scholarly journals Keratoconus Diagnosis: Validation of a Novel Parameter Set Derived from IOP-Matched Scenario

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Dan Lin ◽  
Lei Tian ◽  
Shu Zhang ◽  
Like Wang ◽  
Ying Jie ◽  
...  
Keyword(s):  
Confounding Factor ◽  
Validation Dataset ◽  
Training Set ◽  
Biomechanical Parameter ◽  
Comparable Performance ◽  
Forward Logistic Regression ◽  
Biomechanical Evaluation ◽  
Biomechanical Parameters ◽  
Loading Parameter ◽  
Important Confounding Factor

Purpose. Considering that intraocular pressure (IOP) is an important confounding factor in corneal biomechanical evaluation, the notion of matching IOP should be introduced to eliminate any potential bias. This study aimed to assess the capability of a novel parameter set (NPS) derived from IOP-matched scenario to diagnose keratoconus. Methods. Seventy samples (training set; 35 keratoconus and 35 normal corneas; pairwise matching for IOP) were used to determine NPS by forward logistic regression. A large validation dataset comprising 62 matching samples (31 keratoconus and 31 normal corneas) and 203 unmatching samples (112 keratoconus and 91 normal corneas) was used to evaluate its clinical significance. To further assess its diagnosis capability, NPS was compared with the other two prior biomechanical indexes. Results. NPS was comprised of three biomechanical parameters, namely, DA Ratio Max 1 mm (DRM1), the first applanation time (AT1), and an energy loading parameter (Eload). NPS was successfully applied to the validation dataset, with a higher accuracy of 96.8% and 95.6% in the IOP-matched and -unmatched scenarios, respectively. More surprisingly, accuracy of NPS was 95.5% in the combined validation, an improvement compared to the two prior biomechanical indexes. Conclusions. This is the first study taking IOP bias into consideration to determine a biomechanical parameter set. Our study shows that NPS indeed offers comparable performance in keratoconus diagnosis. Translational Relevance. Determining a parameter set after eliminating the influence from IOP is useful in revealing the essential differences between keratoconus and normal corneas and possibly facilitating further progress in keratoconus diagnosis.

scholarly journals Validating Physiological and Biomechanical Parameters during Intermittent Swimming at Speed Corresponding to Lactate Concentration of 4 mmol·L−1

Sports ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 23
Author(s):  
Gavriil G. Arsoniadis ◽  
Ioannis S. Nikitakis ◽  
Petros G. Botonis ◽  
Ioannis Malliaros ◽  
Argyris G. Toubekis
Keyword(s):  
Blood Lactate ◽  
Perceived Exertion ◽  
Lactate Concentration ◽  
Blood Lactate Concentration ◽  
Constant Speed ◽  
Rating Of Perceived Exertion ◽  
Training Set ◽  
Front Crawl ◽  
Stroke Length ◽  
Biomechanical Parameters

Background: Physiological and biomechanical parameters obtained during testing need validation in a training setting. The purpose of this study was to compare parameters calculated by a 5 × 200-m test with those measured during an intermittent swimming training set performed at constant speed corresponding to blood lactate concentration of 4 mmol∙L−1 (V4). Methods: Twelve competitive swimmers performed a 5 × 200-m progressively increasing speed front crawl test. Blood lactate concentration (BL) was measured after each 200 m and V4 was calculated by interpolation. Heart rate (HR), rating of perceived exertion (RPE), stroke rate (SR) and stroke length (SL) were determined during each 200 m. Subsequently, BL, HR, SR and SL corresponding to V4 were calculated. A week later, swimmers performed a 5 × 400-m training set at constant speed corresponding to V4 and BL-5×400, HR-5×400, RPE-5×400, SR-5×400, SL-5×400 were measured. Results: BL-5×400 and RPE-5×400 were similar (p > 0.05), while HR-5×400 and SR-5×400 were increased and SL-5×400 was decreased compared to values calculated by the 5 × 200-m test (p < 0.05). Conclusion: An intermittent progressively increasing speed swimming test provides physiological information with large interindividual variability. It seems that swimmers adjust their biomechanical parameters to maintain constant speed in an aerobic endurance training set of 5 × 400-m at intensity corresponding to 4 mmol∙L−1.

scholarly journals Validating Physiological and Biomechanical Parameters During Intermittent Swimming at Speed Corresponding to Lactate Concentration of 4 mmol/L

Proceedings ◽  
2019 ◽  
Vol 25 (1) ◽  
pp. 15
Author(s):  
Arsoniadis ◽  
Nikitakis ◽  
Botonis ◽  
Malliaros ◽  
Toubekis
Keyword(s):  
Blood Lactate ◽  
Lactate Concentration ◽  
Blood Lactate Concentration ◽  
Constant Speed ◽  
Maximum Speed ◽  
Swimming Training ◽  
Training Set ◽  
Front Crawl ◽  
Stroke Length ◽  
Biomechanical Parameters

AIM: progressively increasing swimming speed test (5 × 200 m) is used to calculate the speed corresponding to blood lactate concentration of 4 mmol/L (V4) and related physiological and biomechanical parameters. The purpose of this study was to compare the calculated by a 5 × 200-m test parameters with those obtained during an intermittent swimming training set (5 × 400-m) performed at constant speed corresponding to V4. MATERIAL & METHOD: Twelve competitive male swimmers (age, 19 ± 2 years; height, 178 ± 8 cm; body mass, 74.4 ± 10.1 kg) performed a 5 × 200-m front crawl test reaching maximum speed in the last effort. Blood lactate concentration (BL) was measured after each 200 m, and heart rate (HR), stroke rate (SR), and stroke length (SL) were determined during each 200 m. V4 was calculated by interpolation using the individual speed vs. BL, and subsequently HR, SR, SL corresponding to V4 were calculated (HR-V4, SR-V4, SL-V4). One week later, swimmers performed 5 × 400-m at constant speed corresponding to V4. During the 5 × 400-m test, BL (BL-5 × 400) was measured after the 1st, 3rd and 5th repetitions, while HR (HR-5 × 400) was recorded continuously. SR and SL were measured in each 400-m repetition, and mean values were calculated (SR-5 × 400 and SL-5 × 400). RESULTS: V4 and HR-V4 were not different from speed and HR-5 × 400 during the 5 × 400-m test (1.30 ± 0.10 vs. 1.29 ± 0.10 m/s; 160 ± 14 vs. 166 ± 13 b/min, both p > 0.05). BL-5 × 400 was not different from 4 mmol/L (4.9 ± 2.6 mmol/L, p > 0.05). SR was increased and SL was decreased during 5 × 400 m compared to the values corresponding to V4 (SR-V4, 28.9 ± 3.8 vs. SR-5 × 400, 34.5 ± 3.4 strokes/min; SL-V4, 2.38 ± 0.33 vs. SL-5 × 400, 2.25 ± 0.30 m/cycle, both p < 0.05). A Bland-and-Altman plot indicated agreement between variables obtained by the 5 × 200-m and 5 × 400-m tests but with great range of variation (bias: BL, −1.0 ± 2.6 mmol/L; HR, −7 ± 12 b/min; SR, −5.6 ± 3.3 strokes/min; SL, 0.13 ± 0.09 m/cycle). CONCLUSIONS: An intermittent, with progressively increasing speed, swimming test provides physiological information to coaches to apply during an intermittent constant-speed swimming training set at intensity corresponding to BL of 4 mmol/L with large inter-individual variability. It seems that the 5 × 200-m test does not provide valid results for the biomechanical parameters.

scholarly journals Label Noise Cleaning with an Adaptive Ensemble Method Based on Noise Detection Metric

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6718
Author(s):  
Wei Feng ◽  
Yinghui Quan ◽  
Gabriel Dauphin
Keyword(s):  
Majority Vote ◽  
Ensemble Method ◽  
Validation Dataset ◽  
Ensemble Classifiers ◽  
Noise Detection ◽  
K Nearest Neighbor ◽  
Training Set ◽  
Label Noise ◽  
Vote Method ◽  
Real World Datasets

Real-world datasets are often contaminated with label noise; labeling is not a clear-cut process and reliable methods tend to be expensive or time-consuming. Depending on the learning technique used, such label noise is potentially harmful, requiring an increased size of the training set, making the trained model more complex and more prone to overfitting and yielding less accurate prediction. This work proposes a cleaning technique called the ensemble method based on the noise detection metric (ENDM). From the corrupted training set, an ensemble classifier is first learned and used to derive four metrics assessing the likelihood for a sample to be mislabeled. For each metric, three thresholds are set to maximize the classifying performance on a corrupted validation dataset when using three different ensemble classifiers, namely Bagging, AdaBoost and k-nearest neighbor (k-NN). These thresholds are used to identify and then either remove or correct the corrupted samples. The effectiveness of the ENDM is demonstrated in performing the classification of 15 public datasets. A comparative analysis is conducted concerning the homogeneous-ensembles-based majority vote method and consensus vote method, two popular ensemble-based label noise filters.

scholarly journals Diabetes mellitus is not a risk factor for osteoarthritis

RMD Open ◽  
2020 ◽  
Vol 6 (1) ◽  
pp. e001030 ◽  
Author(s):  
Andrew Khor ◽  
Cheryl-Ann Ma ◽  
Cassandra Hong ◽  
Laura Li-Yao Hui ◽  
Ying Ying Leung
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factor ◽  
Web Of Science ◽  
Confounding Factor ◽  
Meta Analysis ◽  
Analysis Model ◽  
Cross Sectional ◽  
Increased Risk ◽  
Analysis Models ◽  
Important Confounding Factor

BackgroundAssociation between diabetes mellitus (DM) and risk of osteoarthritis (OA) can be confounded by body mass index (BMI), a strong risk factor for both conditions. We evaluate the association between DM or hyperglycaemia with OA using systematic review and meta-analysis.MethodsWe searched PubMed and Web of Science databases in English for studies that gave information on the association between DM and OA. Two meta-analysis models were conducted to address: (1) risk of DM comparing subjects with and without OA and (2) risk of OA comparing subjects with and without DM. As far as available, risk estimates that adjusted for BMI were used.Results31 studies with a pooled population size of 295 100 subjects were reviewed. 16 and 15 studies reported positive associations and null/ negative associations between DM and OA. 68.8% of positive studies had adjusted for BMI, compared with 93.3% of null/negative studies. In meta-analysis model 1, there was an increase prevalence of DM in subjects with OA compared with those without (OR 1.56, 95% CI 1.28 to 1.89). In meta-analysis model 2, there was no increased risk of OA (OR 1.14, 95% CI 0.98 to 1.33) in subjects with DM compared with those without, regardless of gender and OA sites. Comparing subjects with DM to those without, an increased risk of OA was noted in cross-sectional studies, but not in case-control and prospective cohort studies.ConclusionsThis meta-analysis does not support DM as an independent risk factor for OA. BMI was probably the most important confounding factor.

scholarly journals Evaluation of Corneal Topography and Biomechanical Parameters after Use of Systemic Isotretinoin in Acne Vulgaris

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Yusuf Yildirim ◽  
Onur Olcucu ◽  
Alper Agca ◽  
Cengiz Alagoz ◽  
Ali Demircan ◽  
...  
Keyword(s):  
Acne Vulgaris ◽  
Corneal Thickness ◽  
Asymmetry Index ◽  
Corneal Topography ◽  
End Of Treatment ◽  
Biomechanical Evaluation ◽  
Oral Isotretinoin ◽  
Biomechanical Parameters ◽  
Thickness Measurements ◽  
Ultrasonic Pachymetry

Purpose. We report the effect of isotretinoin on corneal topography, corneal thickness, and biomechanical parameters in patients with acne vulgaris.Method. Fifty-four eyes of 54 patients who received oral isotretinoin for treatment of acne vulgaris were evaluated. All patients underwent a corneal topographical evaluation with a Scheimpflug camera combined with Placido-disk (Sirius), ultrasonic pachymetry measurements, and corneal biomechanical evaluation with an ocular response analyzer at baseline, in the 1st, 3rd, and 6th months of treatment, and 6 months after isotretinoin discontinuation.Results. The thinnest corneal thickness measured with Sirius differed significantly in the 1st, 3rd, and 6th months compared with the baseline measurement; there was no significant change in ultrasonic central corneal thickness measurements and biomechanical parameters (corneal hysteresis and corneal resistance factor) throughout the study. Average simulated keratometry and surface asymmetry index increased significantly only in the first month of treatment according to the baseline. All changes disappeared 6 months after the end of treatment.Conclusion. Basal tear secretion and corneal morphologic properties were significantly influenced during the systemic isotretinoin treatment and the changes were reversible after discontinuation. No statistical important biomechanical differences were found to be induced by isotretinoin.

scholarly journals Microfluidic Droplet Detection via Region-Based and Single-Pass Convolutional Neural Networks with Comparison to Conventional Image Analysis Methodologies

2021 ◽  
Author(s):  
Gregory Rutkowski ◽  
Ilgar Azizov ◽  
Evan Unmann ◽  
Marcin Dudek ◽  
Brian Arthur Grimes
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
Data Gathering ◽  
Image Data ◽  
Validation Dataset ◽  
Detection Accuracy ◽  
Microfluidic Systems ◽  
Training Set ◽  
Analysis Pipeline

As the complexity of microfluidic experiments and the associated image data volumes scale, traditional feature extraction approaches begin to struggle at both detection and analysis pipeline throughput. Deep-neural networks trained to detect certain objects are rapidly emerging as data gathering tools that can either match or outperform the analysis capabilities of the conventional methods used in microfluidic emulsion science. We demonstrate that various convolutional neural networks can be trained and used as droplet detectors in a wide variety of microfluidic systems. A generalized microfluidic droplet training and validation dataset was developed and used to tune two versions of the You Only Look Once (YOLOv3/YOLOv5) model as well as Faster R-CNN. Each model was used to detect droplets in mono- and polydisperse flow cell systems. The detection accuracy of each model shows excellent statistical symmetry with an implementation of the Hough transform as well as relevant ImageJ plugins. The models were successfully used as droplet detectors in non-microfluidic micrograph observations, where these data were not included in the training set. The models outperformed the traditional methods in more complex, porous-media simulating chip architectures with a significant speedup to per-frame analysis times. Implementing these neural networks as the primary detectors in these microfluidic systems not only makes the data pipelining more efficient, but opens the door for live detection and development of autonomous microfluidic experimental platforms. <br>

scholarly journals Toward Accelerated Training of Parallel Support Vector Machines Based on Voronoi Diagrams

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1605
Author(s):  
Cesar Alfaro ◽  
Javier Gomez ◽  
Javier M. Moguerza ◽  
Javier Castillo ◽  
Jose I. Martinez
Keyword(s):  
Support Vector Machines ◽  
Data Exchange ◽  
Smart Cities ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Training Set ◽  
Vector Machines ◽  
Comparable Performance ◽  
Novel Method ◽  
Classification Tasks

Typical applications of wireless sensor networks (WSN), such as in Industry 4.0 and smart cities, involves acquiring and processing large amounts of data in federated systems. Important challenges arise for machine learning algorithms in this scenario, such as reducing energy consumption and minimizing data exchange between devices in different zones. This paper introduces a novel method for accelerated training of parallel Support Vector Machines (pSVMs), based on ensembles, tailored to these kinds of problems. To achieve this, the training set is split into several Voronoi regions. These regions are small enough to permit faster parallel training of SVMs, reducing computational payload. Results from experiments comparing the proposed method with a single SVM and a standard ensemble of SVMs demonstrate that this approach can provide comparable performance while limiting the number of regions required to solve classification tasks. These advantages facilitate the development of energy-efficient policies in WSN.

scholarly journals Creating cartoons to represent habitual leg movements

2020 ◽  
Vol 78 (3) ◽  
pp. 139-142
Author(s):  
Karla CARLOS ◽  
Eleida Pereira CAMARGO ◽  
Mayara Menezes do MOINHO ◽  
Amanda Moraes de Paula SOUZA ◽  
Melissa Haruka KUROIWA ◽  
...  
Keyword(s):  
Confounding Factor ◽  
Pathological Condition ◽  
Behavioral Pattern ◽  
Video Footage ◽  
Graphic Representations ◽  
Combined Movements ◽  
Per Se ◽  
Important Confounding Factor ◽  
Leg Movements

Abstract Many people have a habit of moving their legs and believe that this behavior is due to the restless legs syndrome (RLS), a highly prevalent neurological condition that greatly impairs the quality of life of affected individuals. This behavioral pattern, characterized by the habit of moving one’s legs and feet, may be an important confounding factor in the diagnosis of RLS. Objective: To describe the main movements associated with this benign behavioral state to characterize a possible clinical condition that can contribute to the differential diagnosis of RLS. Methods: Experienced sleep specialists, who primarily see RLS patients listed the most frequent movements people without RLS report while describing their suspected RLS. We first compiled a list of the lower-limb movements described by the specialists. Then, one of the authors (KC) carried out all movements of the list on camera to obtain a video footage. This footage was sent to one of the authors, EPC, who, alongside a group of students, drew graphic representations (cartoons) of the recorded movements. Results: The panel of sleep experts described 13 leg movements commonly reported by their patients. The experts reported 11 simple movements and two combined movements. Conclusion: In this study we developed an instrument that allows us to oppose and distinguish a pathological condition (RLS) from a behavioral phenomenon. This state of behavioral leg fidgeting needs to be better characterized and may eventually be recognized as a clinical entity per se.

scholarly journals Development and internal validation of a wasp severity score to assess severity and indicate blood purification in persons with Asian wasp stings

2021 ◽  
Author(s):  
Yong Liu ◽  
Hongmei Shu ◽  
Youlin Long ◽  
Xiaoqin Nie ◽  
Hongfu Tang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Severity Score ◽  
Medical Intervention ◽  
Blood Purification ◽  
Validation Dataset ◽  
Early Assessment ◽  
Training Set ◽  
Wasp Sting ◽  
Wasp Stings

Abstract Background In recent years, the incidence of wasp sting has increased annually in China. Organ damage and high mortality due to mass wasp envenomation remain major challenges. Timely and appropriate medical intervention can improve survival. However, there are currently no normalized tools for early assessment of severity. Methods The clinical data of wasp sting patients hospitalized from 2011 to 2019 were used as a training set. Logistic regression was used to explore major risk factors for the development of a severe case of wasp stings (SC). The Wasp Sting Severity Score (WSS) was determined considering these risk factors to identify SCs and was tested in a validation dataset that was prospectively collected in 2020. Results The data of 1131 wasp sting patients from 2011–2019 were included in the training set. Logistic regression analysis showed that tea-colored urine (TCU), number of stings, and lactate dehydrogenase (LDH) and total bilirubin (TBIL) levels were risk factors for developing a SC. The WSS was developed considering these four risk factors, and the total possible WSS was 20 points. The WSS was tested using the validation dataset, comprising the data of 153 patients, in 2020, and we found that a WSS ≥3 points was an important indication for blood purification, with a sensitivity of 71.9%, specificity of 92.6% and an area under the curve (AUC) of 0.918 (95% CI 0.873–0.962). Among patients with more than 30 stings, mortality in those who underwent plasma exchange (PE) within 24 hours after admission was significantly lower than that in those who did not receive PE treatment (14.3% vs. 46.9%, P = 0.003). However, continuous venovenous hemofiltration (CVVH) (P = 0.317) and hemoperfusion (HP) (P = 0.869) did not significantly reduce mortality. Conclusions Patients with WSS scores ≥ 3 should be considered for blood purification as early as possible in addition to routine treatment. In addition, PE is better than CVVH and HP at reducing mortality in patients suffering from severe wasp stings.

Sign in / Sign up

Export Citation Format

Share Document