ERROR LOCALIZATION DIAGNOSTIC MODEL OPTIMIZATION IN DIGITAL STATE MACHINES NETWORKS

2019 ◽  
Author(s):  
Irina Bystrova ◽  
E. Danil'chuk ◽  
Boris Podkopaev
Keyword(s):  
Single Component ◽  
Diagnostic Model ◽  
State Machines ◽  
Model Optimization ◽  
Error Localization ◽  
Diagnostic Models

The problem of constructing a diagnostic model for a network S consisting of a number of digital automata is considered, provided that the diagnostic models of all network components are known. It is assumed that these models are given by systems of logical equations, and the errors to be detected are localized in any but a single component of the network.

scholarly journals Quality control stress test for deep learning-based diagnostic model in digital pathology

2021 ◽  
Author(s):  
Birgid Schömig-Markiefka ◽  
Alexey Pryalukhin ◽  
Wolfgang Hulla ◽  
Andrey Bychkov ◽  
Junya Fukuoka ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cancer Detection ◽  
Stress Testing ◽  
Computational Analysis ◽  
Stress Test ◽  
Digital Pathology ◽  
Model Performance ◽  
Diagnostic Model ◽  
Model Accuracy ◽  
Diagnostic Models

AbstractDigital pathology provides a possibility for computational analysis of histological slides and automatization of routine pathological tasks. Histological slides are very heterogeneous concerning staining, sections’ thickness, and artifacts arising during tissue processing, cutting, staining, and digitization. In this study, we digitally reproduce major types of artifacts. Using six datasets from four different institutions digitized by different scanner systems, we systematically explore artifacts’ influence on the accuracy of the pre-trained, validated, deep learning-based model for prostate cancer detection in histological slides. We provide evidence that any histological artifact dependent on severity can lead to a substantial loss in model performance. Strategies for the prevention of diagnostic model accuracy losses in the context of artifacts are warranted. Stress-testing of diagnostic models using synthetically generated artifacts might be an essential step during clinical validation of deep learning-based algorithms.

scholarly journals CEA and ADA in Pleural Fluid for Differential Malignant Pleural Effusion and Tuberculous Pleural Effusion

2021 ◽  
Author(s):  
Jianhong Yu ◽  
Qirui Cai
Keyword(s):  
Pleural Effusion ◽  
Pleural Fluid ◽  
Roc Curve ◽  
Malignant Pleural Effusion ◽  
Diagnostic Value ◽  
Diagnostic Model ◽  
Diagnostic Efficacy ◽  
Tuberculous Pleural Effusion ◽  
Diagnostic Models ◽  
Independent Risk Factors

Abstract Objective This study aimed to establish a predictive model based on the clinical manifestations and laboratory findings in pleural fluid of patients with pleural effusion for the differential diagnosis of malignant pleural effusion (MPE) and tuberculous pleural effusion (TPE). Methods Clinical data and laboratory indices of pleural fluid were collected from patients with malignant pleural effusion and tuberculous pleural effusion in Zigong First People's Hospital between January 2019 and June 2020，and were compared between the two groups. Independent risk factors or Independent protective factors for malignant pleural effusion were investigated using multivariable logistic regression analysis. Receiver operating characteristic curve (ROC) analysis was performed to assess the diagnostic performance of factors with independent effects, and combined diagnostic models were established based on two or more factors with independence effect. ROC curve was used to evaluate the diagnostic ability of each model, and the fit of the eath model was measured using Hosmer-Lemeshow goodness-of-fit test. Results Patients with MPE were older than those with TPE, the rate of fever of patients with MPE was lower than that of patients with TPE, and these differences were statistically significant (p < 0.05). Carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), cytokeratin-19 fragment antigen (CYFRA21-1), cancer antigen 125 (CA125), and glucose (GLU) levels in the pleural fluid were higher, but total protein (TP), albumin (ALB) and Adenosine deaminase (ADA) levels in the pleural fluid were lower in MPE patients than in TPE patients, and the differences were statistically significant (P<0.05). In multivariate logistic regression analysis, CEA and NSE levels in the pleural fluid were independent risk factors for MPE, whereas ADA levels in pleural fluid and fever were independent protective factors for MPE. The differential diagnostic value of pleural fluid CEA and pleural fluid ADA for MPE and TPE were higher than that of pleural fluid NSE（p<0.05） and the area under the ROC curve was 0.901, 0.892, and 0.601, respectively. Four different binary logistic diagnostic models were established based on pleural fluid CEA combined with pleural fluid NSE, pleural fluid ADA or ( and ) fever. Among them, the model established with the combination of pleural fluid CEA and pleural fluid ADA (logit (P) = 0.513 + 0.457*CEA-0.101*ADA) had the highest diagnostic value for malignant pleural effusion, and its predictive accuracy was high with an area under the ROC curve of 0.968 [95% confidence interval (0.947, 0.988)]. But the diagnostic efficacy of the diagnostic model could not be improved by adding pleural fluid NSE and fever. Conclusion The model established with the combination of CEA and ADA in the pleural fluid has a high differential diagnostic value for malignant pleural effusion and tuberculous pleural effusion, and NSE in the pleural fluid and fever cannot improve the diagnostic efficacy of the diagnostic model.

Nonparametric Decision Support Systems in Medical Diagnosis

2011 ◽  
pp. 1483-1500
Author(s):  
Steven Walczak ◽  
Bradley B. Brimhall ◽  
Jerry B. Lefkowitz
Keyword(s):  
Medical Diagnosis ◽  
Laboratory Tests ◽  
Clinical Laboratory ◽  
Predictive Performance ◽  
Diagnostic Model ◽  
Medical Problems ◽  
Diagnostic Models ◽  
Trained Neural Network ◽  
Diagnostic Capabilities ◽  
D Dimer

Patients face a multitude of diseases, trauma, and related medical problems that are difficult to diagnose and have large treatment and diagnostic direct costs, including pulmonary embolism (PE), which has mortality rates as high as 10%. Advanced decision-making tools, such as nonparametric neural networks (NN), may improve diagnostic capabilities for these problematic medical conditions. The research develops a backpropagation trained neural network diagnostic model to predict the occurrence of PE. Laboratory database values for 292 patients who were determined to be at risk for PE, with almost 15% suffering a confirmed PE, were collected and used to evaluate various NN models’ performances. Results indicate that using NN diagnostic models enables the leveraging of knowledge gained from standard clinical laboratory tests, specifically the d-dimer assay and reactive glucose, significantly improving overall positive predictive value, compared to using either test in isolation, and also increasing negative predictive performance.

Nonparametric Decision Support Systems in Medical Diagnosis

2011 ◽  
pp. 562-579
Author(s):  
Steven Walczak ◽  
Bradley B. Brimhall ◽  
Jerry B. Lefkowitz
Keyword(s):  
Medical Diagnosis ◽  
Laboratory Tests ◽  
Clinical Laboratory ◽  
Predictive Performance ◽  
Diagnostic Model ◽  
Medical Problems ◽  
Diagnostic Models ◽  
Trained Neural Network ◽  
Diagnostic Capabilities ◽  
D Dimer

Patients face a multitude of diseases, trauma, and related medical problems that are difficult to diagnose and have large treatment and diagnostic direct costs, including pulmonary embolism (PE), which has mortality rates as high as 10%. Advanced decision-making tools, such as nonparametric neural networks (NN), may improve diagnostic capabilities for these problematic medical conditions. The research develops a backpropagation trained neural network diagnostic model to predict the occurrence of PE. Laboratory database values for 292 patients who were determined to be at risk for PE, with almost 15% suffering a confirmed PE, were collected and used to evaluate various NN models’ performances. Results indicate that using NN diagnostic models enables the leveraging of knowledge gained from standard clinical laboratory tests, specifically the d-dimer assay and reactive glucose, significantly improving overall positive predictive value, compared to using either test in isolation, and also increasing negative predictive performance.

scholarly journals Deep Learning Based Syndrome Diagnosis of Chronic Gastritis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Guo-Ping Liu ◽  
Jian-Jun Yan ◽  
Yi-Qin Wang ◽  
Wu Zheng ◽  
Tao Zhong ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Practice ◽  
Chronic Gastritis ◽  
Diagnostic Model ◽  
Nonlinear Relationship ◽  
Cognitive Perspective ◽  
Multilabel Learning ◽  
Diagnostic Models ◽  
Syndrome Diagnosis ◽  
The Brain

In Traditional Chinese Medicine (TCM), most of the algorithms used to solve problems of syndrome diagnosis are superficial structure algorithms and not considering the cognitive perspective from the brain. However, in clinical practice, there is complex and nonlinear relationship between symptoms (signs) and syndrome. So we employed deep leaning and multilabel learning to construct the syndrome diagnostic model for chronic gastritis (CG) in TCM. The results showed that deep learning could improve the accuracy of syndrome recognition. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

scholarly journals SAA4 is a Diagnostic Marker to Enhance Detection Forrheumatoid Arthritis Combined with Anti-CCP

2022 ◽  
Author(s):  
Jiahui Li ◽  
Haina Liu ◽  
Bingbing Dai ◽  
Zhijun Fan ◽  
Qiao Wang ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Area Under The Curve ◽  
Density Lipoprotein ◽  
Serum Levels ◽  
Diagnostic Model ◽  
Diagnostic Efficiency ◽  
Combined Model ◽  
Specificity And Sensitivity ◽  
Diagnostic Models ◽  
In Series

Abstract Objective Serum amyloid A4 (SAA4) is an apolipoprotein that is associated with high-density lipoprotein (HDL) in plasma. In this present investigation, we appraised the potential of SAA4 as a novel diagnostic biomarker for rheumatoid arthritis (RA) combined with other established RA biomarkers, including anticitrullinated protein antibody (anti-CCP), rheumatoid factor (RF)，and C-reactive protein (CRP). Based on the correlative measures of the biomarkers, we developed a diagnostic model of RA by integrating serum levels of SAA4 with these clinical parameters. Methods A number of 316 patients were recruited in the current research. The serum levels of SAA4 were assessed by quantitative ELISA. The specificity and sensitivity of biomarkers were evaluated by using a receiver-operator curve (ROC) analysis to determine their diagnostic efficiency. Univariate and multivariate logistic regression analyses were used to screen and construct the diagnostic models for RA , consisting of diagnostic biomarkers and clinical data. A diagnostic nomogram was then generated based on logistic regression analysis results. Results The serum levels of SAA4 were considerably greatest in RA patients in comparison to other control subjects (P<0.001). Compared with anti-CCP, RF and CRP respectively, SAA4 had the highest specificity (88.60%) for diagnosing RA. The combination of SAA4 with anti-CCP could have the highest diagnostic accuracy when paired together, with highest sensitivity (91.14%) in parallel and highest specificity(98.10) in series. We successfully developed two diagnostic models: the combined model of SAA4 and anti-CCP (model A), and the combined model of SAA4, CRP, anti-CCP, RF and history of diabetes (model B). Both models showed a great area under the curve of ROC for either the training cohort or the validation cohort. The data indicated that the novel RA diagnostic models possessed an advantageous discrimination capacity and application potential. Conclusion Serum SAA4 has utility as a biomarker for RA’s diagnosis and can enhance the detection of RA when combined with anti-CCP.

scholarly journals Machine Learning for the Preliminary Diagnosis of Dementia

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Fubao Zhu ◽  
Xiaonan Li ◽  
Haipeng Tang ◽  
Zhuo He ◽  
Chaoyang Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Information Gain ◽  
Diagnostic Model ◽  
Preliminary Diagnosis ◽  
Early Stages ◽  
Item Questionnaire ◽  
Diagnostic Models ◽  
Diagnosis Of Dementia ◽  
Bayes Algorithm

Objective. The reliable diagnosis remains a challenging issue in the early stages of dementia. We aimed to develop and validate a new method based on machine learning to help the preliminary diagnosis of normal, mild cognitive impairment (MCI), very mild dementia (VMD), and dementia using an informant-based questionnaire. Methods. We enrolled 5,272 individuals who filled out a 37-item questionnaire. In order to select the most important features, three different techniques of feature selection were tested. Then, the top features combined with six classification algorithms were used to develop the diagnostic models. Results. Information Gain was the most effective among the three feature selection methods. The Naive Bayes algorithm performed the best (accuracy = 0.81, precision = 0.82, recall = 0.81, and F-measure = 0.81) among the six classification models. Conclusion. The diagnostic model proposed in this paper provides a powerful tool for clinicians to diagnose the early stages of dementia.

Methodology for synthesis of neural network diagnostic models of complex technical objects

2020 ◽  
Vol 6 (4) ◽  
pp. 466-483
Author(s):  
V. V. Grachev ◽  
◽  
A. V. Grishchenko ◽  
V. A. Kruchek ◽  
F. Yu. Bazilevsky ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Test Sample ◽  
Learning Problems ◽  
Current Status ◽  
Design Stage ◽  
Diagnostic Tools ◽  
Diagnostic Model ◽  
Technical Diagnostics ◽  
Diagnostic Models

Despite the vast experience of using the neural networks for solving various machine learning problems, the numerous attempts to use them in technical diagnostics have not yet led to complete solutions so far (with rare exceptions). The reason is the specific nature of technical diagnostics that distinguishes such tasks from traditional machine learning problems. Having analyzed these specific features, the authors propose an approach to diagnosing complex technical objects that is focused on the use in built-in diagnostics systems and is based on the neural network reference diagnostic models of functionally isolated nodes and assemblies. The article describes the methodology for the synthesis of such models, their training on the data obtained by monitoring the object being tested using built-in diagnostic tools, determining the permissible response errors, and adapting to the current status of the object. The fuzzification of the diagnostic model results using the test sample proposed in the article makes it possible to standardize the approach to diagnosing complex technical objects designed for various purposes. The use of D. Trigg’s tracking control signal proposed by the authors to monitor regression residuals during the learning increases the training quality and generalization ability of models. The value of this signal determined by the model run on a test sample is an additional informative diagnostic parameter that increases the accuracy of classifying the status of the object under test. The proposed methodology applied at the complex technical object design stage allows optimizing the monitored parameters’ array and multiplying the efficiency of the diagnostic information recorded by the built-in diagnostic and monitoring tools.

scholarly journals A Transformer Fault Diagnosis Model Using an Optimal Hybrid Dissolved Gas Analysis Features Subset with Improved Social Group Optimization-Support Vector Machine Classifier

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 1922 ◽  
Author(s):  
Jiake Fang ◽  
Hanbo Zheng ◽  
Jiefeng Liu ◽  
Junhui Zhao ◽  
Yiyi Zhang ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Social Group ◽  
Gas Analysis ◽  
Support Vector ◽  
Svm Classifier ◽  
Diagnostic Model ◽  
Dissolved Gas ◽  
Feature Sets ◽  
Diagnostic Models ◽  
Social Group Optimization

Dissolved gas analysis (DGA) is widely used to detect the incipient fault of power transformers. However, the accuracy is greatly limited by selection of DGA features and performance of fault diagnostic model. This paper proposed a fault diagnostic method integrating feature selection and diagnostic model optimization. Firstly, this paper set up three feature sets with eight basic DGA gases, 28 DGA gas ratios and 36 hybrid DGA features, respectively. Then, to eliminate the interference of weak-relevant and irrelevant features, the genetic-algorithm-SVM-feature-screen (GA-SVM-FS) model was built to screen out the optimal hybrid DGA features subset (OHFS) from three feature sets. Next, using the OHFS as the input, the support vector machine (SVM) multi-classifier optimized by ISGOSVM (SVM classifier optimized by improved social group optimization) was built to diagnose fault types of transformers. Finally, the performance of OHFS and ISGOSVM diagnostic model was tested and compared with traditional DGA features and diagnostic models, respectively. The results show that the OHFS screened out is comprised of 14 features, including 12 gas ratios and two gases. The accuracy of OHFS is 3–30% higher than traditional DGA features, and the accuracy of ISGOSVM can increase by 3% to 14% compared with the SGOSVM (SVM classifier optimized by social group optimization), GASVM (SVM classifier optimized by genetic algorithm optimization), PSOSVM (SVM classifier optimized by particle swarm optimization), and SVM diagnostic models. The proposed approach integrating the OHFS with ISGOSVM achieves the highest accuracy of fault diagnose (92.86%).

scholarly journals Development and external validation of a nomogram for neurosyphilis diagnosis among non-HIV patients: a cross-sectional study

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Wenjing Ge ◽  
Yang Zhang ◽  
Chao Peng ◽  
Dongdong Li ◽  
Lijie Gao ◽  
...  
Keyword(s):  
Point Of Care ◽  
External Validation ◽  
Cross Sectional Study ◽  
Western China ◽  
Diagnostic Model ◽  
Sectional Study ◽  
Cross Sectional ◽  
Reference Number ◽  
Diagnostic Models ◽  
Development And Validation

Abstract Background The diagnosis of neurosyphilis is challenging due to the requirement of a lumbar puncture and cerebrospinal fluid (CSF) laboratory tests. Therefore, a convenient diagnostic nomogram for neurosyphilis is warranted. This study aimed to construct diagnostic models for diagnosing neurosyphilis. Methods This cross-sectional study included data of two patient cohorts from Western China Hospital of Sichuan University between September 2015 and April 2021 and Shangjin Hospital between September 2019 and April 2021 as the development cohort and the external validation cohort, respectively. A diagnostic model using logistic regression analysis was constructed to readily provide the probability of diagnosis at point of care and presented as a nomogram. The clinical usefulness of the diagnostic models was assessed using a receiver operating characteristic (ROC) and Harrell concordance (Harrell C) index for discrimination and calibration plots for accuracy, which adopted bootstrap resampling 500 times. Results One hundred forty-eight and 67 patients were included in the development and validation cohorts, respectively. Of those, 131 were diagnosed as having reactive neurosyphilis under the criteria of positive results in both CSF treponemal and non-treponemal tests. In the development cohort, male, psychiatric behaviour disorders, and serum toluidine red unheated serum test were selected as diagnostic indicators applying a stepwise procedure in multivariable logistic model. The model reached 80% specificity, 79% sensitivity, and 0·85 area under the curves (AUC) (95% confidence interval, 0·76–0·91). In the validation cohorts, the Harrell C index for the diagnostic possibility of reactive neurosyphilis was 0·71. Conclusions A convenient model using gender, presence of psychiatric behaviour disorders, and serum TRUST titre was developed and validated to indicate diagnostic results in patients suspected of neurosyphilis. Checking the model value of factors on nomogram is a feasible way to assist clinicians and primary health servers in updating patients’ medical charts and making a quantitatively informed decision on neurosyphilis diagnosis. Trial registration This research was retrospectively registered in the Ethics committee on biomedical research, West China Hospital of Sichuan University. The research registration and committee’s reference number was 1163 in 2020 approval.

Sign in / Sign up

Export Citation Format

Share Document