False Predictive Value Research Articles

Deep learning‐based robust hybrid approaches for brain tumor classification in magnetic resonance images

AbstractThe classification of brain images is an immensely challenging task and one of the most valuable and frequently employed procedures in the field of medical diagnostics. Deep Learning (DL), which falls under the umbrella of artificial intelligence, has introduced novel techniques for automated analysis of medical images. The objective of this study was to develop two hybrid DL models for the segmentation and classification of brain magnetic resonance imaging (MRI) data. The first hybrid model combines fully convolutional networks (FCNs) and residual networks (ResNets) for both segmentation and classification purposes. The second model is a hybrid of SegNet for segmentation and MobileNet for classification. Rest assured, it will provide you with a dependable and promising performance. The analysis was conducted on a labeled dataset comprising images of glioma, meningioma, pituitary, and no‐tumor cases. Python was utilized to implement the aforementioned hybrid models. The proposed models achieved remarkable accuracies of 93.9% and 91.3%, respectively, when evaluated on a brain tumor MRI dataset. Additionally, a comprehensive evaluation of the proposed models was conducted, comparing them with other existing hybrid models in terms of metrics such as the dice score, Jaccard index, positive predictive value (PPV), false predictive value (FPV), testing time, precision, recall, specificity, and F1 score. The results demonstrated that the proposed DL technique can significantly assist doctors and radiologists in the early detection of brain tumor cells.

Accompanying a semi-nested PCR assay to support histopathology findings of fungal keratitis in formalin-fixed paraffin-embedded corneal samples.

Fungal species are responsible for 40%-50% of all microbial keratitis cases. Due to the low amount of extracted DNA in ocular Formalin-fixed Paraffin-embedded (FFPE) samples, selecting a reliable molecular method is a substantial issue in this field. Sixty-six samples were collected via the penetrating keratoplasty (PK) technique. Histopathology assays were performed using hematoxylin-eosin (H&E) and periodic acid Schiff (PAS) staining methods. The ITS1/ITS4 and ITS1/ITS2 primer pairs were used in a semi-nested polymerase chain reaction (PCR) to target the universal internal transcribed spacer (ITS) region. Some PCR results were validated through sequencing. Fungal DNA was detected in 44 of 66 samples (66.7%), and histopathology was positive for 41 of 66 samples (62.1%). Of 41 histopathologically proven fungal-positive cases, 39 were PCR-positive (95%). Moreover, of 44 PCR-positive samples, 39 (88.6%) were histopathology-positive, and 5 (11.3%) were histopathology-negative. Totally in 39 cases (59%), both histopathology and PCR yielded positive results. The Kappa agreement rate between the two diagnostic methods, including histopathology and PCR, was 0.77. Sensitivity, specificity, positive predictive value, and false predictive value were reported as 88.64%, 90.9%, 95.12%, and 80%, respectively. As we reached the acceptable Kappa agreement rate, we concluded that applying the semi-nested PCR assay is a promising method for supporting the evidence by histopathology. Finally, we suggest targeting more specific gene regions using primer pairs that amplify smaller amplicon sizes and surveying novel molecular methods such as NGS to achieve higher sensitivity and Kappa agreement rates.

Suggested methods for prediction using semiparametric regression function

Ferritin is a key organizer of protected deregulation, particularly below risky hyperferritinemia, by straight immune-suppressive and pro-inflammatory things. We conclude that there is a significant association between levels of ferritin and the harshness of COVID-19. In this paper, we introduce a semi-parametric method for prediction by making a combination of NN and regression models. So, two methodologies are adopted, Neural Network (NN) and regression model in designing the model;the data was collected from a nursing home hospital for period 11/7/2021-23/7/2021, the sample size is 100 covid positive patients with 12 females & 38 males out of 50, while 26 female & 24 male are non-COVID out of 50. The input variables of the NN model are identified as the ferritin and a gender variable. The higher results precision is attained by the multilayer perceptron (MLP) networks when we applied the explanatory variables as the inputs with one hidden layer, which covers 3 neurons, as the planned many hidden layers are with one output of the fitting NN model which is used in stages of training and validation beside the actual data. We used a portion of the actual data to verify the behavior of the developed models, we find out that only one observation is a false predictive value. This means that the estimation model has significant parameters to forecast the type of Covid cases (Covid or no Covid). © 2021, Semnan University, Center of Excellence in Nonlinear Analysis and Applications. All rights reserved.

The Atopy Index Inventory: A Brief and Simple Tool to Identify Atopic Patients

Introduction: Atopy and ear, nose and throat (ENT) diseases are frequently associated; however, no clinical tool has been proposed so far to discriminate which patients could be atopic and therefore deserving of a further immunoallergological evaluation. Objective: The aim of this study was to assess and validate a set of dichotomous responses suitable for predicting the presence of atopy in adult patients. Methods: An 11-item questionnaire, i.e., the Atopy Index Inventory (AII), comprised of 4 questions regarding the clinical history for allergic disease and 7 questions evaluating the presence of the most frequent clinical signs affecting allergic patients, was developed and administered to 226 adult subjects (124 atopic subjects and 102 healthy, not atopic subjects). The atopic condition was proven by an immunoallergological evaluation according to the diagnostic criteria of the EAACI guidelines. Internal consistency and clinical validity were tested. Results: In healthy subjects, the first 4 variables of the AII returned a 100% correct response (all answered “no”) and were defined as “decisive” responses. In the logistic regression analysis, when decisive items were negative, the atopic condition was confirmed when answering “yes” to at least 3 “probability” items (cut-off = 2.69). The difference in AII scores between allergic and healthy group was significant using the Mann-Whitney U test (p < 0.0001). The sensitivity and specificity of the AII were 0.97 and 0.91, respectively, with a true predictive value of 0.92 and a false predictive value of 0.97. The ROC curve showed an area of 0.94, with an OR of 0.88 (95% CI 0.87–0.97, p = 0.0001). The internal consistency as determined by the Cronbach α coefficient was 0.88. Conclusion: The AII has been proven to be a brief, simple and sufficiently accurate tool for screening ENT patients in search of atopic individuals and to allow their clinical management.

Neurophysiologic Monitoring

Neurophysiologic monitoring is a diverse group of instruments that are used to monitor the central and peripheral nervous system during surgical procedures. Some are used to monitor anesthetic depth, whereas others are used by neurologists to monitor the integrity of the nervous system during surgical procedure. The goal of neurophysiologic monitoring is to have reliable, reproducible, and predictive monitors that can identify impending compromise to the neurologic system (or anesthetic) with minimal false predictive value and high positive predictive value. This allows for the identification of neurologic tissues by location and type that are at risk of compromise by vascular and/or mechanical injury. This review contains 3 figures, 8 tables, and 34 references. Key Words: auditory evoked potentials, bispectral index monitor, electrocorticography, electroencephalography, electromyographic monitoring, M-ENTROPY, motor evoked potentials, narcotrend index, sensory evoked potentials, spectral analysis

Neighborhood rough set based ECG signal classification for diagnosis of cardiac diseases

Cardiac diseases are one of the foremost reasons of mortality. Hence, the early detection of cardiac diseases based on electrocardiogram (ECG) is important for delivering appropriate and timely treatment to the heart patients and it is increasing the heart patient’s survival. Recent trends in clinical decision making systems appeal automation in ECG signal processing and beat classification. Automatic beat classification is a significant method to support clinical specialists to categorize arrhythmia signals in ECG recording. The main objective of this paper is to construct novel automatic classification system for analysis of ECG signal and decision making purposes. The proposed method involves three main parts: De-noising, feature extraction and classification. Initially, discrete wavelet transform (DWT) is applied before classification for signal De-noising and feature extraction. In this work, neighborhood rough set is applied to classify the ECG signals into normal and four abnormal heart beats. The presence of neighborhood rough set classification algorithm (NRSC) produces very exciting recognition and classification abilities through a wide range of biomedical signal processing. The experimental analysis of the proposed NRSC algorithm is compared with the multi-layered perceptron, decision table, Naive Bayes and J48 classification algorithms. Here, the performance of classification algorithms has been evaluated in terms of sensitivity, specificity, Positive predictive value, negative predictive value, false predictive value, Matthews’s correlation coefficients, F-measure, Folke–Mallows Index and Kulcznski Index. The acquired results showed that the proposed algorithm attained 99.32 % of the classification accuracy using NRSC and DWT. Results indicated that the performance of this proposed NRSC classification method was remarkably superior to that of other classification techniques.

Hybrid Bijective soft set - Neural network for ECG arrhythmia classification

Reliable identification of arrhythmias built by digital signal processing of Electrocardiogram (ECG) is significant in providing appropriate and suitable treatment to a cardiac arrhythmia patient. Due to exploitation of ECG signals with numerous frequency noises and the occurrence of various arrhythmic events in a cardiac rhythm, computerized interpretation of abnormal ECG rhythms is a thought-provoking task. The objective of this paper is to construct novel automatic classification system for analysis of ECG signal and decision making purposes. The proposed classification method is a hybridization of Bijective soft set and back propagation neural network. The Hybrid Bijective soft set neural network based classification algorithm (BISONN) is applied to classify the ECG signals into normal and four abnormal heart beats. Initially, discrete wavelet transform is applied be- fore classification for signal De-noising and feature extraction. The experimental results are obtained by evaluating the proposed method on ECG data from the MIT-BIH arrhythmia database. The experimental analysis of the proposed BISONN algorithm is compared with the Multi-layered Perceptron (MLP), Decision table (DT), Naive Bayes (NB) and J48 classification algorithms. The performance of the classifier is measured in terms of sensitivity, specificity, Positive predictive value, negative predictive value, false predictive value, Matthews's correlation coefficients, F-Measure, Folke-mallows Index and Kulcznski Index. The acquired results clearly confirm the superiority of the BISONN algorithm as compared with other classifiers.

Narrow-band imaging bronchoscopy improves assessment of tumor extent and affects therapeutic strategy for central lung cancer

To determine the sensitivity of narrow-band imaging bronchoscopy (NBI) in the assessment of tumor extent and therapeutic strategy. A total of 196 patients with imaging abnormalities for malignancy were examined with both white light bronchoscopy (WLB) and NBI (Olympus, EVIS LUCERA). Record the tumor infiltration, image and pathological results. There were 152 male and 44 female with a mean age of 58 years. In 22 patients (13.1%), NBI revealed greater tumor extent than WLB alone. And tumor margins were >1 cm wider on NBI examination than on WLB. In 19 patients (11.3%), that finding influenced further therapeutic course, leading to greater resection level (n = 14) or avoidance of surgery (n = 5). According to univariate analysis, tumor size > 30 mm and pathological type of squamous cell carcinoma were independent predictive factors (OR 3.13, 95% CI: 1.06-9.21, P = 0.038; OR 4.68, 95% CI: 1.02-21.58, P = 0.048). The diagnostic sensitivity of NBI group was 88.2%, specificity 83.3%, positive predictive value 98.1% and false predictive value 41.7%. And the diagnostic sensitivity of WLB group was 80.3%, specificity 55.6%, positive predictive value 94.7% and false predictive value 22.2%. The combined use of NBI bronchoscopy and conventional white-light examination has greater sensitivity and specificity for assessing tumor margins. And this technique also significantly improves the assessment of central lung cancer infiltration and influences the therapeutic strategy.

The true predictive value of the human tumor stem cell assay: does a workable assay select for treatment responders?

In practice, the human tumor clonogenic assay is workable for less than half of the patient population to which it is applied, since the remainder of the specimens fail to produce sufficient numbers of colonies. Thereby a bias may be introduced which could result in a false predictive value positive of the test. It is therefore necessary to compare the responses to treatment of patients whose tumors could be assayed in vitro to those whose tumors failed to grow adequately, to assure that the prevalence of treatment responders has not changed within the group of patients for which the assay worked. From an analysis of the treatment response of 70 patients with stage III and IV ovarian carcinomas and 70 patients with stage IV breast cancer, no selection bias did occur and no preferential in vitro growth of tumor samples from patients with treatment response was found.