Independent Validation Dataset Research Articles

Deep learning-assisted colonoscopy images for prediction of mismatch repair deficiency in colorectal cancer.

Deficient mismatch repair or microsatellite instability is a major predictive biomarker for the efficacy of immune checkpoint inhibitors of colorectal cancer. However, routine testing has not been uniformly implemented due to cost and resource constraints. We developed and validated a deep learning-based classifiers to detect mismatch repair-deficient status from routine colonoscopy images. We obtained the colonoscopy images from the imaging database at Endoscopic Center of the Sixth Affiliated Hospital, Sun Yat-sen University. Colonoscopy images from a prospective trial (Neoadjuvant PD-1 blockade by toripalimab with or without celecoxib in mismatch repair-deficient or microsatellite instability-high locally advanced colorectal cancer) were used to test the model. A total of 5226 eligible images from 892 tumors from the consecutive patients were utilized to develop and validate the deep learning model. 2105 colorectal cancer images from 306 tumors were randomly selected to form model development dataset with a class-balanced approach. 3121 images of 488 proficient mismatch repair tumors and 98 deficient mismatch repair tumors were used to form the independent dataset. The model achieved an AUROC of 0.948 (95% CI 0.919-0.977) on the test dataset. On the independent validation dataset, the AUROC was 0.807 (0.760-0.854), and the NPV in was 94.2% (95% CI 0.918-0.967). On the prospective trial dataset, the model identified 29 tumors among the 33 deficient mismatch repair tumors (87.88%). The model achieved a high NPV in detecting deficient mismatch repair colorectal cancers. This model might serve as an automatic screening tool.

Single-cell dissection reveals immunosuppressive F13A1+ macrophage as a hallmark for multiple primary lung cancers.

The increasing prevalence of multiple primarylung cancers (MPLCs) presents challenges to current diagnostic and clinicalmanagement approaches. However, the molecular mechanisms driving MPLCdevelopment and distinguishing it from solitary primary lung cancers (SPLCs)remain largely unexplored. We performed a comparative single-cell RNAsequencing (scRNA-seq) analysis on tumour and adjacent para-tumour tissues fromMPLC and SPLC patients to comparatively evaluate their immunological landscapes.Additionally, multiplex immunofluorescence (mIF) staining and independentvalidation datasets were used to confirm findings. MPLCs and SPLCs share significant similarities in genetic, transcriptomic and immune profiles, suggesting common therapeutic strategies such as EGFR-TKIs andICIs. Notably, an immunosuppressive macrophage subtype, F13A1+ Macrophage (Mϕ), is specifically enriched in MPLCs. This subtype overexpresses M2 macrophagemarkers and exhibits up-regulation of SPP1-CD44/CCL13-ACKR1 interactions, indicatingits role in shaping the immunosuppressive tumour microenvironment and promotingtumour growth in MPLCs. This study unveils shared molecular mechanismsbetween MPLCs and SPLCs, while identifying MPLC-specific cellular and molecularfeatures, such as the role of F13A1+ macrophages. The findings provide novelinsights into MPLC pathogenesis, supporting the development of targetedtherapeutic strategies. Comparative scRNA-seq analysis reveals significant similarities in genetic, transcriptomicand immune profiles between MPLCs and SPLCs. Identification of a unique immunosuppressive F13A1+ macrophage subtype, preferentially enriched in MPLCs, linked to immune evasion and tumourprogression. SPP1-CD44/CCL13-ACKR1 interactions are crucial in MPLC tumour microenvironment, indicating potential targets for therapeutic intervention.

A new global carbon flux estimation methodology by assimilation of both in situ and satellite CO2 observations

Accurate estimation of carbon removal by terrestrial ecosystems and oceans is crucial to the success of global carbon mitigation initiatives. The emergence of multi-source CO2 observations offers prospects for an improved assessment of carbon fluxes. However, the utility of these diverse observations has been limited by their heterogeneity, leading to much variation in estimated carbon fluxes. To harvest the diverse data types, this paper develops a multi-observation carbon assimilation system (MCAS), which simultaneously integrates both satellite and ground-based observations. MCAS modifies the ensemble Kalman filter to apply different inflation factors to different types of observation errors, addressing the heterogeneity between satellite and in situ data. In commonly used independent validation datasets, the carbon flux derived from MCAS outperformed those obtained from a single source, demonstrating a 20% reduction in error compared to existing carbon flux products. We use MCAS to conduct ecosystem and ocean carbon flux inversion for the period of 2016–2020, which reveals that the 5-year average global net terrestrial and ocean sink was 1.84 ± 0.60 and 2.74 ± 0.49 petagrams, absorbing approximately 47% of human-caused CO2 emissions together, which were consistent with the global carbon project estimates of 1.82 and 2.66 petagrams. All these facts suggest MCAS is a better methodology than those for assimilating single-source observation only.

BreathVisionNet: A pulmonary-function-guided CNN-transformer hybrid model for expiratory CT image synthesis

Background and objectiveChronic obstructive pulmonary disease (COPD) has high heterogeneity in etiologies and clinical manifestations. Expiratory Computed tomography (CT) can effectively assess air trapping, aiding in disease diagnosis. However, due to concerns about radiation exposure and cost, expiratory CT is not routinely performed. Recent work on synthesizing expiratory CT has primarily focused on imaging features while neglecting patient-specific pulmonary function. MethodsTo address these issues, we developed a novel model named BreathVisionNet that incorporates pulmonary function data to guide the synthesis of expiratory CT from inspiratory CT. An architecture combining a convolutional neural network and transformer is introduced to leverage the irregular phenotypic distribution in COPD patients. The model can better understand the long-range and global contexts by incorporating global information into the encoder. The utilization of edge information and multi-view data further enhances the quality of the synthesized CT. Parametric response mapping (PRM) can be estimated by using synthesized expiratory CT and inspiratory CT to quantify COPD phenotypes of the normal, emphysema, and functional small airway disease (fSAD), including their percentages, spatial distributions, and voxel distribution maps. ResultsBreathVisionNet outperforms other generative models in terms of synthesized image quality. It achieves a mean absolute error, normalized mean square error, structural similarity index and peak signal-to-noise ratio of 78.207 HU, 0.643, 0.847 and 25.828 dB, respectively. Comparing the predicted and real PRM, the Dice coefficient can reach 0.732 (emphysema) and 0.560 (fSAD). The mean of differences between true and predicted fSAD percentage is 4.42 for the development dataset (low radiation dose CT scans), and 9.05 for an independent external validation dataset (routine dose), indicating that model has great generalizability. A classifier trained on voxel distribution maps can achieve an accuracy of 0.891 in predicting the presence of COPD. ConclusionsBreathVisionNet can accurately synthesize expiratory CT images from inspiratory CT and predict their voxel distribution. The estimated PRM can help to quantify COPD phenotypes of the normal, emphysema, and fSAD. This capability provides additional insights into COPD diversity while only inspiratory CT images are available.

EPID-02. BLOOD-BASED CLASSIFICATION OF IDH-STATUS OF NON-ENHANCING GLIOMAS: A MACHINE LEARNING APPROACH

Abstract BACKGROUND Non-invasive determination of IDH mutational status in patients with glioma could offer significant therapeutic opportunities. While IDH wildtype (WT) tumors typically show enhancement on MRI, IDH mutant (MUT) tumors often lack this enhancement. However, relying solely on anatomic radiology may lead to misclassification, and currently, tissue acquisition is the primary method for assessing IDH-status in gliomas. These limitations hamper the development of neoadjuvant or intraoperative therapeutic strategies based on IDH-status; thus, more minimally invasive methods to determine IDH-status are needed. In this study, we assessed peripheral immune cell proportions, which vary by glioma subtype, from pre-surgery peripheral blood samples as an alternative method of classifying the IDH-status in gliomas without enhancement. MATERIALS AND METHODS We employed a highly accurate large language model (GPT-4-Turbo-128k) with over 99% accuracy to read radiology notes and exclude patients with enhancing gliomas. Then, we identified 12 immune cell subtypes from whole blood using deconvolution algorithms based on DNA methylation data. These immune cell subtypes, along with patient age, were integrated into a machine learning model (random forest) to predict IDH-status (WT vs. MUT), leveraging conditional Generative Adversarial Networks to generate synthetic data and mitigate bias in the datasets. Two independent datasets were included for training and validating the model. RESULTS The random forest model had an AUC of 0.90 and accurately identified IDH-status in 81% of a training set of 287 gliomas (65 WT and 222 MUT at varied time points after diagnosis). In an independent validation data set of 99 gliomas (6 WT and 93 MUT) from pre-surgery blood samples, the AUC was 0.93, and accurately predicted IDH-status in 92% of cases with a sensitivity of 93% and specificity of 83%. CONCLUSIONS We predicted the IDH-status of non-enhancing gliomas using patients’ age and immunomethylomic data from pre-surgical peripheral blood samples. This minimally invasive approach is a promising step toward reducing risk and enabling earlier therapies based on IDH-status.

DeepForest-HTP: A novel deep forest approach for predicting antihypertensive peptides

Hypertension is a major preventable risk factor for cardiovascular disease, affecting over 1.5 billion adults worldwide. Antihypertensive peptides (AHTPs) have gained attention as a natural therapeutic option with minimal side effects. This study proposes a Deep Forest-based machine learning framework for AHTP prediction, leveraging a multi-granularity cascade structure to enhance classification accuracy. We integrated data from BIOPEP-UWM and three previously used datasets, totaling 2000 peptide sequences, and introduced novel feature extraction methods to build a comprehensive dataset for model training.This study represents the first application of Deep Forest for AHTP identification, demonstrating substantial classification performance advantages over traditional methods (e.g., SVM, CNN, and XGBoost) as well as recent mainstream prediction models (Ensemble-AHTPpred, CNN-SVM Ensemble, and mAHTPred). Requiring no complex manual feature engineering, the model adapts flexibly to various data needs, offering a novel perspective for efficient AHTP prediction and promising utility in hypertension management.On the benchmark dataset, the model achieved high accuracy, sensitivity, and AUC, providing a robust tool for identifying safe and effective AHTPs. However, future efforts should incorporate larger and more diverse independent validation datasets to further improve the model and enhance its generalizability. Additionally, the model's predictive accuracy relies on known AHTP targets and sequence features, potentially limiting its ability to detect AHTPs with uncharacterized or atypical properties.

An Empirical Algorithm for Estimating the Absorption of Colored Dissolved Organic Matter from Sentinel-2 (MSI) and Landsat-8 (OLI) Observations of Coastal Waters

Sentinel-2/MSI and Landsat-8/OLI sensors enable the mapping of ocean color-related bio-optical parameters of surface coastal and inland waters. While many algorithms have been developed to estimate the Chlorophyll-a concentration, Chl-a, and the suspended particulate matter, SPM, from OLI and MSI data, the absorption by colored dissolved organic matter, acdom, a key parameter to monitor the concentration of dissolved organic matter, has received less attention. Herein we present an inverse model (hereafter referred to as AquaCDOM) for estimating acdom at the wavelength 412 nm (acdom (412)), within the surface layer of coastal waters, from measurements of ocean remote sensing reflectance, Rrs (λ), for these two high spatial resolution (around 20 m) sensors. Combined with a water class-based approach, several empirical algorithms were tested on a mixed dataset of synthetic and in situ data collected from global coastal waters. The selection of the final algorithms was performed with an independent validation dataset, using in situ, synthetic, and satellite Rrs (λ) measurements, but also by testing their respective sensitivity to typical noise introduced by atmospheric correction algorithms. It was found that the proposed algorithms could estimate acdom (412) with a median absolute percentage difference of ~30% and a median bias of 0.002 m−1 from the in situ and synthetic datasets. While similar performances have been shown with two other algorithms based on different methodological developments, we have shown that AquaCDOM is much less sensitive to atmospheric correction uncertainties, mainly due to the use of band ratios in its formulation. After the application of the top-of-atmosphere gains and of the same atmospheric correction algorithm, excellent agreement has been found between the OLI- and MSI-derived acdom (412) values for various coastal areas, enabling the application of these algorithms for time series analysis. An example application of our algorithms for the time series analysis of acdom (412) is provided for a coastal transect in the south of Vietnam.

Deep learning for quantification of myocardial scar and microvascular obstruction in late gadolinium enhancement cardiovascular magnetic resonance images

Abstract Objectives Detecting and measuring myocardial scar and microvascular obstruction (MVO) accurately following reperfusion therapy is clinically vital for patients with acute myocardial infarction (AMI). Current clinical practice relies on manual delineation of endocardial borders as well as hyper- and hypo-enhanced regions on late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) images for scar and MVO quantification, respectively. However, this approach is subjective, labor-intensive, and time-consuming. The objective of this study is to develop and assess a convolutional neural network (CNN)-based method for the automated quantification of LGE scar and MVO in AMI patients. Methods A total of 1836 LGE images from 252 patients with AMI were analyzed, with the cohort comprising 232 males and an average age of 56±9 years. Our approach, utilizing a combined architecture of cascaded YOLOv8 (You Only Look Once version 8) and nnU-Net, was implemented for the simultaneous segmentation of the left ventricular (LV) myocardium, scar, and MVO in LGE images. Independent datasets for training, validation, and testing were maintained in an 8:1:1 ratio. Performance evaluation was conducted by comparing the results to manual scar and MVO quantification, utilizing metrics such as the Dice similarity coefficient (DSC) and Bland-Altman analysis. Results The automated segmentation process took 0.05 seconds per image. The segmentation accuracy, as assessed by the DSC, yielded values of 0.96±0.04 (per-patient, n=25) and 0.96±0.05 (per-slice, n=184) for scar segmentation, and 0.86±0.17 (per-patient) and 0.89±0.15 (per-slice) for MVO segmentation. In per-patient analysis, the volumes of automatically segmented scar and MVO demonstrated strong agreement with manually derived results, with biases [limits of agreement] of -0.3 [-3.0, 2.4] cm³ and 0.1 [-0.2, 0.3] cm³, respectively. Furthermore, there was strong concordance between automatically and manually derived scar size as a percentage of LV mass (-0.2 [-3.1, 2.7] %) and MVO size as a percentage of scar (1.2 [-5.6, 8.0] %). Conclusions The findings demonstrate excellent agreement between our proposed automated deep-learning solution and clinical expert annotation, suggesting its potential as a predictive tool for prognosis and clinical outcomes in patients with AMI.

Automated quantification of cerebral microbleeds in susceptibility-weighted MRI: association with vascular risk factors, white matter hyperintensity burden, and cognitive function.

To train and validate a deep learning (DL)-based segmentation model for cerebral microbleeds (CMB) on susceptibility-weighted MRI; and to find associations between CMB, cognitive impairment, and vascular risk factors. Participants in this single-institution retrospective study underwent brain MRI to evaluate cognitive impairment between January-September 2023. For training the DL model, the nnU-Net framework was used without modifications. The DL model's performance was evaluated on independent internal and external validation datasets. Linear regression analysis was used to find associations between log-transformed CMB numbers, cognitive function (mini-mental status examination [MMSE]), white matter hyperintensity (WMH) burden, and clinical vascular risk factors (age, sex, hypertension, diabetes, lipid profiles, and body mass index). Training of the DL model (n = 287) resulted in a robust segmentation performance with an average dice score of 0.73 (95% CI, 0.67-0.79) in an internal validation set, (n = 67) and modest performance in an external validation set (dice score = 0.46, 95% CI, 0.33-0.59, n = 68). In a temporally independent clinical dataset (n = 448), older age, hypertension, and WMH burden were significantly associated with CMB numbers in all distributions (total, lobar, deep, and cerebellar; all P <.01). MMSE was significantly associated with hyperlipidemia (β = 1.88, 95% CI, 0.96-2.81, P <.001), WMH burden (β = -0.17 per 1% WMH burden, 95% CI, -0.27-0.08, P <.001), and total CMB number (β = -0.01 per 1 CMB, 95% CI, -0.02-0.001, P = .04) after adjusting for age and sex. The DL model showed a robust segmentation performance for CMB. In all distributions, CMB had significant positive associations with WMH burden. Increased WMH burden and CMB numbers were associated with decreased cognitive function. CMB = cerebral microbleed; DL = deep learning, DSC = dice similarity coefficient; MMSE = mini-mental status examination; SVD = small vessel disease; SWI = susceptibility-weighted image; WMH = white matter hyperintensity.

In-depth investigation of the complex pathophysiological mechanisms between diabetes and ischemic stroke through gene expression and regulatory network analysis

This study explores the intricate relationship between diabetes and ischemic stroke (IS) through gene expression analysis and regulatory network investigation to identify potential biomarkers and therapeutic targets. Using datasets from the Gene Expression Omnibus (GEO) database, differential gene analysis was conducted on GSE43950 (diabetes) and GSE16561 (IS), revealing overlapping differentially expressed genes (DEGs). Functional enrichment analysis, Protein-Protein Interaction (PPI) network construction, and hub gene identification were performed, followed by validation in independent datasets (GSE156035 and GSE58294). The analysis identified 307 upregulated and 156 downregulated overlapping DEGs with significant enrichment in GO and KEGG pathways. Key hub genes (TLR2, TLR4, HDAC1, ITGAM) were identified through a PPI network (257 nodes, 456 interactions), with their roles in immune and inflammatory responses highlighted through GeneMANIA analysis. TRRUST-based transcription factor enrichment analysis revealed regulatory links involving RELA, SPI1, STAT3, and SP1. Differential expression analysis confirmed that RELA and SPI1 were upregulated in diabetes, while SPI1, STAT3, and SP1 were linked to IS. These transcription factors are involved in regulating immunity and inflammation, providing insights into the molecular mechanisms underlying diabetes-IS comorbidity. This bioinformatics-driven approach offers new understanding of the gene interactions and pathways involved, paving the way for potential therapeutic targets.

P10.09.A BLOOD-BASED CLASSIFICATION OF IDH-STATUS OF NON-ENHANCING GLIOMAS: A MACHINE LEARNING APPROACH

Abstract BACKGROUND Non-invasive determination of IDH mutational status in patients with glioma could offer significant therapeutic opportunities. While IDH wildtype tumors (e.g., GBM) typically show enhancement on MRI, IDH mutant tumors often lack this enhancement. However, relying solely on anatomic radiology may lead to misclassification, and currently, tissue acquisition is the primary method for assessing IDH status in gliomas. This limitation hampers the development of neoadjuvant or intraoperative therapeutic strategies based on IDH status; thus, more minimally invasive methods to determine IDH status are needed. In this study, we assessed immune cell proportions, which vary by glioma subtype, from pre-surgery peripheral blood samples as an alternative method of classifying the IDH status in gliomas without enhancement. MATERIAL AND METHODS First, we employed a highly accurate large language model (GPT-4-Turbo-128k) with over 99% accuracy to read radiology notes and exclude patients with enhancing gliomas. Then, we identified twelve immune cell subtypes from whole blood using deconvolution algorithms based on DNA methylation data. These immune cell subtypes, along with patient age, were integrated into a machine learning model (random forest) to predict IDH status (wildtype vs. mutant), leveraging conditional Generative Adversarial Networks to generate synthetic data and mitigate bias in the datasets. Two independent datasets were included for training and validating the model. RESULTS The random forest model had an area under the ROC curve (AUC) of 0.90 and accurately identified IDH status in 81% of a training set of 287 gliomas (65 wildtype and 222 mutant tumors at varied time points after diagnosis). In an independent validation data set of 99 gliomas (6 wildtype and 93 mutant) from pre-surgery blood samples, the AUC was 0.93, and accuracy predicted IDH status in 92% of cases with a sensitivity of 93% and specificity of 83%. CONCLUSION We could accurately predict IDH status in pre-surgical peripheral blood samples from patients with non-enhancing gliomas. This minimally invasive approach is a promising step toward reducing risk and exploring opportunities for earlier therapies based on IDH status.

Enhancing the convenience of frailty index assessment for elderly Chinese people with machine learning methods.

Frailty is a state that is closely associated with adverse health outcomes in the aging process. The frailty index (FI), which measures frailty in terms of cumulative deficits, has been widely used for frailty assessment in elderly people, and its advantage of self-reported information collection makes it applicable to a broader group of elderly people. Our study aims to simplify the Frailty Index Assessment Scale, while maintaining its reliability and accuracy, to easily and quickly assess frailty in elderly people. In this study, participants (age ≥ 65 years) from the Chinese Longitudinal Healthy Longevity Survey (CLHLS), which had 13,339, 372 and 1214 participants in 2008, 2011, and 2014, respectively, were used. The 2008 dataset was split into 80% for training and 20% for internal validation, and the data from 2011 to 2014 as external validation. In order to obtain effective predictors, we used Lasso regression, Boruta algorithm and random forest classifier score for feature selection. We used six models for predictive model construction and evaluated the models in the validation dataset. Model performance was measured by area under the curve (AUC), accuracy and F1 score. Logistic regression was found to be the best performing and most interpretable algorithm with AUC, accuracy and F1 of 0.974, 0.932 and 0.880 for the validation dataset, respectively. The AUCs for the external independent validation dataset were 0.963 and 0.977, respectively. Subgroup analysis showed that the model had good predictive power in both males and females. The predictive power was stronger among the elderly people over 80 years old, with AUC, accuracy and F1 of 0.973,0.914, and 0.893, respectively. The model also obtained good predictive power in the case of FI measured by different indicators. The model showed good robustness in the follow-up assessment of frailty status in elderly people, with the AUC remaining above 0.95 and accuracy above 0.9 over the long-term follow-up. Using machine learning techniques, we have successfully developed a simple frailty assessment prediction model based on 10 key features to shorten the frailty assessment scale with near full-scale accuracy. A user-friendly website was created to facilitate the application of this prediction model ( https://healthy-aging.shinyapps.io/Frailty_Assessment/ ).

Utilizing machine learning and hemagglutinin sequences to identify likely hosts of influenza H3Nx viruses

Influenza is a disease that represents both a public health and agricultural risk with pandemic potential. Among the subtypes of influenza A virus, H3 influenza virus can infect many avian and mammalian species and is therefore a virus of interest to human and veterinary public health. The primary goal of this study was to train and validate classifiers for the identification of the most likely host species using the hemagglutinin gene segment of H3 viruses. A five-step process was implemented, which included training four machine learning classifiers, testing the classifiers on the validation dataset, and further exploration of the best-performing model on three additional datasets. The gradient boosting machine classifier showed the highest host-classification accuracy with a 98.0 % (95 % CI [97.01, 98.73]) correct classification rate on an independent validation dataset. The classifications were further analyzed using the predicted probability score which highlighted sequences of particular interest. These sequences were both correctly and incorrectly classified sequences that showed considerable predicted probability for multiple hosts. This showed the potential of using these classifiers for rapid sequence classification and highlighting sequences of interest. Additionally, the classifiers were tested on a separate swine dataset composed of H3N2 sequences from 1998 to 2003 from the United States of America, and a separate canine dataset composed of canine H3N2 sequences of avian origin. These two datasets were utilized to look at the applications of predicted probability and host convergence over time. Lastly, the classifiers were used on an independent dataset of environmental sequences to explore the host identification of environmental sequences. The results of these classifiers show the potential for machine learning to be used as a host identification technique for viruses of unknown origin on a species-specific level.

Herbage biomass predictions from UAV data using a derived digital terrain model and machine learning

AbstractMore than 70% of Switzerland's agricultural area is covered by grasslands that often exhibit highly diverse species compositions and heterogeneous growth patterns. An essential requirement for efficient and effective pasture management is the regular estimation of herbage biomass. While various methods exist for estimating herbage biomass, they are often time‐consuming and may not accurately capture the variability within pastures. This highlights the need for more efficient, accurate estimation techniques. To help improve herbage biomass estimation, we present estiGrass3D+, a Random Forest model. This model predicts pasture biomass using a digital terrain model (DTM) derived from a digital surface model (DSM) for sward height modelling, along with vegetation indices and agronomic variables from UAV images only. The model was successfully evaluated with independent test data from different sites on the Swiss central plateau, including both grazed and mown areas. Model performance on an independent validation dataset achieved a NRMSE of 20.3%, while the training dataset had an NRMSE of 21.5%. These consistent results confirm that estiGrass3D+ is both transferable and applicable to unseen data while maintaining accuracy and reliability across different datasets. The wide applicability of our method demonstrates its practicality for predicting herbage biomass under different pasture management scenarios. Additionally, our method of deriving a DTM directly from a DSM simplifies the measurement of grass sward height by UAVs, eliminating the need for prior ground control point (GCP) marking and subsequent aligning, enhancing the efficiency of herbage biomass estimation.

The Lateral Corticospinal Tract Sign: An MRI Marker for Amyotrophic Lateral Sclerosis.

Background Radially sampled averaged magnetization inversion-recovery acquisition (rAMIRA) imaging shows hyperintensity in the lateral corticospinal tract (CST) in patients with motor neuron diseases. Purpose To systematically determine the accuracy of the lateral corticospinal tract sign for detecting patients with amyotrophic lateral sclerosis (ALS) at rAMIRA MRI. Materials and Methods This study included prospectively acquired data from participants in ALS and other motor neuron disease imaging studies at the University Hospital Basel, Switzerland. All participants underwent 3-T axial two-dimensional rAMIRA imaging at four cervical intervertebral disk levels. The lateral CST sign was defined as spinal cord white matter hyperintensity dorsolateral to the anterior horns, with higher signal intensity than in the dorsal columns on axial rAMIRA images. Marker accuracy was assessed in a study data set and in an independent validation data set. Postmortem rAMIRA imaging and histopathologic analysis were performed in one participant who died during the study. Results Participants with ALS (study data set: 38 participants [mean age, 61 years; IQR, 15 years], 22 male participants; validation data set: 10 participants [mean age, 61 years; IQR, 21 years], seven male participants), post-polio syndrome (study data set: 25 participants [mean age, 68 years; IQR, 8 years], 12 male participants), spinal muscular atrophy (study data set: 10 participants [mean age, 43 years; IQR, 14 years], eight male participants; validation data set: five participants [mean age, 38 years; IQR, 19 years], two male participants), and healthy control participants (study data set: 60 participants [mean age, 57 years; IQR, 20 years], 36 male participants; validation data set: 10 participants [mean age, 44 years; IQR, 17 years], seven male participants) were included. The sensitivity and specificity of rAMIRA for ALS were 60% (23 of 38) and 97% (91 of 94) in the study data set and 100% (10 of 10) and 93% (14 of 15) in the validation data set, respectively. Histopathologic analysis showed distinct loss of myelinated axons in the localization of the hyperintensities observed at rAMIRA imaging performed in situ and after organ extraction. Conclusion The recently defined marker at rAMIRA MRI may be a promising tool for assessing upper motor neuron degeneration in the lateral CST in patients with ALS. Clinical trials registration no. NCT03561623, NCT05764434, NCT06137612 © RSNA, 2024 Supplemental material is available for this article.

Aspiring to clinical significance: Insights from developing and evaluating a machine learning model to predict emergency department return visit admissions.

Return visit admissions (RVA), which are instances where patients discharged from the emergency department (ED) rapidly return and require hospital admission, have been associated with quality issues and adverse outcomes. We developed and validated a machine learning model to predict 72-hour RVA using electronic health records (EHR) data. Study data were extracted from EHR data in 2019 from three urban EDs. The development and independent validation datasets included 62,154 patients from two EDs and 73,453 patients from one ED, respectively. Multiple machine learning algorithms were evaluated, including deep significance clustering (DICE), regularized logistic regression (LR), Gradient Boosting Decision Tree, and XGBoost. These machine learning models were also compared against an existing clinical risk score. To support clinical actionability, clinician investigators conducted manual chart reviews of the cases identified by the model. Chart reviews categorized predicted cases across index ED discharge diagnosis and RVA root cause classifications. The best-performing model achieved an AUC of 0.87 in the development site (test set) and 0.75 in the independent validation set. The model, which combined DICE and LR, boosted predictive performance while providing well-defined features. The model was relatively robust to sensitivity analyses regarding performance across age, race, and by varying predictor availability but less robust across diagnostic groups. Clinician examination demonstrated discrete model performance characteristics within clinical subtypes of RVA. This machine learning model demonstrated a strong predictive performance for 72- RVA. Despite the limited clinical actionability potentially due to model complexity, the rarity of the outcome, and variable relevance, the clinical examination offered guidance on further variable inclusion for enhanced predictive accuracy and actionability.

Single-cell analysis of chemotherapy-resistant microenvironment identifies a chemo-response biomarker for pancreatic cancer.

Pancreatic ductal adenocarcinoma (PDAC) is a highly fatal, aggressive cancer due to limited response chemotherapy. The tumor microenvironment (TME) has emerged as a key player in the development of chemoresistance and in malignant progression. In this study, we hypothesized that chemotherapy response is predictable by chemotherapy-related cell types and their differentially expressed genes (DEGs). DEGs of chemoresistance cell types were identified via single cell analysis and Wilcoxon test. A chemotherapy response signature was established using a random forest model and validated with public datasets. Bulk cell fraction was analyzed using BayesPrism algorithms. Log-rank test was used to analyze survival of PDAC patients. We found that natural killer (NK) cells, myeloid cells, and erythroid cells were highly infiltrated in chemo-resistant TME. A total of 36 chemoresistance-related DEGs of chemo-resistant cells were identified in chemo-resistant PDAC. Functional enrichment analysis showed that chemoresistance upregulated various inflammation-related pathways, including TGF-β signaling. Based on these features, we constructed a random forest model to predict the response and survival for PDAC patients, which accurately distinguished high-risk and chemoresistant patients with significantly poorer prognosis in both the training and independent validation datasets. Cox regression analysis indicated that predicted labels were an independent prognostic factor in PDAC. Moreover, deconvolution of TME confirmed higher infiltration levels of M2 macrophage and NK cells in predicted chemoresistance. When combined with chemotherapy response related tumor mutations, the model showed excellent ability in predicting chemotherapy response and survival. The TME was closely associated with the chemotherapy response and prognosis of PDAC. Our TME-based random forest model predicted chemotherapy response with complementary knowledge to the response-related genetic mutations.

Rupture risk assessment in cerebral arteriovenous malformations: an ensemble model using hemodynamic and morphological features

BackgroundCerebral arteriovenous malformation (AVM) is a cerebrovascular disorder posing a risk for intracranial hemorrhage. However, there are few reliable quantitative indices to predict hemorrhage risk accurately. This study aimed to...

The impact of immunity on the risk of coronary artery disease: insights from a multiomics study.

Immune inflammation is intricately associated with coronary artery disease (CAD) progression, necessitating the pursuit of more efficacious therapeutic strategies. This study aimed to uncover potential therapeutic targets for CAD and myocardial infarction (MI) by elucidating the causal connection between regulatory immune-related genes (RIRGs) and these disorders. We performed summary data-based Mendelian randomization analysis to assess the therapeutic targets linked to expression quantitative trait loci and methylation quantitative trait loci of RIRGs in relation to CAD and MI. Independent validation cohorts and datasets from coronary artery and left ventricular heart tissue were analyzed. To strengthen causal inference, colocalization analysis and PhenoScanner phenotype scans were employed. Utilizing multiomics integration, we pinpointed EIF2B2, FCHO1, and DDT as CAD risk genes. Notably, EIF2B2 and FCHO1 displayed significant associations with MI. High EIF2B2 expression, regulated by cg16144293, heightened CAD and MI risk at rs175438. In contrast, enhanced FCHO1 expression, modulated by cg18329931, reduced CAD and MI risk at rs13382133. DDT upregulation influenced by cg11060661 and cg09664220 was associated with decreased CAD risk at rs5760120. Colocalization analysis firmly established these relationships. EIF2B2, FCHO1, and DDT represent risk loci for CAD progression within RIRGs. Our identification of these genes enhances understanding of CAD pathogenesis and directs future drug development efforts.

CBIL-VHPLI: a model for predicting viral-host protein-lncRNA interactions based on machine learning and transfer learning

Virus‒host protein‒lncRNA interaction (VHPLI) predictions are critical for decoding the molecular mechanisms of viral pathogens and host immune processes. Although VHPLI interactions have been predicted in both plants and animals, they have not been extensively studied in viruses. For the first time, we propose a new deep learning-based approach that consists mainly of a convolutional neural network and bidirectional long and short-term memory network modules in combination with transfer learning named CBIL‒VHPLI to predict viral–host protein‒lncRNA interactions. The models were first trained on large and diverse datasets (including plants, animals, etc.). Protein sequence features were extracted using a k-mer method combined with the one-hot encoding and composition–transition–distribution (CTD) methods, and lncRNA sequence features were extracted using a k-mer method combined with the one-hot encoding and Z curve methods. The results obtained on three independent external validation datasets showed that the pre-trained CBIL‒VHPLI model performed the best with an accuracy of approximately 0.9. Pretraining was followed by conducting transfer learning on a viral protein–human lncRNA dataset, and the fine-tuning results showed that the accuracy of CBIL‒VHPLI was 0.946, which was significantly greater than that of the previous models. The final case study results showed that CBIL‒VHPLI achieved a prediction reproducibility rate of 91.6% for the RIP-Seq experimental screening results. This model was then used to predict the interactions between human lncRNA PIK3CD-AS2 and the nonstructural protein 1 (NS1) of the H5N1 virus, and RNA pull-down experiments were used to prove the prediction readiness of the model in terms of prediction. The source code of CBIL‒VHPLI and the datasets used in this work are available at https://github.com/Liu-Lab-Lnu/CBIL-VHPLI for academic usage.