False Negatives Research Articles

Next-generation technology in epilepsy diagnostic: First Moroccan pediatric case series and literature review.

Background: Pediatric epilepsy is the most prevalent neurological disorder among children, characterized by significant heterogeneity in terms of etiology, clinical presentation, and prognosis. In developed countries, genetic testing, particularly next-generation sequencing (NGS), has become standard practice for diagnosis. Methods/Observation: This paper presents the first pediatric Moroccan case series with epilepsy. The diagnosis was established using whole-exome sequencing which identified five variants. Moreover, we evaluated the effectiveness of different NGS technologies in epilepsy diagnosis by conducting a PubMed search with targeted keywords. Results: Whole-exome sequencing and whole-genome sequencing are more effective for epilepsy diagnosis than multi-gene panels. However, they also present significant challenges including false negatives and variants of unknown significance which complicate genetic interpretation and diagnostic process. Conclusion: Despite these limitations, the rapid accumulation of genetic data and advancements in bioinformatic tools are expected to address these issues, improving diagnostic accuracy. Keywords: Epilepsy, Next-generation sequencing, Neuropediatry, Genetics, Morocco.

A hybrid LSTM random forest model with grey wolf optimization for enhanced detection of multiple bearing faults

Bearing degradation is the primary cause of electrical machine failures, making reliable condition monitoring essential to prevent breakdowns. This paper presents a novel hybrid model for the detection of multiple faults in bearings, combining Long Short-Term Memory (LSTM) networks with random forest (RF) classifiers, further enhanced by the Grey Wolf Optimization (GWO) algorithm. The proposed approach is structured in three stages: first, time and frequency domain features are manually extracted from vibration signals; second, these features are processed by a dual-layer LSTM network, which is specifically designed to capture complex temporal relationships within the data; finally, the GWO algorithm is employed to optimize feature selection from the LSTM outputs, feeding the most relevant features into the RF classifier for fault classification. The model was rigorously evaluated using a dataset comprising six distinct bearing health conditions: healthy, outer race fault, ball fault, inner race fault, compounded fault, and generalized degradation. The hybrid LSTM-RF-GWO model achieved a remarkable classification accuracy of 98.97%, significantly outperforming standalone models such as LSTM (93.56%) and RF (98.44%). Furthermore, the inclusion of GWO led to an additional accuracy improvement of 0.39% compared to the hybrid LSTM-RF model without optimization. Other performance metrics, including precision, kappa coefficient, false negative rate (FNR), and false positive rate (FPR), were also improved, with precision reaching 99.28% and the kappa coefficient achieving 99.13%. The FNR and FPR were reduced to 0.0071 and 0.0015, respectively, underscoring the model’s effectiveness in minimizing misclassifications. The experimental results demonstrate that the proposed hybrid LSTM-RF-GWO framework not only enhances fault detection accuracy but also provides a robust solution for distinguishing between closely related fault conditions, making it a valuable tool for predictive maintenance in industrial applications.

A New Epileptic Seizure Prediction Framework Based on Electroencephalography Signals

This research seeks to evaluate how effectively seizures can be predicted and managed in epilepsy using a specialized deep learning model based on Long Short-Term Memory (LSTM) neural networks. The model leverages non-invasive scalp electroencephalography (EEG) recordings for predicting seizures. To develop and assess the proposed LSTM neural network model, a comprehensive dataset was gathered. The model emphasizes achieving high sensitivity and reducing false alarms to improve its real-time applicability. The evaluation involved various metrics to measure accuracy, sensitivity, and rates of false positives and false negatives. The effectiveness of the proposed LSTM neural network model was outstanding, with accuracy rates ranging from 99.07% to 99.95%. Notably, the sensitivity score of 1 confirmed precise prediction for all seizure cases. The model demonstrated minimal false positive and false negative rates, highlighting its reliability in predicting seizures. This study emphasizes the promising potential of the proposed LSTM neural network model in providing advanced warning for seizures. The high accuracy and sensitivity rates suggest its usefulness in enabling timely preventive measures for patients, ultimately reducing the occurrence of seizures. This innovative approach holds significance in enhancing the overall management and quality of life for individuals dealing with epilepsy.

Diagnostic Accuracy of Beta-2 Transferrin Gel Electrophoresis for Detecting Cerebrospinal Fluid Rhinorrhea.

Unilateral thin clear rhinorrhea (UTCR) may represent a variety of pathologies including cerebrospinal fluid (CSF) rhinorrhea. Beta-2 transferrin (B2Tf) gel electrophoresis (GE) has become the preferred testing modality due to reportedly high sensitivity (87%-100%) and specificity (71%-100%). However, there have been relatively few studies assessing its diagnostic accuracy. The purpose of this single-institution study was to determine the accuracy of B2Tf GE in detecting CSF rhinorrhea. A single-center retrospective review was conducted from 2016 and 2024 for all patients who presented with UTCR and underwent B2Tf GE. Institutional review board approval was obtained. The gold standard for diagnostic confirmation of true and false positives (TP, FP) as well as false negatives (FN) was endoscopic exploration. The gold standard for true negative (TN) was response to medical therapy. A total of 105 patients underwent 149 B2Tf GE tests. 40 (38.1%) patients were diagnosed with CSF rhinorrhea. Of the 149 B2-Tf GE tests, there were 51 TPs, 72 TNs, 20 FPs, and 6 FNs yielding 89.5% sensitivity, 78.3% specificity, 71.8% positive predictive value, and 92.3% negative predictive value, respectively. Of the false results the most common causes for error were purulent sinusitis (n = 6, 23.1%), possible mucous contamination from nose-blowing during collection (n = 3, 11.5%), patient collection error (n = 3, 11.5%), and blood contamination (n = 1, 3.8%). Although these single-institutional data demonstrate test accuracy within ranges previously reported in the literature, they also demonstrate diagnostic limitations. Future studies should explore reasons for erroneous B2Tf GE results and how these may change clinical decision-making. IV Laryngoscope, 2024.

Anomaly detection and confidence interval‐based replacement in decay state coefficient of ship power system

AbstractThe anomaly detection and predictive replacement of the degradation decay state coefficient (Desc) of ship power system (SPS) are crucial for ensuring their operational safety and maintenance efficiency. This study introduces the YC3Model, a model based on a dynamic triple sliding window mechanism, and Gaussian process regression) to address this challenge. It combines the temporal variation characteristics of the decay state coefficient's original data, first‐order, and second‐order differential data in both normal and abnormal trend intervals. The model calculates three local statistical measures within each sliding window and employs the Z‐score method for anomaly detection. The combination of three sliding windows reduces false positives and negatives, enhancing the precision of anomaly detection. For detected anomalies, Gaussian process regression is used for prediction and replacement, providing confidence intervals to increase the reliability of the predicted values. Experimental results demonstrate that the YC3Model exhibits superior anomaly detection accuracy and adaptability in the degradation process of SPS, surpassing traditional methods across a range of evaluation metrics. This confirms the potential of YC3Model in health monitoring and predictive maintenance of SPS, offering reliable data input for the intelligent operation and maintenance (IO&M) of SPS.

Artificial intelligence-based quantification of lymphocytes in feline small intestinal biopsies.

Feline chronic enteropathy is a poorly defined condition of older cats that encompasses chronic enteritis to low-grade intestinal lymphoma. The histological evaluation of lymphocyte numbers and distribution in small intestinal biopsies is crucial for classification and grading. However, conventional histological methods for lymphocyte quantification have low interobserver agreement, resulting in low diagnostic reliability. This study aimed to develop and validate an artificial intelligence (AI) model to detect intraepithelial and lamina propria lymphocytes in hematoxylin and eosin-stained small intestinal biopsies from cats. The median sensitivity, positive predictive value, and F1 score of the AI model compared with the majority opinion of 11 veterinary anatomic pathologists, were 100% (interquartile range [IQR] 67%-100%), 57% (IQR 38%-83%), and 67% (IQR 43%-80%) for intraepithelial lymphocytes, and 89% (IQR 71%-100%), 67% (IQR 50%-82%), and 70% (IQR 43%-80%) for lamina propria lymphocytes, respectively. Errors included false negatives in whole-slide images with faded stain and false positives in misidentifying enterocyte nuclei. Semiquantitative grading at the whole-slide level showed low interobserver agreement among pathologists, underscoring the need for a reproducible quantitative approach. While semiquantitative grade and AI-derived lymphocyte counts correlated positively, the AI-derived lymphocyte counts overlapped between different grades. Our AI model, when supervised by a pathologist, offers a reproducible, objective, and quantitative assessment of feline intestinal lymphocytes at the whole-slide level, and has the potential to enhance diagnostic accuracy and consistency for feline chronic enteropathy.

Machine Learning Models for the Spatial Prediction of Gully Erosion Susceptibility in the Piraí Drainage Basin, Paraíba Do Sul Middle Valley, Southeast Brazil

Soil erosion is a global issue—with gully erosion recognized as one of the most important forms of land degradation. The purpose of this study is to compare and contrast the outcomes of four machine learning models, Classification and Regression (CART), eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM), used for mapping susceptibility to soil gully erosion. The controlling factors of gully erosion in the Piraí Drainage Basin, Paraíba do Sul Middle Valley were analysed by image interpretation in Google Earth and gully erosion samples (n = 159) were used for modelling and spatial prediction. The XGBoost and RF models achieved identical results for the area under the receiver operating characteristic curve (AUROC = 88.50%), followed by the SVM and CART models, respectively (AUROC = 86.17%; AUROC = 85.11%). In all models analysed, the importance of the main controlling factors predominated among Lineaments, Land Use and Cover, Slope, Elevation and Rainfall, highlighting the need to understand the landscape. The XGBoost model, considering a smaller number of false negatives in spatial prediction, was considered the most appropriate, compared to the Random Forest model. It is noteworthy that the XGBoost model made it possible to validate the hypothesis of the study area, for susceptibility to gully erosion and identifying that 9.47% of the Piraí Drainage Basin is susceptible to gully erosion. Furthermore, replicable methodologies are evidenced by their rapid applicability at different scales.

Unveiling a Surgical Revolution: The Use of Conventional Histology versus Ex Vivo Fusion Confocal Microscopy in Breast Cancer Surgery.

Ex vivo fusion confocal microscopy (EVFCM) enables the rapid examination of breast tissue and has the potential to reduce the surgical margins and the necessity for further surgeries. Traditional methods, such as frozen section analysis, are limited by the distortion of tissue and artefacts, leading to false negatives and the need for additional surgeries. This study on observational diagnostic accuracy evaluated the ability of EVFCM to detect breast cancer. A total of 36 breast tissue samples, comprising 20 non-neoplastic and 16 neoplastic cases, were analysed using EVFCM and compared to the results obtained from routine histopathology. A Mohs surgeon experienced in EVFCM (evaluator A) and two breast pathologists unfamiliar with EVFCM (evaluators B and C) performed blinded analyses. EVFCM showed high concordance with the histopathology and the detection of neoplasia, with significant kappa values (p < 0.001). Evaluator A achieved 100% sensitivity and specificity. Evaluators B and C achieved a sensitivity of >87%, a specificity of >94%, positive predictive values of >95%, and negative predictive values of 81% and 94%, respectively. EVFCM therefore offers a promising technique for the assessment of margins in breast-conserving surgery. Its widespread adoption could significantly reduce re-excisions, lower healthcare costs, and improve cosmetic and oncological outcomes.

Research progress on human papillomavirus-negative cervical cancer: A review.

Cervical cancer is the fourth most common cancer in women worldwide. The vast majority of cervical cancers are associated with human papillomavirus (HPV) infection, but a small proportion of cervical cancers occur independently of HPV infection, with different subtypes having varying rates of occurrence. Despite the presence of false negatives in current testing, improving the accuracy of detection is crucial for studying the pathogenesis of HPV-negative cervical cancer and improving the prognosis of these patients. Existing research suggests that HPV-negative cervical cancer has a different pathogenesis from HPV-positive cervical cancer, although the exact mechanism is not yet clear. It is currently believed to be associated with the immune microenvironment, certain tumor gene mutations, and some long noncoding RNAs. This article provides an overview of the latest research progress on HPV-negative cervical cancer, including possible reasons, pathogenesis, pathological features, and clinical characteristics, aiming to provide new insights for diagnosis, treatment, and prognosis improvement.

Optimization of testing protocols to screen for COVID-19: a multi-objective model.

In this paper we develop a new multi-objective simulated annealing (MOSA) algorithm to generate optimal testing protocols for infectious diseases, using the COVID-19 pandemic as our context. A SEIR (susceptible-exposed-infected-recovered) epidemiological model is embedded as the computational platform for our MOSA algorithm to optimize testing protocols for screening across three joint objectives: minimum cost of test materials, minimum total infections over the testing horizon, and minimum number of false negatives over the horizon. We demonstrate the application of this optimization tool to recommend screening protocols for K-12 school districts in the U.S.State of North Carolina. Our approach is scalable by population coverage and can be employed at the level of individual school districts or regional collections of districts, individual schools or collections of schools across a district, business sites, or nursing homes, among other congregate settings where individuals may be screened prior to gaining entry to the site. The algorithm can be solved two ways, generating either independent optimal protocols across individual testing locations, or a common protocol covering all locations in the collection of testing sites. Our findings can be used to inform policy decisions to guide the development of effective testing strategies for controlling the spread of COVID-19 or other pandemic diseases in a wide range of congregate settings across various geographic regions.

Frozen Section Analysis of Sentinel Nodes in Patients With Oral Squamous Cell Carcinoma

Frozen section (FS) analysis of sentinel nodes offers potential on-table diagnosis and treatment for occult metastasis in oral squamous cell cancer. Systematic analysis of FS during sentinel node biopsy has not been illuminated in the literature. To systematically review pooled data from studies using FS analysis in evaluating sentinel nodes in patients with cT1-T2 N0 oral squamous cell cancer. An academic librarian led the search of CENTRAL, CINAHL, Cochrane Database of Systematic Reviews, Embase, and MEDLINE for studies published in English between January 2000 and January 2023. Two authors independently screened cohort studies, case series, and randomized clinical trials, in which FS analysis was used to evaluate sentinel nodes in patients with cT1-T2 N0 oral squamous cell cancer. Data were extracted by 2 reviewers. Reporting quality was estimated using the Diagnostic Precision Study Quality Assessment Tool. Data analysis was performed between April and July 2023, and the meta-analysis was completed using the bivariate random-effects model. The primary outcome was the pooled sensitivity of FS sentinel node analysis. Secondary outcomes included evaluation of the FS technique, rate of occult metastasis, false-negative rate, and survival. Seventeen articles with 878 patients met the eligibility criteria. Although protocols varied, confirmatory serial step sectioning was performed in all studies. Occult metastasis was found in 263 of 878 patients (30%), and FS analysis identified 173 cases (65.8%). Following serial sectioning, an additional 90 positive results were identified, leading to 47 patients undergoing staged completion neck dissection. The pooled sensitivity of FS was 0.71 (95% CI, 0.60-0.80), the diagnostic odds ratio was 110, and the false-negative rate was 34.2%. The Cochrane Q value was 15.62 (df = 16; P = .48) and τ2 = 0.36. In this systematic review and meta-analysis, evaluated studies showed various techniques, in which pooled sensitivity reached 0.71, providing a benchmark for comparison to other 1-stop approaches. Due to the high false-negative rate of approximately one-third of patients, intraoperative FS must always be supplemented by serial sectioning. On-table diagnosis remains a key objective for sentinel node biopsy, and FS detection may be improved by standardizing protocols.

Meta-analysis on the Diagnostic Value of SDC2 Methylation in Colorectal Cancer Screening Among Chinese

To systematically evaluate the diagnostic value of syndecan-2 (SDC2) gene methylation status in the detection of Colorectal cancer (CRC) and advanced adenomas (AA) through meta-analysis. Databases including PubMed, Web of Science were searched from 2020 to June 14, 2024. Relevant studies were selected based on predefined inclusion and exclusion criteria. The true positive (TP), false positive (FP), false negative (FN), and true negative (TN) results were calculated for each study. The quality of the included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. A bivariate meta-analysis model was used to pool the sensitivity, specificity, diagnostic odds ratio (DOR), positive likelihood ratio (PLR), and negative likelihood ratio (NLR), and a summary receiver operating characteristic (SROC) curve was constructed. Spearman’s correlation coefficient, Cochran-Q test, and I² test were used to evaluate heterogeneity. Sensitivity analysis was performed to explore the potential sources of heterogeneity. 24 literatures were included for meta-analysis. The pooled sensitivity was 0.77 for CRC and 0.52 for AA, and the pooled specificity was 0.93 for CRC and 0.91 for AA. The pooled PLR was 10.63 for CRC and 5.57 for AA, and the pooled NLR was 0.25 for CRC and 0.53 for AA. The DOR was 43.21 for CRC and 10.47 for AA. The SROC AUC was 0.91 for CRC and 0.83 for AA. The methylation level of the SDC2 gene in stool samples has significant diagnostic value for colorectal cancer and is considered an ideal biomarker for the early detection of this disease.

Characterizing the Transformation and Diagnosis of Atypical Lipomatous Tumor to Dedifferentiated Liposarcoma: Single Institutional Outcomes.

Atypical lipomatous tumor (ALT) in the extremities is a locally aggressive adipocytic tumor with the potential risk of transformation into dedifferentiated liposarcoma (DDLS). Studies seldom differentiate whether DDLS was diagnosed on initial biopsy, final resected specimen, or subsequent recurrence. Our study seeks to characterize how and when patients received their ALT or DDLS diagnoses to better understand the relationship between the two neoplasms. We performed a retrospective review of patients diagnosed with ALT or DDLS of the extremities. Clinical characteristics, including the method of diagnosis of an ALT or DDLS, time between diagnoses, and tumor recurrence was recorded. Univariate/multivariate analysis was performed to identify risk factors. Forty-five patients were diagnosed with ALT after core needle biopsy (CNB) and 41 of them received marginal en bloc excision. Three (7.3%) of these patients had a heterogeneous tumor on final resection, pathology revealed both ALT and DDLS. Four patients (8.2%) were diagnosed with DDLS from CNB and received negative margin en bloc excision. One of these tumors was identified as heterogeneous ALT/DDLS after resection. Fifty-three patients received marginal en bloc resection without CNB after a benign lipomatous mass was suspected on CT/MRI. Among these, one (1.9%) had a tumor with a heterogeneous composition of both ALT and DDLS on pathology. There were 11 (11.7%) ALT recurrences and 1 (1.0%) DDLS recurrence after ALT resection. Obtaining a proper diagnosis whether ALT or DDLS is critical. Our cohort found that amongst those concerning lipomatous lesions biopsied, 7.84% will show biopsy proven DDLS. Additionally, 6.67% of the biopsies will be false negatives and show DDLS on final pathology. Furthermore, our local recurrence for ALT was 11.7% recurring as ALT and 1.0% recurring as DDLS.

Radiomic Analysis of Cohort-Specific Diagnostic Errors in Reading Dense Mammograms Using Artificial Intelligence.

This study aims to investigate radiologists' interpretation errors when reading dense screening mammograms using a radiomics-based artificial intelligence approach. Thirty-six radiologists from China and Australia read 60 dense mammograms. For each cohort, we identified normal areas that looked suspicious of cancer and the malignant areas containing cancers. Then radiomic features were extracted from these identified areas and random forest models were trained to recognize the areas that were most frequently linked to diagnostic errors within each cohort. The performance of the model and discriminatory power of significant radiomic features were assessed. We found that in the Chinese cohort, the AUC values for predicting false positives were 0.864 (CC) and 0.829 (MLO), while in the Australian cohort, they were 0.652 (CC) and 0.747 (MLO). For false negatives, the AUC values in the Chinese cohort were 0.677 (CC) and 0.673 (MLO), and in the Australian cohort, they were 0.600 (CC) and 0.505 (MLO). In both cohorts, regions with higher Gabor and maximum response filter outputs were more prone to false positives, while areas with significant intensity changes and coarse textures were more likely to yield false negatives. This cohort-based pipeline proves effective in identifying common errors for specific reader cohorts based on image-derived radiomic features. This study demonstrates that radiomics-based AI can effectively identify and predict radiologists' interpretation errors in dense mammograms, with distinct radiomic features linked to false positives and false negatives in Chinese and Australian cohorts.

Reduction of Misclassifications in Wildfire Detection: A Weighted Ensemble Deep Learning Approach

Governments worldwide are increasingly prioritizing early wildfire detection to safeguard lives, property, and the environment. Although CNN-based models have demonstrated exceptional performance in various computer vision applications, the evolving nature of wildfire images poses significant challenges for a single CNN-based model in wildfire detection. In this study, we addressed this issue by integrating and weighting the differential learning capabilities of three individual transfer learning models: InceptionV3, ResNet50, and VGG16. Experimental results show that the ensemble deep learning models significantly outperformed all single classifiers across all performance metrics. Both the ensemble and weighted ensemble deep learning models achieved 99.7% accuracy, 99.5% precision, 100% recall, 99.8% F1-score, 0.5%false positive rate, 0.0% false negative rate and 0.3% error rate. Additionally, these models reduced the error rate by 98%, 91%, and 40% compared to the error rates of ResNet50, InceptionV3, and VGG16 respectively. A false negative rate of 0% indicates that our proposed ensemble deep learning models identified and predicted all the wildfire instances present in the test set correctly without a single misclassification. This positions our proposed ensemble deep learning models as superior choices for reducing misclassifications in wildfire detection.

Diagnosis from an Epidemiological Point of View. The Example of COVID-19

A diagnostic test is anything that provides data about the patient's health or disease. All such tests can be formally evaluated for their accuracy and precision (sensitivity and specificity). Once a test has been performed, whether positive or negative, sensitivity and specificity are not the priority issues; the physician's dilemma is whether or not the patient has the disease, once the test result is known. This is the positive and negative predictive value. However, the positive predictive value depends on the prevalence: when prevalence is high, the positive predictive value of the test increases and, as a consequence, there are fewer false positives and more false negatives. When prevalence is low, the opposite occurs: the positive predictive value of the test decreases, and there will be more false positives and fewer false negatives. Furthermore, diagnoses are generally not determined and labeled in isolation; rather, diagnoses are applied sequentially (Bayesian inference). Thus, prior knowledge facilitates rapid decision-making that is generally correct by increasing the pre-test diagnostic probability. When tests are performed in series (one after the other), specificity and positive predictive value are maximized, but sensitivity and negative predictive value are reduced. Thus, we have the example of COVID-19. For a low prevalence scenario (such as the current one), assuming a specificity of 98%, a positive test ensures the diagnosis in at least 2/3 of patients. And a negative result practically rules it out. When the incidence of COVID-19 is high. For example, with a prevalence of 30% or in practice when we are in some "COVID-19 wave", a positive result ensures the diagnosis in 94% but a negative result can occur in up to 10% of patients. On the other hand, a second test after the first gives a more reliable result if its results go in the same direction.

Optical Image Processing using Eulerian Amplification

Recent advancements in digital photography, particularly through mobile phone cameras, microscopes, and satellite imaging, have made high-resolution image capture increasingly accessible. However, these captured images often contain subtle changes in color resolution and density that are challenging to observe with the naked eye. This study explores the application of Eulerian amplification as a method to detect and enhance such small-amplitude variations, making them visible for improved analysis. Unlike traditional approaches, Eulerian methods are particularly effective for processing smooth structures and high-quality printed materials where minor amplifications in color can reveal significant grading details. Using a pixel-by-pixel Eulerian path analysis, this method allows for a detailed comparison of color intensity values on a fine 8-bit scale, which ranges from 0 to 255. Through this analysis, color distribution patterns are visualized across the spatial structure of the image, which is particularly beneficial for identifying specific variations in quality in printed materials, such as highly graded cards. To manage large image structures, spatial decomposition using a multi-level Gaussian pyramid technique is employed. By applying temporal filtering within select frequency bands (0.4–4 Hz) at a coarse pyramid level, the algorithm effectively pools spatial data, enabling the detection of color density shifts that may indicate image defects. The amplified image data is further processed using a classifier neural network, which provides high sensitivity and specificity in detecting edge defects, image centering issues, scuffs, and breakages. The system demonstrates promising results in identifying true positives while maintaining low false-negative rates, thus confirming the reliability of deep machine learning algorithms in high-sensitivity defect detection. This paper presents the significance of Eulerian amplification in optical image processing, offering a robust tool for precise, automated defect detection across a variety of high-resolution image types.

Automated Diagnosing of Melanoma Based on the Stolz Algorithm

The article discusses an algorithm for automating melanoma diagnosing using computer vision and a neural classifier. The aim of the study is to develop an algorithm for efficient classification of melanoma in images, as well as the influence of dermoscopic features on diagnosing. New growths in the image are highlighted. Calculation of parameters for the Stolz formula and calculation of TDS (calculation of diagnosis) were carried out. Based on the calculations performed, the optimization problem was solved to clarify the boundaries of the neoplasm differentiation areas, and the Stolz formula coefficients adjustment, and a set for neural network training was generated; MLP was selected as a classifier. The average accuracy of the algorithm on two independent data sets is 86%. Classification by a neural network of two sets of images according to Stolz parameters is given. Based on the results, a diagnosing was made. Based on the Stolz algorithm, a set of images with skin neoplasms is pre-processed: the neoplasm is isolated, ABCD signs and the overall dermoscopic score are calculated from the image. The proposed algorithm for automated melanoma diagnosing based on the Stolz dermoscopic method showed good results on real sets of images. The reduced accuracy of the model on the HAM10000 set is due to the class imbalance (ratio of classes 1 to 9). A high F-measure value indicated a good balance between sensitivity and specificity of the model, with the model tending to be better at detecting melanoma true positive (TP) cases. High sensitivity is desirable for problems, where reducing false negatives (missing positive cases) is critical, even at the expense of increasing Type I errors. The completeness of the model was 88.54% and 95% and suggests that the model minimizes cases of missing diseases. It is concluded that the more accurately the ABCD parameters are calculated, the more accurately the model will be able to classify the disease; in the future, refining and dividing parameter D into several components can provide the model with additional features for classification.

Introduction of a Novel Cut-off in Newborn Screening of Galactosemia; a Cohort Study

Background: The current newborn screening for Classic Galactosemia (CG) presents significant challenges, including a low positive rate and a high false-positive rate. Objectives: In this study, we aimed to establish new cut-off values (COVs) for CG screening and introduce a novel approach. Methods: Total galactose (TGAL: The sum of galactose (Gal) and galactose-1-phosphate (G-1-P)) levels of all newborns born in Fars, Iran, from August 2006 to December 2020, were reviewed to establish cut-off ranges. A receiver operating characteristic (ROC) curve analysis was performed to define an optimal COV. Results: Out of 1,187,436 newborns, 4,893 (0.41%) were recalled for further evaluation due to an initial TGAL ≥ 4 mg/dL from a positive screening test, with 160 (3.26%) confirmed to have CG. In the initial negative screening results, nine infants were missed as false negatives. An area under the curve of 0.868 suggested that TGAL is a reliable indicator for distinguishing galactosemia from normal subjects. Receiver operating characteristic curve analysis indicated that a cut-off value (COV) of 5.2 mg/dL provided a sensitivity and specificity of 80.0% and 81.3%, respectively, making it an optimal conservative value for deciding on further recall in the Iranian setting. Additionally, a COV of 7.35 mg/dL demonstrated a sensitivity of 71.3% and specificity of 95.7%, making it a suitable cut-off for immediate referral. Conclusions: We proposed a novel protocol for newborn screening in Iran, establishing a TGAL level of 5.2 mg/dL as a conservative cut-off for CG screening, showing excellent sensitivity while ensuring specificity for recalling suspicious cases. Furthermore, a cut-off of 7.35 mg/dL was identified for prompt consideration of urgent treatment.

Deep learning on chest X-ray and computed tomography scans for detection of COVID-19 as a part of a network-centric digital health stack for future pandemics

Developing a reliable rapid screening protocol for highly infectious diseases like COVID-19 is of paramount interest since it facilitates the isolation of infected patients from the rest of the population. Reverse-transcription polymerase chain reaction (RT-PCR) test is presently the most widely accepted gold-standard test to detect COVID-19. In this method, the RNA of the virus is duplicated by a process called reverse transcription to form DNA for facilitating the copying process. Fluorescent dye is attached to the viral genetic material and copied billions of times through the process called polymerase chain reaction. Enhanced fluorescence is used to identify the presence of genetic material of the virus. These tests are time-consuming and have significant false negatives, i.e., a person with COVID-19 might be categorized as not having the virus. Large-scale RT-PCR testing has its own share of problems such as logistics, availability and affordability in underdeveloped nations, and reliability of the test results. Machine learning algorithms can act as a cheaper supplementary/alternative diagnostic tool for the testing process. In the current study, using publicly available chest X-ray image datasets, different convolutional neural network (CNN)-based models were developed for efficient identification of COVID-19 infected patients, and their efficacies were compared. Key innovations in training the CNNs are discussed. Our results indicate that EfficientNet, SeResNext, and ResNet are best at classifying normal, pneumonia and COVID-19 cases, respectively. The ResNet architecture with transfer learning performed best at detecting COVID-19 with an accuracy of 94%, a rate far superior to that in the RT-PCR test, which is typically in the range of 70 &amp;ndash; 80%. This is particularly attractive as an additional noninvasive protocol since such technology-augmented detection is likely to help in reducing the psychological refractory period due to COVID-19 infections. Toward the healthy lung initiative in the post-COVID-19 era, we propose close coupling of the present diagnostic protocols with digital approaches to ensure more reliable personal care within the ambit of large-scale pandemic control mechanisms. Such integration with emerging technological tools can create a benchmark for the first line of defense against future global pandemics.