and Pancreatic Diseases

2021 ◽  
Vol 11 (9) ◽  
pp. 928
Author(s):  
Joon Hyeon Park ◽  
Min Jae Yang ◽  
Ji Su Kim ◽  
Bumhee Park ◽  
Jin Hong Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Total Bilirubin ◽  
Characteristic Curve ◽  
Intraclass Correlation ◽  
Smartphone Application ◽  
Total Serum ◽  
Serum Total Bilirubin ◽  
Good Test ◽  
Good Reliability ◽  
Scleral Jaundice

Outpatient detection of total bilirubin levels should be performed regularly to monitor the recurrence of jaundice in hepatobiliary and pancreatic disease patients. However, frequent hospital visits for blood testing are burdensome for patients with poor medical conditions. This study validates a novel deep-learning-based smartphone application for the self-diagnosis of scleral jaundice in such patients. The system predicts total serum bilirubin levels using the deep-learning-based regression analysis of scleral photos taken by the smartphone’s built-in camera. Enrolled patients were randomly assigned to either the training cohort (n = 90, 1034 photos) or the validation cohort (n = 40, 426 photos). The intraclass correlation coefficient value for predicted serum total bilirubin (PSB) derived from the images repeatedly taken at the same time for the same patient showed good reliability (0.86). A strong correlation between measured serum total bilirubin (MSB) and PSB was observed in the subgroup with MSB levels ≥1.5 mg/dL (Spearman rho = 0.70, p < 0.001). The receiver operating characteristic curve for PSB showed that the area under the curve was 0.93, demonstrating good test performance as a predictor of hyperbilirubinemia (p < 0.001). Using a cut-off PSB ≥1.5, the prediction sensitivity of hyperbilirubinemia was 80.0%, with a specificity of 92.6%. Hence, the tool is effective for patient monitoring.

scholarly journals Reliability of the Polar Vantage M Sports Watch when Measuring Heart Rate at Different Treadmill Exercise Intensities

Sports ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 117
Author(s):  
Mike Climstein ◽  
Jessica L. Alder ◽  
Alyce M. Brooker ◽  
Elissa J. Cartwright ◽  
Kevin Kemp-Smith ◽  
...  
Keyword(s):  
Heart Rate ◽  
Treadmill Exercise ◽  
Intraclass Correlation ◽  
Good Test ◽  
Good Reliability ◽  
Measurement Variability ◽  
Retest Reliability ◽  
Activity Monitors ◽  
Test Retest Reliability ◽  
Standard Error Of Measurement

Background: Usage of wrist-worn activity monitors has rapidly increased in recent years, and these devices are being used by both fitness enthusiasts and in clinical populations. We, therefore, assessed the test–retest reliability of the Polar Vantage M (PVM) watch when measuring heart rate (HR) during various treadmill exercise intensities. Methods: HR was measured every 30 s (simultaneous electrocardiography (ECG) and PVM). Test–retest reliability was determined using an intraclass correlation coefficient (ICC) with 95% confidence intervals (CIs). Standard error of measurement (SEM) and smallest real difference (SRD) were used to determine measurement variability. Results: A total of 29 participants completed the trials. ICC values for PVM during stages 1, 2 and 5 demonstrated good to excellent test–retest reliability (0.78, 0.78 and 0.92; 95% CI (0.54–0.90, 0.54–0.9, 0.79–0.97)). For PVM during stages 0 (rest), 3 and 4, the ICC values indicated poor to good reliability (0.42, 0.68 and 0.58; 95% CI (−0.27–0.73, 0.32–0.85, 0.14–0.80)). Conclusion: This study identified that the test–retest reliability of the PVM was comparable at low and high exercise intensities; however, it revealed a poor to good test–retest reliability at moderate intensities. The PVM should not be used in a clinical setting where monitoring of an accurate HR is crucial to the patients’ safety.

scholarly journals Test-Retest and Interrater Reliability of the Functional Movement Screen

2013 ◽  
Vol 48 (3) ◽  
pp. 331-336 ◽  
Author(s):  
Rebecca Shultz ◽  
Scott C. Anderson ◽  
Gordon O. Matheson ◽  
Brandon Marcello ◽  
Thor Besier
Keyword(s):  
Interrater Reliability ◽  
Intraclass Correlation ◽  
Video Recording ◽  
Functional Movement Screen ◽  
Good Test ◽  
Good Reliability ◽  
Functional Movement ◽  
Retest Reliability ◽  
Test Retest Reliability ◽  
First Session

Context: The Functional Movement Screen (FMS) is a popular test to evaluate the degree of painful, dysfunctional, and asymmetric movement patterns. Despite great interest in the FMS, test-retest reliability data have not been published. Objective: To assess the test-retest and interrater reliability of the FMS and to compare the scoring by 1 rater during a live session and the same session on video. Design: Cross-sectional study. Setting: Human performance laboratory in the sports medicine center. Patients or Other Participants: A total of 21 female (age = 19.6 ± 1.5 years, height = 1.7 ± 0.1 m, mass = 64.4 ± 5.1 kg) and 18 male (age = 19.7 ± 1.0 years, height = 1.9 ± 0.1 m, mass = 80.1 ± 9.9 kg) National Collegiate Athletic Association Division IA varsity athletes volunteered. Intervention(s): Each athlete was tested and retested 1 week later by the same rater who also scored the athlete's first session from a video recording. Five other raters scored the video from the first session. Main Outcome Measure(s): The Krippendorff α (K α) was used to assess the interrater reliability, whereas intraclass correlation coefficients (ICCs) were used to assess the test-retest reliability and reliability of live-versus-video scoring. Results: Good reliability was found for the test-retest (ICC = 0.6), and excellent reliability was found for the live-versus-video sessions (ICC = 0.92). Poor reliability was found for the interrater reliability (K α = .38). Conclusions: The good test-retest and high live-versus-video session reliability show that the FMS is a usable tool within 1 rater. However, the low interrater K α values suggest that the FMS within the limits of generalization should not be used indiscriminately to detect deficiencies that place the athlete at greater risk for injury. The FMS interrater reliability may be improved with better training for the rater.

scholarly journals EXCELLENT RELIABILITY OF SEMI-QUANTITATIVE NAILFOLD CAPILLAROSCOPY IN PATIENTS WITH SYSTEMIC SCLEROSIS – A PILOT STUDY

2016 ◽  
Vol 25 (4) ◽  
pp. 194-198
Author(s):  
Ana Maria Gheorghiu ◽  
◽  
Raida Oneata ◽  
Mihai Bojinca ◽  
Rucsandra Dobrota ◽  
...  
Keyword(s):  
Systemic Sclerosis ◽  
Pilot Study ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Nailfold Capillaroscopy ◽  
Qualitative Assessment ◽  
Rater Agreement ◽  
Quality Of Data ◽  
Good Test ◽  
Good Reliability

Background. Semi-quantitative nailfold capillaroscopy (NFC) scoring represents a promising tool for assessing disease activity, severity and change in systemic sclerosis (SSc), however there is no consensus yet over which capillaroscopy abnormalities should be analyzed and how. Objective. Investigation of the reliability of the qualitative and semi-quantitative scoring of NFC assessment between two raters and test-retest for each rater in a SSc cohort. Methods. This is a single-center pilot study where 2 raters assessed the NFC images of 48 consecutive patients with SSc. Data were analyzed in 3 ways: 1. qualitatively by “normal”/“abnormal” category; 2. qualitatively by the following categories: “early”, “active”, “late” SSc patterns, “normal”, and unclassifiable in any pattern, and step; 3. Semi-quantitatively by calculating the mean score for capillary loss, disorganization of the microvascular array, giant capillaries, microhaemorrhages and capillary ramifications and combinations of giant capillaries and microhaemorrhages (as a surrogate for vascular activity). Disorganization and ramifications (surrogate for vascular damage) were also assessed. Variables for all steps were calculated for all fingers and for each finger. Inter-rater/intra-rater agreement was assessed by Cohen’s kappa coefficients for qualitative variables and by intraclass correlation coefficients (ICC) for mean score values of abnormalities. Results. Inter-rater reliability ranged from good to excellent agreement for mean score values of abnormalities in all fingers (ICC coefficients 0.745 to 0.897) and was excellent for activity (ICC coefficient of 0.923) and damage combinations (ICC coefficient of 0.918). Assessment of abnormalities in a qualitative manner (normal/abnormal or with capillaroscopy patterns) showed weaker inter-rater agreement than the semi-quantitative assessment (k coefficient <0.7). Intra-rater variability was good to excellent for mean score values of abnormalities and activity and damage combinations in all fingers and separate fingers for both raters; for qualitative assessment, only one of the raters had good test-retest reliability. Conclusion. Reliability of NFC assessment is essential in SSc trials/clinical practice to ensure quality of data. This pilot study demonstrates very good reliability between raters of the semi-quantitative NFC assessment in a SSc cohort. Combinations of NFC abnormalities had very good reliability and might be preferred because they are less time consuming.

scholarly journals Role of serum bilirubin as a marker of acute gangrenous appendicitis

2012 ◽  
Vol 1 (2) ◽  
pp. 89-92 ◽  
Author(s):  
P Ghimire ◽  
P Thapa ◽  
N Yogi ◽  
P Ghimire
Keyword(s):  
Logistic Regression ◽  
Leucocyte Count ◽  
Total Bilirubin ◽  
Serum Bilirubin ◽  
Total Bilirubin Level ◽  
Total Serum ◽  
Total Leucocyte Count ◽  
Serum Total Bilirubin ◽  
Gangrenous Appendicitis ◽  
Significant Difference

Background: This study has compared the difference in serum bilirubin between patients with gangrenous and non-gangrenous appendicitis. Methods: A prospective analytical study of, 141 patients who underwent appendectomy, from March 2010 to March 2011 in Manipal Teaching Hospital, Pokhara, Nepal was carried out. Clinico-demographic data, Alvarado’s score, total serum bilirubin, total leucocyte count and histopathological report of all the cases were collected in a prestructured proforma. Comparison between gangrenous and non-gangrenous appendicitis groups was carried out using independent sample t test, Chisquare test, and direct logistic regression. The data was analyzed using SPSS 11.6 software. Result: Around 43% (61 out of 141) patients had gangrenous appendicitis and statistically significant difference was found between the two groups in total Alvarado’s score, total count and total bilirubin level. The effect size as indicated by eta square statistics was large for total bilirubin (eta squared=0.39) as compared to total Alvarado’s score (0.09) and total leucocyte count (0.05). Direct logistic regression model showed serum total bilirubin as the only independent variable to make a unique statistically significant contribution in predicting gangrenous appendicitis. Conclusion: Pre-operative assessment of serum total bilirubin can serve as an important maker of acute gangrenous appendicitis. DOI: http://dx.doi.org/10.3126/njms.v1i2.6606 Nepal Journal of Medical Sciences. 2012;1(2): 89-92

scholarly journals Association between Daily Living Walking Speed and Walking Speed in Laboratory Settings in Healthy Older Adults

2020 ◽  
Vol 17 (8) ◽  
pp. 2707
Author(s):  
Hisashi Kawai ◽  
Shuichi Obuchi ◽  
Yutaka Watanabe ◽  
Hirohiko Hirano ◽  
Yoshinori Fujiwara ◽  
...  
Keyword(s):  
Older Adults ◽  
Walking Speed ◽  
Characteristic Curve ◽  
Intraclass Correlation ◽  
Smartphone Application ◽  
Community Dwelling ◽  
Older Individuals ◽  
Daily Lives ◽  
Adverse Health Outcomes ◽  
Average Maximum

Although there is evidence on the predictors of adverse health outcomes in older individuals, walking speed has typically been measured in laboratory settings (LWS); LWS may be distinct from individuals’ actual walking speed in their daily lives (DWS). We examined whether DWS differs from LWS among older adults, and its association with physical frailty. Participants were 90 community-dwelling older adults. A five-meter normal (LWSnor) and maximum (LWSmax) walking speed was measured with a stopwatch. DWS was measured using a global positioning system-related smartphone application for one month during their daily lives. DWSavr, DWSmax, and DWSsd were defined as the average, maximum, and standard deviation of walking speed for one month. Participants’ mean DWSavr and DWSmax were 1.28 m/s and 2.14 m/s, respectively, significantly slower than the mean LWSnor (1.42 m/s) and LWSmax (2.24 m/s); the intraclass correlation coefficient between DWS and LWS were 0.188 to 0.341. DWS was significantly correlated with grip strength, one-legged stance, and LWS. The area under the receiver operating characteristic curve of DWSsd concerning pre-frailty was largest among DWSs, at 0.615, while that of LWSnor was 0.643. The findings suggest that DWS differs from LWS and is associated with physical function and pre-frailty.

scholarly journals The Determination of Total Serum Bilirubin Concentration in Type 2 Diabetes patients

2021 ◽  
Keyword(s):  
Type 2 Diabetes ◽  
Total Bilirubin ◽  
Serum Bilirubin ◽  
Total Serum Bilirubin ◽  
Total Serum ◽  
Diabetic Patients ◽  
Serum Total Bilirubin ◽  
Elevated Concentration ◽  
Significant Difference

Bilirubin represent a natural end-product of heme metabolism and is used as as a marker in diagnosis off hepatobiliary diseases. Recent studies demonstrated that serum bilirubin levels are related to the risk of Type 2 diabetes mellitus (T2D) development and subsequent complications. The aim of this study was to analyzed serum total bilirubin concentrations and its relationship with biochemical and clinical characteristics in T2D patients. Total of 109 participants were included in this study, 54 controls and 55 diabetic patients, both gender, while ages ranged from 35 to 70 years. Biochemical parameters were analyzed by standard IFCC methods while serum total bilirubin concentrations was determined by the method of Jendrassik/Gróf. All analyses and measurements were provided by using the chemical analyzer VITROS 350. Results showed a significant difference in concentrations of glucose, glycated hemoglobin (HbA1c), lipid profile (total cholesterol, triglycerides, HDL cholesterol, LDL cholesterol) and bilirubin between T2D patients and controls (p<0.05). Also, significant association was found between bilirubin and glucose concentrations in two investigated populations (p<0.05). It appears that elevated concentration of bilirubin and biochemical characteristics are associated with the progression development of Type 2 diabetes and its related vascular complications. Therefore, total serum bilirubin concentrations could be used as potential T2D biomarker and therefore, as new therapeutic target.

scholarly journals Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ling-Ping Cen ◽  
Jie Ji ◽  
Jian-Wei Lin ◽  
Si-Tong Ju ◽  
Hong-Jie Lin ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Efficiency ◽  
Characteristic Curve ◽  
Weighted Average ◽  
Age Related Macular Degeneration ◽  
Learning Platform ◽  
Age Related ◽  
Public Data ◽  
Primary Test ◽  
Retinal Fundus

AbstractRetinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

scholarly journals Development and Verification of a Deep Learning Algorithm to Evaluate Small-Bowel Preparation Quality

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1127
Author(s):  
Ji Hyung Nam ◽  
Dong Jun Oh ◽  
Sumin Lee ◽  
Hyun Joo Song ◽  
Yun Jeong Lim
Keyword(s):  
Deep Learning ◽  
Small Bowel ◽  
Scoring System ◽  
Operating Characteristic ◽  
Clinical Evidence ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
External Validation ◽  
Test Results ◽  
Deep Learning Algorithm

Capsule endoscopy (CE) quality control requires an objective scoring system to evaluate the preparation of the small bowel (SB). We propose a deep learning algorithm to calculate SB cleansing scores and verify the algorithm’s performance. A 5-point scoring system based on clarity of mucosal visualization was used to develop the deep learning algorithm (400,000 frames; 280,000 for training and 120,000 for testing). External validation was performed using additional CE cases (n = 50), and average cleansing scores (1.0 to 5.0) calculated using the algorithm were compared to clinical grades (A to C) assigned by clinicians. Test results obtained using 120,000 frames exhibited 93% accuracy. The separate CE case exhibited substantial agreement between the deep learning algorithm scores and clinicians’ assessments (Cohen’s kappa: 0.672). In the external validation, the cleansing score decreased with worsening clinical grade (scores of 3.9, 3.2, and 2.5 for grades A, B, and C, respectively, p < 0.001). Receiver operating characteristic curve analysis revealed that a cleansing score cut-off of 2.95 indicated clinically adequate preparation. This algorithm provides an objective and automated cleansing score for evaluating SB preparation for CE. The results of this study will serve as clinical evidence supporting the practical use of deep learning algorithms for evaluating SB preparation quality.

scholarly journals Accuracy of New Deep Learning Model-Based Segmentation and Key-Point Multi-Detection Method for Ultrasonographic Developmental Dysplasia of the Hip (DDH) Screening

Diagnostics ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1174
Author(s):  
Si-Wook Lee ◽  
Hee-Uk Ye ◽  
Kyung-Jae Lee ◽  
Woo-Young Jang ◽  
Jong-Ha Lee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Intraclass Correlation ◽  
Alpha Angle ◽  
Learning Model ◽  
Developmental Dysplasia ◽  
Human Observer ◽  
Intraobserver Variability ◽  
Cad System ◽  
Deep Learning Model ◽  
Dysplasia Of The Hip

Hip joint ultrasonographic (US) imaging is the golden standard for developmental dysplasia of the hip (DDH) screening. However, the effectiveness of this technique is subject to interoperator and intraobserver variability. Thus, a multi-detection deep learning artificial intelligence (AI)-based computer-aided diagnosis (CAD) system was developed and evaluated. The deep learning model used a two-stage training process to segment the four key anatomical structures and extract their respective key points. In addition, the check angle of the ilium body balancing level was set to evaluate the system’s cognitive ability. Hence, only images with visible key anatomical points and a check angle within ±5° were used in the analysis. Of the original 921 images, 320 (34.7%) were deemed appropriate for screening by both the system and human observer. Moderate agreement (80.9%) was seen in the check angles of the appropriate group (Cohen’s κ = 0.525). Similarly, there was excellent agreement in the intraclass correlation coefficient (ICC) value between the measurers of the alpha angle (ICC = 0.764) and a good agreement in beta angle (ICC = 0.743). The developed system performed similarly to experienced medical experts; thus, it could further aid the effectiveness and speed of DDH diagnosis.

Sign in / Sign up

Export Citation Format

Share Document