PLoS Comput Biol. 2025 Apr 7;21(4):e1012972. doi: 10.1371/journal.pcbi.1012972. Online ahead of print.

ABSTRACT

Metabolites acting as substrates and regulators of all biochemical reactions play an important role in maintaining the functionality of cellular metabolism. Despite advances in the constraint-based framework for metabolic modeling at a genome-scale, we lack reliable proxies for metabolite concentrations that can be efficiently determined and that allows us to investigate the relationship between concentrations of metabolites in specified metabolic states in the absence of measurements. Here, we introduce a constraint-based approach, the flux-sum coupling analysis (FSCA), which facilitates the study of the interdependencies between metabolite concentrations by determining coupling relationships based on the flux-sum of metabolites. Application of FSCA on metabolic models of Escherichia coli, Saccharomyces cerevisiae, and Arabidopsis thaliana showed that the three coupling relations are present in all models and pinpointed similarities in coupled metabolite pairs. Using the available concentration measurements of E. coli metabolites, we demonstrated that the coupling relationships identified by FSCA can capture the qualitative associations between metabolite concentrations and that flux-sum is a reliable proxy for metabolite concentration. Therefore, FSCA provides a novel tool for exploring and understanding the intricate interdependencies between the concentration of metabolites, advancing the understanding of metabolic regulation, and improving flux-centered systems biology approaches.

PMID:40193389 | DOI:10.1371/journal.pcbi.1012972

Neurology. 2025 Apr 8;104(7_Supplement_1):4960. doi: 10.1212/WNL.0000000000212037. Epub 2025 Apr 7.

ABSTRACT

OBJECTIVE: The safety and efficacy of subcutaneous forms of levodopa/carbidopa.

BACKGROUND: Parkinson's is a motor degenerative disease. The cardinal motor manifestations of Parkinson disease are postural instability, short shuffling gait, cogwheel rigidity of extremities and head, tremors at rest, writing changes (e.g. small handwriting) and bradykinesia. The known and acceptable treatment is oral levodopa/carbidopa but the patients experience (on off phenomenon) where the patients encounter sudden halt of the drug effect so subcutaneous sustained release form is now in trials to assess its efficacy and safety.

DESIGN/METHODS: We searched six different databases for RCTs and single arm studies until November 2024 to screen included studies talking about Subcutaneous forms of levodopa/carbidopa such as subcutaneous levodopa/carbidopa known as ND0612 and Foslevodopa/Foscarbidopa known as ABBV-951. We included 6 studies (2 RCTs and 4 single arm studies). There were adverse events related to the drug such as hallucinations and anxiety and adverse events related to infusion site such as infusion site nodules and infusion site erythema.

RESULTS: 658 total patients, of which 565 experienced side effects with a percentage of 85.86%. ND0612: subcutaneous levodopa/carbidopa, patients experienced 263 side effects events while ABBV-951: Foslevodopa/Foscarbidopa, experienced a total of 256 side effects events. Continuation of subcutaneous form is accompanied with serious adverse events related to the infusion site: complications like pain, erythema, nodules, cellulitis, haemorrhage and hematoma and events leads to discontinuation. there were also drug related adverse events in some studies such as hallucinations and anxiety.

CONCLUSIONS: Our pooling analysis focused on serious and highly distressing adverse effects related to the site of infusion of subcutaneous forms of ND0612 and ABBV-951 which evoked strong negative reactions in patients leading to high rate of discontinuation. Limitations: our analysis included single arm studies. Implications of this study include a need for further research with an extended follow-up period. Disclaimer: Abstracts were not reviewed by Neurology® and do not reflect the views of Neurology® editors or staff. Disclosure: Dr. Fathy has nothing to disclose. Ms. Ibrahim has nothing to disclose. Dr. Al Haj Ali has nothing to disclose. Mr. Saad has nothing to disclose. Dr. Abd El Aziz has nothing to disclose. Dr. Nasser has nothing to disclose. Dr. Hegazy has nothing to disclose. Dr. Shaheen has a non-compensated relationship as a A Research Position Candidate Under Trial Task with Solvemed Company that is relevant to AAN interests or activities. Dr. Saha has nothing to disclose.

PMID:40193855 | DOI:10.1212/WNL.0000000000212037

Medicine (Baltimore). 2025 Apr 4;104(14):e42031. doi: 10.1097/MD.0000000000042031.

ABSTRACT

A laboratory-initiated preemptive and reactive cytochrome P450 and SLCO1B1 PGx testing protocol was evaluated in a private toxicology laboratory with the intent of identifying enzyme frequencies and associated adverse drug events. This study involved non-experimental observational research. During the retrospective medical chart review, patient demographics, statements of medical necessity, and PGx testing data were collected. Frequencies and percentages were calculated for the collected data, and statistical analysis was performed using Intellectus online software. A total of 192 PGx patient records from September 2019 to October 2021 were retrospectively reviewed. For patient demographics, men (n = 118; (61%)) were the majority gender identified among the patient population and Caucasians (n = 112; (58%)) followed by African Americans (n = 37; (19%)) were the most identified ancestry. The mean age of the patients was 69 (±9) years. CYP1A2 hyperinducers, followed by CYP3A5 poor metabolizers and CYP2B6 intermediate metabolizers, are the most encountered cytochrome P450 and SLCO1B1 enzymes. Regarding drug-gene interactions, 41 patients had 1 interaction, 29 had 2, and 31 had 3 or more interactions. For drug-drug interactions, 35 patients had 1 interaction, 15 had 2, and 30 had 3 or more interactions. Overall, 123 patients showed a minor or greater impact on drug-drug or drug-gene interactions. Overall, our study identified cytochrome P450 and SCLCO1B1 enzyme frequencies and patients experiencing actionable adverse drug events. By raising awareness of PGx test results through individualized clinician training, education, and interventions, these adverse events can be promptly identified and resolved.

PMID:40193664 | DOI:10.1097/MD.0000000000042031

PLOS Digit Health. 2025 Apr 7;4(4):e0000785. doi: 10.1371/journal.pdig.0000785. eCollection 2025 Apr.

ABSTRACT

Chronic pain is commonly treated with long-term opioid therapy, but rapid opioid dose tapering has been associated with increased adverse events. Little is known about heterogeneity in the population of patients on high dose opioids and their response to different treatments. Our aim was to examine opioid dose management and other patient characteristics in a longitudinal, clinically diverse, national population of opioid dependent patients. We used spectral clustering, an unsupervised artificial intelligence (AI) approach, to identify patients in a national claims data warehouse who were on an opioid dose tapering regimen from 2008-2018. Due to the size and heterogeneity of our cohort, we did not impose any restrictions on the kind or number of clusters to be identified in the data. Of 113,618 patients with 12 consecutive months at a stable mean opioid dose of ≥ 50 morphine milligram equivalents, 30,932 had one tapering period that began at the first 60-day period with ≥ 15% reduction in average daily dose across overlapping 60-day windows through 7 months of follow-up. We identified 10 clusters that were similar in baseline characteristics but differed markedly in the magnitude, velocity, duration, and endpoint of tapering. A cluster comprising 42% of the sample, characterised by moderately rapid, steady tapering, often (73%) to a final dose of zero, had excess drug-related events, mental health events, and deaths, compared with a cluster comprising 55% of the sample, characterised by slow, steady tapering. Four clusters demonstrated tapers of various velocities followed by complete or nearly complete reversal, with combined drug-related event rates close to that of the slowest tapering cluster. Unsupervised AI methods, such as spectral clustering, are powerful to identify clinically meaningful patterns in opioid prescribing data and to highlight salient subpopulation characteristics for designing safe tapering protocols. They are especially useful for identifying rare events in large data. Our findings highlight the importance of considering tapering velocity along with duration and final dose and should stimulate research to understand the causes and consequences of taper reversals in the context of patient-centered care.

PMID:40193396 | DOI:10.1371/journal.pdig.0000785

Fam Cancer. 2025 Apr 7;24(2):35. doi: 10.1007/s10689-025-00462-y.

ABSTRACT

Recent updated management guidelines for Familial Adenomatous Polyposis (FAP) have been published by professional bodies internationally. These recommendations reflect the diverse needs and capabilities of varying health systems worldwide, including thresholds for intervention and population health priorities. Whilst guidelines are closely aligned in many regards, there are areas of disparity. However, alongside discrepancies in guideline recommendations, common challenges also face professional bodies across the globe. Generation of a robust evidence-base in the environment of limited data is difficult in rare diseases such as FAP, underscored by the fact that expert consensus opinion underpins virtually all guidelines. The presence of a wide phenotypic spectrum in FAP and the other hereditary gastrointestinal polyposis syndromes, whilst now well recognised, further complicates the creation of universal recommendations. In this review we draw comparison between the various international guidelines for the management of FAP, using examples to focus on thematic areas of agreement and divergence. However, beyond this, we also wish to highlight the persisting evidence gaps in clinical management, and any areas of ongoing debate among clinicians, where we are yet to establish the optimal approach.

PMID:40192835 | DOI:10.1007/s10689-025-00462-y

J Biochem Mol Toxicol. 2025 Apr;39(4):e70247. doi: 10.1002/jbt.70247.

ABSTRACT

Alzheimer's disease (AD) is a chronic and progressive neurodegenerative disorder marked by memory deterioration and cognitive impairment. Bisphenol A (BPA), a common environmental pollutant, has been linked to neurotoxicity and may contribute to AD development. This study aims to uncover potential toxicological targets and molecular mechanisms of BPA-induced AD. BPA's potential neurotoxic effects were predicted using ProTox and ADMETlab. Target prediction for BPA was conducted through the STITCH and Swiss Target Prediction platforms, while AD-related targets were compiled from GeneCards, OMIM, and the Therapeutic Target Database (TTD). Protein-protein interaction (PPI) networks were constructed using STRING and visualized in Cytoscape, and gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses were performed. Molecular docking was employed to evaluate the binding interactions between BPA and the identified core targets. Through systematic bioinformatics analyses, 137 candidate targets for BPA-elicited AD were identified. Screening via PPI network analysis highlighted five key targets: STAT3, AKT1, INS, EGFR, and PTEN. GO and KEGG pathway enrichment revealed significant involvement in oxidative stress, neuronal apoptosis, neurodegenerative processes, and pathways such as PI3K/AKT, MAPK, lipid and atherosclerosis, and AD signaling. Molecular docking simulations confirmed strong binding affinities between BPA and these core targets. This study sheds light on the molecular mechanisms underlying BPA's neurotoxic effects in the context of AD and provides a foundation for further research into preventive and therapeutic strategies. The integration of network toxicology and molecular docking offers a robust framework for unraveling toxic pathways of uncharacterized environmental and chemical agents.

PMID:40192506 | DOI:10.1002/jbt.70247

Cardiovasc Hematol Disord Drug Targets. 2025 Apr 4. doi: 10.2174/011871529X361464250319084053. Online ahead of print.

ABSTRACT

Atherosclerosis and ischemic events play a pivotal role in the pathogenesis of several cardiovascular diseases (CVD). The primary aim of preventing recurrent thrombosis in patients who underwent cardiovascular surgery is the antiplatelet agent administration. Nevertheless, despite the aspirin therapy or double (aspirin plus clopidogrel) therapy, the effectiveness of antithrombotic treatment remains controversial. In recent years, we have learned that some percentage of patients still demonstrate no clinical response to aspirin treatment and may experience a vascular complication. This article provides an overview of recent scientific studies that have focused on experimental detection and genotyping of single nucleotide polymorphisms (SNPs) in patients, involving the main therapeutic target genes: cyclooxygenase COX-1 and COX-2, guanylate cyclase GUCY1A3, the glycoprotein complex GPIIb-IIIa, and the platelet receptor protein PEAR1." The aspirin resistance (AR) ranges considerably from 0 % to 66% in patients with ischemic heart disease (IHD) and relatively healthy people (control group). SNP distribution analysis has been proposed to explain the inadequate high platelet reactivity (HPR) among patients with IHD under aspirin treatment. Various SNPs have been proposed to explain the development of CVD and the persistent HPR under aspirin treatment widely used in the prevention of recurrent cardiovascular thrombotic events. Meanwhile, the efficacy of aspirin therapy in secondary thrombosis prevention in patients with IHD is not strongly associated with known SNP. The inconsistent results of different AR clinical trials are likely due to the design of the experiments and methodological and quantitative issues; therefore, careful interpretation of the SNP genotyping results is necessary.

PMID:40192046 | DOI:10.2174/011871529X361464250319084053

Cell Mol Life Sci. 2025 Apr 7;82(1):144. doi: 10.1007/s00018-025-05587-y.

ABSTRACT

The cystic fibrosis (CF) causing variant G542X harbours a premature translation stop signal in the cystic fibrosis transmembrane conductance regulator (CFTR) mRNA. This results in nonsense-mediated decay and loss of functional CFTR protein which leads to defective anion transport and the development of CF disease pathology. Currently available CF modulator therapies cannot be used to treat this variant. We used an adenine base editor (ABE8e Cas9) and guide RNA (sgRNA)/enhanced green fluorescent protein (EGFP) plasmids encapsulated in receptor targeted nanoparticles (RTN), delivered to Bmi-1 transduced basal human CF nasal epithelial cells harbouring the homozygous CFTR G542X variant, to convert the stop codon to G542R, a variant which is amenable to modulator therapy. ABE resulted in 17% of alleles edited to G542R and further selection of GFP fluorescent cells by FACS liberated a population with 52% G542R edited alleles with no editing of neighbouring adenines (A) and few off target edits using a gRNA homology-based approach. In cells differentiated at air-liquid-interface (ALI), 17% and 52% editing of CFTR G542X increased mRNA abundance. 52% editing alone or 17% and 52% editing of CFTR G542X plus treatment with CFTR modulators (VX-445/VX-661/VX-770; ETI/Trikafta/Kaftrio) increased epithelial CFTR protein expression, CFTR protein band C abundance, CFTR172 inhibitable anion transport, and changes in airway surface liquid height and pH in response to vasoactive intestinal peptide (VIP) stimulation. Epithelial scratch repair speed and directionality was also improved. These data provide proof-of-concept that ABE of G542X to G542R in human CF airway epithelial cells could provide a feasible therapy for this variant.

PMID:40192756 | DOI:10.1007/s00018-025-05587-y

Hum Brain Mapp. 2025 Apr 1;46(5):e70201. doi: 10.1002/hbm.70201.

ABSTRACT

Tractography parcellation classifies streamlines reconstructed from diffusion MRI into anatomically defined fiber tracts for clinical and research applications. However, clinical scans often have incomplete fields of view (FOV) where brain regions are partially imaged, leading to partial, or truncated fiber tracts. To address this challenge, we introduce TractCloud-FOV, a deep learning framework that robustly parcellates tractography under conditions of incomplete FOV. We propose a novel training strategy, FOV-Cut Augmentation (FOV-CA), in which we synthetically cut tractograms to simulate a spectrum of real-world inferior FOV cutoff scenarios. This data augmentation approach enriches the training set with realistic truncated streamlines, enabling the model to achieve superior generalization. We evaluate the proposed TractCloud-FOV on both synthetically cut tractography and two real-life datasets with incomplete FOV. TractCloud-FOV significantly outperforms several state-of-the-art methods on all testing datasets in terms of streamline classification accuracy, generalization ability, tract anatomical depiction, and computational efficiency. Overall, TractCloud-FOV achieves efficient and consistent tractography parcellation in diffusion MRI with incomplete FOV.

PMID:40193105 | DOI:10.1002/hbm.70201

Jpn J Radiol. 2025 Apr 7. doi: 10.1007/s11604-025-01755-z. Online ahead of print.

ABSTRACT

PURPOSE: To compare the quality of standard 512-matrix, standard 1024-matrix, and Swin2SR-based 2048-matrix phantom images under different scanning protocols.

MATERIALS AND METHODS: The Catphan 600 phantom was scanned using a multidetector CT scanner under two protocols: 120 kV/100 mA (CT dose index volume = 3.4 mGy) to simulate low-dose CT, and 70 kV/40 mA (0.27 mGy) to simulate ultralow-dose CT. Raw data were reconstructed into standard 512-matrix images using three methods: filtered back projection (FBP), adaptive statistical iterative reconstruction at 40% intensity (ASIR-V), and deep learning image reconstruction at high intensity (DLIR-H). The Swin2SR super-resolution model was used to generate 2048-matrix images (Swin2SR-2048), while the super-resolution convolutional neural network (SRCNN) model generated 2048-matrix images (SRCNN-2048). The quality of 2048-matrix images generated by the two models (Swin2SR and SRCNN) was compared. Image quality was evaluated by ImQuest software (v7.2.0.0, Duke University) based on line pair clarity, task-based transfer function (TTF), image noise, and noise power spectrum (NPS).

RESULTS: At equivalent radiation doses and reconstruction method, Swin2SR-2048 images identified more line pairs than both standard-512 and standard-1024 images. Except for the 0.27 mGy/DLIR-H/standard kernel sequence, TTF-50% of Teflon increased after super-resolution processing. Statistically significant differences in TTF-50% were observed between the standard 512, 1024, and Swin2SR-2048 images (all p < 0.05). Swin2SR-2048 images exhibited lower image noise and NPSpeak compared to both standard 512- and 1024-matrix images, with significant differences observed in all three matrix types (all p < 0.05). Swin2SR-2048 images also demonstrated superior quality compared to SRCNN-2048, with significant differences in image noise (p < 0.001), NPSpeak (p < 0.05), and TTF-50% for Teflon (p < 0.05).

CONCLUSION: Transformer-enhanced 2048-matrix CT images improve spatial resolution and reduce image noise compared to standard-512 and -1024 matrix images.

PMID:40193009 | DOI:10.1007/s11604-025-01755-z

Rheumatol Int. 2025 Apr 7;45(4):91. doi: 10.1007/s00296-025-05825-3.

ABSTRACT

To analyse the types and applications of artificial intelligence (AI) technologies to predict treatment response in rheumatoid arthritis (RA) and spondyloarthritis (SpA). A comprehensive search in Medline, Embase, and Cochrane databases (up to August 2024) identified studies using AI to predict treatment response in RA and SpA. Data on study design, AI methodologies, data sources, and outcomes were extracted and synthesized. Findings were summarized descriptively. Of the 4257 articles identified, 89 studies met the inclusion criteria (74 on RA, 7 on SpA, 4 on Psoriatic Arthritis and 4 a mix of them). AI models primarily employed supervised machine learning techniques (e.g., random forests, support vector machines), unsupervised clustering, and deep learning. Data sources included electronic medical records, clinical biomarkers, genetic and proteomic data, and imaging. Predictive performance varied by methodology, with accuracy ranging from 60 to 70% and AUC values between 0.63 and 0.92. Multi-omics approaches and imaging-based models showed promising results in predicting responses to biologic DMARDs and JAK inhibitors but methodological heterogeneity limited generalizability. AI technologies exhibit substantial potential in predicting treatment responses in RA and SpA, enhancing personalized medicine. However, challenges such as methodological variability, data integration, and external validation remain. Future research should focus on refining AI models, ensuring their robustness across diverse patient populations, and facilitating their integration into clinical practice to optimize therapeutic decision-making in rheumatology.

PMID:40192881 | DOI:10.1007/s00296-025-05825-3

Insights Imaging. 2025 Apr 7;16(1):84. doi: 10.1186/s13244-025-01959-x.

ABSTRACT

OBJECTIVES: To address SPECT's radioactivity, complexity, and costliness in measuring renal function, this study employs artificial intelligence (AI) with non-contrast CT to estimate single-kidney glomerular filtration rate (GFR) and split renal function (SRF).

METHODS: 245 patients with atrophic kidney or hydronephrosis were included from two centers (Training set: 128 patients from Center I; Test set: 117 patients from Center II). The renal parenchyma and hydronephrosis regions in non-contrast CT were automatically segmented by deep learning. Radiomic features were extracted and combined with clinical characteristics using multivariable linear regression (MLR) to obtain a radiomics-clinical-estimated GFR (rcGFR). The relative contribution of single-kidney rcGFR to overall rcGFR, the percent renal parenchymal volume, and the percent renal hydronephrosis volume were combined by MLR to generate the estimation of SRF (rcphSRF). The Pearson correlation coefficient (r), mean absolute error (MAE), and Lin's concordance coefficient (CCC) were calculated to evaluate the correlations, differences, and agreements between estimations and SPECT-based measurements, respectively.

RESULTS: Compared to manual segmentation, deep learning-based automatic segmentation could reduce the average segmentation time by 434.6 times to 3.4 s. Compared to single-kidney GFR measured by SPECT, the rcGFR had a significant correlation of r = 0.75 (p < 0.001), MAE of 10.66 mL/min/1.73 m2, and CCC of 0.70. Compared to SRF measured by SPECT, the rcphSRF had a significant correlation of r = 0.92 (p < 0.001), MAE of 7.87%, and CCC of 0.88.

CONCLUSIONS: The non-contrast CT and AI methods are feasible to estimate single-kidney GFR and SRF in patients with atrophic kidney or hydronephrosis.

CRITICAL RELEVANCE STATEMENT: For patients with an atrophic kidney or hydronephrosis, non-contrast CT and artificial intelligence methods can be used to estimate single-kidney glomerular filtration rate and split renal function, which may minimize the radiation risk, enhance diagnostic efficiency, and reduce costs.

KEY POINTS: Renal function can be assessed using non-contrast CT and AI. Estimated renal function significantly correlated with the SPECT-based measurements. The efficiency of renal function estimation can be refined by the proposed method.

PMID:40192862 | DOI:10.1186/s13244-025-01959-x

Plant Mol Biol. 2025 Apr 7;115(2):56. doi: 10.1007/s11103-025-01582-w.

ABSTRACT

Precision agriculture methods can achieve the highest yield by applying the optimum amount of water, selecting appropriate pesticides, and managing crops in a way that minimises environmental impact. A rapidly emerging advanced research area, computer vision and deep learning, plays a significant role in effective crop management, such as superior genotype selection, plant classification, weed and pest detection, root localization, fruit counting and ripeness detection, and yield prediction. Also, phenotyping of plants involves analysing characteristics of plants such as chlorophyll content, leaf size, growth rate, leaf surface temperature, photosynthesis efficiency, leaf count, emergence time, shoot biomass, and germination time. This article presents an exhaustive study of recent techniques in computer vision and deep learning in plant science, with examples. The study provides the frequently used imaging parameters for plant image analysis with formulae, the most popular deep neural networks for plant classification and detection, object counting, and various applications. Furthermore, we discuss the publicly available plant image datasets for disease detection, weed control, and fruit detection with the evaluation metrics, tools and frameworks, future advancements and challenges in machine learning and deep learning models.

PMID:40192856 | DOI:10.1007/s11103-025-01582-w

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