Method For Early Diagnosis Research Articles

The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms

Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.

Deep Learning Based Detection of Silicosis from Computed Tomography Images

Artificial intelligence has increasingly been used in interpreting medical images to support the timely treatment of diseases by providing early and accurate diagnosis. Pneumoconiosis is a tissue reaction that develops as a result of the accumulation of inorganic dust in the lungs. The most common types of pneumoconiosis include diseases such as coal worker's pneumoconiosis, silicosis, asbestosis, and siderosis. Silicosis, which has maintained its importance since the 1900s and has seen over 182,000 articles published in the last 10 years, is a global health problem. The automated detection and recognition of silicosis in lung computed tomography (CT) images can be considered the backbone of assisting the silicosis diagnosis process. Automated medical assistance systems developed using artificial intelligence can simplify the medical examination process and reduce the time required to start accurate treatment. Although the literature contains various studies that benefit silicosis diagnosis using chest X-ray images or pneumoconiosis diagnosis using CT images, there is not enough classification study that can particularly aid the diagnosis of silicosis in CT images.The method of early detection of silicosis from chest radiographs and CT images has been a challenging task due to the high variability among pneumoconiosis readers. Based on the success of deep learning in the classification and segmentation of medical images, this study has shown that deep learning networks and transfer learning algorithms can detect silicosis with high accuracy by classifying CT images. The performance of the six algorithms examined in the study is compared, and the algorithm with the best performance is recommended. Performance criteria such as accuracy, precision, specificity, and F1-score of the algorithms used in the study were calculated. The accuracy rates of the models were obtained as 92.62%, 93.03%, 92.76%, 95.38%, 97.29%, and 95.17% for AlexNet, VGG16, ResNet50, InceptionV3, Xception, and DenseNet121, respectively. These results show that Xception outperformed the other algorithms and was the most successful algorithm in the automatic detection of silicosis with an accuracy rate of 97.29%.Additionally, a new dataset consisting of tomography images from silicosis patients is presented in this study. Experimental results have shown that transfer learning algorithms can significantly benefit the diagnosis of silicosis by successfully classifying CT images. The findings of the study highlight the clinical importance of artificial intelligence methods in medical image analysis and early disease diagnosis.

Early Alzheimer's disease diagnosis via handwriting with self-attention mechanisms.

The neurodegenerative diseases like Alzheimer's disease (AD) can result in progressive decline in both cognitive functions and motor skills, which have critical need for accurate early diagnosis. However, current diagnosis approaches primarily rely on timely clinical magnetic resonance imaging (MRI) scans, which impede widely application for potential patients. Leveraging handwriting as a diagnostic tool offers significant potential for identifying AD in its early stages. This study aims to develop an efficient, rapid, and accurate method for early diagnosis of AD by utilizing handwriting analysis, a promising avenue due to its association with compromised motor skills in neurodegenerative diseases. We propose a novel methodology that leverages self-attention mechanisms for the early diagnosis of AD. Our approach integrates data from 25 distinct handwriting tasks available in the DARWIN (Diagnosis AlzheimeR WIth haNdwriting) dataset. The Self-Attention model achieved an accuracy of 94.3% and an F1-score of 94.5%, outperforming other state-of-the-art models, including traditional machine learning and deep learning approaches. Specially, the Self-Attention model surpassed the previous best model, the convolutional neural networks, by approximately 4% in both accuracy and F1-score. Additionally, the model demonstrated superior precision (94.7%), sensitivity (94.5%), and specificity (94.1%), indicating high reliability and excellent identification of true positive and true negative cases, which is crucial in medical diagnostics. Handwriting analysis, powered by self-attention mechanisms, offers significant potential as a diagnostic tool for identifying AD in its early stages, providing an effective alternative to traditional MRI-based diagnosis.

Exploring EEG-Based Biomarkers for Improved Early Alzheimer's Disease Detection: A Feature-Based Approach Utilizing Machine Learning

This paper presents a comprehensive investigation into Electroencephalogram (EEG) signal processing and analysis techniques aimed at enhancing early diagnosis methods for Alzheimer's Disease (AD). Leveraging a dataset that has EEG data of individuals diagnosed with Mild Cognitive Impairment (MCI), AD, Healthy Controls, and the study explores Preprocessing Methods and Feature Extraction Techniques, with machine learning model notably Support Vector Machines (SVM).In the preprocessing phase, a combination of high pass, lowpass, Savitzky–Golay, and median filters are applied, informed by a comprehensive review of filter comparison literature. Feature extraction encompasses three primary categories: ‘Statistical, ‘Frequency Domain’ and ‘Time Domain’. The scope of this work is to explore features in all these three domains and build SVM based model for efficient classification. In our investigation, we achieved a categorization accuracy of 92% through the utilization of statistical features. Employing time domain features resulted in an accuracy of 87%, while frequency domain features also yielded an 87% accuracy rate in our study. The primary objective of this study is that it aims to enhance early AD diagnosis through advanced EEG signal processing and machine learning techniques, focusing on preprocessing methods, feature extraction, and classification accuracy.

Inflammatory cytokines, metabolites, and rheumatoid arthritis.

Rheumatoid arthritis (RA) is a chronic autoimmune disease characterized by persistent inflammation and joint destruction. Although the roles of inflammatory cytokines and metabolites in RA pathogenesis have caught a lot of attention, there is a lack of systematic studies, and their causal relationships remain unclear. We conducted a two-step mendelian randomization analysis utilizing genetic data from genome-wide association studies (GWAS) of inflammatory cytokines, metabolites, and RA. The first step assessed the causal effect of 91 inflammatory cytokines and 1400 metabolites on RA risk using inverse variance weighted method, complemented by MR-Egger, weighted median, simple mode and MR-PRESSO to ensure robustness and assess pleiotropy. The second step evaluated the mediation effects of selected metabolites on the relationship between cytokines and RA. The analysis identified 9 inflammatory cytokines, including IL-1α and IL-10, which significantly increase RA risk, while TNF-β exhibited a protective effect. Additionally, 6 metabolites were associated with increased RA risk, including 1-(1-enyl-palmitoyl)-2-arachidonoyl-GPE and arachidonate (20:4n6). Conversely, 5 metabolites, such as docosatrienoate (22:3n3) and Cholesterol, were found to reduce RA risk. The mediation analysis revealed that TNF-β may exerts its protective effect through its influence on specific metabolites, and X-24949, which accounted for a -2.58% mediated effect in the TNF-β-RA causal pathway. This study explores the complex interplay between inflammatory cytokines, metabolites, and RA. The findings suggest potential biomarkers for early diagnosis and novel therapeutic targets, particularly those related to lipid metabolites and specific cytokines like TNF-β. Key message What is already known on this topic Inflammatory factors and metabolites are considered to be related to the onset and progression of RA. What this study adds We conducted a MR analysis to identify all inflammatory factors and metabolites associated with RA and calculated the mediation effect of inflammatory cytokines on RA through metabolites. This study contributes to a comprehensive understanding of the pathophysiological processes of RA. How this study might affect research, practice or policy This has laid the groundwork for developing early diagnosis methods and future treatments.

Inhibition of M2 tumor-associated macrophages polarization by modulating the Wnt/β-catenin pathway as a possible liver cancer therapy method

The problem of liver cancer is becoming increasingly important due to the epidemic of metabolic diseases and persistent high alcohol consumption. This determines great attention to the development and improvement of methods for early diagnosis and treatment of liver cancer. Huang et al presented a study in the World Journal of Gastroenterology , in which they showed that the use of the traditional Chinese medicine Calculus bovis (CB) can suppress tumor growth in mice by inhibiting M2 tumor-associated macrophages (TAM) through modulating the activity of the Wnt/β-catenin pathway. The interaction of CB components with the Wnt/β-catenin pathway, M2 TAM polarization, and tumor dynamics were studied using network pharmacology, transcriptomics, and molecular docking. It is now generally accepted that the polarization of TAM and the differentiation of the functions of M1 and M2 phagocytes are of great importance for the progression of neoplasms. It is assumed that M2 TAM promote proliferation and migration of tumor cells. Attempts to medicinally influence the Wnt/β-catenin pathway in order to modulate phagocyte polarization now belong to one of the most promising areas of immunotherapy of oncological diseases. Undoubtedly, the work of the Chinese authors deserves attention and further development.

Oral microbiome dysbiosis may be associated with intra cranial aneurysms

BackgroundAlthough the etiology of aneurysms remains elusive, recent advances in high-throughput sequencing technology and ongoing human microbiome investigations suggest a potential link between microbiome composition and the onset of various human diseases.ObjectiveThis study aimed to utilize high-throughput 16 S rRNA gene sequencing to analyze the oral flora bacterial profiles of individuals, comparing patients with intracranial aneurysms to a healthy control group. Importantly, we sought to identify differences in the oral microbiota and offer novel insights and methods for early diagnosis and identification of intracranial aneurysms.MethodSaliva samples were collected from 60 patients with cerebral aneurysms (case group) and 130 healthy individuals (control group). The V3-V4 region of the bacterial 16 S rRNA gene was amplified and sequenced using the HiSeq high-throughput sequencing platform to establish the bacterial profile. Sequencing data were analyzed using QIIME2 and Metastats software to compare composition differences and relative abundance at the phylum and genus levels in the oral microbiota of the two groups.ResultsSignificant differences in oral microbiota composition were observed between patients in the case and control groups (P < 0.05). Genus-level identification highlighted key positions occupied by Eubacterium, Saccharimonadaceae, Rothia, Gemella, Streptococcus, Lactobacillales, Phocaeicola, Bacteroides, Saccharimonadales, and Abiotrophia.ConclusionThis study revealed noteworthy distinctions in the composition, abundance, and diversity of oral microbiota between intracranial aneurysm patients and healthy controls. These disparities suggest a potential correlation between oral microbiota and the development of intracranial aneurysms, offering new avenues for early diagnosis and intervention. However, limitations such as a small sample size, lack of prospective design, and absence of causal inference warrant further validation and exploration.

Diagnostic value of nocturnal trend changes in a dynamic electrocardiogram for coronary heart disease

ObjectiveTo explore the diagnostic value of intermittent changes in the nocturnal ST segment trend graph in a dynamic electrocardiogram (ECG) for coronary heart disease (CHD).MethodsA total of 205 patients who underwent coronary angiography were included in this retrospective study. The study sample was determined through a power analysis aimed at achieving power of 80% with a significance level of 0.05. The participants were divided into the CHD (n = 101) and the non-CHD (n = 104) group, based on the degree of coronary artery diameter stenosis. The morphological changes in the ST segment trend graph were observed and divided into two categories: ‘wall-shaped’ and ‘peak-shaped’ changes.ResultsAmong the 205 patients, 94 had nocturnal ST segment dynamic changes and 111 did not. The detection rate of CHD without nocturnal ST segment dynamic changes was 21.59%, significantly lower than the detection rate of 93.18% in those with nocturnal ST segment changes, reflecting a statistically significant difference (P < 0.05). The positive rate of ST segment in patients with single-vessel disease (71.88%) was lower than in patients with multi-vessel disease (78.57%), and both differences were statistically significant (P < 0.05). The duration of ST segment trend graph changes in 94 cases in the CHD group with intermittent changes in the nocturnal ST segment trend graph was higher than in the non-CHD group, but no significant difference was observed (P > 0.05). The detection rate of CHD in the peak-shaped dynamic change group of the nocturnal ST segment trend graph was significantly higher (76/82) than in the wall-shaped (6/82) dynamic change group (P < 0.05).ConclusionPeak-shaped changes in the nocturnal ST segment trend graph indicate coronary artery lesions. Nocturnal ST segment changes observed through dynamic ECG monitoring can serve as a valuable non-invasive predictor for CHD, providing a feasible method for early diagnosis and intervention in clinical practice.

Retrospective Evaluation of Intestinal Protozoa Parasites in Patients Presenting to Kafkas University Health Research and Application Hospital Between 2019-2022.

This study aimed to retrospectively evaluate the prevalence of protozoan parasites in stool samples collected from patients presenting with various gastrointestinal complaints to the Medical Parasitology Laboratory of Kafkas University Research and Application Hospital between 2019 and 2022. Stool samples were initially examined using the native-Lugol method for the detection of protozoan parasites, followed by the formol-ethyl acetate sedimentation method, Giemsa, and carbol fuchsin staining methods. Specific immunochromatographic card tests were used for the diagnosis of Entamoeba histolytica, Cryptosporidium spp., and Giardia intestinalis. Of the 2.267 stool samples examined over the four-year period from January 2019 to December 2022, 7.63% were found to contain one or more protozoan parasites. Among these parasites, Entamoeba histolytica was detected at the highest rate of 4.06%. The other parasite species were identified as follows: Blastocystis spp. 1.15%, Entamoeba spp. and Entamoeba coli each 0.52%, Giardia intestinalis 0.48%, Endolimax nana 0.17%, and Entamoeba histolytica/dispar 0.08%. This study indicates that despite a decrease in the prevalence of intestinal protozoan infections in the Kars region, these infections remain a significant public health issue. Therefore, improvements in hygiene and sanitation conditions, increased public health education, and the widespread implementation of early diagnosis and treatment methods are necessary. Special measures should be taken to protect vulnerable groups, particularly children and the elderly.

Pre-clinical study of IR808 dye for cervical cancer in vitro and in vivo imaging.

There is an urgent need for improved methods for early screening and rapid diagnosis of cervical cancer since current conventional screening methods are plagued by operator subjectivity and unnecessary biopsies. IR808 is a tumour-targeting near-infrared (NIR) fluorescent dye that permits NIR imaging without the requirement of chemical conjugation. Our study investigates an IR808-based strategy for real-time monitoring of the cervix in vivo and rapid assessment of cervical specimens in vitro. We investigated the uptake of IR808 in vitro using normal cervical epithelial cells and three cervical cancer cell lines. The biodistribution of IR808 was examined in vivo via intravenous injection into tumour-bearing mice. Additionally, in vitro tissues were stained with IR808 to simulate the identification of cervical tumors in the clinical setting. Biocompatibility of the dye in both cellular and animal models was also examined. IR808 exhibited significant tumour-to-background ratios in fluorescence molecular imaging of in vivo tumors in nude mice. The application of NIR fluorescent dye IR808 in specific imaging screening, safe and non-invasive real-time monitoring, and rapid identification of cervical tumors from tissue specimens is expected to improve current screening methods for cervical cancer.

Automated early ovarian cancer detection system based on bioinformatics

Ovarian cancer is a common gynecological tumor, with a high mortality rate and difficult clinical treatment. Early detection of ovarian cancer has significant diagnostic value. In response to the problem of poor diagnostic performance of traditional early diagnosis methods, this article designed an automated early ovarian cancer detection system to improve the detection of early ovarian cancer. The conventional early diagnosis methods include serum CA125 (carbohydrate antigen 125) detection and positron emission tomography/computed tomography (PET/CT) imaging. This article combined serum CA125 detection and PET/CT imaging to detect the CA125 level and maximum standardized uptake value (SUV) in patient’s serum. When the CA125 level exceeded 35U/ml and the maximum SUV value exceeded 2.5, the test was considered positive. This article selected 200 patients from Jingzhou Hospital for the experiment and compared the three detection methods. The average specificity of single serum CA125 detection, single PET/CT imaging, and automated detection in patients under 50 were 61.24%, 79.57%, and 97.79%, respectively. The automated early ovarian cancer detection system designed in this article can significantly improve the specificity of early ovarian cancer detection and has excellent application value for early ovarian cancer detection.

Functional inorganic nanoparticles in cancer: Biomarker detection, imaging, and therapy

Cancer poses a major global public health challenge. Developing more effective early diagnosis methods and efficient treatment techniques is crucial to enhance early detection sensitivity and treatment outcomes. Nanomaterials offer sensitive, accurate, rapid, and straightforward approaches for cancer detection, diagnosis, and treatment. Inorganic nanoparticles are widely used in medicine because of their high stability, large specific surface area, unique surface properties, and unique quantum size effects. Functional inorganic nanoparticles involve modifying inorganic nanoparticles to enhance their physical properties, enrichment capabilities, and drug-loading efficiency and to minimize toxicity. This Review provides an overview of various types of inorganic nanoparticles and their functionalization characteristics. We then discuss the progress of functional inorganic nanoparticles in cancer biomarker detection and imaging. Furthermore, we discuss the application of functional inorganic nanoparticles in radiotherapy, chemotherapy, gene therapy, immunotherapy, photothermal therapy, photodynamic therapy, sonodynamic therapy, and combination therapy, highlighting their characteristics and advantages. Finally, the toxicity and potential challenges of functional inorganic nanoparticles are analyzed. The purpose of this Review is to explore the application of functional inorganic nanoparticles in diagnosing and treating cancers, while also presenting a new avenue for cancer diagnosis and treatment.

SRPK Inhibitors Reduce the Phosphorylation and Translocation of SR Protein Splicing Factors, thereby Correcting BIN1, MCL-1 and BCL2 Splicing Errors and Enabling Apoptosis of Cholangiocarcinoma Cells.

Cholangiocarcinoma (CCA) is a malignancy of the bile duct epithelium that is commonly found in the Thai population. CCA has poor prognosis and a low survival rate due to the lack of early diagnosis methods and the limited effectiveness of current treatments. A number of oncogenic spliced-transcripts resulting from mRNA splicing errors have been reported in CCA, and aberrant mRNA splicing is suspected to be a key driver of this cancer type. The hyperphosphorylation of serine/arginine rich-splicing factors (SRSFs) by serine/arginine protein kinases (SRPKs) causes them to translocate to the nucleus where they facilitate gene splicing errors that generate cancer-related mRNA/protein isoforms. The correlation between SRPK expression and the survival of CCA patients was analyzed using data from The Cancer Genome Atlas (TCGA) dataset. The effect of SRPK inhibitors (SRPIN340 and SPHINX31) on two CCA cell lines (KKU-213A and TFK-1) was also investigated. The induction of cell death was studied by Calcein-AM/PI staining, AnnexinV/7AAD staining, immunofluorescence (IF), and Western blotting (WB). The phosphorylation and nuclear translocation of SRSFs was tracked by WB and IF, and the repair of splicing errors was examined by Reverse Transcription-Polymerase Chain Reaction (RT-PCR). High levels of SRPK1 and SRPK2 transcripts, and in particular SRPK1, correlated with shorter survival in CCA patients. SRPIN340 and SPHINX31 increased the number of dead and apoptotic cells in a dose-dependent manner. CCA also showed diffuse expression of cytoplasmic cytochrome C and upregulation of cleaved caspase-3. Moreover, SRSFs showed low levels of phosphorylation, resulting in the accumulation of cytoplasmic SRSF1. To link these phenotypes with aberrant gene splicing, the apoptosis-associated genes Bridging Integrator 1 (BIN1), Myeloid cell leukemia factor 1 (MCL-1) and B-cell lymphoma 2 (BCL2) were selected for further investigation. Treatment with SRPIN340 and SPHINX31 decreased anti-apoptotic BIN1+12A and increased pro-apoptotic MCL-1S and BCL-xS. The SRPK inhibitors SRPIN340 and SPHINX31 can suppress the phosphorylation of SRSFs and their nuclear translocation, thereby producing BIN1, MCL-1 and BCL2 isoforms that favor apoptosis and facilitate CCA cell death.

A Lightweight Multi-Mental Disorders Detection Method Using Entropy-Based Matrix from Single-Channel EEG Signals.

Background: Mental health issues are increasingly prominent worldwide, posing significant threats to patients and deeply affecting their families and social relationships. Traditional diagnostic methods are subjective and delayed, indicating the need for an objective and effective early diagnosis method. Methods: To this end, this paper proposes a lightweight detection method for multi-mental disorders with fewer data sources, aiming to improve diagnostic procedures and enable early patient detection. First, the proposed method takes Electroencephalography (EEG) signals as sources, acquires brain rhythms through Discrete Wavelet Decomposition (DWT), and extracts their approximate entropy, fuzzy entropy, permutation entropy, and sample entropy to establish the entropy-based matrix. Then, six kinds of conventional machine learning classifiers, including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Naive Bayes (NB), Generalized Additive Model (GAM), Linear Discriminant Analysis (LDA), and Decision Tree (DT), are adopted for the entropy-based matrix to achieve the detection task. Their performances are assessed by accuracy, sensitivity, specificity, and F1-score. Concerning these experiments, three public datasets of schizophrenia, epilepsy, and depression are utilized for method validation. Results: The analysis of the results from these datasets identifies the representative single-channel signals (schizophrenia: O1, epilepsy: F3, depression: O2), satisfying classification accuracies (88.10%, 75.47%, and 89.92%, respectively) with minimal input. Conclusions: Such performances are impressive when considering fewer data sources as a concern, which also improves the interpretability of the entropy features in EEG, providing a reliable detection approach for multi-mental disorders and advancing insights into their underlying mechanisms and pathological states.

Phage display–based acoustic biosensor for early cancer diagnosis

The probability of a cancer patient being cured depends largely on the stage of disease at the time of diagnosis. It is therefore very important to develop methods for early cancer diagnosis that would allow screening of a large number of samples in a short time. Here, a unique method is presented for rapid immunodetection of heat shock proteins (HSPs). The method uses a compact acoustic sensor based on a lateral-field piezoelectric resonator and specific phage antibodies. The phage antibodies for the first time were developed against HSPs of P3X63Ag8.653 mouse myeloma cells. The change in the electric impedance modulus of resonator after recording of phage antibody–HSP interaction served as the analytic signal with analysis time less than 5 min. Antibody-HSP interaction confirmed by microscopic analysis and flow cytometry. This study establishes a new strategy for early cancer diagnosis by compact acoustic sensor with phage antibodies as sensing element. The results can be used to develop a noninvasive rapid method of early cancer diagnosis on basis of HSP determination and to control the content of HSPs in the monitoring of tumor therapy.

Working conditions and health status in workers in boiler and welding production in power engineering

Introduction. Preserving the health of qualified workers of older age groups is especially important under conditions of exposure to occupational hazards. The purpose of the study was to assess the influence of occupational hazards on the development of occupational and somatic diseases among workers of various age groups in the main occupations of mechanical engineering. Materials and methods. The study tested the results of hygienic research at workplaces of an enterprise in the power engineering industry in the manufacture of welded metal structures. We assessed the health status in workers based on the results of an in-depth medical examination and ultrasound examination of the vessels of the upper extremities with assessment of blood flow indices. Using a survey method, data were obtained on assessing the influence of production factors on the health status in workers. Results. The working conditions in the main occupational workers groups were assessed as harmful grades 1–3, the priority occupational hazards were: increased noise, and at the workplaces of electric gas workers there were also fibrogenic aerosols, chemical substances, and heavy physical work. Electric and gas welders and boilermakers work in the most unfavourable conditions, about 30% of whom continue to work after reaching retirement age. We have established a significant gain in the incidence of arterial hypertension and sensorineural hearing loss among workers over 40 years of age and an increase in the prevalence of all chronic diseases in the age group over 60 years. Limitations. The study is limited by the number of workers examined and the lack of ability to assess the health status of the studied contingent of workers over time. Conclusion. In conditions of exposure to elevated noise and other occupational hazards, there is an enhancement in the prevalence of work-related and somatic diseases in workers over 40 years of age. With advancing age, the rise in the vascular resistance index is observed, however, the first signs of peripheral blood flow disturbance are often recorded at a young age. In this regard, it is necessary to introduce methods of early diagnosis and prevention of occupational and work-related pathology.

New insight in cervical cancer diagnosis using convolution neural network architecture

&lt;p&gt;The Pap smear is a screening method for early cervical cancer diagnosis. The selection of the right optimizer in the convolutional neural network (CNN) model is key to the success of the CNN in image classification, including the classification of cervical cancer Pap smear images. In this study, stochastic gradient descent (SGD), root mean square propagation (RMSprop), Adam, AdaGrad, AdaDelta, Adamax, and Nadam optimizers were used to classify cervical cancer Pap smear images from the SipakMed dataset. Resnet-18, Resnet-34, and VGG-16 are the CNN architectures used in this study, and each architecture uses a transfer-learning model. Based on the test results, we conclude that the transfer learning model performs better on all CNNs and optimization techniques and that in the transfer learning model, the optimization has little influence on the training of the model. Adamax, with accuracy values of 72.8% and 66.8%, had the best accuracy for the VGG-16 and Resnet-18 architectures, respectively. Resnet-34 had 54.0%. This is 0.034% lower than Nadam. Overall, Adamax is a suitable optimizer for CNN in cervical cancer classification on Resnet-18, Resnet-34, and VGG-16 architectures. This study provides new insights into the configuration of CNN models for Pap smear image analysis.&lt;/p&gt;

Unraveling Alzheimer’s Disease Classification with Deep Learning: A Comprehensive Review

Abstract: Alzheimer's disease (AD) is a neurological disease that progresses over time and is the primary global cause of dementia. Timely and accurate diagnosis is essential for therapeutic and interventional success. Conventional approaches, like clinical evaluations and neuroimaging procedures, are not always able to detect the illness at an early stage. This paper provides an extensive overview of current developments in using deep learning methods for AD early diagnosis and Identification. Numerous approaches have been put up, utilizing diverse forms of data such as MRI scans, eye-tracking actions, and text data that is clinically significant. Convolutional neural networks (CNNs), deep neural networks (DNNs), and long short-term memory networks (LSTMs) are just a few of the deep learning designs used by these models, which highlight how flexible and adaptive these methods are. Using cutting-edge methods to extract discriminative features from the data, feature extraction and selection have become essential components of these models. Additionally, a number of studies have concentrated on improving model performance through the use of methods such as depth-wise convolutional procedures, ensemble learning approaches, and particle swarm optimization for hyperparameter tweaking. Even with high accuracy rates attained, there is still opportunity for development, particularly with regard to managing data scarcity and model interpretability. This survey indicates possible routes for future research and offers insightful information about the state of deep learning applications in AD categorization.

Diagnostic and prognostic value of serum Cys-C, retinol-binding protein, and ischemia-modified albumin in patients with coronary heart disease: A diagnostic accuracy study.

The use of 3 biomarkers - cystatin-C (Cys-C), retinol-binding protein (RBP), and ischemia-modified albumin (IMA) - for the clinical classification and outcome of coronary heart disease (CHD) has not been adequately evaluated. We explored the serum levels of these 3 markers and evaluated their diagnostic and prognostic values in patients with CHD. This retrospective case-control study, conducted between June 2017 and June 2018, included 201 patients with CHD hospitalized at the Henan Provincial People's Hospital and 127 healthy individuals from Henan Provincial People's Hospital as controls. Cys-C, RBP, IMA levels, and other laboratory parameters in the 2 groups were determined, and patient outcomes were analyzed. Cys-C, RBP, and IMA levels were higher in the case group than in the control group (P < .05). Logistic regression analysis confirmed that these 3 biomarkers were independent risk factors for CHD. Each indicator has clinical significance in the diagnosis and prognosis of CHD, with RBP being the most significant. The AUC value for CHD detection using a combination of the 3 indicators was 0.783, and the sensitivity and specificity values were 78% and 74.6%, respectively. Simultaneous detection of Cys-C, RBP, and IMA could be an optimal method for early diagnosis and prognosis of CHD.

Prognostic algorithm for early diagnosis of subcritical conditions as predictors of sudden cardiac death

Aim. To develop a method for early diagnosis of subcritical homeostasis disorders leading to sudden cardiac death (SCD). The basis is to improve the efficiency of predictive algorithms.Material and methods. This pilot, controlled, open-label, randomized, prospective clinical trial included 220 patients at risk of SCD and 150 patients without risk of SCD. Main and control groups was formed according to the global cardiovascular risk score. Based on the informative features proposed by specialized experts using multivariate statistics methods (discriminant analysis), two condition classes were formed. The conducted exploratory analysis confirmed the significance of diagnostic criteria in relation to SCD manifestation (manifestation of cardiac arrest — MCA), which is an integral assessment of a fatal complication. The development of decision rules was carried out on the basis of soft computing technology.Results. Taking into account the priority of clinical research, namely, the identification of subcritical stages of MCA, a classifier is proposed according to basic severity of patients — the severity of critical condition risk (SCCR). The discriminant function and intersection areas between MCA subclasses in the conditions of early SCD diagnosis determine the transition to soft computing technology. Membership functions for severe MCA are formed, followed by their iteration according to E. Shortliffe. The final decision rule, using a fuzzy classifier, differentiates the MCA into stages with different SCCR. In parallel with standard protocols for the management of severe somatic patients (chronic obstructive pulmonary disease, chronic kidney disease, hepatocellular failure), based on the proposed algorithm with an integral assessment of critical conditions, using the MCA decision rule in the main group in 30,5% of cases, subcritical stage was revealed, followed by targeted treatment and preventive support. In the first group, a subcritical condition was detected in 67 patients (30,5%); a critical condition without SCD — in 3 patients (1,4%). In all noted cases, early prevention of SCD was successfully carried out (these patients were transferred to a class with a lower SCD degree). Using conventional prognostic scores in this group, 46 patients (20,9%) were identified with a subcritical condition and 1 (0,4%) with a critical condition. In the control group, subcritical condition was determined in 35 patients (23,3%), of which 17 patients (11,3%) had a moderate risk of SCD. Using conventional prognostic scores, 23 patients (15,3%) with subcritical condition were identified.Conclusion. In the conditions of intensive care unit, general medicine departments, hemodialysis department, cardiac surgery, and organ transplantation department, an algorithm for early diagnosis and risk stratification of SCD with an integral assessment (MCA) should be used. The fuzzy classifier MCA according to SCCR makes it possible to carry out timely correction of treatment measures in addition to standard protocols.