Large-scale Screening Research Articles

A Novel Model for Noninvasive Haemoglobin Detection Based on Visibility Network and Clustering Network for Multi-Wavelength PPG Signals

Non-invasive haemoglobin (Hb) testing devices enable large-scale haemoglobin screening, but their accuracy is not comparable to traditional blood tests. To this end, this paper aims to design a non-invasive haemoglobin testing device and propose a classification-regression prediction framework for non-invasive testing of haemoglobin using visibility graphs (VG) with network clustering of multi-sample pulse-wave-weighted undirected graphs as the features to optimize the detection accuracy of non-invasive haemoglobin measurements. Different prediction methods were compared by analyzing 608 segments of multiwavelength fingertip PPG signal data from 152 volunteers and analyzing and comparing the data and methods. The results showed that the classification using NVG with complex network clustering as features in the interval classification model was the best, with its classification accuracy (acc) of 93.35% and model accuracy of 88.28%. Among the regression models, the classification regression stack: SVM-Light Gradient Boosting Machine (LGBM) was the most effective, with a Mean Absolute Error (MAE) of 6.67 g/L, a Root Mean Square Error (RMSE) of 8.21 g/L, and an R-Square (R2) of 0.64. The results of this study indicate that the use of complex network technology in non-invasive haemoglobin detection can effectively improve its accuracy, and the detector designed in this study is promising to carry out a more accurate large-scale haemoglobin screening.

A psychologically interpretable artificial intelligence framework for the screening of loneliness, depression, and anxiety.

Negative emotions such as loneliness, depression, and anxiety (LDA) are prevalent and pose significant challenges to emotional well-being. Traditional methods of assessing LDA, reliant on questionnaires, often face limitations because of participants' inability or potential bias. This study introduces emoLDAnet, an artificial intelligence (AI)-driven psychological framework that leverages video-recorded conversations to detect negative emotions through the analysis of facial expressions and physiological signals. We recruited 50 participants to undergo questionnaires and interviews, with their responses recorded on video. The emoLDAnet employs a combination of deep learning (e.g., VGG11) and machine learning (e.g., decision trees [DTs]) to identify emotional states. The emoLDAnet incorporates the OCC-PAD-LDA psychological transformation model, enhancing the interpretability of AI decisions by translating facial expressions into psychologically meaningful data. Results indicate that emoLDAnet achieves high detection rates for loneliness, depression, and anxiety, with F1-scores exceeding 80% and Kendall's correlation coefficients above 0.5, demonstrating strong agreement with traditional scales. The study underscores the importance of the OCC-PAD-LDA model in improving screening accuracy and the significant impact of machine learning classifiers on the framework's performance. The emoLDAnet has the potential to support large-scale emotional well-being early screening and contribute to the advancement of mental health care.

Accuracy of a Novel High-Throughput "Car Blood Pressure" Measurement Protocol.

More than one in three adults with hypertension in the United States are unaware of their condition, highlighting the importance of large-scale screening campaigns. Currently, the identification of hypertension is largely limited to medical settings. To help overcome this barrier, we developed a novel high-throughput screening protocol that measures blood pressure (BP) while patients remain seated in an automobile ("car-BP"). The aim of this study was to provide an initial assessment of the accuracy of car-BP. Three BP readings were determined in a clinic exam room before and after three BP readings were taken while patients were seated in a parked car outside (n=100 participants). The same validated device model (Omron HEM-907XL) and BP measurement methods adhering to guidelines were used in both scenarios. The average of all 6 clinic readings was compared to the average of the 3 car-BP readings in each individual. Mean clinic and car-BP readings were 120.9 ± 16.2/78.0 ± 9.9 and 118.9 ± 15.2/76.0 ± 10.0mm Hg, respectively. The paired mean and absolute mean differences in systolic BP levels between methods were -1.92mm Hg (95% confidence interval (CI) -3.2 to -0.7mm Hg) and 4.8mm Hg (95%CI 3.8 to 5.6mm Hg), respectively. A total of 85% of participants had both systolic and diastolic BP levels ≤10mm Hg different between measurement scenarios (meeting the a priori determined study primary outcome). Car-BP represents an innovative and accessible approach for potential large-scale hypertension screening campaigns.

Pooled screening for endogenous HHV-6 in subjects with coronary artery disease.

Endogenous human herpesvirus 6 (eHHV-6) is integrated into the genomes of approximately 1% of individuals and has been linked to angina pectoris which, like myocardial infarction (MI), generally denotes coronary artery disease. To investigate this association further, we screened 2976 genomicDNA samples from patients with MI for eHHV-6 using multiplex qPCR. We identified 17 eHHV-6-positive individuals (0.57%), including 6 with eHHV-6A, 10 with eHHV-6B, and 1 with the solo-DR form, an eHHV-6B variantcharacterized by the presence of a single direct repeat (DR) within the host genome. While subjects with eHHV-6 had slightly higher total cholesterol levels, this difference was not statistically significant after correction for multiple testing. Our large-scale screening demonstrates the prevalence of eHHV-6 in MI patients and highlights the potential of this approach for studying its impact on diseases and other complex traits.

Establishment and application of a zebrafish model of Werner syndrome identifies sapanisertib as a potential antiaging drug

Aging is a complex process that affects multiple organs, and the discovery of a pharmacological approach to ameliorate aging is considered the Holy Grail of medicine. Here, we performed an N-ethyl-N-nitrosourea forward genetic screening in zebrafish and identified an accelerated aging mutant named meteor (met), harboring a mutation in the Werner syndrome RecQ-like helicase (wrn) gene. Loss of wrn leads to a short lifespan and age-related characteristics in the intestine of zebrafish embryos, such as cellular senescence, genomic instability, and epigenetic alteration. Therefore, we conducted a screening of antiaging drugs using the met mutant and revealed that sapanisertib effectively ameliorated most of the aging phenotypes of the mutant. Mechanistically, the geroprotective effects of sapanisertib may be attributed to inhibition of mTORC1/2. Furthermore, sapanisertib also attenuated chronological aging in wild-type aged zebrafish and replicative-senescence in human foreskin fibroblasts. Taken together, our study introduces a unique and efficient model for large-scale antiaging drug screening in vertebrates and suggests sapanisertib as a potential therapeutic option for treating premature aging and promoting healthy aging.

Student experience of intensive delivery in large scale studio-based learning

ABSTRACT This article explores the effect of the intensive mode of delivery on the student experience in large scale studio-based learning, by reporting on the shift to block teaching at Griffith University’s Bachelor of Film and Screen Media Production. We use quantitative student experience data over a six-year period (the three years prior to the introduction and the first three full years of the block model) for all 8 first-year core courses and 11 second year elective courses, and perform a reflexive thematic analysis of 3,036 comments in student experience surveys of 46 first-year core course instances. We conclude that the intensive mode of delivery benefits active learning strategies, can create a stronger student-teacher rapport and positively impacts students’ perception of their own learning. We argue that students might react more positively to iterative feedback and continuous assessment, and that instructors need to carefully consider volume of learning as well as avoid course overlaps and overly complex course designs. The article adds to a growing body of literature on intensive delivery and fills a gap in the knowledge of its effects on the student experience in large-scale studio-based screen production degrees.

P-317. Performance of nasal MRSA PCR screening test in pediatric patients admitted to hospital

Abstract Background Few studies reported Methicillin-Resistant Staphylococcus aureus (MRSA) polymerase chain reaction (PCR) nasal screening as a tool for clinical stewardship in children. This multicenter study evaluated the diagnostic test characteristics of the MRSA-PCR in predicting the presence of invasive MRSA infection in large number of pediatric patients admitted to hospital. Methods A retrospective cohort study is performed by chart review of children over 1 month of age admitted to OSF Health Care System, Illinois, between May 2013 and June 2022 and who has at least one MRSA-PCR nasal screening test and any subsequent culture of sterile body site performed. Data were validated, duplicates were removed, and missing or incomplete information related to screening results were removed before predictive values and post-test probabilities were calculated for MRSA infection in all patients as well as subgroup of high-risk, skin-soft tissue infections, and patients who were presented with respiratory symptoms or diagnosed with pneumonia. Results Overall, 373 (7.7%) of 4850 patients were tested positive with MRSA-PCR. Among patients screened positive, 91 (1.9%) had invasive MRSA infection. Sensitivity, specificity, positive and negative predictive value of screening test are 32.9%, 92.8%, 98.6%, and 8.0%, respectively. Table shows the screening test characteristics for various clinical diagnoses. Conclusion Large-scale nasal PCR screening test for MRSA in hospital-admitted pediatric patients shows very high negative predictive value, particularly in high-risk group. However, low prevalence of MRSA infection may not allow this screening tool to de-escalate antibiotic coverage in children admitted to hospital and suspected of invasive MRSA infection. Disclosures All Authors: No reported disclosures

Nonlinear association between liver fat content and lumbar bone mineral density in overweight and obese individuals: evidence from a large-scale health screening data in China.

The impact of fatty liver disease on lumbar bone mineral density (BMD) represents an intriguing area of study, particularly in light of established research linking obesity to bone metabolism. However, there remains limited investigation into the correlation between quantifying liver fat content (LFC) and lumbar BMD among overweight and obese populations, particularly within the Chinese demographic. This study aims to accurately quantify LFC and investigate its association with lumbar BMD in overweight or obese individuals. This cross-sectional study was conducted at the Health Management Center of Henan Provincial People's Hospital from January 2019 to February 2023, involving 6996 participants with a body mass index (BMI) of 24 kg/m² or higher. LFC and lumbar BMD were assessed using computed tomography. The study utilized one-way ANOVA, subgroup analysis, multifactor regression analysis, smooth curve fitting, and threshold and saturation effect analysis to explore the relationship between LFC and lumbar BMD. Furthermore, inflammatory cell analysis was included to investigate the potential mediating role of inflammatory cells in the association between LFC and lumbar BMD. After adjusting for confounding variables, multivariate regression analysis revealed a significant negative association between LFC and lumbar BMD (β = -0.323, 95% CI: -0.464 to -0.183, P < 0.001). Particularly, participants in the highest baseline LFC quartile (Q4 group) exhibited a more pronounced negative impact on lumbar BMD compared to those in the lowest quartile (Q1 group) (β = -5.026, 95% CI: -7.040 to -3.012, P < 0.001). Threshold saturation effect analysis identified a turning point in the LFC-BMD relationship (K = 5.4). Below this point, LFC showed a positive correlation with lumbar BMD (β = 0.962, 95% CI: 0.016-1.907, P < 0.05), whereas above it, LFC was significantly negatively correlated with lumbar BMD (β = -0.405, 95% CI: -0.558 to -0.253, P < 0.001). Additionally, mediation analysis indicated that leukocytes and monocytes potentially mediated the association between LFC and lumbar BMD, with mediation ratios of -5.78 and -6.68%, respectively. Among individuals categorized as overweight or obese, elevated levels of LFC were associated with reduced lumbar BMD, particularly noticeable above a threshold of 5.4%. Additionally, various types of inflammatory cells are presumed to exert a substantial mediating influence on the correlation between LFC and lumbar BMD.

Absolute risk prediction for esophageal squamous cell carcinoma adaptable to regional disease burden across diverse regions.

Esophageal squamous cell carcinoma (ESCC) exhibits a long latency period and has a significant geographical disparity in incidence, which underscores the need for models predicting the long-term absolute risk adaptable to regional disease burden. 31,883 participants in a large-scale population-based screening trial (Hua County, China) were enrolled to develop the model. Severe dysplasia and above (SDA) identified at screening or follow-up were defined as the outcome. We calculated the absolute risk in three steps: 1) constructing a relative risk model using logistic regression, 2) calculating the age-specific baseline hazard, and 3) adjusting for the competing risk of all-cause death excluding ESCC. Flexible incidence rate parameters were integrated into the model to ensure its relevance across diverse regions worldwide. A total of 295 SDAs were detected. The relative risk model consisted of old age, male gender, irregular meal pattern, preference for hot or hard food, BMI of less than 22 kg/m2, and ESCC family history. The area under the receiver operating characteristic curve was 0.753 (95% CI: 0.749-0.757). The averaged 5-year and 10-year absolute risk were 0.53% and 1.30% among participants. Based on our model, we developed an online calculator incorporated flexible incidence rate parameters, demonstrating ideal risk stratification tailored to regions with varying disease burdens (https://pkugenetics.shinyapps.io/escc_risk_prediction/). We developed an absolute risk model to predict individualized long-term risk of ESCC, accounting for local disease burden. This model has the potential to mitigate the global burden of ESCC by enabling targeted screening and personalized prevention strategies.

The development of a screener for Cerebral Visual Impairment

This study explored the secondary use of Luxembourg’s school monitoring tool for a large-scale screening of Cerebral Visual Impairment (CVI)-related difficulties. 44 items, with and without time constraint, were developed, and pretested among 959 children. All children subsequently participated in an individual evaluation of higher-level visual processing (HLVP) measures related with CVI. A clinical outcome was attributed post hoc with 32 children being classified as having CVI-related difficulties. To explore the predictive power of the CVI items included in the monitoring, item responses were matched to the results of the individual HLVP assessment. Of all items, the untimed item targeting the combined functions of surface and rotation significantly distinguished group performances (<.05). To improve condition discrimination, different item combinations were tested. Sensitivity and specificity metrics were computed resulting in ranges of 37.5% - 81.3% and 27% - 88.8% respectively. The item combination with the highest sensitivity (81.3%) was retained considering a viable trade-off between sensitivity and specificity metrics. These results support the secondary use of an existing large-scale monitoring tool to screen for CVI-related difficulties in the beginning of elementary school, provided that additional sources of information are progressively implemented to strengthen the tool’s predictive power.

A Novel Aggregation-Induced Emission-Based Electrochemiluminescence Aptamer Sensor Utilizing Red-Emissive Sulfur Quantum Dots for Rapid and Sensitive Malathion Detection.

Rapid, effective, and cost-effective methods for large-scale screening of pesticide residues in the environment and agricultural products are important for assessing potential environmental risks and safeguarding human health. Here, we constructed a novel aggregation-induced emission (AIE) electrochemical aptamer (Apt) sensor based on red-emissive sulfur quantum dots (SQDs), which aimed at the rapid screening and quantitative detection of malathion. SQDs were prepared using a two-step oxidation method with good electrochemiluminescence (ECL) optical properties. These SQDs were modified onto the electrode surface to serve as ECL luminophores. Subsequently, Apt was introduced and modified to form a double-helix structure with the complementary chain (cDNA). The ECL signal was reduced because the biomolecules had poor electrical conductivity and inefficient electron transfer. When the target malathion was added, the double helix structure was unraveled, the malathion Apt fell off the electrode surface, and the ECL signal was restored. The linear range of detection was 1.0 × 10-13-1.0 × 10-8 mol·L-1, and the detection limit was 0.219 fM. The successful preparation of the sensor not only develops the ECL optical properties of SQDs but also expands the application of SQDs in ECL sensing.

Non covalent inhibitors of SARS-CoV-2 main protease, a rescaffolding attempt

Out of the results of the sole large-scale screening for inhibitors of SARS-CoV-1 main protease reported in 2013, attempts to improve the 3-pyridyl-bearing hits found have been conducted in research laboratories, either on this enzyme or more recently on the closely related SARS-CoV-2 main protease. From the resulting structural information reported, we sought to design analogues featuring some of the components providing an affinity for the active site of these proteases along with a different scaffold which would allow for further structure-activity relationship studies and/or pharmacological improvements. We describe here the introduction of a bridging component aiming at the stabilization of the ligand conformation adopted when bound to these proteases. Accordingly, this led us to prepare 3,3-disubtituted piperazin-2-ones from an array of ketones, via either a Bargellini reaction or a multistage condensation/cyclization/hydrolysis involving ethylene diamine and potassium cyanide. However, even the most elaborate and lipophilic biphenyl-bearing analog made, displayed only a weak effect in a bioluminescence-based SARS-CoV-2 main protease inhibition assay.

A Hydrogel-Based Multiplex Coculture Platform for Retinal Component Cells.

There is growing interest in generating in vitro models of tissues and tissue-related diseases to mimic normal tissue organization and pathogenesis for different purposes. The retina is a highly complex multicellular tissue where the organization of the cellular components relative to each other is critical for retinal function. Many retinopathies arise due to the disruption of this order. In this study, we aimed to generate a coculture model of retina-derived cells, namely RPE and Müller cells, in multiplexed 3D hydrogels. Using methacrylated gelatin (GelMA)-based 3D hydrogels, we compared the behavior of RPE and Müller cells when they were cultured together. These patterned multiplex hydrogels containing cells were cultured for several days to reflect how cells would reorganize themselves in the presence of another cellular component derived from the same tissue. Here, we present a multicellular multiplex platform for the creation of cellular networks with cells of retinal tissue that can be easily adapted to create more complex tissue-like alternatives for large-scale tissue modeling and screening purposes. We also present an alternative method of coculture by generating spheroids from one of the components while keeping the other component free and motile in the hydrogel. The latter model predicts enhanced possibilities of cellular interactions by retarding the movement of one of the component cells.

Recent Advances in Nontargeted Screening of Chemical Hazards in Foodstuffs.

The emergence of several chemical substances continues to enrich and facilitate the development of food science, but their irrational use also poses a threat to food safety and human health. Nontargeted screening (NTS) has become an important tool for rapid traceability and efficient identification of chemical hazards in food matrices. NTS in food analysis is highly integrated with sample pretreatment, instrumental analysis platforms, data acquisition and analysis, and toxicology. This article is a systemic review of current sample preparation, analytical platforms, and toxicity-guided NTS techniques and provides the latest advancements in workflows and innovative applications of the NTS process based on mass spectrometric techniques. High-throughput toxicity screening platforms play an important role in NTS of unknown chemical hazards of complex food matrices. Advanced machine learning and artificial intelligence are increasingly accessible fields that may effectively process large-scale screening data and advance food NTS research.

Development of a multi-laboratory integrated predictive model for silicosis utilizing machine learning: a retrospective case-control study.

Due to the high global prevalence of silicosis and the ongoing challenges in its diagnosis, this pilot study aims to screen biomarkers from routine blood parameters and develop a multi-biomarker model for its early detection. A case-control study was conducted to screen biomarkers for the diagnosis of silicosis using LASSO regression, SVM and RF. A sample of 612 subjects (half cases and half controls) were randomly divided into training and test groups in a 2:1 ratio. Logistic regression analysis and receiver operating characteristic (ROC) curves were used to construct a multiple biomarker-based model for the diagnosis of silicosis, which was applied to both the training and the testing datasets. The training cohort revealed significant statistical differences (P < 0.05) in multiple hematologic parameters between silicosis patients and healthy individuals. Based on machine learning, eight silicosis biomarkers were screened and identified from routine blood cell, biochemical and coagulation parameters. D-dimer (DD), Albumin/Globulin (A/G), lactate dehydrogenase (LDH) and white blood cells (WBC) were selected for constructing the logistic regression model for silicosis diagnostics. This model had a satisfactory performance in the training cohort with an area under the ROC curve (AUC) of 0.982, a diagnostic sensitivity of 95.4%, and a specificity of 92.2%. In addition, the model had a prediction accuracy of 0.936 with an AUC of 0.979 in the independent test cohort. Moreover, the diagnostic accuracies of the logistic model in silicosis stages 1, 2, and 3 were 88.0, 95.4, and 94.3% with an AUC of 0.968, 0.983, and 0.990 for silicosis, respectively. A diagnostic model based on DD, A/G, LDH and WBC is successfully proposed for silicosis diagnostics. It is cheap, sensitive, specific, and preliminarily offers a potential strategy for the large-scale screening of silicosis.

A review of 3D bioprinting for organoids

Abstract Current two-dimensional (2D) cell models for effective drug screening suffer from significant limitations imposed by the lack of realism in the physiological environment. Three-dimensional (3D) organoids models hold immense potential in mimicking the key functions of human organs by overcoming the limitations of traditional 2D cell models. However, current techniques for preparation of 3D organoids models had limitations in reproducibility, scalability, and the ability to closely replicate the complex microenvironment found in vivo. Additionally, traditional 3D cell culture systems often involve lengthy and labor-intensive processes that hinder high-throughput applications necessary for a large-scale drug screening. Advancements in 3D bioprinting technologies offer promising solutions to these challenges by enabling precise spatial control over cell placement and material composition, thereby facilitating the creation of more physiologically relevant organoids than current techniques. This review provides a comprehensive summary of recent advances in 3D bioprinting technologies for creating organoids models, which begins with an introduction to different types of 3D bioprinting techniques (especially focus on volumetric bioprinting (VBP) technique), followed by an overview of bioinks utilized for organoids bioprinting. Moreover, we also introduce the applications of 3D bioprinting organoids in disease models, drug efficiency evaluation and regenerative medicine. Finally, the challenges and possible strategies for the development and clinical translation of 3D bioprinting organoids are concluded.

A scalable CRISPR-Cas9 gene editing system facilitates CRISPR screens in the malaria parasite Plasmodium berghei.

Many Plasmodium genes remain uncharacterized due to low genetic tractability. Previous large-scale knockout screens have only been able to target about half of the genome in the more genetically tractable rodent malaria parasite Plasmodium berghei. To overcome this limitation, we have developed a scalable CRISPR system called P. berghei high-throughput (PbHiT), which uses a single cloning step to generate targeting vectors with 100-bp homology arms physically linked to a guide RNA (gRNA) that effectively integrate into the target locus. We show that PbHiT coupled with gRNA sequencing robustly recapitulates known knockout mutant phenotypes in pooled transfections. Furthermore, we provide an online resource of knockout and tagging designs to target the entire P. berghei genome and scale-up vector production using a pooled ligation approach. This work presents for the first time a tool for high-throughput CRISPR screens in Plasmodium for studying the parasite's biology at scale.

Consistency analysis of two US techniques for evaluating hepatic steatosis in patients with metabolic dysfunction-associated steatotic liver disease

BackgroundUS tools to quantify hepatic steatosis have recently been made clinically available by different manufacturers, but comparative data on their consistency are lacking.ObjectiveUS tools to quantify hepatic steatosis have recently been made clinically available by different manufacturers, but comparative data on their consistency are lacking. The aim of our study was to compare the diagnostic consistency for evaluating hepatic steatosis by two different US techniques, hepatorenal index by B-mode Ratio and attenuation coefficient by attenuation imaging (ATI).MethodsPatients with suspicion or previously diagnosed of metabolic dysfunction-associated steatotic liver disease (MASLD) who attended fatty liver consulting room from June 2023 to September 2023 were prospectively recruited. Patients underwent two different US techniques of B-mode Ratio and ATI, and laboratory test were collected. According to previously proposed cut-off values, B-mode Ratio ≥ 1.22, 1.42, 1.54, and ATI ≥ 0.62, 0.70, and 0.78 dB/cm/MH were used for assessing of mild, moderate, and severe hepatic steatosis, respectively. Kappa consistency test was used to evaluate the consistency of hepatic steatosis.ResultsA total of 62 patients were enrolled, including 44 males (71.0%) with an age of (41 ± 13) years and a body mass index of (27.0 ± 3.5) kg/m2. In the hyperlipidemia group, the B-mode Ratio and ATI were significantly higher than those in the non-hyperlipidemia group, with values of 1.68 ± 0.39 vs. 1.28 ± 0.35 (p = 0.001) and 0.74 ± 0.12 dB/cm/MH vs. 0.64 ± 0.11 dB/cm/MH (p = 0.005), respectively. The correlation coefficient between B-mode Ratio and ATI was 0.732 (p < 0.001). Using B-mode Ratio and ATI as diagnostic criteria for MASLD, the proportion of patients with MASLD was 79% and 82%, respectively. The Kappa coefficient for assessing MASLD was 0.90 (p < 0.001). Furthermore, these two different US techniques were used for grading hepatic steatosis, with no, mild, moderate, and severe steatosis accounting for 21%, 18%, 13%, and 48%, as well as 18%, 29%, 22%, and 31%, respectively. The linear weighted Kappa coefficient for staging hepatic steatosis was 0.78 (95% confidence interval: 0.68–0.87, p < 0.001).ConclusionThe non-invasive methods of two different US techniques based on B-mode Ratio and ATI have good consistency for evaluating hepatic steatosis, and can be used for large-scale community screening.

Coronary health index based on immunoglobulin light chains to assess coronary heart disease risk with machine learning: a diagnostic trial.

Recent studies suggest a connection between immunoglobulin light chains (IgLCs) and coronary heart disease (CHD). However, current diagnostic methods using peripheral blood IgLCs levels or subtype ratios show limited accuracy for CHD, lacking comprehensive assessment and posing challenges in early detection and precise disease severity evaluation. We aim to develop and validate a Coronary Health Index (CHI) incorporating total IgLCs levels and their distribution. Additionally, we aim to evaluate its effectiveness by integrating patient data and using machine learning models through diagnostic trial. The CHI was developed and combined with other clinical data. Nine machine learning models were screened to identify optimal diagnostic performance, with the XGBoost model emerging as the top performer. Performance was assessed based on accuracy, sensitivity, and its ability to identify severe CHD cases characterized by complex lesions (SYNTAX score > 33). The XGBoost model demonstrated high accuracy and sensitivity in diagnosing CHD, with an area under the curve (AUC) of 0.927. It also accurately identified patients with severe CHD, achieving an AUC of 0.991. An online web tool was introduced for broader external validation, confirming the model's effectiveness. Combining the CHI with the XGBoost model offers significant advantages in diagnosing CHD and assessing disease severity. This approach can guide clinical interventions and improve large-scale CHD screening.

HDAC and MEK inhibition synergistically suppresses HOXC6 and enhances PD-1 blockade efficacy in BRAFV600E-mutant microsatellite stable colorectal cancer

BackgroundB-Raf proto-oncogene, serine/threonine kinase (BRAF)V600E-mutant microsatellite stable (MSS) colorectal cancer (CRC) constitutes a distinct CRC subgroup, traditionally perceived as minimally responsive to standard therapies. Recent clinical attempts, such as BRAF...