Nat Commun. 2025 Apr 6;16(1):3284. doi: 10.1038/s41467-025-58656-y.

ABSTRACT

To thrive in extreme conditions, organisms have evolved a diverse arsenal of adaptations that confer resilience. These species, their traits, and the mechanisms underlying them comprise a valuable resource that can be mined for numerous conceptual insights and applied objectives. One of the most dramatic adaptations to water limitation is desiccation tolerance. Understanding the mechanisms underlying desiccation tolerance has important potential implications for medicine, biotechnology, agriculture, and conservation. However, progress has been hindered by a lack of standardization across sub-disciplines, complicating the integration of data and slowing the translation of basic discoveries into practical applications. Here, we synthesize current knowledge on desiccation tolerance across evolutionary, ecological, physiological, and cellular scales to provide a roadmap for advancing desiccation tolerance research. We also address critical gaps and technical roadblocks, highlighting the need for standardized experimental practices, improved taxonomic sampling, and the development of new tools for studying biology in a dry state. We hope that this perspective can serve as a roadmap to accelerating research breakthroughs and unlocking the potential of desiccation tolerance to address global challenges related to climate change, food security, and health.

PMID:40189591 | DOI:10.1038/s41467-025-58656-y

BMC Biol. 2025 Apr 7;23(1):92. doi: 10.1186/s12915-025-02188-w.

ABSTRACT

When applied to vertebrate vocalizations, source-filter theory, initially developed for human speech, has revolutionized our understanding of animal communication, resulting in major insights into the form and function of animal sounds. However, animal calls and human nonverbal vocalizations can differ qualitatively from human speech, often having more chaotic and higher-frequency sources, making formant measurement challenging. We review the considerable achievements of the "formant revolution" in animal vocal communication research, then highlight several important methodological problems in formant analysis. We offer concrete recommendations for effectively applying source-filter theory to non-speech vocalizations and discuss promising avenues for future research in this area.Brief Formants (vocal tract resonances) play key roles in animal communication, offering researchers exciting promise but also potential pitfalls.

PMID:40189499 | DOI:10.1186/s12915-025-02188-w

Age Ageing. 2025 Mar 28;54(4):afaf082. doi: 10.1093/ageing/afaf082.

ABSTRACT

BACKGROUND: Hospitalisation often results in adverse effects in older adults, particularly an increased risk of functional and cognitive decline. Although in-hospital exercise interventions have shown benefits, their impact on intrinsic capacity (IC) remains unknown.

OBJECTIVE: To assess the effects of multicomponent exercise training on IC in acutely hospitalised older adults.

DESIGN: Pooled analysis of two randomised clinical trials.

SETTING: Three Acute Care for Elders units.

SUBJECTS: Hospitalised older adults (≥75 years).

METHODS: The control group received standard care, whereas the exercise group participated in an in-hospital multicomponent exercise program. The primary outcome was IC assessed using a composite score (0-100) across five domains: vitality (handgrip strength), cognition (Mini-Mental State Examination), psychological health (Yesavage Geriatric Depression Scale), locomotion (Short Physical Performance Battery) and sensory function (self-reported vision and hearing). Adverse outcomes were evaluated 1 year after discharge, including emergency visits, hospital re-admission and mortality.

RESULTS: A total of 570 patients (age 87.3 ± 4.8 years) were enrolled during acute hospitalisation [median duration 8 (interquartile range = 3) days] and randomised to the exercise (n = 288) or control group (n = 282). The exercise intervention significantly improved IC compared to the control group [7.74 points, 95% confidence interval (CI) 6.45-9.03, P < .001], with benefits observed in all IC domains. IC score at discharge was inversely associated with mortality risk during follow-up (OR = 0.98 per each increase in IC score at discharge, 95% CI = 0.96, 0.99, P = .010), although no association was found with emergency visits (P = .866) or re-admissions (P = .567).

CONCLUSIONS: In-hospital exercise is an effective strategy to enhance IC in hospitalised older adults. Additionally, the IC score at discharge was inversely related to the mortality risk within 1 year of discharge.

PMID:40188489 | DOI:10.1093/ageing/afaf082

STAR Protoc. 2025 Apr 5;6(2):103745. doi: 10.1016/j.xpro.2025.103745. Online ahead of print.

ABSTRACT

Nanoflow liquid chromatography-tandem mass spectrometry (nLC-MS) benefits untargeted metabolomics by enhancing sensitivity and integrating proteomics for the same sample. Here, we present a protocol to enable nLC-MS for dual metabolomics and proteomics. We describe steps for solid-phase micro-extraction (SPME)-assisted metabolite cleaning and enrichment, which avoids capillary column blockage. We then detail nLC-MS data acquisition and analysis. This protocol has been applied in diverse specimens including biofluids, cell lines, and tissues. For complete details on the use and execution of this protocol, please refer to Lin et al.1.

PMID:40188434 | DOI:10.1016/j.xpro.2025.103745

Lancet Infect Dis. 2025 Apr 3:S1473-3099(25)00073-8. doi: 10.1016/S1473-3099(25)00073-8. Online ahead of print.

ABSTRACT

BACKGROUND: The substantial burden of post-COVID-19 condition (also known as long COVID) underscores the need for effective pharmacological interventions. Given that viral persistence has been hypothesised as a potential cause of long COVID, antiviral therapy might offer a promising approach to alleviating long COVID symptoms. We therefore investigated the efficacy, safety, and tolerability of nirmatrelvir-ritonavir for treating long COVID.

METHODS: In this phase 2, decentralised, double-blind, randomised controlled trial, adults (aged ≥18 years) from the 48 states across the contiguous USA, with previous documented SARS-CoV-2 infection and long COVID symptoms starting within 4 weeks of initial infection and persisting for at least 12 weeks, were eligible for inclusion. Key exclusion criteria were use of nirmatrelvir-ritonavir within the previous 2 months, CYP3A4-dependent medications, or strong CYP3A4 inducers; acute medical illness such as SARS-CoV-2 infection within the past 2 weeks; active liver disease; renal impairment; and immunocompromise. Using software for 1:1 stratified block random assignment, participants were randomly allocated to receive either two tablets of nirmatrelvir (150 mg each) and one tablet of ritonavir (100 mg), or placebo and one tablet of ritonavir (100 mg), orally administered twice daily for 15 days, stratified by age, sex at birth, and COVID-19 vaccination status. Participants, clinicians, and the study team were masked to treatment allocation. The primary efficacy endpoint was the change in the Patient-Reported Outcomes Measurement Information System (PROMIS)-29 Physical Health Summary Score (PHSS) from baseline to day 28, analysed by intention to treat. Safety endpoints were reported from baseline to week 6 in all participants who were exposed to the study treatment. This trial is registered with ClinicalTrials.gov (NCT05668091) and is now closed to new participants.

FINDINGS: Between April 14, 2023, and Feb 26, 2024, 119 participants were screened. 100 were enrolled (66 [66%] female participants and 34 [34%] male participants), with 49 assigned to the nirmatrelvir-ritonavir group and 51 to the placebo-ritonavir group (intention-to-treat population). Three participants in the nirmatrelvir-ritonavir group and two in the placebo-ritonavir group withdrew before starting treatment and were excluded from the safety population. The mean PROMIS-29 PHSS at baseline was 39·6 (95% CI 37·4 to 41·9) in the nirmatrelvir-ritonavir group and 36·3 (34·4 to 38·2) in the placebo-ritonavir group. The adjusted change from baseline to day 28 was 0·45 (-0·93 to 1·83) in the nirmatrelvir-ritonavir group and 1·01 (-0·30 to 2·31) in the placebo-ritonavir group (adjusted mean difference -0·55 [95% CI -2·32 to 1·21; p=0·54]). No deaths or serious adverse events were recorded between baseline and week 6. Study drug-related treatment-emergent adverse events were reported in more participants in the nirmatrelvir-ritonavir group (35 [76%] of 46) compared with the placebo-ritonavir group (27 [55%] of 49), mostly driven by dysgeusia. Early treatment termination due to an adverse event occurred in two participants in the nirmatrelvir-ritonavir group and one in the placebo-ritonavir group.

INTERPRETATION: Nirmatrelvir-ritonavir administered for 15 days did not significantly improve health outcomes in participants with long COVID compared with placebo-ritonavir at day 28. However, the study showed the feasibility of large-scale, decentralised trials in long COVID.

FUNDING: Pfizer, Fred Cohen, and Carolyn Klebanoff.

PMID:40188838 | DOI:10.1016/S1473-3099(25)00073-8

Allergol Int. 2025 Apr 4:S1323-8930(25)00026-7. doi: 10.1016/j.alit.2025.03.002. Online ahead of print.

ABSTRACT

The association of human leukocyte antigen (HLA) with the risk of drug-induced skin eruptions has been extensively studied. The sensitivity of the association of specific HLA alleles with drug eruptions ranges from approximately 50 to 100%, indicating a significant influence of HLA alleles on the risk of developing such reactions. Consequently, HLA testing holds substantial clinical potential as a genetic diagnostic tool to avoid drug eruptions. For instance, when prescribing drugs like carbamazepine and lamotrigine, which are known to cause severe drug eruptions, preemptive HLA genetic testing can help predict an individual's risk. This approach enables clinicians to reduce the overall incidence of drug eruptions by selecting alternative therapeutic agents or adjusting dosages based on the results of HLA genetic testing.

PMID:40187963 | DOI:10.1016/j.alit.2025.03.002

J Affect Disord. 2025 Apr 3:S0165-0327(25)00564-6. doi: 10.1016/j.jad.2025.04.012. Online ahead of print.

ABSTRACT

BACKGROUND: Treatment-resistant depression (TRD) affects one-third of major depressive disorder (MDD) patients. Previous pharmacogenetic studies suggest genetic variation may influence medication response but findings are heterogeneous. We conducted a comprehensive genetic investigation using proxy TRD phenotypes (TRDp) that mirror the treatment options of MDD from UK Biobank primary care records.

METHODS: Among 15,125 White British MDD patients, we identified TRDp with medication changes (switching or receiving multiple antidepressants [AD]); augmentation therapy (antipsychotics; mood stabilizers; valproate; lithium); or electroconvulsive therapy (ECT). Hospitalized TRDp patients (HOSP-TRDp) were also identified. We conducted genome-wide association analysis, estimated SNP-heritability (hg2), and assessed the genetic burden for nine psychiatric diseases using polygenic risk scores (PRS).

RESULTS: TRDp patients were more often female, unemployed, less educated, and had higher BMI, with hospitalization rates twice as high as non-TRDp. While no credible risk variants emerged, heritability analysis showed significant genetic influence on TRDp (liability hg2 21-24 %), particularly for HOSP-TRDp (28-31 %). TRDp classified by AD changes and augmentation carried an elevated yet varied polygenic burden for MDD, ADHD, BD, and SCZ. Higher BD PRS increased the likelihood of receiving ECT, lithium, and valproate by 1.27-1.80 fold. Patients in the top 10 % PRS relative to the average had a 12-36 % and 24-51 % higher risk of TRDp and HOSP-TRDp, respectively.

CONCLUSIONS: Our findings support a significant polygenic basis for TRD, highlighting genetic and phenotypic distinctions from non-TRD. We demonstrate that different TRDp endpoints are enriched with various spectra of psychiatric genetic liability, offering insights into pharmacogenomics and TRD's complex genetic architecture.

PMID:40187433 | DOI:10.1016/j.jad.2025.04.012

Cell Rep Med. 2025 Apr 2:102053. doi: 10.1016/j.xcrm.2025.102053. Online ahead of print.

ABSTRACT

Application of machine learning (ML) on cancer-specific pharmacogenomic datasets shows immense promise for identifying predictive response biomarkers to enable personalized treatment. We introduce CAN-Scan, a precision oncology platform, which applies ML on next-generation pharmacogenomic datasets generated from a freeze-viable biobank of patient-derived primary cell lines (PDCs). These PDCs are screened against 84 Food and Drug Administration (FDA)-approved drugs at clinically relevant doses (Cmax), focusing on colorectal cancer (CRC) as a model system. CAN-Scan uncovers prognostic biomarkers and alternative treatment strategies, particularly for patients unresponsive to first-line chemotherapy. Specifically, it identifies gene expression signatures linked to resistance against 5-fluorouracil (5-FU)-based drugs and a focal copy-number gain on chromosome 7q, harboring critical resistance-associated genes. CAN-Scan-derived response signatures accurately predict clinical outcomes across four independent, ethnically diverse CRC cohorts. Notably, drug-specific ML models reveal regorafenib and vemurafenib as alternative treatments for BRAF-expressing, 5-FU-insensitive CRC. Altogether, this approach demonstrates significant potential in improving biomarker discovery and guiding personalized treatments.

PMID:40187357 | DOI:10.1016/j.xcrm.2025.102053

Int Immunopharmacol. 2025 Apr 4;154:114554. doi: 10.1016/j.intimp.2025.114554. Online ahead of print.

ABSTRACT

Metabolic dysfunction-associated steatotic liver disease (MASLD) is an increasingly concerning global health issue characterized by pronounced hepatic steatosis and liver fibrosis. Hepatic monocyte-derived macrophages (MDMs) are crucial in the pathogenesis of liver fibrosis under MASLD. Nevertheless, the precise functions of MDMs and the underlying mechanisms governing their differentiation remain inadequately elucidated. In this study, we revealed an orchestrator of this process: Glycoprotein Non-Metastatic Melanoma Protein B (GPNMB), one of the characteristic genes of MDMs. Notably, myeloid-specific Gpnmb-knockout contributed to the retention of resident Kupffer cells (KCs) and rerouted monocyte differentiation towards a monocyte-derived macrophage subset that occupies the Kupffer cell niche (MoKC subset, resembling resident KCs), thereby impeding the formation of hepatic lipid-associated macrophages (LAMs). This transition has a profound impact, manifested in significantly reduced steatosis and modestly decreased liver fibrosis in myeloid-specific Gpnmb-knockout mice. In conclusion, our research clarifies the complex interactions between Gpnmb and MDMs and underscores the therapeutic potential of targeting Gpnmb within MDMs to manage MASLD.

PMID:40186908 | DOI:10.1016/j.intimp.2025.114554

Arch Bronconeumol. 2025 Mar 18:S0300-2896(25)00082-1. doi: 10.1016/j.arbres.2025.03.003. Online ahead of print.

ABSTRACT

BACKGROUND: In patients with non-cystic fibrosis bronchiectasis (BE) Pseudomonas aeruginosa (PA) has been recently associated with low rather than high number of exacerbations without distinguishing chronic versus intermittent infection. The aim of our study was to determine whether the intermittent or chronic stage of P. aeruginosa (PA) infection is associated with the rate of exacerbations, quality of life and respiratory microbiome biodiversity after a one-year follow-up.

METHODS: We conducted a longitudinal study, with 1-year follow-up, in patients with BE intermittently or chronically infected by PA involving sequential (3-monthly) measurements of microbiological (cultures, PA load, phenotype and biofilms presence) immunological (Serum IgGs against P. aeruginosa were measured by ELISA immunoassay) and clinical variables (Quality-of-Life and the number exacerbations). Additionaly, 16S sequencing was performed on a MiSeq Platform and compared between chronically infected patients with the mucoid PA versus intermittently infected patients with the non-mucoid PA.

RESULTS: We collected 235 sputa and 262 serum samples from 80 BE patients, 61 with chronic and 19 with intermittent PA infection. Chronically compared to intermittently. Presented reduced quality of life but less hospitalized exacerbations after 1-year follow-up. Chronically infected patients presented reduced sputum biodiversity and higher systemic IgGs against P. aeruginosa levels that were associated to decreased number of hospitalized exacerbations.

CONCLUSIONS: The assessment of Chronic versus intermittent P. aeruginosa infection has clinical implications such as quality of life, rate of hospitalized exacerbations and lung microbiome biodiversity. The distinction of these two phenotypes is easy to perform in clinical practice.

TRIAL REGISTRATION: NCT04803695.

PMID:40187923 | DOI:10.1016/j.arbres.2025.03.003

Radiat Oncol. 2025 Apr 5;20(1):50. doi: 10.1186/s13014-025-02622-x.

ABSTRACT

BACKGROUND: Brain metastases are common complications in patients with cancer and significantly affect prognosis and treatment strategies. The accurate segmentation of brain metastases is crucial for effective radiation therapy planning. However, in resource-limited areas, the unavailability of MRI imaging is a significant challenge that necessitates the development of reliable segmentation models for computed tomography images (CT).

PURPOSE: This study aimed to develop and evaluate a Diffusion-CSPAM-U-Net model for the segmentation of brain metastases on CT images and thereby provide a robust tool for radiation oncologists in regions where magnetic resonance imaging (MRI) is not accessible.

METHODS: The proposed Diffusion-CSPAM-U-Net model integrates diffusion models with channel-spatial-positional attention mechanisms to enhance the segmentation performance. The model was trained and validated on a dataset consisting of CT images from two centers (n = 205) and (n = 45). Performance metrics, including the Dice similarity coefficient (DSC), intersection over union (IoU), accuracy, sensitivity, and specificity, were calculated. Additionally, this study compared models proposed for brain metastases of different sizes with those proposed in other studies.

RESULTS: The diffusion-CSPAM-U-Net model achieved promising results on the external validation set. Overall average DSC of 79.3% ± 13.3%, IoU of 69.2% ± 13.3%, accuracy of 95.5% ± 11.8%, sensitivity of 80.3% ± 12.1%, specificity of 93.8% ± 14.0%, and HD of 5.606 ± 0.990 mm were measured. These results demonstrate favorable improvements over existing models.

CONCLUSIONS: The diffusion-CSPAM-U-Net model showed promising results in segmenting brain metastases in CT images, particularly in terms of sensitivity and accuracy. The proposed diffusion-CSPAM-U-Net model provides an effective tool for radiation oncologists for the segmentation of brain metastases in CT images.

PMID:40188354 | DOI:10.1186/s13014-025-02622-x

NPJ Digit Med. 2025 Apr 5;8(1):188. doi: 10.1038/s41746-025-01582-6.

ABSTRACT

Preeclampsia (PE), a severe hypertensive disorder during pregnancy, significantly contributes to maternal and neonatal mortality. Existing prediction biomarkers are often invasive and expensive, hindering their widespread application. This study introduces PROMPT (Preeclampsia Risk factor + Ophthalmic data + Mean arterial pressure Prediction Test), an AI-driven model leveraging retinal photography for PE prediction, registered at ChiCTR (ChiCTR2100049850) in August 2021. Analyzing 1812 pregnancies before 14 gestational weeks, we extracted retinal parameters using a deep learning system. The PROMPT achieved an AUC of 0.87 (0.83-0.90) for PE prediction and 0.91 (0.85-0.97) for preterm PE prediction using machine learning, significantly outperforming the baseline model (p < 0.001). It also improved detection of severe adverse pregnancy outcomes from 35% to 41%. Economically, PROMPT was estimated to avert 1809 PE cases and saved over $50 million per 100,000 screenings. These results position PROMPT as a non-invasive and cost-effective tool for prenatal care, especially valuable in low- and middle-income countries.

PMID:40188283 | DOI:10.1038/s41746-025-01582-6

Sci Rep. 2025 Apr 5;15(1):11712. doi: 10.1038/s41598-025-95291-5.

ABSTRACT

Autism spectrum disorder (ASD) presents significant challenges in diagnosis and intervention due to its diverse clinical manifestations and underlying biological complexity. This study explored machine learning approaches to enhance ASD screening accuracy and identify meaningful subtypes using clinical assessments from AGRE database integrated with molecular data from GSE15402. Analysis of ADI-R scores from a large cohort of 2794 individuals demonstrated that deep learning models could achieve exceptional screening accuracy of 95.23% (CI 94.32-95.99%). Notably, comparable performance was maintained using a streamlined set of just 27 ADI-R sub-items, suggesting potential for more efficient diagnostic tools. Clustering analyses revealed three distinct subgroups identifiable through both clinical symptoms and gene expression patterns. When ASD were grouped based on clinical features, stronger associations emerged between symptoms and underlying molecular profiles compared to grouping based on gene expression alone. These findings suggest that starting with detailed clinical observations may be more effective for identifying biologically meaningful ASD subtypes than beginning with molecular data. This integrated approach combining clinical and molecular data through machine learning offers promising directions for developing more precise screening methods and personalized intervention strategies for individuals with ASD.

PMID:40188264 | DOI:10.1038/s41598-025-95291-5

Sci Rep. 2025 Apr 5;15(1):11687. doi: 10.1038/s41598-025-96575-6.

ABSTRACT

Parkinson's disease (PD) is a neurodegenerative disorder affecting motor control, leading to symptoms such as tremors and stiffness. Early diagnosis is essential for effective treatment, but traditional methods are often time-consuming and expensive. This study leverages Artificial Intelligence (AI) and Machine Learning (ML) techniques, using voice analysis to detect early signs of PD. We applied a hybrid model combining Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Multiple Kernel Learning (MKL), and Multilayer Perceptron (MLP) to a dataset of 81 voice recordings. Acoustic features such as Mel-Frequency Cepstral Coefficients (MFCCs), jitter, and shimmer were analyzed. The model achieved 91.11% accuracy, 92.50% recall, 89.84% precision, 91.13% F1 score, and an area-under-the-curve (AUC) of 0.9125. SHapley Additive exPlanations (SHAP) provided data explainability, identifying key features driving the PD diagnosis, thus enhancing AI interpretability and trustability. Furthermore, a probability-based scoring system was developed to enable PD patients and clinicians to track disease progression. This AI-driven approach offers a non-invasive, cost-effective, and rapid tool for early PD detection, facilitating personalized treatment through vocal biomarkers.

PMID:40188263 | DOI:10.1038/s41598-025-96575-6

Abdom Radiol (NY). 2025 Apr 5. doi: 10.1007/s00261-025-04934-8. Online ahead of print.

ABSTRACT

PURPOSE: To develop deep learning models for automated detection and segmentation of uterine fibroids using multi-orientation MRI.

METHODS: Pre-treatment sagittal and axial T2-weighted MRI scans acquired from patients diagnosed with uterine fibroids were collected. The proposed segmentation models were constructed based on the three-dimensional nnU-Net framework. Fibroid detection efficacy was assessed, with subgroup analyses by size and location. The segmentation performance was evaluated using Dice similarity coefficients (DSCs), 95% Hausdorff distance (HD95), and average surface distance (ASD).

RESULTS: The internal dataset comprised 299 patients who were divided into the training set (n = 239) and the internal test set (n = 60). The external dataset comprised 45 patients. The sagittal T2WI model and the axial T2WI model demonstrated recalls of 74.4%/76.4% and precision of 98.9%/97.9% for fibroid detection in the internal test set. The models achieved recalls of 93.7%/95.3% for fibroids ≥ 4 cm. The recalls for International Federation of Gynecology and Obstetrics (FIGO) type 2-5, FIGO types 0\1\2(submucous), fibroids FIGO types 5\6\7(subserous) were 100%/100%, 73.3%/78.6%, and 80.3%/81.9%, respectively. The proposed models demonstrated good performance in segmentation of the uterine fibroids with mean DSCs of 0.789 and 0.804, HD95s of 9.996 and 10.855 mm, and ASDs of 2.035 and 2.115 mm in the internal test set, and with mean DSCs of 0.834 and 0.818, HD95s of 9.971 and 11.874 mm, and ASDs of 2.031 and 2.273 mm in the external test set.

CONCLUSION: The proposed deep learning models showed promise as reliable methods for automating the detection and segmentation of the uterine fibroids, particularly those of clinical relevance.

PMID:40188260 | DOI:10.1007/s00261-025-04934-8

Nat Commun. 2025 Apr 6;16(1):3274. doi: 10.1038/s41467-025-58521-y.

ABSTRACT

The UniProt database is a valuable resource for biocatalyst discovery, yet predicting enzymatic functions remains challenging, especially for low-similarity sequences. Identifying superior enzymes with enhanced catalytic properties is even harder. To overcome these challenges, we develop ESM-Ezy, an enzyme mining strategy leveraging the ESM-1b protein language model and similarity calculations in semantic space. Using ESM-Ezy, we identify novel multicopper oxidases (MCOs) with superior catalytic properties, achieving a 44% success rate in outperforming query enzymes (QEs) in at least one property, including catalytic efficiency, heat and organic solvent tolerance, and pH stability. Notably, 51% of the MCOs excel in environmental remediation applications, and some exhibited unique structural motifs and unique active centers enhancing their functions. Beyond MCOs, 40% of L-asparaginases identified show higher specific activity and catalytic efficiency than QEs. ESM-Ezy thus provides a promising approach for discovering high-performance biocatalysts with low sequence similarity, accelerating enzyme discovery for industrial applications.

PMID:40188191 | DOI:10.1038/s41467-025-58521-y

J Transl Med. 2025 Apr 5;23(1):405. doi: 10.1186/s12967-025-06414-5.

ABSTRACT

BACKGROUND: Identification of seizures is essential for the treatment of epilepsy. Current machine-learning and deep-learning models often perform well on public datasets when classifying generalized seizures with prominent features. However, their performance was less effective in detecting brief, localized seizures. These seizure-like patterns can be masked by fixed brain rhythms.

METHODS: Our study proposes a supervised multilayer hybrid model called GEM-CRAP (gradient-enhanced modulation with CNN-RES, attention-like, and pre-policy networks), with three parallel feature extraction channels: a CNN-RES module, an amplitude-aware channel with attention-like mechanisms, and an LSTM-based pre-policy layer integrated into the recurrent neural network. The model was trained on the Xuanwu Hospital and HUP iEEG dataset, including intracranial, cortical, and stereotactic EEG data from 83 patients, covering over 8500 labeled electrode channels for hybrid classification (wakefulness and sleep). A post-SVM network was used for secondary training on channels with classification accuracy below 80%. We introduced an average channel deviation rate metric to assess seizure detection accuracy.

RESULTS: For public datasets, the model achieved over 97% accuracy for intracranial and cortical EEG sequences in patients, and over 95% for mixed sequences, with deviations below 5%. In the Xuanwu Hospital dataset, it maintained over 94% accuracy for wakefulness seizures and around 90% during sleep. SVM secondary training improved average channel accuracy by over 10%. Additionally, a strong positive correlation was found between channel accuracy distribution and the temporal distribution of seizure states.

CONCLUSIONS: GEM-CRAP enhances focal epilepsy detection through adaptive adjustments and attention mechanisms, achieving higher precision and robustness in complex signal environments. Beyond improving seizure interval detection, it excels in identifying and analyzing specific epileptic waveforms, such as high-frequency oscillations. This advancement may pave the way for more precise epilepsy diagnostics and provide a suitable artificial intelligence algorithm for closed-loop neurostimulation.

PMID:40188070 | DOI:10.1186/s12967-025-06414-5

Chin J Traumatol. 2025 Mar 15:S1008-1275(25)00029-X. doi: 10.1016/j.cjtee.2024.10.006. Online ahead of print.

ABSTRACT

PURPOSE: Distal radius fracture is a common trauma fracture and timely preoperative diagnosis is crucial for the patient's recovery. With the rise of deep-learning applications in the medical field, utilizing deep-learning for diagnosing distal radius fractures has become a significant topic. However, previous research has suffered from low detection accuracy and poor identification of occult fractures. This study aims to design an improved deep-learning model to assist surgeons in diagnosing distal radius fractures more quickly and accurately.

METHODS: This study, inspired by the comprehensive analysis of anteroposterior and lateral X-ray images by surgeons in diagnosing distal radius fractures, designs a dual-channel feature fusion network for detecting distal radius fractures. Based on the Faster region-based convolutional neural network framework, an additional Residual Network 50, which is integrated with the Deformable and Separable Attention mechanism, was introduced to extract semantic information from lateral X-ray images of the distal radius. The features extracted from the 2 channels were then combined via feature fusion, thus enriching the network's feature information. The focal loss function was also employed to address the sample imbalance problem during the training process.The selection of cases in this study was based on distal radius X-ray images retrieved from the hospital's imaging database, which met the following criteria: inclusion criteria comprised clear anteroposterior and lateral X-ray images, which were diagnosed as distal radius fractures by experienced radiologists. The exclusion criteria encompassed poor image quality, the presence of severe multiple or complex fractures, as well as non-adult or special populations (e.g., pregnant women). All cases meeting the inclusion criteria were labeled as distal radius fracture cases for model training and evaluation. To assess the model's performance, this study employed several metrics, including accuracy, precision, recall, area under the precision-recall curve, and intersection over union.

RESULTS: The proposed dual-channel feature fusion network achieved an average precision (AP)50 of 98.5%, an AP75 of 78.4%, an accuracy of 96.5%, and a recall of 94.7%. When compared to traditional models, such as Faster region-based convolutional neural network, which achieved an AP50 of 94.1%, an AP75 of 70.6%, a precision of 91.1%, and a recall of 92.3%, our method shows notable improvements in all key metrics. Similarly, when compared to other classic object detection networks like You Only Look Once version 4 (AP50=95.2%, AP75=72.2 %, precision=91.2%, recall=92.4%) and You Only Look Once version 5s (AP50=95.1%, AP75=73.8%, precision=93.7%, recall=92.8%), the dual-channel feature fusion network outperforms them in precision, recall, and AP scores. These results highlight the superior accuracy and reliability of the proposed method, particularly in identifying both apparent and occult distal radius fractures, demonstrating its effectiveness in clinical applications where precise detection of subtle fractures is critical.

CONCLUSION: This study found that combining anteroposterior and lateral X-ray images of the distal radius as input for deep-learning algorithms can more accurately and efficiently identify distal radius fractures, providing a reference for research on distal radius fractures.

PMID:40187904 | DOI:10.1016/j.cjtee.2024.10.006

Anal Chim Acta. 2025 May 15;1351:343920. doi: 10.1016/j.aca.2025.343920. Epub 2025 Mar 8.

ABSTRACT

BACKGROUND: Pharmaceutical residual such as antibiotics and disinfectants in aquaculture wastewater have significant potential risks for environment and human health. Surface enhanced Raman spectroscopy (SERS) has been widely used for the detection of pharmaceuticals due to its high sensitivity, low cost, and rapidity. However, it is remain a challenge for high-sensitivity SERS detection and accurate identification of complex pollutants.

RESULTS: Hence, in this work, we developed an aluminum foil (AlF) based SERS detection substrate and established a multilayer perceptron (MLP) deep learning model for the rapid identification of antibiotic components in a mixture. The detection method demonstrated exceptional performance, achieving a high SERS enhancement factor of 4.2 × 105 and excellent sensitivity for trace amounts of fleroxacin (2.7 × 10-8 mol/L), levofloxacin (1.95 × 10-8 mol/L), and pefloxacin (6.9 × 10-8 mol/L),sulfadiazine, methylene blue, and malachite green at a concentration of 1 × 10-8 mol/L can all be detected, the concentrations of the six target compounds and their Raman intensities exhibit a good linear relationship. Moreover, the AlF SERS substrate can be prepared rapidly without adding organic reagents, and it exhibited good reproducibility, with RSD<9.6 %. Additionally, the algorithm model can accurately identify the contaminants mixture of sulfadiazine, methylene blue, and malachite green with a recognition accuracy of 97.8 %, an F1-score of 98.2 %, and a 5-fold cross validation score of 97.4 %, the interpretation analysis using Shapley Additive Explanations (SHAP) reveals that MLP model can specifically concentrate on the distribution of characteristic peaks.

SIGNIFICANCE: The experimental results indicated that the MLP model demonstrated strong performance and good robustness in complex matrices. This research provides a promising detection and identification method for the antibiotics and disinfectants in actual aquaculture wastewater treatment.

PMID:40187885 | DOI:10.1016/j.aca.2025.343920

Anal Chim Acta. 2025 May 15;1351:343900. doi: 10.1016/j.aca.2025.343900. Epub 2025 Mar 5.

ABSTRACT

Osteoarthritis (OA) is a major cause of disability worldwide, with symptoms like joint pain, limited functionality, and decreased quality of life, potentially leading to deformity and irreversible damage. Chemical changes in joint tissues precede imaging alterations, making early diagnosis challenging for conventional methods like X-rays. Although Raman imaging provides detailed chemical information, it is time-consuming. This paper aims to achieve rapid osteoarthritis diagnosis and grading using a self-developed Raman imaging system combined with deep learning denoising and acceleration algorithms. Our self-developed aberration-corrected line-scanning confocal Raman imaging device acquires a line of Raman spectra (hundreds of points) per scan using a galvanometer or displacement stage, achieving spatial and spectral resolutions of 2 μm and 0.2 nm, respectively. Deep learning algorithms enhance the imaging speed by over 4 times through effective spectrum denoising and signal-to-noise ratio (SNR) improvement. By leveraging the denoising capabilities of deep learning, we are able to acquire high-quality Raman spectral data with a reduced integration time, thereby accelerating the imaging process. Experiments on the tibial plateau of osteoarthritis patients compared three excitation wavelengths (532, 671, and 785 nm), with 671 nm chosen for optimal SNR and minimal fluorescence. Machine learning algorithms achieved a 98 % accuracy in distinguishing articular from calcified cartilage and a 97 % accuracy in differentiating osteoarthritis grades I to IV. Our fast Raman imaging system, combining an aberration-corrected line-scanning confocal Raman imager with deep learning denoising, offers improved imaging speed and enhanced spectral and spatial resolutions. It enables rapid, label-free detection of osteoarthritis severity and can identify early compositional changes before clinical imaging, allowing precise grading and tailored treatment, thus advancing orthopedic diagnostics and improving patient outcomes.

PMID:40187878 | DOI:10.1016/j.aca.2025.343900