Aging Clin Exp Res. 2025 Mar 22;37(1):101. doi: 10.1007/s40520-025-03009-4.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is more likely to occur in the elderly population, and these patients often become depressed. It has been recognized that psychological disorders are not conducive to the control of many diseases. Thus, this study aims to determine whether alleviating depression can delay the progression of IPF and frailty in elderly patients with IPF.

METHODS: IPF patients over 60 years old were included in the study. None had a prior history of psychological disorders. All developed depression after being diagnosed with IPF. During the 12-month follow-up, some patients received anti-depression interventions and the rest didn't. Depression, IPF, frailty and peripheral inflammation at baseline and after follow-up were evaluated by indicators and scales such as BDI-II, FVC %pred, 6MWT, mMRC, CFS, TFI, SGRQ, K-BILD, IL-6, and TNF-α. Multivariate logistic regression was employed for data analysis.

RESULTS: There were 213 elderly patients with IPF. Among the 89 patients who received anti-depression interventions, the above-mentioned indicators and scales did not deteriorate during the follow-up period (P > 0.05). Among the remaining 124 patients, the FVC %pred, and 6MWT levels decreased, and the mMRC grade, CFS, TFI, SGRQ and K-BILD scores, and peripheral IL-6 and TNF-α levels increased during the follow-up period (P < 0.05).

DISCUSSION: Compared with non-intervened IPF patients, those receiving anti-depression interventions seemed to maintain a certain stability in IPF, frailty, and peripheral inflammation over a period.

CONCLUSION: Improving depression may help delay the deterioration of patients' IPF and frailty at certain stages.

TRIAL REGISTRATION: Registration on UMIN-CTR.

REGISTRATION NUMBER: UMIN000057161. Date of registration: February 27th, 2025.

PMID:40120048 | DOI:10.1007/s40520-025-03009-4

Fam Cancer. 2025 Mar 22;24(2):31. doi: 10.1007/s10689-025-00455-x.

ABSTRACT

Telomere biology disorders (TBDs) are a group of genetic conditions characterized by defects in telomere maintenance leading to multisystemic organ involvement and a predisposition to hematologic malignancies. The management of patients with TBDs who develop acute myeloid leukemia (AML) presents a significant challenge due to their limited bone marrow reserve and non-hematopoietic organ dysfunction. We present the case of a 45-year-old patient with a previously unrecognized TBD who presented with AML. The patient's history of longstanding cytopenias, idiopathic avascular necrosis, and pulmonary fibrosis were suggestive of a TBD, which was confirmed through telomere length testing and the presence of a TERT variant. Due to his underlying TBD, he was treated with dose-reduced azacitidine and venetoclax, adapting the approach commonly employed in elderly, co-morbid AML patients ineligible for intensive chemotherapy. This resulted in a complete remission with incomplete count recovery that has persisted for greater than 12 months to date. Aside from prolonged myelosuppression, the patient tolerated the regimen well with minimal toxicity. To our knowledge, this is the first report of the successful utilization of azacitidine and venetoclax as an AML treatment modality in TBD patients and underscores the potential of this regimen as an effective non-intensive treatment strategy for high grade myeloid neoplasms arising in the context of inherited bone marrow failure syndromes.

PMID:40119960 | DOI:10.1007/s10689-025-00455-x

Methods Enzymol. 2025;712:197-223. doi: 10.1016/bs.mie.2025.01.033. Epub 2025 Mar 6.

ABSTRACT

Group II introns are transposable elements that can propagate in host genomes through the "copy and paste" mechanism. They usually comprise RNA and protein components for effective propagation. Recently, we found that some bacterial GII-C introns without protein components had multiple copies in their resident genomes, implicating their potential transposition activity. We demonstrated that some of these systems are active for hydrolytic DNA cleavage and proved their DNA manipulation capability in bacterial or mammalian cells. These introns are therefore named HYdrolytic Endonucleolytic Ribozymes (HYERs). Here, we provide a detailed protocol for the systematic identification and characterization of HYERs and present our perspectives on its potential application in nucleic acid manipulation.

PMID:40121073 | DOI:10.1016/bs.mie.2025.01.033

Neurobiol Dis. 2025 Mar 20:106878. doi: 10.1016/j.nbd.2025.106878. Online ahead of print.

ABSTRACT

BACKGROUND: Fatigue is a debilitating symptom in Parkinson's disease (PD), significantly affecting quality of life. Despite its prevalence, the underlying neurophysiological mechanisms remain poorly understood. Recent evidence suggests that deficits in cortical motor preparation processes may contribute to PD-related fatigue.

METHODS: This study investigated premovement facilitation (PMF), a marker of corticospinal excitability during motor preparation, in 20 healthy subjects (HS) and 28 PD patients, subdivided into those with fatigue (PDwF, n = 14) and without fatigue (PDwoF, n = 14). Participants performed a reaction time (RT) task involving thumb abduction following a visual go signal, while transcranial magnetic stimulation (TMS) was applied over the primary motor cortex (M1) at intervals of 50, 100, and 150 ms before movement onset. Motor-evoked potentials (MEPs) were recorded from the abductor pollicis brevis (APB) and the task-irrelevant abductor digiti minimi (ADM).

RESULTS: In HS and PDwoF, MEP APB amplitude increased progressively when TMS was applied at 150, 100, and 50 ms before movement onset, reflecting intact PMF, with the greater MEP APB amplitude at the shorter interval (50 ms). However, in PDwF patients, PMF was absent on the most affected side, while it remained preserved on the less affected side. Furthermore, the absence of PMF correlated with fatigue severity (FSS scores) and rigidity subscores, highlighting a link between impaired motor preparation and clinical symptoms.

CONCLUSION: These findings suggest that cortical dysfunction in motor preparation contributes to PD-related fatigue, particularly in the most affected hemisphere. The observed PMF deficits provide a potential neurophysiological marker for fatigue in PD, supporting future investigations into targeted therapeutic interventions to restore motor excitability and alleviate fatigue symptoms.

PMID:40120830 | DOI:10.1016/j.nbd.2025.106878

J Agric Food Chem. 2025 Mar 22. doi: 10.1021/acs.jafc.4c13199. Online ahead of print.

ABSTRACT

Acetic acid is a key metabolite in yeast fermentation, influencing wine quality through its role in volatile acidity. In Saccharomyces cerevisiae, acetic acid production involves aldehyde dehydrogenases, primarily Ald6p during fermentation and Ald4p under respiratory conditions. However, the regulatory mechanisms of these enzymes throughout fermentation and how they differ in commonly used strains remain partially unclear. This study explores cytosolic peroxiredoxin Tsa1p as a novel regulator of acetic acid metabolism. TSA1 gene deletion revealed strain-dependent effects on acetic acid metabolism and tolerance, showing reduced production and enhanced consumption in the laboratory media. Under respiration, Ald4p-driven acetic acid production, which raises extracellular pH, was mitigated by the absence of Tsa1p. During wine fermentation, TSA1 deletion decreased the initial acetic acid surge by downregulating the ALD6 transcription and enzymatic activity. These findings establish Tsa1p as a metabolic regulator and a potential target for modulating acetic acid levels to manage volatile acidity and improve wine quality.

PMID:40120136 | DOI:10.1021/acs.jafc.4c13199

Bioinformatics. 2025 Mar 22:btaf123. doi: 10.1093/bioinformatics/btaf123. Online ahead of print.

ABSTRACT

MOTIVATION: In systems biology, modelling strategies aim to decode how molecular components interact to generate dynamical behaviour. Boolean modelling is more and more used, but the description of the dynamics generated by discrete variables with only two values may be too limited to capture certain dynamical properties. Multivalued logical models can overcome this limitation by allowing more than two levels for each component. However, multivaluing a Boolean model is challenging.

RESULTS: We present MRBM, a method for efficiently identifying the components of a Boolean model to be multivalued in order to capture specific fixed-point reachabilities in the asynchronous dynamics. To this goal, we defined a new updating scheme locating reachability properties in the most permissive dynamics. MRBM is supported by mathematical demonstrations and illustrated on a toy model and on two models of stem cell differentiation.

AVAILABILITY AND IMPLEMENTATION: The MRBM method and the BMs used in this manuscript are available on GitHub at: https://github.com/NdnBnBn/MRBM, and archived in Zenodo (doi: 10.5281/ZENODO.14979798).

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40119940 | DOI:10.1093/bioinformatics/btaf123

BMC Bioinformatics. 2025 Mar 21;26(1):86. doi: 10.1186/s12859-025-06102-7.

ABSTRACT

BACKGROUND: The Anatomical Therapeutic Chemical (ATC) classification system, proposed and maintained by the World Health Organization, is among the most widely used drug classification schemes. Recently, it has become a key research focus in drug repositioning. Computational models often pair drugs with ATC codes to explore drug-ATC code associations. However, the limited information available for ATC codes constrains these models, leaving significant room for improvement.

RESULTS: This study presents an inference method to identify highly related target proteins, structural features, and side effects for each ATC code, constructing comprehensive biological profiles. Association networks for target proteins, structural features, and side effects are established, and a random walk with restart algorithm is applied to these networks to extract raw associations. A permutation test is then conducted to exclude false positives, yielding robust biological profiles for ATC codes. These profiles are used to construct new ATC code kernels, which are integrated with ATC code kernels from the existing model PDATC-NCPMKL. The recommendation matrix is subsequently generated using the procedures of PDATC-NCPMKL. Cross-validation results demonstrate that the new model achieves AUROC and AUPR values exceeding 0.96.

CONCLUSION: The proposed model outperforms PDATC-NCPMKL and other previous models. Analysis of the contributions of the newly added ATC code kernels confirms the value of biological profiles in enhancing the prediction of drug-ATC code associations.

PMID:40119265 | DOI:10.1186/s12859-025-06102-7

Sci Rep. 2025 Mar 21;15(1):9827. doi: 10.1038/s41598-025-93509-0.

ABSTRACT

Observational studies enable causal inferences when randomized controlled trials (RCTs) are not feasible. However, integrating sensitive medical data across multiple institutions introduces significant privacy challenges. The data collaboration quasi-experiment (DC-QE) framework addresses these concerns by sharing "intermediate representations"-dimensionality-reduced data derived from raw data-instead of the raw data. Although DC-QE can estimate treatment effects, its application to medical data remains unexplored. The aim of this study was to apply the DC-QE framework to medical data from a single institution to simulate distributed data environments under independent and identically distributed (IID) and non-IID conditions. We propose a method for generating intermediate representations within the DC-QE framework. Experimental results show that DC-QE consistently outperformed individual analyses across various accuracy metrics, closely approximating the performance of centralized analysis. The proposed method further improved performance, particularly under non-IID conditions. These outcomes highlight the potential of the DC-QE framework as a robust approach for privacy-preserving causal inferences in healthcare. Broader adoption of this framework and increased use of intermediate representations could grant researchers access to larger, more diverse datasets while safeguarding patient confidentiality. This approach may ultimately aid in identifying previously unrecognized causal relationships, support drug repurposing efforts, and enhance therapeutic interventions for rare diseases.

PMID:40118898 | DOI:10.1038/s41598-025-93509-0

Pediatr Blood Cancer. 2025 Mar 22:e31668. doi: 10.1002/pbc.31668. Online ahead of print.

ABSTRACT

BACKGROUND: L-asparaginase is essential in treating pediatric acute lymphoblastic leukemia (ALL) but is limited by hypersensitivity reactions in up to 70% of patients, leading to severe, dose-limiting complications and compromised event-free survival.

PROCEDURE: This study conducted a genome-wide association study (GWAS) in a discovery cohort of 221 pediatric cancer patients who experienced l-asparaginase-induced hypersensitivity reactions (≥CTCAE grade 2) and 705 controls without hypersensitivity despite equivalent exposure. Results were replicated in an independent cohort of 41 cases and 139 controls.

RESULTS: Significant associations were identified between hypersensitivity and four genes crucial for amino acid stress response: CYP1B1 (rs59569490; odds ratio [OR] = 8.5; 95% confidence interval [CI], 3.9-18.5; p = 1.5 × 10-10), SEC16B (rs115461320; OR = 4.2; 95% CI, 2.5-7.9; p = 1.2 × 10-6), OPLAH (rs11993268; OR = 4.8; 95% CI, 2.4-9.9; p = 2.0 × 10-6), and SORCS2 (rs11940340; OR = 6.7; 95% CI, 2.8-15.7; p = 5.7 × 10-7). Variants in SEC16B, OPLAH, and SORCS2 remained significant in the analysis of the replication cohort (p < 0.05). Patients who carried risk alleles in two or more of these genes experienced an 86.4% increased incidence of hypersensitivity reactions in the discovery cohort (OR = 25.2; 95% CI, 7.4-86.2; p = 1.0 × 10-10), which was replicated in the independent cohort with a 100% incidence in carriers (p = 0.04).

CONCLUSIONS: The cumulative incidence of these large effect variants highlights their significance for the identification of patients at high risk of l-asparaginase-induced hypersensitivity. Successfully identifying patients at increased risk of hypersensitivity reactions can inform personalized treatment strategies and limit these harmful dose-limiting reactions in pediatric ALL.

PMID:40119746 | DOI:10.1002/pbc.31668

Bioanalysis. 2025 Mar 21:1-13. doi: 10.1080/17576180.2025.2481019. Online ahead of print.

ABSTRACT

Pharmacogenomics (PGx) is transforming therapeutic development by providing insights into how genetic variations influence drug response, safety, and efficacy. This review provides a structured analysis of PGx in clinical research, beginning with an overview of key genes involved in drug metabolism, transport, and targets. Following this, it examines strategies for identifying PGx-relevant genes, including phenotype-driven, hypothesis-driven, population-focused, and clinical-driven approaches. Technical platforms such as PCR, MassARRAY, and next-generation sequencing are analyzed for their suitability in PGx studies. The discussion then shifts to assay validation processes, covering both analytical and clinical validation, to ensure data reliability in clinical trials. Finally, regulatory expectations for PGx in clinical trials are discussed, focusing on key requirements across all phases of drug development. This review aims to provide a clear and practical framework for integrating PGx into clinical research to enhance drug safety, efficacy, and personalized medicine.

PMID:40118816 | DOI:10.1080/17576180.2025.2481019

BJS Open. 2025 Mar 4;9(2):zraf013. doi: 10.1093/bjsopen/zraf013.

ABSTRACT

BACKGROUND: A real-time deep learning system was developed to identify the extrahepatic bile ducts during indocyanine green fluorescence-guided laparoscopic cholecystectomy.

METHODS: Two expert surgeons annotated surgical videos from 113 patients and six class structures. YOLOv7, a real-time object detection model that enhances speed and accuracy in identifying and localizing objects within images, was trained for structures identification. To evaluate the model's performance, single-frame and short video clip validations were used. The primary outcomes were average precision and mean average precision in single-frame validation. Secondary outcomes were accuracy and other metrics in short video clip validations. An intraoperative prototype was developed for the verification experiments.

RESULTS: A total of 3993 images were extracted to train the YOLOv7 model. In single-frame validation, all classes' mean average precision was 0.846, and average precision for the common bile duct and cystic duct was 0.864 and 0.698 respectively. The model was trained to detect six different classes of objects and exhibited the best overall performance, with an accuracy of 94.39% for the common bile duct and 84.97% for the cystic duct in video clip validation.

CONCLUSION: This model could potentially assist surgeons in identifying the critical landmarks during laparoscopic cholecystectomy, thereby minimizing the risk of bile duct injuries.

PMID:40119711 | DOI:10.1093/bjsopen/zraf013

IET Syst Biol. 2025 Jan-Dec;19(1):e70010. doi: 10.1049/syb2.70010.

ABSTRACT

Cancer is a serious and complex disease caused by uncontrolled cell growth and is becoming one of the leading causes of death worldwide. Anticancer peptides (ACPs), as a bioactive peptide with lower toxicity, emerge as a promising means of effectively treating cancer. Identifying ACPs is challenging due to the limitation of experimental conditions. To address this, we proposed a dual-channel-based deep learning method, termed ACP-DPE, for ACP prediction. The ACP-DPE consisted of two parallel channels: one was an embedding layer followed by the bi-directional gated recurrent unit (Bi-GRU) module, and the other was an adaptive embedding layer followed by the dilated convolution module. The Bi-GRU module captured the peptide sequence dependencies, whereas the dilated convolution module characterised the local relationship of amino acids. Experimental results show that ACP-DPE achieves an accuracy of 82.81% and a sensitivity of 86.63%, surpassing the state-of-the-art method by 3.86% and 5.1%, respectively. These findings demonstrate the effectiveness of ACP-DPE for ACP prediction and highlight its potential as a valuable tool in cancer treatment research.

PMID:40119615 | DOI:10.1049/syb2.70010

Pest Manag Sci. 2025 Mar 22. doi: 10.1002/ps.8790. Online ahead of print.

ABSTRACT

BACKGROUND: Rice diseases that are not detected in a timely manner may trigger large-scale yield reduction and bring significant economic losses to farmers.

AIMS: In order to solve the problems of insufficient rice disease detection accuracy and a model that is lightweight, this study proposes a lightweight rice disease detection method based on the improved YOLOv8. The method incorporates a full-dimensional dynamic convolution (ODConv) module to enhance the feature extraction capability and improve the robustness of the model, while a dynamic non-monotonic focusing mechanism, WIoU (weighted interpolation of sequential evidence for intersection over union), is employed to optimize the bounding box loss function for faster convergence and improved detection performance. In addition, the use of a high-resolution detector head improves the small target detection capability and reduces the network parameters by removing redundant layers.

RESULTS: Experimental results show a 66.6% reduction in parameters and a 61.9% reduction in model size compared to the YOLOv8n baseline. The model outperforms Faster R-CNN, YOLOv5s, YOLOv6n, YOLOv7-tiny, and YOLOv8n by 29.2%, 3.8%, 5.2%, 5.7%, and 5.2%, respectively, in terms of the mean average precision (mAP), which shows a significant improvement in the detection performance.

CONCLUSION: The YOLOv8-OW model provides a more effective solution, which is suitable for deployment on resource-limited mobile devices, to provide real-time and accurate disease detection support for farmers and further promotes the development of precision agriculture. © 2025 Society of Chemical Industry.

PMID:40119571 | DOI:10.1002/ps.8790

Genome Biol. 2025 Mar 21;26(1):64. doi: 10.1186/s13059-025-03519-4.

ABSTRACT

Discovering a lower-dimensional embedding of single-cell data can improve downstream analysis. The embedding should encapsulate both the high-level features and low-level variations. While existing generative models attempt to learn such low-dimensional representations, they have limitations. Here, we introduce scVAEDer, a scalable deep-learning model that combines the power of variational autoencoders and deep diffusion models to learn a meaningful representation that retains both global structure and local variations. Using the learned embeddings, scVAEDer can generate novel scRNA-seq data, predict perturbation response on various cell types, identify changes in gene expression during dedifferentiation, and detect master regulators in biological processes.

PMID:40119479 | DOI:10.1186/s13059-025-03519-4

J Cheminform. 2025 Mar 21;17(1):35. doi: 10.1186/s13321-025-00979-5.

ABSTRACT

Protein-protein interactions (PPIs) are central to the mechanisms of signaling pathways and immune responses, which can help us understand disease etiology. Therefore, there is a significant need for efficient and rapid automated approaches to predict changes in PPIs. In recent years, there has been a significant increase in applying deep learning techniques to predict changes in binding affinity between the original protein complex and its mutant variants. Particularly, the adoption of graph neural networks (GNNs) has gained prominence for their ability to learn representations of protein-protein complexes. However, the conventional GNNs have mainly concentrated on capturing local features, often disregarding the interactions among distant elements that hold potential important information. In this study, we have developed a transformer-based graph neural network to extract features of the mutant segment from the three-dimensional structure of protein-protein complexes. By embracing both local and global features, the approach ensures a more comprehensive understanding of the intricate relationships, thus promising more accurate predictions of binding affinity changes. To enhance the representation capability of protein features, we incorporate a large-scale pre-trained protein language model into our approach and employ the global protein feature it provides. The proposed model is shown to be able to predict the mutation changes in binding affinity with a root mean square error of 1.10 and a Pearson correlation coefficient of near 0.71, as demonstrated by performance on test and validation cases. Our experiments on all five datasets, including both single mutant and multiple mutant cases, demonstrate that our model outperforms four state-of-the-art baseline methods, and the efficacy was subjected to comprehensive experimental evaluation. Our study introduces a transformer-based graph neural network approach to accurately predict changes in protein-protein interactions (PPIs). By integrating local and global features and leveraging pretrained protein language models, our model outperforms state-of-the-art methods across diverse datasets. The results of this study can provide new views for studying immune responses and disease etiology related to protein mutations. Furthermore, this approach may contribute to other biological or biochemical studies related to PPIs.Scientific contribution Our scientific contribution lies in the development of a novel transformer-based graph neural network tailored to predict changes in protein-protein interactions (PPIs) with excellent accuracy. By seamlessly integrating both local and global features extracted from the three-dimensional structure of protein-protein complexes, and leveraging the rich representations provided by pretrained protein language models, our approach surpasses existing methods across diverse datasets. Our findings may offer novel insights for the understanding of complex disease etiology associated with protein mutations. The novel tool can be applicable to various biological and biochemical investigations involving protein mutations.

PMID:40119464 | DOI:10.1186/s13321-025-00979-5

Cancer Cell Int. 2025 Mar 21;25(1):111. doi: 10.1186/s12935-025-03756-4.

ABSTRACT

Nowadays, gastric cancer has become a significant issue in the global cancer burden, and its impact cannot be ignored. The rapid development of artificial intelligence technology is attempting to address this situation, aiming to change the clinical management landscape of gastric cancer fundamentally. In this transformative change, machine learning and deep learning, as two core technologies, play a pivotal role, bringing unprecedented innovations and breakthroughs in the diagnosis, treatment, and prognosis evaluation of gastric cancer. This article comprehensively reviews the latest research status and application of artificial intelligence algorithms in gastric cancer, covering multiple dimensions such as image recognition, pathological analysis, personalized treatment, and prognosis risk assessment. These applications not only significantly improve the sensitivity of gastric cancer risk monitoring, the accuracy of diagnosis, and the precision of survival prognosis but also provide robust data support and a scientific basis for clinical decision-making. The integration of artificial intelligence, from optimizing the diagnosis process and enhancing diagnostic efficiency to promoting the practice of precision medicine, demonstrates its promising prospects for reshaping the treatment model of gastric cancer. Although most of the current AI-based models have not been widely used in clinical practice, with the continuous deepening and expansion of precision medicine, we have reason to believe that a new era of AI-driven gastric cancer care is approaching.

PMID:40119433 | DOI:10.1186/s12935-025-03756-4

BMC Med Imaging. 2025 Mar 21;25(1):95. doi: 10.1186/s12880-025-01636-x.

ABSTRACT

PURPOSE: To develop an automatic segmentation model for surgical marks, titanium clips, in target volume delineation of breast cancer radiotherapy after lumpectomy.

METHODS: A two-stage deep-learning model is used to segment the titanium clips from CT image. The first network, Location Net, is designed to search the region containing all clips from CT. Then the second network, Segmentation Net, is designed to search the locations of clips from the previously detected region. Ablation studies are performed to evaluate the impact of various inputs for both networks. The two-stage deep-learning model is also compared with the other existing deep-learning methods including U-Net, V-Net and UNETR. The segmentation accuracy of these models is evaluated by three metrics: Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and Average Surface Distance (ASD).

RESULTS: The DSC, HD95 and ASD of the two-stage model are 0.844, 2.008 mm and 0.333 mm, while their values are 0.681, 2.494 mm and 0.785 mm for U-Net, 0.767, 2.331 mm and 0.497 mm for V-Net, 0.714, 2.660 mm and 0.772 mm for UNETR. The proposed 2-stage model achieved the best performance among the four models.

CONCLUSION: With the two-stage searching strategy the accuracy to detect titanium clips can be improved comparing to those existing deep-learning models with one-stage searching strategy. The proposed segmentation model can facilitate the delineation of tumor bed and subsequent target volume for breast cancer radiotherapy after lumpectomy.

PMID:40119258 | DOI:10.1186/s12880-025-01636-x

Intensive Care Med Exp. 2025 Mar 21;13(1):39. doi: 10.1186/s40635-025-00746-8.

ABSTRACT

BACKGROUND: Patient-ventilator asynchrony (PVA) is a mismatch between the patient's respiratory drive/effort and the ventilator breath delivery. It occurs frequently in mechanically ventilated patients and has been associated with adverse events and increased duration of ventilation. Identifying PVA through visual inspection of ventilator waveforms is highly challenging and time-consuming. Automated PVA detection using Artificial Intelligence (AI) has been increasingly studied, potentially offering real-time monitoring at the bedside. In this review, we discuss advances in automatic detection of PVA, focusing on developments of the last 15 years.

RESULTS: Nineteen studies were identified. Multiple forms of AI have been used for the automated detection of PVA, including rule-based algorithms, machine learning and deep learning. Three licensed algorithms are currently reported. Results of algorithms are generally promising (average reported sensitivity, specificity and accuracy of 0.80, 0.93 and 0.92, respectively), but most algorithms are only available offline, can detect a small subset of PVAs (focusing mostly on ineffective effort and double trigger asynchronies), or remain in the development or validation stage (84% (16/19 of the reviewed studies)). Moreover, only in 58% (11/19) of the studies a reference method for monitoring patient's breathing effort was available. To move from bench to bedside implementation, data quality should be improved and algorithms that can detect multiple PVAs should be externally validated, incorporating measures for breathing effort as ground truth. Last, prospective integration and model testing/finetuning in different ICU settings is key.

CONCLUSIONS: AI-based techniques for automated PVA detection are increasingly studied and show potential. For widespread implementation to succeed, several steps, including external validation and (near) real-time employment, should be considered. Then, automated PVA detection could aid in monitoring and mitigating PVAs, to eventually optimize personalized mechanical ventilation, improve clinical outcomes and reduce clinician's workload.

PMID:40119215 | DOI:10.1186/s40635-025-00746-8

Sci Rep. 2025 Mar 21;15(1):9845. doi: 10.1038/s41598-025-94664-0.

ABSTRACT

Colorectal cancer (CRC) ranks as the third most common and second deadliest cancer worldwide. The immune system, particularly tertiary lymphoid structures (TLS), significantly influences CRC progression and prognosis. TLS maturation, especially in the presence of germinal centers, correlates with improved patient outcomes; however, consistent and objective TLS assessment is hindered by varying histological definitions and limitations of traditional staining methods. This study involved 656 patients with colorectal adenocarcinoma from CHU Brest, France. We employed dual immunohistochemistry staining for CD21 and CD23 to classify TLS maturation stages in whole-slide images and implemented a fivefold cross-validation. Using ResNet50 and Vision Transformer models, we compared various aggregation methods, architectures, and pretraining techniques. Our automated system, TLS-PAT, achieved high accuracy (0.845) and robustness (kappa = 0.761) in classifying TLS maturation, particularly with the Vision Transformer pretrained on ImageNet using Max Confidence aggregation. This AI-driven approach offers a standardized method for automated TLS classification, complementing existing detection techniques. Our open-source tools are designed for easy integration with current methods, paving the way for further research in external datasets and other cancer types.

PMID:40119179 | DOI:10.1038/s41598-025-94664-0

Sci Rep. 2025 Mar 21;15(1):9805. doi: 10.1038/s41598-025-94680-0.

ABSTRACT

Accurate embryo morphology assessment is essential in assisted reproductive technology for selecting the most viable embryo. Artificial intelligence has the potential to enhance this process. However, the limited availability of embryo data presents challenges for training deep learning models. To address this, we trained two generative models using two datasets-one we created and made publicly available, and one existing public dataset-to generate synthetic embryo images at various cell stages, including 2-cell, 4-cell, 8-cell, morula, and blastocyst. These were combined with real images to train classification models for embryo cell stage prediction. Our results demonstrate that incorporating synthetic images alongside real data improved classification performance, with the model achieving 97% accuracy compared to 94.5% when trained solely on real data. This trend remained consistent when tested on an external Blastocyst dataset from a different clinic. Notably, even when trained exclusively on synthetic data and tested on real data, the model achieved a high accuracy of 92%. Furthermore, combining synthetic data from both generative models yielded better classification results than using data from a single generative model. Four embryologists evaluated the fidelity of the synthetic images through a Turing test, during which they annotated inaccuracies and offered feedback. The analysis showed the diffusion model outperformed the generative adversarial network, deceiving embryologists 66.6% versus 25.3% and achieving lower Fréchet inception distance scores.

PMID:40119109 | DOI:10.1038/s41598-025-94680-0