Eur Radiol. 2025 Apr 7. doi: 10.1007/s00330-025-11554-9. Online ahead of print.

ABSTRACT

OBJECTIVES: This study aimed to evaluate the performance of an artificial intelligence (AI)-based software for fracture detection in pediatric patients within a real-life clinical setting. Specifically, it sought to assess (1) the stand-alone AI performance in real-life cohort and in selected set of medicolegal relevant fractures and (2) its influence on the diagnostic performance of inexperienced emergency room physicians.

MATERIALS AND METHODS: The retrospective study involved 1672 radiographs of children under 18 years, obtained consecutively (real-life cohort) and selective (medicolegal cohort) in a tertiary pediatric emergency department. On these images, the stand-alone performance of a commercially available, deep learning-based software was determined. Additionally, three pediatric residents independently reviewed the radiographs before and after AI assistance, and the impact on their diagnostic accuracy was assessed.

RESULTS: In our cohort (median age 10.9 years, 59% male), the AI demonstrated a sensitivity of 92%, specificity of 83%, and accuracy of 87%. For medicolegally relevant fractures, the AI achieved a sensitivity of 100% for proximal tibia fractures, but only 68% for radial condyle fractures. AI assistance improved the residents' patient-wise sensitivity from 84 to 87%, specificity from 91 to 92%, and diagnostic accuracy from 88 to 90%. In 2% of cases, the readers, with the assistance of AI, erroneously discarded their correct diagnosis.

CONCLUSION: The AI exhibited strong stand-alone performance in a pediatric setting and can modestly enhance the diagnostic accuracy of inexperienced physicians. However, the economic implications must be weighed against the potential benefits in patient safety.

KEY POINTS: Question Does an artificial intelligence-based software for fracture detection influence inexperienced physicians in a real-life pediatric trauma population? Findings Addition of a well-performing artificial intelligence-based software led to a limited increase in diagnostic accuracy of inexperienced human readers. Clinical relevance Diagnosing fractures in children is especially challenging for less experienced physicians. High-performing artificial intelligence-based software as a "second set of eyes," enhances diagnostic accuracy in a common pediatric emergency room setting.

PMID:40192806 | DOI:10.1007/s00330-025-11554-9

Int J Legal Med. 2025 Apr 7. doi: 10.1007/s00414-025-03469-3. Online ahead of print.

ABSTRACT

Bone age assessment (BAA) means challenging tasks in forensic science especially in some extreme situations like only skulls found. This study aimed to develop an accurate three-dimensional deep learning (DL) framework at skull CT metadata for BAA and try to explore new skull markers. In this study, retrospective data of 385,175 Skull CT slices from 1,085 patients ranging from 16.32 to 90.56 years were obtained. The cohort was randomly split into a training set (90%, N = 976) and a test set (10%, N = 109). Additional 101 patients were collected from another center as an external validation set. Evaluations and comparisons with other state-of-the-art DL models and traditional machine learning (ML) models based on hand-crafted methods were hierarchically performed. The mean absolute error (MAE) was the primary parameter. A total of 1186 patients (mean age ± SD: 54.72 ± 14.91, 603 males & 583 females) were evaluated. Our method achieved the best MAE on the training set, test set and external validation set were 6.51, 5.70, and 8.86 years in males, while in females, the best MAE were 6.10, 7.84, and 10.56 years, respectively. In the test set, the MAE of other 2D or 3D models and ML methods based on manual features were ranged from 10.12 to 14.12. The model results showed a tendency of larger errors in the elderly group. The results suggested the proposed three-dimensional DL framework performed better than existing DL and manual methods. Furthermore, our framework explored new skeletal markers for BAA and could serve as a backbone for extracting features from three-dimensional skull CT metadata in a professional manner.

PMID:40192774 | DOI:10.1007/s00414-025-03469-3

Analyst. 2025 Apr 7. doi: 10.1039/d5an00075k. Online ahead of print.

ABSTRACT

Rapid and reliable detection of chemical warfare agents (CWAs) is essential for military defense and counter-terrorism operations. Although Raman spectroscopy provides a non-destructive method for on-site detection, existing methods show difficulty in coping with complex spectral overlap and concentration changes when analyzing mixtures containing trace components and highly complex mixtures. Based on the idea of convolutional neural networks and multi-layer perceptrons, this study proposes a qualitative and quantitative analysis algorithm of Raman spectroscopy based on deep learning (RS-MLP). The reference feature library is built from pure substance spectral features, while multi-head attention adaptively captures mixture weights. The MLP-Mixer then performs hierarchical feature matching for qualitative identification and quantitative analysis. The recognition rate of spectral data for the four types of combinations used for validation reached 100%, with an average root mean square error (RMSE) of less than 0.473% for the concentration prediction of three components. Furthermore, the model exhibited robust performance even under conditions of highly overlapping spectra. At the same time, the interpretability of the model is also enhanced. The model has excellent accuracy and robustness in component identification and concentration identification in complex mixtures and provides a practical solution for rapid and non-contact detection of persistent chemicals in complex environments.

PMID:40192710 | DOI:10.1039/d5an00075k

Eur Heart J Acute Cardiovasc Care. 2025 Apr 7:zuaf058. doi: 10.1093/ehjacc/zuaf058. Online ahead of print.

NO ABSTRACT

PMID:40192550 | DOI:10.1093/ehjacc/zuaf058

J Sports Sci. 2025 Apr 7:1-19. doi: 10.1080/02640414.2025.2488157. Online ahead of print.

ABSTRACT

Predicting high-run chases in cricket is a complex task influenced by various factors, including team rankings, match conditions, pitch behavior, and inning scores. This study evaluates the effectiveness of probabilistic machine learning models, namely Naïve Bayes (NB), Bayesian Network (BN), Bayesian Regularized Neural Network (BRNN), Hidden Naïve Bayes (HNB), Correlation Feature-Based Filter Weighting Naïve Bayes (CFWNB), and Class-Specific Attribute Weighted Naïve Bayes (CAWNB), in predicting high run chases in T20I cricket. Model performance was assessed using accuracy, precision, sensitivity, specificity, F1-score, AUC-ROC, and entropy, while Monte Carlo simulations ensured robustness across multiple iterations. Non-parametric statistical tests were employed due to the non-normal distribution of performance metrics, with the Friedman test revealing significant ranking variations among models. The results demonstrate that CAWNB consistently outperforms other models in terms of accuracy, precision, AUC, and F1-score, making it the most reliable choice for high-run chase prediction. Future research should explore hybrid Bayesian deep learning approaches, real-time data adaptation, and the application of these models to other cricket formats and sports analytics to further enhance predictive performance.

PMID:40192186 | DOI:10.1080/02640414.2025.2488157

Radiol Med. 2025 Apr 7. doi: 10.1007/s11547-025-01985-1. Online ahead of print.

ABSTRACT

Interstitial lung diseases (ILD) constitute a large and heterogeneous group of disorders affecting the lung parenchyma. While idiopathic pulmonary fibrosis (IPF), the most common type of ILD, is the prototype of progressive fibrosis, other forms, collectively termed "progressive pulmonary fibrosis" (PPF), can show a similar clinical course. Detecting chronic fibrosing ILD progression necessitates radiological evidence using high-resolution computed tomography (HRCT), which determines eligibility for treatment. However, assessing the extent of fibrosis and progression on HRCT images is difficult and lacks specific guidelines. Therefore, expert oversight and high-quality visual assessment/scoring of complex disease patterns is essential to monitor disease changes. Twelve Italian chest radiologists deliberated on the current state of quantifying lung fibrosis using existing literature to develop practice-oriented consensus statements to assist radiologists in visually assessing/scoring lung fibrosis on HRCT images in patients with PPF. The resulting statements cover three key areas: (1) technical requirements necessary for accurate HRCT image assessment; (2) an easy-to-use quantification protocol for routine clinical practice; and (3) a multiple specialist approach by combining radiological, clinical, and histopathological findings for the correct diagnosis, prompt detection of PPF, and timely start of antifibrotic treatment. In future, automated quantitative HRCT evaluation will lead to new clinical assessment tools.

PMID:40192924 | DOI:10.1007/s11547-025-01985-1

Expert Rev Mol Diagn. 2025 Apr 7. doi: 10.1080/14737159.2025.2482639. Online ahead of print.

ABSTRACT

INTRODUCTION: Breast cancer remains a major global health challenge. While advances in precision oncology have contributed to improvements in patient outcomes and provided a deeper understanding of the biological mechanisms that drive the disease, historically, research and patients' allocation to treatment have heavily relied on single-omic approaches, analyzing individual molecular dimensions such as genomics, transcriptomics, or proteomics. While these have provided deep insights into breast cancer biology, they often fail to offer a complete understanding of the disease's complex molecular landscape.

AREAS COVERED: In this review, the authors explore the recent advancements in multi-omic research in the realm of breast cancer and using clinical data show how multi-omic integration can offer a more holistic understanding of the molecular alterations and their functional consequences underlying breast cancer.

EXPERT OPINION: The overall developments in multi-omic research and AI are expected to complement precision diagnostics through potentially refining prognostic models, and treatment selection. Overcoming challenges such as cost, data complexity, and lack of standardization is crucial for unlocking the full potential of multi-omics and AI in breast cancer patient care to enable the advancement of personalized treatments and improve patient outcomes.

PMID:40193192 | DOI:10.1080/14737159.2025.2482639

Phys Rev Lett. 2025 Mar 21;134(11):118402. doi: 10.1103/PhysRevLett.134.118402.

ABSTRACT

When cell sheets fold during development, their apical or basal surfaces constrict and cell shapes approach the geometric singularity in which these surfaces vanish. Here, we reveal the mechanical consequences of this geometric singularity for tissue folding in a minimal vertex model of an epithelial monolayer. In simulations of the buckling of the epithelium under compression and numerical solutions of the corresponding continuum model, we discover an "unbuckling" bifurcation: at large compression, the buckling amplitude can decrease with increasing compression. By asymptotic solution of the continuum equations, we reveal that this bifurcation comes with a large stiffening of the epithelium. Our results thus provide the mechanical basis for absorption of compressive stresses by tissue folds such as the cephalic furrow during germband extension in Drosophila.

PMID:40192356 | DOI:10.1103/PhysRevLett.134.118402

Elife. 2025 Apr 7;13:RP102819. doi: 10.7554/eLife.102819.

ABSTRACT

The formation of the mammalian brain requires regionalization and morphogenesis of the cranial neural plate, which transforms from an epithelial sheet into a closed tube that provides the structural foundation for neural patterning and circuit formation. Sonic hedgehog (SHH) signaling is important for cranial neural plate patterning and closure, but the transcriptional changes that give rise to the spatially regulated cell fates and behaviors that build the cranial neural tube have not been systematically analyzed. Here, we used single-cell RNA sequencing to generate an atlas of gene expression at six consecutive stages of cranial neural tube closure in the mouse embryo. Ordering transcriptional profiles relative to the major axes of gene expression predicted spatially regulated expression of 870 genes along the anterior-posterior and mediolateral axes of the cranial neural plate and reproduced known expression patterns with over 85% accuracy. Single-cell RNA sequencing of embryos with activated SHH signaling revealed distinct SHH-regulated transcriptional programs in the developing forebrain, midbrain, and hindbrain, suggesting a complex interplay between anterior-posterior and mediolateral patterning systems. These results define a spatiotemporally resolved map of gene expression during cranial neural tube closure and provide a resource for investigating the transcriptional events that drive early mammalian brain development.

PMID:40192104 | DOI:10.7554/eLife.102819

Aging Clin Exp Res. 2025 Apr 7;37(1):120. doi: 10.1007/s40520-025-03025-4.

ABSTRACT

BACKGROUND: Real-world data on adverse drug reactions (ADRs) associated with idarucizumab and andexanet alfa are limited.

AIM: This study aimed to assess the frequency, the characteristics and clinical and demographic factors associated with ADRs related to their use.

METHODS: This is a retrospective analysis of ADR reports collected in Vigibase® until May 31, 2023. Multivariable logistic regression estimated reporting odds ratios (RORs) for serious ADRs, death, and thromboembolic events according to demographical and clinical covariates.

RESULTS: A total of 1095 Individual Case Safety Reports (ICSRs) reporting idarucizumab (72%) or andexanet alfa (28%) as suspected/interacting agents were collected. Most of the subjects were males (44.5%), with a median age of 78 years, and exposed to only one suspected/interacting medication (73.6%). ADRs were defined as serious in 88.6% of cases, with a total of 614 (56.1%) fatal cases. Compared to patients without concomitant medications, probability of serious ADRs and death were both higher in those receiving ≥ 5 concomitant medications in the idarucizumab subgroup (ROR 4.04 and 1.66, respectively) and in those receiving 1-4 concomitant medications in the andexanet alfa subgroup (ROR 5.66 and 4.80, respectively). Moreover, the probability of thromboembolic events was significantly lower for subjects aged > 75 years (ROR for 75-84 years 0.55; ROR for ≥ 85 years 0.50).

DISCUSSION: In real-world, ADRs associated with idarucizumab and andexanet alfa use are generally serious, resulting in death in a high percentage of subjects.

CONCLUSION: Clinicians should pay particular attention when managing individuals needing these drugs, especially if vulnerable and requiring polytherapy.

PMID:40192996 | DOI:10.1007/s40520-025-03025-4

Oncol Res. 2025 Mar 19;33(4):919-935. doi: 10.32604/or.2024.054537. eCollection 2025.

ABSTRACT

OBJECTIVE: Prostate cancer (PCA) is the second most widespread cancer among men globally, with a rising mortality rate. Enzyme-responsive lipid nanoparticles (ERLNs) are promising vectors for the selective delivery of anticancer agents to tumor cells. The goal of this study is to fabricate ERLNs for dual delivery of gefitinib (GF) and simvastatin (SV) to PCA cells.

METHODS: ERLNs loaded with GF and SV (ERLNGFSV) were assembled using bottom-up and top-down techniques. Subsequently, these ERLN cargoes were coated with triacylglycerol, and phospholipids and capped with chitosan (CS). The ERLNGFSV, and CS engineered ERLNGFSV (CERLNGFSV) formulations were characterized for particle size (PS), zeta potential (ZP), and polydispersity index (PDI). The biocompatibility, and cytotoxicity of the plain and GF plus SV-loaded ERLN cargoes were assessed using erythrocytes and PC-3 cell line. Additionally, molecular docking simulations (MDS) were conducted to examine the influence of GF and SV on succinate dehydrogenase (SDH), glutathione peroxidase-4 (GPX-4), and 5α-reductase (5α-RD).

RESULTS: These results showed that plain, ERLNGFSV, and CERLNGFSV cargoes have a nanoscale size and homogeneous appearance. Moreover, ERLNGFSV and CERLNGFSV were biocompatible, with no detrimental effects on erythrocytes. Treatment with GF, SV, GF plus SV, ERLNGFSV, and CERLNGFSV significantly reduced the viability of PC-3 cells compared to control cells. Particularly, the blend of GF and SV, as well as ERLNGFSV and CERLNGFSV augmented PC-3 cell death. Also, treating PC-3 cells with free drugs, their combination, ERLNGFSV, and CERLNGFSV formulations elevated the percentage of apoptotic cells. MDS studies demonstrated that GF and SV interact with the active sites of SDH, GPX-4, and 5α-reductase.

CONCLUSIONS: This study concludes that SVGF combination and ERLNs loading induce particular delivery, and synergism on PC-3 death through action on multiple pathways involved in cell proliferation, and apoptosis, besides the interaction with SDH, GPX-4, and 5α-RD. Therefore, GFSV-loaded ERLN cargoes are a promising strategy for PCA treatment. In vivo studies are necessary to confirm these findings for clinical applications.

PMID:40191728 | PMC:PMC11964872 | DOI:10.32604/or.2024.054537

ACS Omega. 2025 Mar 20;10(12):12366-12374. doi: 10.1021/acsomega.4c11382. eCollection 2025 Apr 1.

ABSTRACT

The increasing prevalence of infections byCandida hemeulonii sensu stricto, particularly due to its resistance to standard antifungal therapies, represents a significant healthcare challenge. Traditional treatments often fail, emphasizing the need to explore alternative therapeutic strategies. Drug repurposing, which reevaluates existing drugs for new applications, offers a promising path. This study examines the potential of repurposing alexidine dihydrochloride as an antifungal agent againstC. hemeulonii sensu stricto. Minimum Inhibitory Concentration (MIC) and Minimum Fungicidal Concentration (MFC) values were established using broth microdilution methods. To further assess antifungal activity, different assays were conducted, including growth inhibition, biofilm inhibition, biofilm eradication, and cell damage. Checkerboard assays were employed to study the compound's fungicidal potential and interactions with other antifungals. Additional tests, sorbitol protection assay, efflux pump inhibition, cell membrane permeability assays, and nucleotide leakage were performed. In vivo efficacy and safety were evaluated inTenebrio molitor larvae. Alexidine demonstrated fungicidal activity againstC. hemeulonii sensu stricto, with an MIC of 0.5 μg/mL. Biofilm formation was significantly inhibited, with a reduction of 78.69%. Mechanistic studies revealed nucleotide leakage, indicating membrane impact, but no significant protein leakage was detected. In vivo, alexidine displayed a favorable safety profile, with no evidence of hemolysis or acute toxicity in the T. molitor model. These findings support alexidine as a strong candidate for antifungal drug repurposing, especially for treatingC. hemeulonii sensu stricto infections. Its efficacy in inhibiting growth and biofilm formation, combined with a positive safety profile, underscores its potential for clinical development as an antifungal therapy.

PMID:40191372 | PMC:PMC11966325 | DOI:10.1021/acsomega.4c11382

RSC Adv. 2025 Apr 4;15(14):10622-10633. doi: 10.1039/d4ra09055a. eCollection 2025 Apr 4.

ABSTRACT

Peroxisome proliferator-activated receptors (PPARs) are ligand-activated nuclear receptors with a crucial regulatory role in carbohydrate and lipid metabolism and are emerging druggable targets in "metabolic syndrome" (MetS) and cancers. However, there is a need to identify ligands that can activate specific PPAR subtypes, particularly PPARβ/δ, which is less studied compared with other PPAR isoforms (α and γ). Herein, using the drug-repurposing approach, the ZINC database of clinically approved drugs was screened to target the PPARβ/δ receptor through high-throughput-virtual-screening, followed by molecular docking and molecular dynamics (MD) simulation. The top-scoring ligands were subjected to drug-likeness analysis. The hit molecule was tested in an in vitro model of NAFLD (non-alcoholic fatty liver disease). The top five ligands with strong binding affinity towards PPARβ/δ were canagliflozin > empagliflozin > lumacaftor > eprosartan > dapagliflozin. RMSD/RMSF analysis demonstrated stable protein-ligand complexation (PLC) by the top-scoring ligands with PPARβ/δ. In silico ADMET prediction analysis revealed favorable pharmacokinetic profiles of these top five ligands. Canagliflozin showed significant (P < 0.001) dose-dependent decrease in lipid accumulation and the associated oxidative stress-inflammatory response, suggesting its promising anti-steatotic potential. These outcomes pave the way for further validation and development of PPAR activity-modulating therapeutics.

PMID:40190631 | PMC:PMC11970364 | DOI:10.1039/d4ra09055a

NAR Genom Bioinform. 2025 Apr 4;7(2):lqaf033. doi: 10.1093/nargab/lqaf033. eCollection 2025 Jun.

ABSTRACT

We describe FoundHaplo, an identity-by-descent algorithm that can be used to screen untyped disease-causing variants using single nucleotide polymorphism (SNP) array data. FoundHaplo leverages knowledge of shared disease haplotypes for inherited variants to identify those who share the disease haplotype and are, therefore, likely to carry the rare [minor allele frequency (MAF) ≤ 0.01%] variant. We performed a simulation study to evaluate the performance of FoundHaplo across 33 disease-harbouring loci. FoundHaplo was used to infer the presence of two rare (MAF ≤ 0.01%) pathogenic variants, SCN1B c.363C>G (p.Cys121Trp) and WWOX c.49G>A (p.E17K), which can cause mild dominant and severe recessive epilepsy, respectively, in the Epi25 cohort and the UK Biobank. FoundHaplo demonstrated substantially better sensitivity at inferring the presence of these rare variants than existing genome-wide imputation. FoundHaplo is a valuable screening tool for searching disease-causing variants with known founder effects using only SNP genotyping data. It is also applicable to nonhuman applications and nondisease-causing traits, including rare-variant drivers of quantitative traits. The FoundHaplo algorithm is available at https://github.com/bahlolab/FoundHaplo (DOI:10.5281/zenodo.8058286).

PMID:40191585 | PMC:PMC11970371 | DOI:10.1093/nargab/lqaf033

J Intern Med. 2025 Apr 6. doi: 10.1111/joim.20087. Online ahead of print.

ABSTRACT

BACKGROUND: Methotrexate (MTX) is the mainstay initial treatment of rheumatoid arthritis (RA), but individual response varies and remains difficult to predict. The role of genetics remains unclear, but studies suggest its importance.

METHODS: Incident RA patients starting MTX-monotherapy were identified through a large-scale Swedish register linkage. Demographic, clinical, medical, and drug history features were combined with fully imputed genotype data and used to train and evaluate multiple learning models to predict key MTX treatment outcomes.

RESULTS: Among 2432 patients, we consistently observed an estimated area under the curve (AUC) of ∼0.62, outperforming models trained on sex and age. The best performance was observed for EULAR primary response (AUC = 0.67), whereas models struggled the most with predicting discontinuation. Genetics provided negligible improvements to prediction quality.

CONCLUSIONS: Despite an extensive study population with broad multi-modal data, predicting MTX treatment outcomes remains a challenge. Common genetic variants added minimal predictive power over clinical features.

PMID:40190030 | DOI:10.1111/joim.20087

Hum Vaccin Immunother. 2025 Dec;21(1):2488557. doi: 10.1080/21645515.2025.2488557. Epub 2025 Apr 6.

ABSTRACT

It is estimated that 40-50% of severe asthma has an atopic basis, representing a clinical challenge and a significant economic burden for healthcare systems. The most effective treatment has emerged with the use of biologic therapies such as omalizumab; however, the rate of therapy switching due to loss of efficacy is high, which has a negative impact on the healthcare system. The aim was to evaluate the influence of genetic polymorphisms as predictors of omalizumab survival. We conducted a retrospective observational cohort study of 110 patients with uncontrolled severe allergic asthma treated with omalizumab in a tertiary hospital. We analyzed FCER1A (rs2251746, rs2427837), FCER1B (rs1441586, rs573790, rs1054485, rs569108), C3 (rs2230199), FCGR2A (rs1801274), FCGR2B (rs3219018, rs1050501), FCGR3A (rs10127939, rs396991), IL1RL1 (rs1420101, rs17026974, rs1921622) and GATA2 (rs4857855) by real-time PCR using Taqman probes. Drug survival was defined as the time from initiation to discontinuation of omalizumab. Cox regression analysis adjusted for the presence of respiratory disease, GERD, SAHS and years with asthma showed that the SNPs FCER1B rs573790 - CT (p < .001; HR = 3.38; CI95% = 1.66-6.87), FCGR3A rs10127939-AC (p = .018; HR = 3.85; CI95% = 1.25-11.81) and FCGR3A rs396991-CC (p = .020; HR = 2.23; CI95% = 1.14-4.38) were the independent variables associated with worse survival in patients diagnosed with asthma. A trend toward statistical significance was also found between and FCGR3A rs10127939-CC (p = .080; HR = 0.13; CI95% = 0.01-1.28) and longer drug survival. The results of this study demonstrate the potential influence of the polymorphisms studied on omalizumab survival and the clinical benefit that could be achieved by defining predictive biomarkers of drug survival.

PMID:40189906 | DOI:10.1080/21645515.2025.2488557

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e70002. doi: 10.1111/eci.70002.

ABSTRACT

BACKGROUND: Recent advancements in deep learning (DL), a subset of artificial intelligence, have shown the potential to automate and improve disease recognition, phenotyping and prediction of disease onset and outcomes by analysing various sources of medical data. The electrocardiogram (ECG) is a valuable tool for diagnosing and monitoring cardiovascular conditions.

METHODS: The implementation of DL in ECG analysis has been used to detect and predict rhythm abnormalities and conduction abnormalities, ischemic and structural heart diseases, with performance comparable to physicians. However, despite promising development of DL algorithms for automatic ECG analysis, the integration of DL-based ECG analysis and deployment of medical devices incorporating these algorithms into routine clinical practice remains limited.

RESULTS: This narrative review highlights the applications of DL in 12-lead ECG analysis. Furthermore, we review randomized controlled trials that assess the clinical effectiveness of these DL tools. Finally, it addresses different key barriers to widespread implementation in clinical practice, including regulatory hurdles, algorithm transparency and data privacy concerns.

CONCLUSIONS: By outlining both the progress and the obstacles in this field, this review aims to provide insights into how DL could shape the future of ECG analysis and enhance cardiovascular care in daily clinical practice.

PMID:40191935 | DOI:10.1111/eci.70002

Eur J Clin Invest. 2025 Apr;55 Suppl 1:e14370. doi: 10.1111/eci.14370.

ABSTRACT

BACKGROUND: The management of cardiotoxicity related to cancer therapies has emerged as a significant clinical challenge, prompting the rapid growth of cardio-oncology. As cancer treatments become more complex, there is an increasing need to enhance diagnostic and therapeutic strategies for managing their cardiovascular side effects.

OBJECTIVE: This review investigates the potential of artificial intelligence (AI) to revolutionize cardio-oncology by integrating diverse data sources to address the challenges of cardiotoxicity management.

METHODS: We explore applications of AI in cardio-oncology, focusing on its ability to leverage multiple data sources, including electronic health records, electrocardiograms, imaging modalities, wearable sensors, and circulating serum biomarkers.

RESULTS: AI has demonstrated significant potential in improving risk stratification and longitudinal monitoring of cardiotoxicity. By optimizing the use of electrocardiograms, non-invasive imaging, and circulating biomarkers, AI facilitates earlier detection, better prediction of outcomes, and more personalized therapeutic interventions. These advancements are poised to enhance patient outcomes and streamline clinical decision-making.

CONCLUSIONS: AI represents a transformative opportunity in cardio-oncology by advancing diagnostic and therapeutic capabilities. However, successful implementation requires addressing practical challenges such as data integration, model interpretability, and clinician training. Continued collaboration between clinicians and AI developers will be essential to fully integrate AI into routine clinical workflows.

PMID:40191923 | DOI:10.1111/eci.14370

ACS Nano. 2025 Apr 7. doi: 10.1021/acsnano.5c02004. Online ahead of print.

ABSTRACT

Swimming kinematics and macroscale mechanical testing have shown that the vertebral column of sharks acts as a biological spring, storing and releasing energy during locomotion. Using synchrotron X-ray nanotomography and deep-learning image segmentation, we studied the ultrastructure and deformation mechanism of mineralized shark vertebrae from Carcharhinus limbatus (Blacktip shark). The vertebral centrum con regions: the corpus calcareum, a hypermineralized double cone, and the intermediale, blocks of mineralized cartilage interspersed by unmineralized arches. At the micron scale, mineralized cartilage has previously been described as a 3D network of interconnected mineral plates that vary in thickness and spacing. The corpus calcareum consists of stacked, interconnected, curved mineralized planes permeated by a network of organic occlusions. The mineral network in the intermedialia resembles trabecular bone, including thicker struts in the direction opposite to the predominant biological strain. We characterized collagenous fiber elements winding around lacunar spaces in the intermedialia, and we hypothesize the swirling arrangement and elasticity of the fibers to be distributing stress. With little permanent deformation detected in mineralized structures, it is likely that the soft organic matrix is crucial for absorbing energy through deformation, irreversible damage, and viscoelastic behavior. In the corpus calcareum, cracks typically terminate toward thick struts along the mineral planes, resembling the microscale crack deflection and arrest mechanism found in other staggered biocomposites, such as nacre or bone. Using transmission electron microscopy (TEM), we observed preferentially oriented, needlelike bioapatite crystallites and d-band patterns of collagen type-II fibrils resulting from intrafibrillar mineralization.

PMID:40191917 | DOI:10.1021/acsnano.5c02004

Front Aging Neurosci. 2025 Mar 21;17:1532470. doi: 10.3389/fnagi.2025.1532470. eCollection 2025.

ABSTRACT

Conventional computer-aided diagnostic techniques for Alzheimer's disease (AD) predominantly rely on magnetic resonance imaging (MRI) in isolation. Genetic imaging methods, by establishing the link between genes and brain structures in disease progression, facilitate early prediction of AD development. While deep learning methods based on MRI have demonstrated promising results for early AD diagnosis, the limited dataset size has led most AD studies to lean on statistical approaches within the realm of imaging genetics. Existing deep-learning approaches typically utilize pre-defined regions of interest and risk variants from known susceptibility genes, employing relatively straightforward feature fusion methods that fail to fully capture the relationship between images and genes. To address these limitations, we proposed a multi-modal deep learning classification network based on MRI and single nucleotide polymorphism (SNP) data for AD diagnosis and mild cognitive impairment (MCI) progression prediction. Our model leveraged a convolutional neural network (CNN) to extract whole-brain structural features, a Transformer network to capture genetic features, and employed a cross-transformer-based network for comprehensive feature fusion. Furthermore, we incorporated an attention-map-based interpretability method to analyze and elucidate the structural and risk variants associated with AD and their interrelationships. The proposed model was trained and evaluated using 1,541 subjects from the ADNI database. Experimental results underscored the superior performance of our model in effectively integrating and leveraging information from both modalities, thus enhancing the accuracy of AD diagnosis and prediction.

PMID:40191788 | PMC:PMC11968703 | DOI:10.3389/fnagi.2025.1532470