Inflammopharmacology. 2025 May 17. doi: 10.1007/s10787-025-01771-5. Online ahead of print.

ABSTRACT

Respirable silica exposure adversely affects lung tissue immunopathology, triggering oxidative bursts in macrophages and neutrophils, releasing Damage-associated molecular patterns (DAMPs), including calprotectin proteins, S100A8, and S100A9. Calprotectin constitutes up to 45% of these innate immune cells, and serum levels of these alarmins correlate with inflammation, fibrosis, remodelling, and drug response in chronic diseases, including inflammatory bowel disease, asthma, and cystic fibrosis. The consequence of releasing calprotectin protein could trigger the pro-fibrotic effect of silicosis. This study aimed to investigate the role of calprotectin (S100A8/S100A9) as a pro-inflammatory and pro-fibrotic mediator in silica-induced lung fibrosis and evaluated the therapeutic potential of the calprotectin inhibitor, paquinimod. Using a mouse model of silicosis, silica exposure significantly elevated calprotectin expression, lung inflammation, and fibrosis, as evidenced by increased levels of epithelial-to-mesenchymal transition (EMT) markers, collagen deposition, and matrix metalloproteinases (MMPs). In vitro, stimulation of human bronchial fibroblasts with S100A8/S100A9 upregulated fibrotic markers (COL1A1 and α-SMA), which were reduced by inhibitors of TLR4 and RAGE receptors, as well as by paquinimod. Treatment with paquinimod effectively reduced these pathological changes, normalized calprotectin levels, decreased fibrosis scores, and attenuated NF-κB activation. These findings highlighted calprotectin's pivotal role in silica-induced lung fibrosis and inflammation, suggesting that its inhibition could be a promising therapeutic approach for silicosis and other fibro-inflammatory lung diseases. Further research is warranted to explore the precise mechanisms linking calprotectin to lung fibrosis and its potential as a biomarker and therapeutic target.

PMID:40381145 | DOI:10.1007/s10787-025-01771-5

Stem Cell Rev Rep. 2025 May 17. doi: 10.1007/s12015-025-10893-w. Online ahead of print.

ABSTRACT

The advent of intestinal organoids, three-dimensional structures derived from stem cells, has significantly advanced the field of biology by providing robust in vitro models that closely mimic the architecture and functionality of the human intestine. These organoids, generated from induced pluripotent stem cells (iPSCs), embryonic stem cells (ESCs), or adult stem cells, possess remarkable capabilities for self-renewal, differentiation into diverse intestinal cell types, and functional recapitulation of physiological processes, including nutrient absorption, epithelial barrier integrity, and host-microbe interactions. The utility of intestinal organoids has been extensively demonstrated in disease modeling, drug screening, and personalized medicine. Notable examples include iPSC-derived organoids, which have been effectively employed to model enteric infections, and ESC-derived organoids, which have provided critical insights into fetal intestinal development. Patient-derived organoids have emerged as powerful tools for investigating personalized therapeutics and regenerative interventions for conditions such as inflammatory bowel disease (IBD), cystic fibrosis, and colorectal cancer. Preclinical studies involving transplantation of human intestinal organoids into murine models have shown promising outcomes, including functional integration, epithelial restoration, and immune system interactions. Despite these advancements, several challenges persist, particularly in achieving reproducibility, scalability, and maturation of organoids, which hinder their widespread clinical translation. Addressing these limitations requires the establishment of standardized protocols for organoid generation, culture, storage, and analysis to ensure reproducibility and comparability of findings across studies. Nevertheless, intestinal organoids hold immense promise for transforming our understanding of gastrointestinal pathophysiology, enhancing drug development pipelines, and advancing personalized medicine. By bridging the gap between preclinical research and clinical applications, these organoids represent a paradigm shift in the exploration of novel therapeutic strategies and the investigation of gut-associated diseases.

PMID:40380985 | DOI:10.1007/s12015-025-10893-w

Radiol Med. 2025 May 17. doi: 10.1007/s11547-025-02019-6. Online ahead of print.

ABSTRACT

PURPOSE: To evaluate diagnostic accuracy and image quality of deep learning (DL) cine sequences for LV and RV parameters compared to conventional balanced steady-state free precession (bSSFP) cine sequences in cardiovascular magnetic resonance (CMR).

MATERIAL AND METHODS: From January to April 2024, patients with clinically indicated CMR were prospectively included. LV and RV were segmented from short-axis bSSFP and DL cine sequences. LV and RV end-diastolic volume (EDV), end-systolic volume (EDV), stroke volume (SV), ejection fraction, and LV end-diastolic mass were calculated. The acquisition time of both sequences was registered. Results were compared with paired-samples t test or Wilcoxon signed-rank test. Agreement between DL cine and bSSFP was assessed using Bland-Altman plots. Image quality was graded by two readers based on blood-to-myocardium contrast, endocardial edge definition, and motion artifacts, using a 5-point Likert scale (1 = insufficient quality; 5 = excellent quality).

RESULTS: Sixty-two patients were included (mean age: 47 ± 17 years, 41 men). No significant differences between DL cine and bSSFP were found for all LV and RV parameters (P ≥ .176). DL cine was significantly faster (1.35 ± .55 m vs 2.83 ± .79 m; P < .001). The agreement between DL cine and bSSFP was strong, with bias ranging from 45 to 1.75% for LV and from - 0.38 to 2.43% for RV. Among LV parameters, the highest agreement was obtained for ESV and SV, which fell within the acceptable limit of agreement (LOA) in 84% of cases. EDV obtained the highest agreement among RV parameters, falling within the acceptable LOA in 90% of cases. Overall image quality was comparable (median: 5, IQR: 4-5; P = .330), while endocardial edge definition of DL cine (median: 4, IQR: 4-5) was lower than bSSFP (median: 5, IQR: 4-5; P = .002).

CONCLUSION: DL cine allows fast and accurate quantification of LV and RV parameters and comparable image quality with conventional bSSFP.

PMID:40381163 | DOI:10.1007/s11547-025-02019-6

Interdiscip Sci. 2025 May 17. doi: 10.1007/s12539-025-00701-x. Online ahead of print.

ABSTRACT

In top-down proteomics, the accurate identification and characterization of proteoform through mass spectrometry represents a critical objective. As a result, achieving accuracy in identification results is essential. Multiple primary structure alterations in proteins generate a diverse range of proteoforms, resulting in an exponential increase in potential proteoform. Moreover, the absence of a definitive reference set complicates the standardization of results. Therefore, enhancing the accuracy of proteoform characterization continues to be a significant challenge. We introduced a ResNeXt-based deep learning model, PrSMBooster, for rescoring proteoform spectrum matches (PrSM) during proteoform characterization. As an ensemble method, PrSMBooster integrates four machine learning models, logistic regression, XGBoost, decision tree, and support vector machine, as weak learners to obtain PrSM features. The basic and latent features of PrSM are subsequently input into the ResNeXt model for final rescoring. To verify the effect and accuracy of the PrSMBooster model in rescoring proteoform characterization, it was compared with the characterization algorithm TopPIC across 47 independent mass spectrometry datasets from various species. The experimental results indicate that in most mass spectrometry datasets, the number of PrSMs obtained after rescoring with PrSMBooster increases at a false discovery rate (FDR) of 1%. Further analysis of the experimental results confirmed that PrSMBooster improves the accuracy of PrSM scoring, generates more mass spectrometry characterization results, and demonstrates strong generalization ability.

PMID:40381130 | DOI:10.1007/s12539-025-00701-x

Eur Spine J. 2025 May 17. doi: 10.1007/s00586-025-08908-8. Online ahead of print.

ABSTRACT

PURPOSE: This study aimed to develop deep learning algorithms (DLAs) utilising convolutional neural networks (CNNs) to classify cervical spondylotic myelopathy (CSM) and cervical spondylotic radiculopathy (CSR) from plain cervical spine radiographs.

METHODS: Data from 300 patients (150 with CSM and 150 with CSR) were used for internal validation (IV) using five-fold cross-validation strategy. Additionally, 100 patients (50 with CSM and 50 with CSR) were included in the external validation (EV). Two DLAs were trained using CNNs on plain radiographs from C3-C6 for the binary classification of CSM and CSR, and for the prediction of the spinal canal area rate using magnetic resonance imaging. Model performance was evaluated on external data using metrics such as area under the curve (AUC), accuracy, and likelihood ratios.

RESULTS: For the binary classification, the AUC ranged from 0.84 to 0.96, with accuracy between 78% and 95% during IV. In the EV, the AUC and accuracy were 0.96 and 90%, respectively. For the spinal canal area rate, correlation coefficients during five-fold cross-validation ranged from 0.57 to 0.64, with a mean correlation of 0.61 observed in the EV.

CONCLUSION: DLAs developed with CNNs demonstrated promising accuracy for classifying CSM and CSR from plain radiographs. These algorithms have the potential to assist non-specialists in identifying patients who require further evaluation or referral to spine specialists, thereby reducing delays in the diagnosis and treatment of CSM.

PMID:40381026 | DOI:10.1007/s00586-025-08908-8

Anal Chem. 2025 May 17. doi: 10.1021/acs.analchem.5c01326. Online ahead of print.

ABSTRACT

Accurate and rapid discrimination of multiple explosives with high precision is of paramount importance for national security, ecological protection, and human health yet remains a significant challenge with conventional analytical techniques. Herein, we present an innovative deep learning-assisted artificial vision platform based on cyclodextrin-protected multicolor fluorescent gold nanoclusters (CD-AuNCs) with four distinct emission wavelengths, enabling the highly accurate discrimination of seven explosives. The sensor array leverages the host-guest interactions between the cyclodextrin ligands on the AuNCs' surface and the target explosives, generating unique fluorescence fingerprint patterns. Mechanistic studies reveal that the fluorescence enhancement of CD-AuNCs is attributed to ligand rigidification, while fluorescence quenching is primarily caused by photoinduced electron transfer between CD-AuNCs and explosives. The multicolor fluorescence responses are captured by using a smartphone, and the corresponding RGB values are simultaneously extracted. To enhance the recognition accuracy, a dense convolutional network (DenseNet) algorithm with advanced image recognition capability is integrated with the fluorescence sensor array. This platform achieves remarkable 100% recognition accuracy at a concentration of 200 μM, enabling the rapid and precise visual classification of explosives. The proposed strategy not only provides a powerful tool for on-site explosive monitoring but also offers a versatile platform for the intelligent detection of diverse analytes, demonstrating significant potential for real-world applications in environmental and security monitoring.

PMID:40380950 | DOI:10.1021/acs.analchem.5c01326

J Chem Inf Model. 2025 May 17. doi: 10.1021/acs.jcim.5c00038. Online ahead of print.

ABSTRACT

Extensive research has shown that microRNAs (miRNAs) play a crucial role in cancer progression, treatment, and drug resistance. They have been recognized as promising potential therapeutic targets for overcoming drug resistance in cancer treatment. However, limited attention has been paid to predicting the association between miRNAs and drugs by computational methods. Existing approaches typically focus on constructing miRNA-drug interaction graphs, which may result in their performance being limited by interaction density. In this work, we propose a novel deep learning method that integrates sequence and structural information to infer miRNA-drug associations (MDAs), called DLST-MDA. This approach innovates by utilizing attribute information on miRNAs and drugs instead of relying on the commonly used interaction graph information. Specifically, considering the sequence lengths of miRNAs and drugs, DLST-MDA employs multiscale convolutional neural network (CNN) to learn sequence embeddings at different granularity levels from miRNA and drug sequences. Additionally, it leverages the power of graph neural networks to capture structural information from drug molecular graphs, providing a more representational analysis of the drug features. To evaluate DLST-MDA's effectiveness, we manually constructed a benchmark data set for various experiments based on the latest databases. Results indicate that DLST-MDA performs better than other state-of-the-art methods. Furthermore, case studies of three common anticancer drugs can evidence their usefulness in discovering novel MDAs. The data and source code are released at https://github.com/sheng-n/DLST-MDA.

PMID:40380921 | DOI:10.1021/acs.jcim.5c00038

Biochemistry. 2025 May 17. doi: 10.1021/acs.biochem.5c00186. Online ahead of print.

ABSTRACT

It is an exciting time for researchers working to link proteins to their functions. Most techniques for extracting functional information from genomic sequences were developed several years ago, with major progress driven by the availability of big data. Now, groundbreaking advances in deep-learning and AI-based methods have enriched protein databases with three-dimensional information and offer the potential to predict biochemical properties and biomolecular interactions, providing key functional insights. This progress is expected to increase the proportion of functionally bright proteins in databases and deepen our understanding of life at the molecular level.

PMID:40380914 | DOI:10.1021/acs.biochem.5c00186

Funct Integr Genomics. 2025 May 17;25(1):103. doi: 10.1007/s10142-025-01611-3.

ABSTRACT

Epitranscriptomic changes in the transcripts of cancer related genes could modulate protein levels. RNA editing, particularly A-to-I(G) editing catalyzed by ADAR1, has been implicated in cancer progression. RNA editing events in the 3' untranslated region (3'UTR) can regulate mRNA stability, localization, and translation, underscoring the importance of exploring their impact in cancer. Here, we performed an in silico analysis to detect breast cancer enriched RNA editing sites using the TCGA breast cancer RNA-seq dataset. Notably, the majority of differential editing events mapped to 3' untranslated regions (3'UTRs). We confirmed A-to-I(G) editing in the 3'UTRs of MDM2 (Mouse Double Minute 2 homolog), GINS1 (GINS Complex Subunit 1), and F11R (Junctional Adhesion Molecule A) in breast cancer cells. RNA immunoprecipitation with ADAR1 antibody confirmed the interaction between ADAR1 and MDM2, GINS1, and F11R 3'UTRs. ADAR1 knockdown revealed decreased editing levels, establishing ADAR1 as the editing enzyme. A reporter assay for MDM2, an oncogene overexpressed mostly in luminal breast cancers, demonstrated that RNA editing enhances protein expression, in agreement with reduced MDM2 protein levels in ADAR1 knockdown cells. Further exploration into the mechanisms of 3'UTR editing events revealed an interaction between ADAR1 and CSTF2, a core component of the polyadenylation machinery, as identified through biotin-based proximity labeling mass spectroscopy, and co-immunoprecipitation experiments. Furthermore, CSTF2 knockdown reduced both ADAR1 and MDM2 protein levels. Our findings highlight implications for MDM2 regulation by ADAR1-dependent 3'UTR RNA editing and present an interplay between RNA editing on 3'UTRs and the mRNA polyadenylation machinery. These results improve our understanding of ADAR1's role in cancer-associated 3' UTR RNA editing and its potential as a therapeutic target.

PMID:40381037 | DOI:10.1007/s10142-025-01611-3

Stud Health Technol Inform. 2025 May 15;327:1270-1274. doi: 10.3233/SHTI250602.

ABSTRACT

Electronic Health Records (EHRs) provide valuable longitudinal data for tracking disease progression, especially in rare diseases like ciliopathies which often involve chronic renal decline. While important biomarkers are available in structured databases, crucial information such as external lab tests and detailed disease history may only be found in clinical narratives. This study aims to enrich structured datasets with unstructured clinical text and assess its impact on estimating chronic kidney disease progression in ciliopathy patients. Our results demonstrate that data enrichment increased the number of eligible patients for longitudinal analysis by 73.5%, expanded available measurements by 189%, and significantly extended the median follow-up duration from 3.2 to 6.6 years. Using linear mixed regression to model individual estimated glomerular filtration (eGFR) rate trajectories over age, we found that data enrichment reduced standard errors by 30%, indicating a substantial increase in precision and reliability. These findings underscore the value of EHR data enrichment for longitudinal analysis in rare disease research.

PMID:40380706 | DOI:10.3233/SHTI250602

Stud Health Technol Inform. 2025 May 15;327:123-127. doi: 10.3233/SHTI250286.

ABSTRACT

Rare diseases, while individually rare, cumulatively affect a large population, and patients often undergo long and arduous diagnostic odysseys. Toward the goal of supporting earlier diagnosis of rare diseases, we developed generalizable methods of extracting rare diseases and phenotypes from structured electronic health records and clinical notes. We analyzed the distributions of the age of onset of phenotypes per disease to identify disease-phenotype associations, producing a dataset with over 500 thousand associations covering 2300 rare diseases. Disease-phenotype associations are characterized by disease prevalence and mean age of onset of the phenotype to aid phenotype selection according to the priorities of the clinical decision support task.

PMID:40380398 | DOI:10.3233/SHTI250286

Stud Health Technol Inform. 2025 May 15;327:32-36. doi: 10.3233/SHTI250268.

ABSTRACT

Rare diseases are challenging to diagnose and collectively affect a large fraction of the population. This work sought to develop an approach to generate models for probabilistic reasoning focused on the presence of a specified phenotypic abnormality. The approach generates a Bayesian network, a graphical AI model that uses probability to reason under uncertainty, that includes all diseases that can cause the specified abnormality as well as all phenotypic abnormalities caused by those diseases. The approach efficiently computes the probabilities of the possible diagnoses and evaluates the impact of additional evidence. One can use the model to identify the observations that yield the greatest information to reduce uncertainty. An example model for diagnosis of a finding of enlarged kidney is presented to demonstrate the feasibility and advantages of the approach. Further work includes incorporation of age of onset and inheritance pattern of the diseases, hierarchical relationships among diseases and phenotypic abnormalities to allow diagnosis based on information at varying levels of granularity, and user interfaces to simplify interaction with the models.

PMID:40380380 | DOI:10.3233/SHTI250268

Stud Health Technol Inform. 2025 May 15;327:1433-1437. doi: 10.3233/SHTI250639.

ABSTRACT

The increasing adoption of deep learning methods has intensified the demand for explanations regarding how AI systems generate their results. This necessity originated primarily in the domain of image processing and has expanded to encompass the complexities of large language models (LLMs), particularly in medical contexts. For example, when LLM-based chatbots provide medical advice, the challenge lies in articulating the rationale behind their recommendations, especially when specific features may not be identifiable. This paper explores the distinction between explanation, interpretation, and understanding within AI-driven decision support systems. By adopting Daniel Dennett's intentional stance, we propose a methodology for analyzing how AI explanations can facilitate deeper user engagement and comprehension. Furthermore, we examine the implications of this methodology for the development and regulation of medical chatbots.

PMID:40380742 | DOI:10.3233/SHTI250639

Stud Health Technol Inform. 2025 May 15;327:1418-1422. doi: 10.3233/SHTI250636.

ABSTRACT

Recently, machine learning methods have emerged to predict dental disease progression, often relying on costly annotated datasets and frequently exhibiting low generalization performance. This study evaluates the application of Siamese networks for detecting subtle changes in longitudinal dental x-rays and predicting the time span category between dental treatments using periapical radiographs and patient demographic data. We assume that the ability of these models to detect the time intervals between dental treatments would ensure their capability to identify more complex patterns related to disease progression. The baseline models based on CNNs and MLP achieved moderate performance, while the Siamese network models demonstrated significant improvements, with the highest-performing model achieving an accuracy of 86.32% ± 1.60%. Moreover, the introduction of demographic features such as age and gender into the model led to a significant reduction in performance variance. These results underscore the effectiveness of Siamese networks in capturing subtle temporal changes in dental radiographs in longitudinal settings, offering the potential to integrate these models into clinical workflows. Future research will explore self-supervised learning models for dental disease progression, especially in clinical settings with limited labeled data.

PMID:40380739 | DOI:10.3233/SHTI250636

Stud Health Technol Inform. 2025 May 15;327:1343-1347. doi: 10.3233/SHTI250621.

ABSTRACT

Patients admitted to the intensive care unit (ICU) are often treated with multiple high-risk medications. Over- and underprescribing of indicated medications, and inappropriate choice of medications frequently occur in the ICU. This risk has to be minimized. We evaluate the performance of recommendation methods in suggesting appropriate medications and examine whether incorporating clinical patient data beyond the medication list improves recommendations. Using the MIMIC-III dataset, we formulate medication list completion as a recommendation task. Our analysis includes four autoencoder-based approaches and two strong baselines. We used as inputs either only known medications, or medications together with patient data. We showed that medication recommender systems based on autoencoders may successfully recommend medications in the ICU.

PMID:40380724 | DOI:10.3233/SHTI250621

Stud Health Technol Inform. 2025 May 15;327:1290-1294. doi: 10.3233/SHTI250606.

ABSTRACT

Ovarian cancer, a leading cause of cancer-related deaths among women, comprises distinct subtypes each requiring different treatment approaches. This paper presents a deep-learning framework for classifying ovarian cancer subtypes using Whole Slide Imaging (WSI). Our method contains three stages: image tiling, feature extraction, and multi-instance learning. Our approach is trained and validated on a public dataset from 80 distinct patients, achieving up to 89,8% accuracy with a notable improvement in computational efficiency. The results demonstrate the potential of our framework to augment diagnostic precision in clinical settings, offering a scalable solution for the accurate classification of ovarian cancer subtypes.

PMID:40380710 | DOI:10.3233/SHTI250606

Stud Health Technol Inform. 2025 May 15;327:1225-1229. doi: 10.3233/SHTI250585.

ABSTRACT

Artificial intelligence (AI) has transformed medical diagnostics by enhancing the accuracy of disease detection, particularly through deep learning models to analyze medical imaging data. However, the energy demands of training these models, such as ResNet and MobileNet, are substantial and often overlooked; however, researchers mainly focus on improving model accuracy. This study compares the energy use of these two models for classifying thoracic diseases using the well-known CheXpert dataset. We calculate power and energy consumption during training using the EnergyEfficientAI library. Results demonstrate that MobileNet outperforms ResNet by consuming less power and completing training faster, resulting in lower overall energy costs. This study highlights the importance of prioritizing energy efficiency in AI model development, promoting sustainable, eco-friendly approaches to advance medical diagnosis.

PMID:40380690 | DOI:10.3233/SHTI250585

Stud Health Technol Inform. 2025 May 15;327:1135-1139. doi: 10.3233/SHTI250567.

ABSTRACT

Optical Coherence Tomography (OCT) has become an indispensable imaging modality in ophthalmology, providing high-resolution cross-sectional images of the retina. Accurate classification of OCT images is crucial for diagnosing retinal diseases such as Age-related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). This study explores the efficacy of various deep learning models, including convolutional neural networks (CNNs) and Vision Transformers (ViTs), in classifying OCT images. We also investigate the impact of integrating metadata (patient age, sex, eye laterality, and year) into the classification process, even when a significant portion of metadata is missing. Our results demonstrate that multimodal models leveraging both image and metadata inputs, such as the Multimodal ResNet18, can achieve competitive performance compared to image-only models, such as DenseNet121. Notably, DenseNet121 and Multimodal ResNet18 achieved the highest accuracy of 95.16%, with DenseNet121 showing a slightly higher F1-score of 0.9313. The multimodal ViT-based model also demonstrated promising results, achieving an accuracy of 93.22%, indicating the potential of Vision Transformers (ViTs) in medical image analysis, especially for handling complex multimodal data.

PMID:40380672 | DOI:10.3233/SHTI250567

Stud Health Technol Inform. 2025 May 15;327:914-918. doi: 10.3233/SHTI250505.

ABSTRACT

This study investigates the application of a Long Short-Term Memory (LSTM) architecture for classifying hypertension using accelerometer data, specifically focusing on physical activity and sleep from the publicly available NHANES 2011-2012 dataset. The LSTM model captures the sequential patterns in this data, providing insights into behavioral patterns related to hypertension. The performance of the LSTM model is compared to traditional machine learning methods as well as other commonly used sequence models, including Recurrent Neural Networks (RNN), Transformers (TF), and 1D Convolutional Networks (Conv1D). The results show that the LSTM model achieves superior accuracy at 96.37%, outperforming the RNN (75.67%), TF (77.10%), and Conv1D (89.34%), as well as the other machine learning models, which range from 60.92% to 64.75%. These findings underscore the potential of LSTM models for integration into wearable health monitoring systems, enabling early detection or management of hypertension.

PMID:40380612 | DOI:10.3233/SHTI250505

Stud Health Technol Inform. 2025 May 15;327:884-885. doi: 10.3233/SHTI250491.

ABSTRACT

AI-driven "audiomics" leverages voice and respiratory sounds as non-invasive biomarkers to diagnose and manage pulmonary conditions, including COVID-19, tuberculosis, ILD, asthma, and COPD. By analyzing acoustic features, machine and deep learning enhance diagnostic accuracy and track disease progression. Key applications include cough-based TB detection, smartphone COVID-19 screening, and speech analysis for asthma and COPD monitoring. Ethical challenges like data privacy and standardization remain barriers to clinical adoption. With ongoing research, audiomics holds promise for transforming respiratory diagnostics and personalized care.

PMID:40380599 | DOI:10.3233/SHTI250491