Positive Predictive Rate Research Articles

Lipid levels and insulin resistance markers in patients with colorectal cancer: Propensity score matching analysis.

Colorectal cancer (CRC) is a prevalent malignant neoplasm characterized by subtle early manifestations. To investigate the correlation among serum lipid profiles, the triglyceride-glucose (TyG) index, and the atherosclerotic index (AI) in patients with CRC. Furthermore, it explored the clinical diagnostic utility of combining serum lipids with cancer antigens in the context of CRC. A retrospective analysis encompassed 277 patients with CRC and 1034 healthy individuals. Following propensity score matching, patients with CRC exhibited significantly reduced levels of serum triglyceride (TG), total cholesterol (TC), high-density lipoprotein cholesterol, and low-density lipoprotein cholesterol (LDL-C), as well as a diminished TyG index. Conversely, they displayed elevated AI levels compared to their healthy counterparts. Patients in advanced stages exhibited lower serum levels of TG, TC, and LDL-C compared to those in early stages. Patients with positive lymph node metastasis demonstrated reduced levels of TG, LDL-C, and the TyG index. Receiver operating characteristic analysis revealed that the combination of the TyG index, carcinoembryonic antigen, and carbohydrate antigen 19-9 yielded the highest positive prediction rate for CRC at 75.3%. Preoperative serum lipid profiles exhibit a robust association with patients with CRC. The concurrent assessment of multiple serum lipids and cancer antigens effectively enhances the diagnostic accuracy for CRC.

Evaluation of the QRS detector using the Medicom-combi complex for daily monitoring of ECG and blood pressure using the MIT-BIH ECG signal test database

Purpose. To evaluate the accuracy of the QRS complex detectorof the Medicom-combi complex for daily monitoring of ECG and blood pressure using the MIT-BIH ECG signal test database in accordance with the requirements of GOST R IEC60601–2–47–2017, 30324.2.47–2012.Materials and methods. During the tests, the operation of the detector was evaluated using the MIT-BIH Arrhythmia Database, containing 48 records of 30 minutes each. Each selected QRS complex was assigned one of the following types: N (supraventricular complex, normal QRS complex, including bundle branch block), V (ventricular complex), U (complex that experts find difficult to determine) and A (artifact). Rates of sensitivity (Sen), specificity or positive predictive rate (PPR), and overdiagnosis (FPR) were determined.Results. The sensitivity of the QRS complex detector of the Medicom-combi complex for daily monitoring of ECG and blood pressure was 99,98%, and the specificity was 99,87%. The sensitivity of determining ventricular complexes was 99,97%, the specificity of determining ventricular complexes was 99,64%. Overdiagnosis of ventricular complexes does not exceed 0,03%.Conclusion. The Medicom-combi complex for daily monitoring of ECG and blood pressure, designed for long-term ECG monitoring, has sufficient sensitivity and specificity for analyzing Holter ECG recordings, as well as identifying ventricular ectopic complexes.

Lipid levels and insulin resistance markers in gastric cancer patients: diagnostic and prognostic significance.

Gastric cancer (GC) is a highly heterogeneous and aggressive malignant tumor that seriously affects the life safety of people all over the world. Its early manifestations are subtle. The present study aimed to investigate the clinical significance of serum lipid profiles, insulin resistance markers including the triglyceride-glucose (TyG) index and the atherosclerotic index (AI), in GC patients. A retrospective analysis encompassed 215 GC patients and 827 healthy individuals. The study results show that the total cholesterol, triglycerides, low-density lipoprotein, high-density lipoprotein levels, and the TyG index of GC patients were significantly lower than those of the control group before and after propensity score matching analysis. In the GC group, the levels of CEA, CA199, CA125, and CA724 tumor markers were higher than those in the healthy control group. Patients in advanced stages exhibited lower serum levels of serum lipids and TyG index compared to those in early stages. ROC analysis revealed that the TyG index, CA125, and CA199 combination yielded the highest positive prediction rate for GC at 98.6%. TyG index is significantly associated with the risk of adverse reactions after chemotherapy (OR = 1.104, 95% CI 1.028-1.186, P < 0.01). Multiple tumor markers and the TyG index combined detection showed correlations with five adverse reactions caused by chemotherapy (r < 0.6, P < 0.05). Preoperative lipid profiles in the serum show a strong correlation with patients diagnosed with GC. Evaluating a combination of various serum lipids and cancer markers significantly improves diagnostic precision for GC and the ability to predict chemotherapy side effects.

Reclassification of Urinary Cytology according to the Paris System for Reporting Urinary Cytology Correlation with Histological Diagnosis

Introduction: The Paris System for Reporting Urinary Cytology (TPS) was designed to provide precise diagnostic criteria when evaluating urine cytology and standardize the terminology used in reporting. In our study, we have aimed to determine the effect of TPS on the diagnostic performance of urine cytology, its impact on establishing appropriate risk stratification, and its effectiveness in the diagnosis and follow-up of the patients. Methods: We reevaluated 200 liquid-based urine cytologies with available histological diagnoses reported between 2015 and 2021 according to TPS criteria and compared them with the original cytological diagnoses. Area under the curve, sensitivity, specificity, and diagnostic accuracy of both methods were calculated and statistically analyzed to determine the diagnostic performance of the original reporting and TPS. Results: The sensitivity, specificity, positive predictive, negative predictive, and diagnostic accuracy rates of TPS were 60%, 99.3%, 97.2%, 97.2%, 85.7%, and 87.2%, respectively. In TPS, the risk of malignancy for negative for high-grade urothelial carcinoma, atypical urothelial cells, suspicious for high-grade urothelial carcinoma, and high-grade urothelial carcinoma (HGUC) is 3.5%, 20.9%, 60.8%, 97.2%, respectively. In the original reporting, the corresponding risks were 13.4%, 15%, 52%, 100%, respectively. A statistically significant difference was observed between diagnostic criteria of original cytology and TPS (p = 0.001). When the original reporting was compared with the TPS, the discriminative power of TPS in the diagnosis of HGUC was significantly higher (p < 0.001). Conclusions: The use of TPS provided a more accurate risk stratification of patients. The diagnostic performance of urine cytology was improved, especially for HGUC.

A Comparative Analysis of U-Net and Vision Transformer Architectures in Semi-Supervised Prostate Zonal Segmentation.

The precise segmentation of different regions of the prostate is crucial in the diagnosis and treatment of prostate-related diseases. However, the scarcity of labeled prostate data poses a challenge for the accurate segmentation of its different regions. We perform the segmentation of different regions of the prostate using U-Net- and Vision Transformer (ViT)-based architectures. We use five semi-supervised learning methods, including entropy minimization, cross pseudo-supervision, mean teacher, uncertainty-aware mean teacher (UAMT), and interpolation consistency training (ICT) to compare the results with the state-of-the-art prostate semi-supervised segmentation network uncertainty-aware temporal self-learning (UATS). The UAMT method improves the prostate segmentation accuracy and provides stable prostate region segmentation results. ICT plays a more stable role in the prostate region segmentation results, which provides strong support for the medical image segmentation task, and demonstrates the robustness of U-Net for medical image segmentation. UATS is still more applicable to the U-Net backbone and has a very significant effect on a positive prediction rate. However, the performance of ViT in combination with semi-supervision still requires further optimization. This comparative analysis applies various semi-supervised learning methods to prostate zonal segmentation. It guides future prostate segmentation developments and offers insights into utilizing limited labeled data in medical imaging.

Predictive factors for COVID-19 severity and mortality in hospitalized children

BackgroundUnderstanding the factors influencing disease progression and severity in pediatric COVID-19 cases is essential for effective management and intervention strategies. This study aimed to evaluate the discriminative ability of clinical and laboratory parameters to identify predictors of COVID-19 severity and mortality in hospitalized children.MethodsIn this multicenter retrospective cohort study, we included 468 pediatric patients with COVID-19. We developed a predictive model using their demographic, clinical, and laboratory data. The performance of the model was assessed using various metrics including sensitivity, specificity, positive predictive value rates, and receiver operating characteristics (ROC).ResultsOur findings demonstrated strong discriminatory power, with an area under the curve (AUC) of 0.818 for severity and 0.873 for mortality prediction. Key risk factors for severe COVID-19 in children include low albumin levels, elevated C-reactive protein (CRP), lactate dehydrogenase (LDH), and underlying medical conditions. Furthermore, ROC curve analysis highlights the predictive value of CRP, LDH, and albumin, with AUC values of 0.789, 0.752, and 0.758, respectively.ConclusionOur study indicates that laboratory values are valuable in predicting COVID-19 severity in children. Various factors, including CRP, LDH, and albumin levels, demonstrated statistically significant differences between patient groups, suggesting their potential as predictive markers for disease severity. Implementing predictive analyses based on these markers could aid clinicians in making informed decisions regarding patient management.

Optimizing Startup Success Prediction Through SMOTE Oversampling and Classification

Rapid technological advancements have led to a surge in the number of startups competing with innovative ideas. Predicting the chances of a startup's future success becomes crucial for entrepreneurs in making informed decisions and strategizing their growth. This study investigates the effectiveness of the Gradient Boosting classification algorithm in predicting startup success. To address potential class imbalance within the dataset, a pre-processing step utilizing Synthetic Minority Oversampling Technique (SMOTE) was employed. The dataset itself encompassed a wide range of variables related to startup attributes and performance metrics. The F1-score metric was utilized to evaluate the model's accuracy while minimizing false positive predictions that could potentially mislead investors. Gradient Boosting algorithm was employed to analyze the dataset, which was pre-processed using SMOTE to handle potential class imbalance. This technique helps to create synthetic data points for the minority class, resulting in a more balanced dataset for the classification model. The dataset itself encompassed a wide range of variables related to startup attributes and performance. The F1-score metric was utilized to evaluate the model's accuracy while minimizing false positive predictions that could potentially mislead investors. Gradient Boosting algorithm achieved an F1-score of 86% for predicting successful startups and 85% for predicting unsuccessful ones. The low false positive prediction rate of 7.9% on the test data further validates the model's reliability. The findings demonstrate the effectiveness of Gradient Boosting in predicting startup success with high accuracy and minimal false positives

Predictive value of hematocrit, serum albumin level difference, and fibrinogen-to-albumin ratio for COVID-19-associated acute respiratory failure

BackgroundAcute respiratory failure is the main clinical manifestation and a major cause of death in patients with COVID-19. However, few reports on its prevention and control have been published because of the need for laboratory predictive indicators. This study aimed to evaluate the predictive value of hematocrit level, serum albumin level difference, and fibrinogen-to-albumin ratio for COVID-19-associated acute respiratory failure. Material and methodsA total of 120 patients with COVID-19 from the First Affiliated Hospital of Anhui Medical University were selected between December 2022 and March 2023. Patients were divided into acute respiratory failure and non-acute respiratory failure groups and compared patient-related indicators between them using univariate and multivariate logistic regression analyses. Receiver operating characteristic analysis was performed to determine the discrimination accuracy. ResultsIn total, 48 and 72 patients were enrolled in the acute respiratory failure and non-acute respiratory failure groups, respectively. The Quick COVID-19 Severity Index scores, fibrinogen-to-albumin ratio, hematocrit and serum albumin level difference, fibrinogen, and hematocrit levels were significantly higher in the acute respiratory failure group than in the non-acute respiratory failure group. A Quick COVID-19 Severity Index >7, fibrinogen-to-albumin ratio >0.265, and hematocrit and serum albumin level difference >12.792 had a 96.14 % positive predictive rate and a 94.06 % negative predictive rate. ConclusionBoth fibrinogen-to-albumin ratio and hematocrit and serum albumin level difference are risk factors for COVID-19-associated acute respiratory failure. The Quick COVID-19 Severity Index score combined with fibrinogen-to-albumin ratio, and hematocrit and serum albumin level difference predict high and low risks with better efficacy and sensitivity than those of the Quick COVID-19 Severity Index score alone; therefore, these parameters can be used collectively as a risk stratification method for assessing patients with COVID-19.

Automatic multi-label diagnosis of single-lead ECG using novel hybrid residual recurrent convolutional neural networks

Arrhythmia is a prevalent cardiovascular disease that can unveil various heart health issues. In recent times, the rise of wearable devices has garnered attention towards the advantages of portable single-lead ECG devices in heart health monitoring. Achieving end-to-end ECG automatic diagnosis through deep learning is essential due to the time-consuming and labour-intensive characteristics of manual diagnosis of ECG records. This paper presents the design of a hybrid residual recurrent convolutional neural network (HRRCNN) for automatically diagnosing single-lead ECG with multiple labels. Firstly, the convolutional layers and residual networks extract the spatial and short-term temporal features. Subsequently, a hybrid recurrent neural network (RNN) comprised of a double-layer bidirectional gated recurrent unit (GRU) and a bidirectional long short-term memory (LSTM) is employed to capture long and short-term temporal features. Finally, an output layer, comprising an attention layer and a fully connected layer, converts the extracted features into classification results. To evaluate the performance of HRRCNN, a dataset from the Shanghai First People’s Hospital Affiliated to Shanghai JiaoTong University(Shanghai General Hospital, SGH) is utilized. The experimental results demonstrate that HRRCNN achieves an accuracy of 95.08 %, F1-macro of 87.22 %, Sensitivity of 88.51 %, and a positive prediction rate of 86.13 %. Comparative analysis with existing methods underscores the superior performance of HRRCNN, thereby establishing its potential as an out-of-hospital heart health monitoring tool and an auxiliary tool in clinical settings.

Computer Vision for Identification of Increased Fetal Heart Variability in Cardiotocogram

Introduction: Increased fetal heart rate variability (IFHRV), defined as fetal heart rate (FHR) baseline amplitude changes of >25 beats per minute with a duration of ≥1 min, is an early sign of intrapartum fetal hypoxia. This study evaluated the level of agreement of machine learning (ML) algorithms-based recognition of IFHRV patterns with expert analysis. Methods: Cardiotocographic recordings and cardiotocograms from 4,988 singleton term childbirths were evaluated independently by two expert obstetricians blinded to the outcomes. Continuous FHR monitoring with computer vision analysis was compared with visual analysis by the expert obstetricians. FHR signals were graphically processed and measured by the computer vision model labeled SALKA. Results: In visual analysis, IFHRV pattern occurred in 582 cardiotocograms (11.7%). Compared with visual analysis, SALKA recognized IFHRV patterns with an average Cohen’s kappa coefficient of 0.981 (95% CI: 0.972–0.993). The sensitivity of SALKA was 0.981, the positive predictive rate was 0.822 (95% CI: 0.774–0.903), and the false-negative rate was 0.01 (95% CI: 0.00–0.02). The agreement between visual analysis and SALKA in identification of IFHRV was almost perfect (0.993) in cases (N = 146) with neonatal acidemia (i.e., umbilical artery pH <7.10). Conclusions: Computer vision analysis by SALKA is a novel ML technique that, with high sensitivity and specificity, identifies IFHRV features in intrapartum cardiotocograms. SALKA recognizes potential early signs of fetal distress close to those of expert obstetricians, particularly in cases of neonatal acidemia.

Utility of the United Kingdom National Health Services Breast Screening Program Diagnostic Protocol in Fine-needle Aspiration Cytology with Cell Block Preparation in Cases of Palpable Breast Lumps: A Reliable, Fast, and Accurate Diagnostic Method for the Assessment of Breast Lumps with Histopathologic Correlation.

A palpable breast lump is a common diagnostic problem for clinicians and surgeons. Fine-needle aspiration cytology (FNAC) has many advantages such as less cost, less sample processing time, less pain, less chance of hematoma, and less discomfort. FNAC with cell block preparation further increased both sensitivity and specificity by nearly 100%. With the cell block preparation, we can also use newer tests like estrogen receptor-progesterone receptor-human epidermal growth factor receptor 2. The aim of this study was to derive conclusions about the correlation, including sensitivity, specificity, positive and negative predictive values (NPVs), and the diagnostic accuracy of FNAC, with or without cell blocks, compared to the final histopathology in cases of palpable breast masses. A cross-sectional prospective study was conducted after getting approval from the Human Ethics Research Committee from January 2018 to December 2019, which included 65 patients. Patients diagnosed clinically for breast lumps who underwent diagnostic FNAC with cell block, followed by a histopathological examination at our hospital, were included in the study. FNAC without cell block sensitivity, specificity, positive predictive value (PPV), NPV, efficiency rate, and diagnostic accuracy are 91.3%, 100%, 100%, 90.1%, 86.2%, and 96.5%, respectively. FNAC with cell block sensitivity, specificity, PPV, NPV, efficiency rate, and diagnostic accuracy are all 100%. All of our results beat the standard estimate. Fine-needle aspiration cytology is a patient-friendly, easy, reliable, repeatable, and simple diagnostic test. Whenever it is combined with cell block preparation, improves the accuracy of FNAC diagnosis which is more accurate and comparable to golden-standard biopsy with histopathology examination.

Evaluating convolutional neural network-enhanced electrocardiography for hypertrophic cardiomyopathy detection in a specialized cardiovascular setting.

The efficacy of convolutional neural network (CNN)-enhanced electrocardiography (ECG) in detecting hypertrophic cardiomyopathy (HCM) and dilated HCM (dHCM) remains uncertain in real-world applications. This retrospective study analyzed data from 19,170 patients (including 140 HCM or dHCM) in the Shinken Database (2010-2017). We evaluated the sensitivity, positive predictive rate (PPR), and F1 score of CNN-enhanced ECG in a ''basic diagnosis'' model (total disease label) and a ''comprehensive diagnosis'' model (including disease subtypes). Using all-lead ECG in the "basic diagnosis" model, we observed a sensitivity of 76%, PPR of 2.9%, and F1 score of 0.056. These metrics improved in cases with a diagnostic probability of ≥ 0.9 and left ventricular hypertrophy (LVH) on ECG: 100% sensitivity, 8.6% PPR, and 0.158 F1 score. The ''comprehensive diagnosis'' model further enhanced these figures to 100%, 13.0%, and 0.230, respectively. Performance was broadly consistent across CNN models using different lead configurations, particularly when including leads viewing the lateral walls. While the precision of CNN models in detecting HCM or dHCM in real-world settings is initially low, it improves by targeting specific patient groups and integrating disease subtype models. The use of ECGs with fewer leads, especially those involving the lateral walls, appears comparably effective.

Identifying patients with acute aortic dissection using an electrocardiogram with convolutional neural network

BackgroundThe potential of utilizing artificial intelligence with electrocardiography (ECG) for initial screening of aortic dissection (AD) is promising. However, achieving a high positive predictive rate (PPR) remains challenging. Methods and resultsThis retrospective analysis of a single-center, prospective cohort study (Shinken Database 2010–2017, N = 19,170) used digital 12-lead ECGs from initial patient visits. We assessed a convolutional neural network (CNN) model's performance for AD detection with eight-lead (I, II, and V1-6), single-lead, and double-lead (I, II) ECGs via five-fold cross-validation. The mean age was 63.5 ± 12.5 years for the AD group (n = 147) and 58.1 ± 15.7 years for the non-AD group (n = 19,023). The CNN model achieved an area under the curve (AUC) of 0.936 (standard deviation [SD]: 0.023) for AD detection with eight-lead ECGs. In the entire cohort, the PPR was 7 %, with 126 out of 147 AD cases correctly diagnosed (sensitivity 86 %). When applied to patients with D-dimer levels ≥1 μg/dL and a history of hypertension, the PPR increased to 35 %, with 113 AD cases correctly identified (sensitivity 86 %). The single V1 lead displayed the highest diagnostic performance (AUC: 0.933, SD: 0.03), with PPR improvement from 8 % to 38 % within the same population. ConclusionsOur CNN model using ECG data for AD detection achieved an over 30% PPR when applied to patients with elevated D-dimer levels and hypertension history while maintaining sensitivity. A similar level of performance was observed with a single-lead V1 ECG in the CNN model.

Erken Evre Karaciğer Fibrozisini Öngörmede Shear Wave Elastografinin Rolü

Aim: We examined the relationship between shear wave elastography (SWE) values and histopathological results in our study. Thus, we found the sensitivity of SWE in demonstrating early fibrosis. Materials and Methods: A total of consecutive 70 patients with chronic hepatitis B were prospectively evaluated. The patients included in fibrosis stages (F) 0, 1, 2, 3 and 4 according to Ishak scoring were examined with SWE. SWE measurements of F2, F3 and F4 patients who were found to have early stage fibrosis were compared with those of F0 and F1 patients. Results: The velocity+SD, and kPa+SD values in the group requiring treatment (F2, F3 and F4) were significantly higher than the group not requiring treatment (F0 and F1 )(p &amp;lt; 0.05). The sensitivity rate of the 1.85 cut-off value for velocity+SD was 53.8%, the positive prediction rate was 80.8%, the specificity rate was 83.3%, and the negative prediction rate was 58.1%. For kPa+SD, the cut-off value of 10.8 had a sensitivity rate of 51.3%, a positive prediction rate of 95.2%, a specificity of 96.7%, and a negative predictive rate of 60.4%. A significant correlation was observed between the fibrosis score and the kPa+SD distribution. Conclusion: SWE can differentiate the patients requiring treatment (F2, F3 and F4) from the patients not requiring treatment.

Hybrid Integration of Bagging and Decision Tree Algorithms for Landslide Susceptibility Mapping

Landslides represent a significant global natural hazard, threatening human settlements and the natural environment. The primary objective of the study was to develop a landslide susceptibility modeling approach that enhances prediction accuracy and informs land-use planning decisions. The study utilized a hybrid ensemble-based methodology to improve prediction accuracy and effectively capture the complexity of landslide susceptibility patterns. This approach harnessed the power of ensemble models, employing a bagging algorithm with base learners, including the reduced error pruning decision tree (REPTree) and functional tree (FT) models. Ensemble models are particularly valuable because they combine the strengths of multiple models, enhancing the overall performance and robustness of the landslide susceptibility prediction. The study focused on Yanchuan County, situated within the hilly and gully region of China’s Loess Plateau, known for its susceptibility to landslides, using sixteen critical landslide conditioning factors, encompassing topographic, environmental, and geospatial variables, namely elevation, slope, aspect, proximity to rivers and roads, rainfall, the normalized difference vegetation index, soil composition, land use, and more. Model performances were evaluated and verified using a range of metrics, including receiver operating characteristic (ROC) curves, trade-off statistical metrics, and chi-square analysis. The results demonstrated the superiority of the integrated models, particularly the bagging FT (BFT) model, in accurately predicting landslide susceptibility, as evidenced by its high area under the curve area (AUC) value (0.895), compared to the other models. The model excelled in both positive predictive rate (0.847) and negative predictive rate (0.886), indicating its efficacy in identifying landslide and non-landslide areas and also in the F-score metric with a value of 0.869. The study contributes to the field of landslide risk assessment, offering a significant investigation tool for managing and mitigating landslide hazards in Yanchuan County and similar regions worldwide.

Accuracy of dual-energy computed tomography for bone marrow edema in the sacroiliac joint: A systematic review and meta-analysis.

This systematic literature review and meta-analysis aimed to assess the accuracy, sensitivity, and specificity of dual-energy computed tomography (DECT) of the sacroiliac joint. Bone marrow edema (BME) of the sacroiliac joint is an early manifestation of some diseases, such as ankylosing spondylitis, and is usually examined by nuclear magnetic resonance imaging (MRI); however, MRI can be intolerable for some patients; hence, numerous studies have analyzed DECT examinations. We searched PUBMED, CNKI, and EMBASE in 2023 for articles containing the following terms (DECT) or (DE-CT) or (dual-energy CT) or "dual-energy CT" or (dual-energy computed tomography) and ((sacroiliac joint) or (ankylosing spondylitis) or (sacroiliac arthritis) or (sacroiliitis)). An initial search identified 444 articles, of which 7 met the criteria. Data were extracted to calculate the sensitivity, specificity, and diagnostic odds for analysis using R software. Out of 291 patients and 577 sacroiliac joints, 429 (74.35%) exhibited BME. All studies used magnetic resonance as the control group. The overall sensitivity and specificity of DECT were 79%, and 92%, respectively, with positive prediction rate of 92.55% and negative prediction rate of 83.73%. DECT appears to be a promising diagnostic tool for detecting BME in the sacroiliac joint and can be used as an alternative examination method for patients in whom MRI is contraindicated.

ECG classification efficient modeling with artificial bee colony optimization data augmentation and attention mechanism.

In addressing the key issues of the data imbalance within ECG signals and modeling optimization, we employed the TimeGAN network and a local attention mechanism based on the artificial bee colony optimization algorithm to enhance the performance and accuracy of ECG modeling. Initially, the TimeGAN network was introduced to rectify data imbalance and create a balanced dataset. Furthermore, the artificial bee colony algorithm autonomously searched hyperparameter configurations by minimizing Wasserstein distance. Control experiments revealed that data augmentation significantly boosted classification accuracy to 99.51%, effectively addressing challenges with unbalanced datasets. Moreover, to overcome bottlenecks in the existing network, the introduction of the Efficient network was adopted to enhance the performance of modeling optimized with attention mechanisms. Experimental results demonstrated that this integrated approach achieved an impressive overall accuracy of 99.70% and an average positive prediction rate of 99.44%, successfully addressing challenges in ECG signal identification, classification, and diagnosis.

Comparison of long-read sequencing and MLPA combined with long-PCR sequencing of CYP21A2 mutations in patients with 21-OHD.

21-Hydroxylase deficiency (21-OHD) is caused by mutations in the CYP21A2 gene. Due to the complex structure and the high genetic heterogeneity of the CYP21A2 gene, genetic testing for 21-OHD is currently facing challenges. Moreover, there are no comparative studies on detecting CYP21A2 mutations by both second-generation sequencing and long-read sequencing (LRS, also known as third-generation sequencing). To detect CYP21A2 variations in 21-OHD patients using targeted capture with LRS method based on the PacBio (Pacific Biosciences) Sequel II platform. A total of 67 patients with 21-OHD were admitted in Wuhan Children's Hospital. The full sequence of CYP21A2 gene was analyzed by targeted capture combined with LRS based on the PacBio Sequel II platform. The results were compared with those of long-polymerase chain reaction (Long-PCR) combined with multiplex ligation probe amplification (MLPA) detection. Based on the in vitro study of 21-hydroxylase activity of common mutations, the patient genotypes were divided into groups of Null, A, B, and C, from severe to mild. The correlation between different genotype groups and clinical typing was observed. The study analyzed a total of 67 patients. Among them, 44 (65.67%) were males and 23 (34.33%) were females, with a male-to-female ratio of approximately 1.9:1. A total of 27 pathogenic variants were identified in the 67 patients, of which micro-conversion accounted for 61.9%, new variants of CYP21A2 accounted for 8.2%; deletion accounted for 22.4% (CYP21A2 single deletion and chimeric TNXA/TNXB accounted for 12.7%, chimeric CYP21A1P/CYP21A2 accounted for 9.7%); and duplication accounted for 3.0% (CYP21A2 Gene Duplication). I2G was the most common variant (26.9%). Targeted capture LRS and MLPA combined with Long-PCR detection of CYP21A2 mutations showed 30 detection results with differences. The overall genotype-phenotype correlation was 82.1%. The positive predictive rate of the Null group for salt wasting (SW) type was 84.6%, the A group for SW type was 88.9%, the group B for simple virilization (SV) type was 82.4%, and the group C for SV type was 62.5%. The correlation coefficient rs between the severity of the phenotype and the genotype group was 0.682 (P < 0.05). Targeted capture combined with LRS is an integrated approach for detecting CYP21A2 mutations, allowing precise determination of connected sites for multiple deletions/insertions and cis/trans configurations without analyzing parental genomic samples. The overall genotype-phenotype correlation for 21-OHD is generally strong, with higher associations observed between genotype and phenotype for group Null, A, and B mutations, and larger genotype-phenotype variation in group C mutations. Targeted capture with LRS sequencing offers a new method for genetic diagnosis in 21-OHD patients.

Application of artificial intelligence-based dual source CT scanning in the differentiation of lung adenocarcinoma in situ and minimally invasive adenocarcinoma.

Lung adenocarcinoma is the most common type of lung cancer with highly incidence and mortality. Due to the overlap of morphological features, it is difficult to distinguish clinically between preinvasive lesions (in situ adenocarcinoma, AIS) and invasive lesions (minimally invasive adenocarcinoma, MIA), which appear as ground glass cloudy nodules. This study was performed to probe the application value of artificial intelligence (AI)-based dual source CT scanning in the differentiation of AIS as well as MIA. The clinical data of 136 patients in Shanghai Baoshan Hospital of Integrated Traditional Chinese and Western Medicine from January 2019 to January 2022 were retrospectively analyzed. The accuracy of AI in distinguishing lung AIS (n=76) and MIA (n=60) were analyzed. The effectiveness of AI in detecting nodules and its diagnostic efficacy for AIS and MIA were explored. The proportion of patients with clear and regular lesion boundaries in AIS was higher than that in MIA. The mean lesion diameter of AIS patients was shorter than MIA patients. There was no difference in the CT value between AIS and MIA in the ground glass nodule density area of pure ground glass nodule and mixed ground glass nodule, but the CT value of the solid nodule density area in AIS was lower. The occurrence of pulmonary vascular abnormality, air bronchogram sign, and pleural depression in AIS patients were lower than MIA patients. The detection rate of AI for lung adenocarcinoma with nodule diameter ≤ 5 mm, complete solid nodules and ground glass nodules was significantly higher than radiologists. The sensitivity, specificity, positive prediction rate, negative prediction rate and accuracy of AI detection were significantly higher than radiologists. AI-based dual source CT scanning can clearly show the morphological characteristics of lung adenocarcinoma, which is helpful for the differential diagnosis of lung AIS as well as MIA.

SEResUTer: a deep learning approach for accurate ECG signal delineation and atrial fibrillation detection

Objective. Accurate detection of electrocardiogram (ECG) waveforms is crucial for computer-aided diagnosis of cardiac abnormalities. This study introduces SEResUTer, an enhanced deep learning model designed for ECG delineation and atrial fibrillation (AF) detection. Approach. Built upon a U-Net architecture, SEResUTer incorporates ResNet modules and Transformer encoders to replace convolution blocks, resulting in improved optimization and encoding capabilities. A novel masking strategy is proposed to handle incomplete expert annotations. The model is trained on the QT database (QTDB) and evaluated on the Lobachevsky University Electrocardiography Database (LUDB) to assess its generalization performance. Additionally, the model’s scope is extended to AF detection using the the China Physiological Signal Challenge 2021 (CPSC2021) and the China Physiological Signal Challenge 2018 (CPSC2018) datasets. Main results. The proposed model surpasses existing traditional and deep learning approaches in ECG waveform delineation on the QTDB. It achieves remarkable average F1 scores of 99.14%, 98.48%, and 98.46% for P wave, QRS wave, and T wave delineation, respectively. Moreover, the model demonstrates exceptional generalization ability on the LUDB, achieving average SE, positive prediction rate, and F1 scores of 99.05%, 94.59%, and 94.62%, respectively. By analyzing RR interval differences and the existence of P waves, our method achieves AF identification with 99.20% accuracy on the CPSC2021 test set and demonstrates strong generalization on CPSC2018 dataset. Significance. The proposed approach enables highly accurate ECG waveform delineation and AF detection, facilitating automated analysis of large-scale ECG recordings and improving the diagnosis of cardiac abnormalities.