Independent Test Research Articles

Gluconeogenesis unraveled: A proteomic Odyssey with machine learning

The metabolic pathway known as gluconeogenesis, which produces glucose from non-carbohydrate substrates, is essential for maintaining balanced blood sugar levels while fasting. It’s extremely important to anticipate gluconeogenesis rates accurately to recognize metabolic disorders and create efficient treatment strategies. The implementation of deep learning and machine learning methods to forecast complex biological processes has been gaining popularity in recent years. The recognition of both the regulation of the pathway and possible therapeutic applications of proteins depends on accurate identification associated with their gluconeogenesis patterns. This article analyzes the uses of machine learning and deep learning models, to predict gluconeogenesis efficiency. The study also discusses the challenges that come with restricted data availability and model interpretability, as well as possible applications in personalized healthcare, metabolic disease treatment, and the discovery of drugs. The predictor utilizes statistics moments on the structures of gluconeogenesis and their enzymes, while Random Forest is utilized as a classifier to ensure the accuracy of this model in identifying the best outcomes. The method was validated utilizing the independent test, self-consistency, 10 k fold cross-validations, and jackknife test which achieved 92.33 %, 91.87 %, 87.88 %, and 87.02 %. An accurate prediction of gluconeogenesis has significant implications for understanding metabolic disorders and developing targeted therapies. This study contributes to the rising field of predictive biology by mixing algorithms for deep learning, and machine learning, with metabolic pathways.

Carbon dioxide storage and cumulative oil production predictions in unconventional reservoirs applying optimized machine-learning models

To achieve carbon dioxide (CO2) storage through enhanced oil recovery, accurate forecasting of CO2 subsurface storage and cumulative oil production is essential. This study develops hybrid predictive models for the determination of CO2 storage mass and cumulative oil production in unconventional reservoirs. It does so with two multi-layer perceptron neural networks (MLPNN) and a least-squares support vector machine (LSSVM), hybridized with grey wolf optimization (GWO) and/or particle swarm optimization (PSO). Large, simulated datasets were divided into training (70%) and testing (30%) groups, with normalization applied to both groups. Mahalanobis distance identifies/eliminates outliers in the training subset only. A non-dominated sorting genetic algorithm (NSGA-II) combined with LSSVM selected seven influential features from the nine available input parameters: reservoir depth, porosity, permeability, thickness, bottom-hole pressure, area, CO2 injection rate, residual oil saturation to gas flooding, and residual oil saturation to water flooding. Predictive models were developed and tested, with performance evaluated with an overfitting index (OFI), scoring analysis, and partial dependence plots (PDP), during training and independent testing to enhance model focus and effectiveness. The LSSVM-GWO model generated the lowest root mean square error (RMSE) values (0.4052 MMT for CO2 storage and 9.7392 MMbbl for cumulative oil production) in the training group. That trained model also exhibited excellent generalization and minimal overfitting when applied to the testing group (RMSE of 0.6224 MMT for CO2 storage and 12.5143 MMbbl for cumulative oil production). PDP analysis revealed that the input features “area” and “porosity” had the most influence on the LSSVM-GWO model's prediction performance. This paper presents a new hybrid modeling approach that achieves accurate forecasting of CO2 subsurface storage and cumulative oil production. It also establishes a new standard for such forecasting, which can lead to the development of more effective and sustainable solutions for oil recovery.

The links between symptom burden, illness perception, psychological resilience, social support, coping modes, and cancer-related worry in Chinese early-stage lung cancer patients after surgery: a cross-sectional study

ObjectivesThis study aims to investigate the links between the clinical, demographic, and psychosocial factors and cancer-related worry in patients with early-stage lung cancer after surgery.MethodsThe study utilized a descriptive cross-sectional design. Questionnaires, including assessments of cancer-related worry, symptom burden, illness perception, psychological resilience, coping modes, social support and participant characteristics, were distributed to 302 individuals in early-stage lung cancer patients after surgery. The data collection period spanned from January and October 2023. Analytical procedures encompassed descriptive statistics, independent Wilcoxon Rank Sum test, Kruskal-Wallis- H- test, Spearman correlation analysis, and hierarchical multiple regression.ResultsAfter surgery, 89.07% had cancer-related worries, with a median (interquartile range, IQR) CRW score of 380.00 (130.00, 720.00). The most frequently cited concern was the cancer itself (80.46%), while sexual issues were the least worrisome (44.37%). Regression analyses controlling for demographic variables showed that higher levels of cancer-related worry (CRW) were associated with increased symptom burden, illness perceptions, and acceptance-rejection coping modes, whereas they had lower levels of psychological resilience, social support and confrontation coping modes, and were more willing to obtain information about the disease from the Internet or applications. Among these factors, the greatest explanatory power in the regression was observed for symptom burden, illness perceptions, social support, and sources of illness information (from the Internet or applications), which collectively explained 52.00% of the variance.ConclusionsHealthcare providers should be aware that worry is a common issue for early stage lung cancer survivors with a favorable prognosis. During post-operative recovery, physicians should identify patient concerns and address unmet needs to improve patients’ emotional state and quality of life through psychological support and disease education.

Declining empathy trends throughout medical curriculum and association factors of low empathy among medical students and residents: a single center study

BackgroundA physician’s empathy level substantially impacts clinical competence, patient relationships, and treatment outcomes. Yet, understanding empathy trends from medical students to resident doctors within a single institution is limited. This study delves into empathy trends within a single-center academic setting and identifies factors associated with low empathy.MethodsThis cross-sectional study enrolled the second—to sixth-year medical students of Phramongkutklao College of Medicine and the first—to second-year residents at Phramongkutklao Hospital. It utilized a standardized questionnaire covering demographics, family relationships, the Maudsley Personality Inventory (MPI), and the Jefferson Scale of Empathy (JSE). The relationship between variables and JSE scores was analyzed using independent t-test, one-way ANOVA, and Chi-square tests. Multivariable logistic and linear regression analyses examined associated factors and trends across educational levels. A quadratic term was incorporated to evaluate the presence of a nonlinear trend.ResultsA total of 520 participants, comprising 189 (36.4%) preclinical students, 153 (29.4%) clinical students, and 178 (34.2%) residents, completed the survey. The JSE showed a Cronbach’s alpha of 0.83. The average empathy score was 103.8 ± 15.0, with 27.1% of low empathy levels. Specialty preference and sex-adjusted average empathy scores decreased from 114.5 (95%CI: 112.0–117.0) among second-year medical students to 95.2 (95%CI: 92.2–98.2) among second-year residents (Pnon−linear<0.001). The adjusted proportion of low empathy is highest among sixth-year medical students (54.4%, 95%CI: 34.4–73.2%). Factors associated with low empathy included those preferring procedure-oriented specialties (AOR: 4.16, 95%CI: 1.54–11.18) and a higher parental income (AOR: 2.97, 95%CI: 1.09 to 8.10). Subgroup analysis revealed that residents with a GPAX above 3.5 and those in technology-oriented specialties were also associated with lower empathy (AOR: 3.46, 95%CI: 1.40–8.59 and AOR: 2.93, 95%CI: 1.05–8.12, respectively).ConclusionA declining empathy trend was observed among medical students, which then plateaued among residents. Additionally, residents in technology-oriented specialties may require empathy enhancements due to their ongoing patient consultations. Addressing these issues requires collaborative planning between students and teachers to foster empathy throughout the medical curriculum.

Bioinformatics analysis-based mining of potential markers for inflammatory bowel disease and their immune relevance.

The incidence of inflammatory bowel disease (IBD) is increasing every year and is characterized by a prolonged course, frequent relapses, difficulty in curing, and a lack of more efficacious therapeutic biomarkers. The aim of this study was to find key core genes as therapeutic biomarkers for IBD. GSE75214 in Gene Expression Omnibus (GEO) was used as the experimental set. The genes in the top 25% of standard deviation of all samples in the experimental set were subjected to systematic weighted gene co-expression network analysis (WGCNA) to find candidate genes. Then, least absolute shrinkage and selection operator (LASSO) logistic regression was used to further screen the central genes. Finally, the validity of hub genes was verified on GEO dataset GSE179285 using "BiocManager" R package. Twelve well-preserved modules were identified in the experimental set using the WGCNA method. Among them, five modules significantly associated with IBD were screened as clinically significant modules, and four candidate genes were screened from these five modules. Then TIMP1, GUCA2B, and HIF1A were screened as hub genes. These hub genes successfully distinguished tumor samples from healthy tissues by artificial neural network algorithm in an independent test set with an area under the working characteristic curve of 0.946 for the subjects. IBD differentially expressed gene (DEGs) are involved in immunoregulatory processes. TIMP1, GUCA2B, and HIF1A, as core genes of IBD, have the potential to be therapeutic targets for patients with IBD, and our findings may provide a new outlook on the future treatment of IBD.

Automatic Transcranial Sonography-Based Classification of Parkinson's Disease Using a Novel Dual-Channel CNXV2-DANet.

Transcranial sonography (TCS) has been introduced to assess hyper-echogenicity in the substantia nigra of the midbrain for Parkinson's disease (PD); however, its subjective and resource-demanding nature has impeded its widespread application. An AI-empowered TCS-based PD classification tool is greatly demanding, yet relevant research is severely scarce. Therefore, we proposed a novel dual-channel CNXV2-DANet for TCS-based PD classification using a large cohort. A total of 1176 TCS images from 588 subjects were retrospectively enrolled from Beijing Tiantan Hospital, encompassing both the left and right side of the midbrain for each subject. The entire dataset was divided into a training/validation/testing set at a ratio of 70%/15%/15%. Development of the proposed CNXV2-DANet was performed on the training set with comparisons between the single-channel and dual-channel input settings; model evaluation was conducted on the independent testing set. The proposed dual-channel CNXV2-DANet was compared against three state-of-the-art networks (ConvNeXtV2, ConvNeXt, Swin Transformer). The results demonstrated that both CNXV2-DANet and ConvNeXt V2 performed more superiorly under dual-channel inputs than the single-channel input. The dual-channel CNXV2-DANet outperformed the single-channel, achieving superior average metrics for accuracy (0.839 ± 0.028), precision (0.849 ± 0.014), recall (0.845 ± 0.043), F1-score (0.820 ± 0.038), and AUC (0.906 ± 0.013) compared with the single channel metrics for accuracy (0.784 ± 0.037), precision (0.817 ± 0.090), recall (0.748 ± 0.093), F1-score (0.773 ± 0.037), and AUC (0.861 ± 0.047). Furthermore, the dual-channel CNXV2-DANet outperformed all other networks (all p-values < 0.001). These findings suggest that the proposed dual-channel CNXV2-DANet may provide the community with an AI-empowered TCS-based tool for PD assessment.

The Effectivenes Of Using Flash Cards To Teach Students' Vocabulary Mastery At SMP Darut Tauhid

Vocabulary is an essential element of language ability and serves as a foundation for pupils' speaking, listening, reading, and writing abilities.This study aims to determine the effectivenes of using flash cards to teach students’ vocabulary mastery at SMP Darut Tauhid. The research design is independent sample t-test, while the research method is quantitative. The participants in this study all student`classVII totaling 60 people, 30 male students and 30 female students. the data in this study were collected using instruments pre-test and posh-test (multiple choice), then normality test, homogeneity test and descriptive statistics were used to evaluate data analysis requirements. in this study the independent sample t test analysis was used to test the hypothesis using computer software assistance through the SPSS (Statistcal Package For the Scial Sciens) version 25 for windows program. Based on the results of research and discussion, the following conclusions can be drawn: There is an effectivenes of using flash cards to teach students’ vocabulary mastery at SMP Darut Tauhid. This is indicated by the results of the significance (2-tailed) of 0.000 &lt; 0.05 then as the basis for the performance of the decision in the independent sample test, it can be concluded that H0 is rejected and Ha is accepted. Thus, it can be concluded that there is The use of Flash cards effective on students‟ vocabulary at SMP Darut Tauhid.

7T-high resolution MRI-derived radiomic analysis for the identification of symptomatic intracranial atherosclerotic plaques.

High-resolution magnetic resonance imaging (HR-MRI) allows for detailed visualization of intracranial atherosclerotic plaques. Radiomics can be used as a tool for objective quantification of the plaque's characteristics. We analyzed the radiomics features (RFs) obtained from 7 T HR-MRI of patients with intracranial atherosclerotic disease (ICAD) to determine distinct characteristics of culprit and non-culprit plaques. Patients with stroke due to ICAD underwent HR-MRI. Culprit plaques in the vascular territory of the stroke were identified. Degree of stenosis, area degree of stenosis and plaque burden were calculated. A three-dimensional segmentation of the plaque was performed, and RFs were obtained. A machine learning model for prediction and identification of culprit plaques using significantly different RFs was evaluated. The study included 33 patients with ICAD as stroke etiology. Univariate analysis revealed 24 RFs in pre-contrast MRI, 21 in post-contrast MRI, 13 RFs that were different between pre and post contrast MRIs. Additionally, six shape-based RFs significantly differed from culprit and non-culprit plaques. The random forest model achieved an accuracy rate of 81% (88% sensitivity and 75% specificity) in identifying culprit plaques in the independent testing dataset. This model successfully identified the culprit plaques in all patients during the testing phase. Symptomatic plaques had a distinct signature RFs compared to other plaques within the same subject. A machine learning model built with RFs successfully identified the symptomatic atherosclerotic plaques in most cases. Radiomics is a promising tool for stratification of plaques in patients with ICAD.

Pengaruh Model Pembelajaran Reciprocal Teaching terhadap Keaktifan Belajar Peserta Didik Pendidikan Agama Kristen dan Budi Pekerti Kelas VIII SMP Negeri 2 Pollung Tahun Pembelajaran 2023/2024

The aim of this research is to find out whether there is a difference in the learning activity of students who use the reciprocal teaching model compared to conventional ones in class VIII Christian Religious Education and Character education at SMP Negeri 2 Pollung for the 2023/2024 academic year. The research hypothesis is: "The Reciprocal Teaching Model has a positive and significant effect on the Learning Activeness of Christian Religious Education and Character Education Students in Class VIII of SMP Negeri 2 Pollung for the 2023/2024 Academic Year." The population is all students who are Protestant Christians in Class VIII of SMP Negeri 2 Pollung which consists of 6 classes totaling 180 students. The research sample was determined using the Purposive Sampling technique, namely 30 students in class VIII5 as the experimental class which used the reciprocal teaching model and 30 students in class VIII4 as the control class which used ordinary treatment (conventional class). This research method is the Quasi Experimental Design method using a Nonequivalent Control Design. The instrument used in this research was a test with 30 items. Research data for the questionnaire was analyzed using the average difference test formula (N-Gain Score). It was found that the average value for the experimental class was 0.6370 in the medium category, while the average value for the control class was 0.2531. in the low category so it is known that increasing the Learning Activeness of Class VIII Christian Religious Education and Character Education students at SMP Negeri 2 Pollung for the 2023/2024 academic year is more effective using the Reciprocal Teaching model than using conventional treatment. Then carrying out an independent test using the t test obtained a value of t = 7.040 &gt; t table (α = 0.05; df = 58) = 2,000. Thus, it can be concluded that the research hypothesis is accepted, namely that there is a difference in the learning activity of students before and after learning with the Reciprocal Teaching Model in Learning Christian Religious Education and Character Education for Class VIII SMP Negeri 2 Pollung for the 2023/2024 Academic Year and H0 is rejected.

Lifetime depression and mania/hypomania risk predicted by neural markers in three independent young adult samples during working memory and emotional regulation.

Objective markers of pathophysiological processes underlying lifetime depression and mania/hypomania risk can provide biologically informed targets for novel interventions to help prevent the onset of affective disorders in individuals with subsyndromal symptoms. Greater activity within and functional connectivity (FC) between the central executive network (CEN), supporting emotional regulation (ER) subcomponent processes such as working memory (WM), the default mode network (DMN), supporting self-related information processing, and the salience network (SN), is thought to interfere with cognitive functioning and predispose to depressive disorders. Using an emotional n-back paradigm designed to examine WM and ER capacity, we examined in young adults: (1) relationships among activity and FC in these networks and lifetime depression and mania/hypomania risk; (2) the extent to which these relationships were specific to lifetime depression risk versus lifetime mania/hypomania risk; (3) whether findings in a first, Discovery sample n = 101, 63 female, age = 23.85 (2.9) could be replicated in a two independent Test samples of young adults: Test sample 1: n = 90, 60 female, age = 21.7 (2.0); Test sample 2: n = 96, 65 female, age = 21.6 (2.1). The Mood Spectrum Self-Report (MOODS-SR-L) assessed lifetime mania/hypomania risk and depression risk. We showed significant clusters of activity to each contrast in similar locations in the anatomic mask in each Test sample as in the Discovery sample, and, using extracted mean BOLD signal from these clusters as IVs, we showed similar patterns of IV-DV relationships in each Test sample as in the Discovery sample. Specifically, in the Discovery sample, greater DMN activity during WM was associated with greater lifetime depression risk. This finding was specific to depression and replicated in both independent samples (all ps<0.05 qFDR). Greater CEN activity during ER was associated with increased lifetime depression risk and lifetime mania/hypomania risk in all three samples (all ps< 0.05 qFDR). These replicated findings provide promising objective, neural markers to better identify, and guide and monitor early interventions for, depression and mania/hypomania risk in young adults.

Clear Cell Renal Cell Carcinoma: Characterizing the Phenotype of Von Hippel-Lindau Mutation Using MRI.

The von Hippel-Lindau (VHL) mutation is an important alteration in clear cell renal cell carcinoma (ccRCC); however, its imaging phenotype remains unclear. To investigate whether MRI features can reflect the VHL mutation status. Retrospective. 3 T/fast spin echo T2-weighted, spin-echo echo planar diffusion-weighted, gradient recalled echo T1-weighted, gradient recalled echo chemical-shift T1-weighted, and contrast-enhanced gradient recalled echo T1-weighted sequences. One hundred five patients with ccRCC who underwent preoperative contrast-enhanced MRI and subsequent genomic sequencing: 59 consecutive patients from our institution (38 [64.41%] with VHL mutations) formed a training cohort, and 46 from The Cancer Genome Atlas (TCGA) database (24 [52.17%] with VHL mutations) formed an independent test cohort. Two radiologists, with 23 and 33 years of experience respectively, jointly evaluated the semantic MRI features of the primary lesion in ccRCCs to propose potential features related to VHL mutations in both cohorts. Three additional readers, with 5, 7, and 10 years of experience respectively, independently reviewed all lesions to assess the interobserver agreement of MRI features. A VHL mutational likelihood score (VHL-MULIS) system was constructed using the training cohort and validated using the independent test cohort. Fisher's test or chi-square test, t-test or Mann-Whitney U test, logistic regression, Cohen's kappa (κ), area under the receiver operating characteristic curve (AUC). A two-sided P value <0.05 was considered statistically significant. In both the local and public cohorts, T2-weighted signal intensity and presence of microscopic fat from primary lesions were significantly associated with VHL mutation status. The VHL-MULIS incorporated maximum diameter, T2-weighted signal intensity, and presence of microscopic fat in the training cohort and demonstrated promising diagnostic ability (AUC, 0.82; sensitivity, 0.79; specificity, 0.82) and substantial interobserver agreement (κ, 0.787) in the test cohort. The VHL mutation exhibited a distinct MRI phenotype. Integrating multiple semantic MRI features has potential to reflect the mutation status in patients with ccRCC. 3 TECHNICAL EFFICACY: Stage 2.

Multitask Learning on Graph Convolutional Residual Neural Networks for Screening of Multitarget Anticancer Compounds.

Recently, various modern experimental screening pipelines and assays have been developed to find promising anticancer drug candidates. However, it is time-consuming and almost infeasible to screen an immense number of compounds for anticancer activity via experimental approaches. To partially address this issue, several computational advances have been proposed. In this study, we present iACP-GCR, a model based on multitask learning on graph convolutional residual neural networks with two types of shortcut connections, to identify multitarget anticancer compounds. In our architecture, the graph convolutional residual neural networks are shared by all the prediction tasks before being separately customized. The NCI-60 data set, one of the most reliable and well-known sources of experimentally verified compounds, was used to develop our model. From that data set, we collected and refined data about compounds screened across nine cancer types (panels), including breast, central nervous system, colon, leukemia, nonsmall cell lung, melanoma, ovarian, prostate, and renal, for model training and evaluation. The model performance evaluated on an independent test set shows that iACP-GCR surpasses the three advanced computational methods for multitask learning. The integration of two shortcut connection types in the shared networks also improves the prediction efficiency. We also deployed the model as a public web server to assist the research community in screening potential anticancer compounds.

Perpaduan Metode Debate dan Numbered Head Together terhadap Keaktifan Belajar dan Kepercayaan Diri Siswa pada Mata Pelajaran Pendidikan Agama Kristen

In order for students to achieve the best learning outcomes, they must be involved in their studies and confident. Combining the debate method and the Number Head method together is one of the useful strategies to increase self-confidence and activity. If the Number Head Together method encourages students to actively participate in their education, the debate method seeks to develop students' self-confidence in voicing their opinions. The purpose of this study was to determine the difference in the influence of the experimental class and the control class. The Independent T-Test and Test 3 (Hotteling's T2 Test) were used in experimental research and hypothesis testing. From the first hypothesis test, the Sig value was produced. 0.068&gt; 0.05, which means that there is no effect of learning with a combination of the Number Head Together - Debate Method and learning without treatment on student learning activity. While the results of the second Hypothesis test show a Sig value. 0.416&gt; 0.05, namely there is no effect of learning with a combination of the Number Head Together - Debate Method on student self-confidence. And the results of the Hotteling T2 test show that the ρ-value for learning activity is 0.342 &gt; 0.05, meaning that there is no difference in the average learning activity between students from both classes. The ρ-value for self-confidence is 0.049 &lt; 0.05, meaning that there is a difference in the average self-confidence between students from both classes.

A Point Cloud Graph Neural Network for Protein-Ligand Binding Site Prediction.

Predicting protein-ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein-ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein-ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket's advancement and practicality for protein-ligand binding site prediction.

Investigation of the Epidemiological Situation of Malta Fever in the Cities under Mashhad University of Medical Sciences during the years 2016 to 2022

Background Management of Malta fever disease requires policy-making and accurate epidemiological statistics and information. Aim The present study was conducted to determine the epidemiological status of Malta fever. Materials and Methods This study is of the secondary data analysis type, which was conducted using the recorded data of patients with brucellosis in the health center of Mashhad City from 2016 to 2022. Data related to 12,714 cases of brucellosis were analyzed using R software and Chi-2, Pearson, and independent t-statistical tests. Results The average age of the patients was 33.18 ± 18.81 years. About 87% of disease cases were related to rural areas and 13% to urban areas. The average annual incidence of the disease was 287 cases per 100,000 population at risk of the disease. The highest incidence rate was in 2020, and the lowest incidence rate was in 2016. The most cases of disease were related to the first three months of the year, and the least cases were related to the last three months of the year. Most cases of the disease were related to housewives, cattle breeders, and farmers. Conclusion The incidence of the disease increased from the beginning of the study to 2020 and decreased from 2020 to the end of the study. Health policymakers should integrate medicine, ecology, and education for the prevention and control of brucellosis. This holistic strategy recognizes the interconnectedness of human, animal, and environmental health, emphasizing the need for collaborative efforts across sectors to address the multifaceted nature of the disease.

Fast intraoperative detection of primary CNS lymphoma and differentiation from common CNS tumors using stimulated Raman histology and deep learning.

Accurate intraoperative diagnosis is crucial for differentiating between primary CNS lymphoma (PCNSL) and other CNS entities, guiding surgical decision-making, but represents significant challenges due to overlapping histomorphological features, time constraints, and differing treatment strategies. We combined stimulated Raman histology (SRH) with deep learning to address this challenge. We imaged unprocessed, label-free tissue samples intraoperatively using a portable Raman scattering microscope, generating virtual H&E-like images within less than three minutes. We developed a deep learning pipeline called RapidLymphoma based on a self-supervised learning strategy to (1) detect PCNSL, (2) differentiate from other CNS entities, and (3) test the diagnostic performance in a prospective international multicenter cohort and two additional independent test cohorts. We trained on 54,000 SRH patch images sourced from surgical resections and stereotactic-guided biopsies, including various CNS tumor/non-tumor lesions. Training and test data were collected from four tertiary international medical centers. The final histopathological diagnosis served as ground-truth. In the prospective test cohort of PCNSL and non-PCNSL entities (n=160), RapidLymphoma achieved an overall balanced accuracy of 97.81% ±0.91, non-inferior to frozen section analysis in detecting PCNSL (100% vs. 78.94%). The additional test cohorts (n=420, n=59) reached balanced accuracy rates of 95.44% ±0.74 and 95.57% ±2.47 in differentiating IDH-wildtype diffuse gliomas and various brain metastasis from PCNSL. Visual heatmaps revealed RapidLymphoma's capabilities to detect class-specific histomorphological key features. RapidLymphoma is valid and reliable in detecting PCNSL and differentiating from other CNS entities within three minutes, as well as visual feedback in an intraoperative setting. This leads to fast clinical decision-making and further treatment strategy planning.

Expert-Level Detection of Referable Glaucoma from Fundus Photographs in a Safety Net Population: The AI and Teleophthalmology in Los Angeles Initiative.

To develop and test a deep learning (DL) algorithm for detecting referable glaucoma in the Los Angeles County (LAC) Department of Health Services (DHS) teleretinal screening program. Fundus photographs and patient-level labels of referable glaucoma (defined as cup-to-disc ratio [CDR] ≥ 0.6) provided by 21 trained optometrist graders were obtained from the LAC DHS teleretinal screening program. A DL algorithm based on the VGG-19 architecture was trained using patient-level labels generalized to images from both eyes. Area under the receiver operating curve (AUC), sensitivity, and specificity were calculated to assess algorithm performance using an independent test set that was also graded by 13 clinicians with one to 15 years of experience. Algorithm performance was tested using reference labels provided by either LAC DHS optometrists or an expert panel of 3 glaucoma specialists. 12,098 images from 5,616 patients (2,086 referable glaucoma, 3,530 non-glaucoma) were used to train the DL algorithm. In this dataset, mean age was 56.8 ± 10.5 years with 54.8% females and 68.2% Latinos, 8.9% Blacks, 2.7% Caucasians, and 6.0% Asians. 1,000 images from 500 patients (250 referable glaucoma, 250 non-glaucoma) with similar demographics (p ≥ 0.57) were used to test the DL algorithm. Algorithm performance matched or exceeded that of all independent clinician graders in detecting patient-level referable glaucoma based on LAC DHS optometrist (AUC = 0.92) or expert panel (AUC = 0.93) reference labels. Clinician grader sensitivity (range: 0.33-0.99) and specificity (range: 0.68-0.98) ranged widely and did not correlate with years of experience (p ≥ 0.49). Algorithm performance (AUC = 0.93) also matched or exceeded the sensitivity (range: 0.78-1.00) and specificity (range: 0.32-0.87) of 6 LAC DHS optometrists in the subsets of the test dataset they graded based on expert panel reference labels. A DL algorithm for detecting referable glaucoma developed using patient-level data provided by trained LAC DHS optometrists approximates or exceeds performance by ophthalmologists and optometrists, who exhibit variable sensitivity and specificity unrelated to experience level. Implementation of this algorithm in screening workflows could help reallocate eye care resources and provide more reproducible and timely glaucoma care.

Automated peripheral nerve segmentation for MR-neurography

BackgroundMagnetic resonance neurography (MRN) is increasingly used as a diagnostic tool for peripheral neuropathies. Quantitative measures enhance MRN interpretation but require nerve segmentation which is time-consuming and error-prone and has not become clinical routine. In this study, we applied neural networks for the automated segmentation of peripheral nerves.MethodsA neural segmentation network was trained to segment the sciatic nerve and its proximal branches on the MRN scans of the right and left upper leg of 35 healthy individuals, resulting in 70 training examples, via 5-fold cross-validation (CV). The model performance was evaluated on an independent test set of one-sided MRN scans of 60 healthy individuals.ResultsMean Dice similarity coefficient (DSC) in CV was 0.892 (95% confidence interval [CI]: 0.888–0.897) with a mean Jaccard index (JI) of 0.806 (95% CI: 0.799–0.814) and mean Hausdorff distance (HD) of 2.146 (95% CI: 2.184–2.208). For the independent test set, DSC and JI were lower while HD was higher, with a mean DSC of 0.789 (95% CI: 0.760–0.815), mean JI of 0.672 (95% CI: 0.642–0.699), and mean HD of 2.118 (95% CI: 2.047–2.190).ConclusionThe deep learning-based segmentation model showed a good performance for the task of nerve segmentation. Future work will focus on extending training data and including individuals with peripheral neuropathies in training to enable advanced peripheral nerve disease characterization.Relevance statementThe results will serve as a baseline to build upon while developing an automated quantitative MRN feature analysis framework for application in routine reading of MRN examinations.Key PointsQuantitative measures enhance MRN interpretation, requiring complex and challenging nerve segmentation.We present a deep learning-based segmentation model with good performance.Our results may serve as a baseline for clinical automated quantitative MRN segmentation.Graphical

DRpred: A Novel Deep Learning-Based Predictor for Multi-Label mRNA Subcellular Localization Prediction by Incorporating Bayesian Inferred Prior Label Relationships.

The subcellular localization of messenger RNA (mRNA) not only helps us to understand the localization regulation of gene expression but also helps to understand the relationship between RNA localization pattern and human disease mechanism, which has profound biological and medical significance. Several predictors have been proposed for predicting the subcellular localization of mRNA. However, there is still considerable room for improvement in their predictive performance, especially regarding multi-label prediction. This study proposes a novel multi-label predictor, DRpred, for mRNA subcellular localization prediction. This predictor first utilizes Bayesian networks to capture the dependencies among labels. Subsequently, it combines these dependencies with features extracted from mRNA sequences using Word2vec, forming the input for the predictor. Finally, it employs a neural network combining BiLSTM and an attention mechanism to capture the internal relationships of the input features for mRNA subcellular localization. The experimental validation on an independent test set demonstrated that DRpred obtained a competitive predictive performance in multi-label prediction and outperformed state-of-the-art predictors in predicting single subcellular localizations, obtaining accuracies of 82.14%, 93.02%, 80.37%, 94.00%, 90.58%, 84.53%, 82.01%, 79.71%, and 85.67% for the chromatin, cytoplasm, cytosol, exosome, membrane, nucleolus, nucleoplasm, nucleus, and ribosome, respectively. It is anticipated to offer profound insights for biological and medical research.

Stack-HDAC3i: A high-precision identification of HDAC3 inhibitors by exploiting a stacked ensemble-learning framework

Epigenetics involves reversible modifications in gene expression without altering the genetic code itself. Among these modifications, histone deacetylases (HDACs) play a key role by removing acetyl groups from lysine residues on histones. Overexpression of HDACs is linked to the proliferation and survival of tumor cells. To combat this, HDAC inhibitors (HDACi) are commonly used in cancer treatments. However, pan-HDAC inhibition can lead to numerous side effects. Therefore, isoform-selective HDAC inhibitors, such as HDAC3i, could be advantageous for treating various medical conditions while minimizing off-target effects. To date, computational approaches that use only the SMILES notation without any experimental evidence have become increasingly popular and necessary for the initial discovery of novel potential therapeutic drugs. In this study, we develop an innovative and high-precision stacked-ensemble framework, called Stack-HDAC3i, which can directly identify HDAC3i using only the SMILES notation. Using an up-to-date benchmark dataset, we first employed both molecular descriptors and Mol2Vec embeddings to generate feature representations that cover multi-view information embedded in HDAC3i, such as structural and contextual information. Subsequently, these feature representations were used to train baseline models using nine popular ML algorithms. Finally, the probabilistic features derived from the selected baseline models were fused to construct the final stacked model. Both cross-validation and independent tests showed that Stack-HDAC3i is a high-accuracy prediction model with great generalization ability for identifying HDAC3i. Furthermore, in the independent test, Stack-HDAC3i achieved an accuracy of 0.926 and Matthew’s correlation coefficient of 0.850, which are 0.44–6.11% and 0.83–11.90% higher than its constituent baseline models, respectively.