J Med Internet Res. 2025 Mar 18;27:e63962. doi: 10.2196/63962.

ABSTRACT

BACKGROUND: Monitoring the emotional states of patients with psychiatric problems has always been challenging due to the noncontinuous nature of clinical assessments, the effect of the health care environment, and the inherent subjectivity of evaluation instruments. However, mental states in psychiatric disorders exhibit substantial variability over time, making real-time monitoring crucial for preventing risky situations and ensuring appropriate treatment.

OBJECTIVE: This study aimed to leverage new technologies and deep learning techniques to enable more objective, real-time monitoring of patients. This was achieved by passively monitoring variables such as step count, patient location, and sleep patterns using mobile devices. We aimed to predict patient self-reports and detect sudden variations in their emotional valence, identifying situations that may require clinical intervention.

METHODS: Data for this project were collected using the Evidence-Based Behavior (eB2) app, which records both passive and self-reported variables daily. Passive data refer to behavioral information gathered via the eB2 app through sensors embedded in mobile devices and wearables. These data were obtained from studies conducted in collaboration with hospitals and clinics that used eB2. We used hidden Markov models (HMMs) to address missing data and transformer deep neural networks for time-series forecasting. Finally, classification algorithms were applied to predict several variables, including emotional state and responses to the Patient Health Questionnaire-9.

RESULTS: Through real-time patient monitoring, we demonstrated the ability to accurately predict patients' emotional states and anticipate changes over time. Specifically, our approach achieved high accuracy (0.93) and a receiver operating characteristic (ROC) area under the curve (AUC) of 0.98 for emotional valence classification. For predicting emotional state changes 1 day in advance, we obtained an ROC AUC of 0.87. Furthermore, we demonstrated the feasibility of forecasting responses to the Patient Health Questionnaire-9, with particularly strong performance for certain questions. For example, in question 9, related to suicidal ideation, our model achieved an accuracy of 0.9 and an ROC AUC of 0.77 for predicting the next day's response. Moreover, we illustrated the enhanced stability of multivariate time-series forecasting when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods, such as recurrent neural networks or long short-term memory cells.

CONCLUSIONS: The stability of multivariate time-series forecasting improved when HMM preprocessing was combined with a transformer model, as opposed to other time-series forecasting methods (eg, recurrent neural network and long short-term memory), leveraging the attention mechanisms to capture longer time dependencies and gain interpretability. We showed the potential to assess the emotional state of a patient and the scores of psychiatric questionnaires from passive variables in advance. This allows real-time monitoring of patients and hence better risk detection and treatment adjustment.

PMID:40101216 | DOI:10.2196/63962

JMIR Med Educ. 2025 Mar 18;11:e55709. doi: 10.2196/55709.

ABSTRACT

BACKGROUND: Health care practitioners use clinical decision support systems (CDSS) as an aid in the crucial task of clinical reasoning and decision-making. Traditional CDSS are online repositories (ORs) and clinical practice guidelines (CPG). Recently, large language models (LLMs) such as ChatGPT have emerged as potential alternatives. They have proven to be powerful, innovative tools, yet they are not devoid of worrisome risks.

OBJECTIVE: This study aims to explore how medical students perform in an evaluated clinical case through the use of different CDSS tools.

METHODS: The authors randomly divided medical students into 3 groups, CPG, n=6 (38%); OR, n=5 (31%); and ChatGPT, n=5 (31%); and assigned each group a different type of CDSS for guidance in answering prespecified questions, assessing how students' speed and ability at resolving the same clinical case varied accordingly. External reviewers evaluated all answers based on accuracy and completeness metrics (score: 1-5). The authors analyzed and categorized group scores according to the skill investigated: differential diagnosis, diagnostic workup, and clinical decision-making.

RESULTS: Answering time showed a trend for the ChatGPT group to be the fastest. The mean scores for completeness were as follows: CPG 4.0, OR 3.7, and ChatGPT 3.8 (P=.49). The mean scores for accuracy were as follows: CPG 4.0, OR 3.3, and ChatGPT 3.7 (P=.02). Aggregating scores according to the 3 students' skill domains, trends in differences among the groups emerge more clearly, with the CPG group that performed best in nearly all domains and maintained almost perfect alignment between its completeness and accuracy.

CONCLUSIONS: This hands-on session provided valuable insights into the potential perks and associated pitfalls of LLMs in medical education and practice. It suggested the critical need to include teachings in medical degree courses on how to properly take advantage of LLMs, as the potential for misuse is evident and real.

PMID:40101183 | DOI:10.2196/55709

PLoS One. 2025 Mar 18;20(3):e0319679. doi: 10.1371/journal.pone.0319679. eCollection 2025.

ABSTRACT

The Stability of the economy is always a great challenge across the world, especially in under developed countries. Many researchers have contributed to forecasting the Stock Market and controlling the situation to ensure economic stability over the past several decades. For this purpose, many researchers have built various models and gained benefits. This journey continues to date and will persist for the betterment of the stock market. This study is also a part of this journey, where four learning-based models are tailored for stock price prediction. Daily business data from the Karachi Stock Exchange (100 Index), covering from February 22, 2008 to February 23, 2021, is used for training and testing these models. This paper presenting four deep learning models with different architectures, namely the Artificial Neural Network model, the Recurrent Neural Network with Attention model, the Long Short-Term Memory Network with Attention model, and the Gated Recurrent Unit with Attention model. The Long Short-Term Memory with attention model was found to be the top-performing technique for accurately predicting stock exchange prices. During the Training, Validation and Testing Sessions, we observed the R-Squared values of the proposed model to be 0.9996, 0.9980 and 0.9921, respectively, making it the best-performing model among those mentioned above.

PMID:40100866 | DOI:10.1371/journal.pone.0319679

PLoS One. 2025 Mar 18;20(3):e0317863. doi: 10.1371/journal.pone.0317863. eCollection 2025.

ABSTRACT

Efficient image retrieval from a variety of datasets is crucial in today's digital world. Visual properties are represented using primitive image signatures in Content Based Image Retrieval (CBIR). Feature vectors are employed to classify images into predefined categories. This research presents a unique feature identification technique based on suppression to locate interest points by computing productive sum of pixel derivatives by computing the differentials for corner scores. Scale space interpolation is applied to define interest points by combining color features from spatially ordered L2 normalized coefficients with shape and object information. Object based feature vectors are formed using high variance coefficients to reduce the complexity and are converted into bag-of-visual-words (BoVW) for effective retrieval and ranking. The presented method encompass feature vectors for information synthesis and improves the discriminating strength of the retrieval system by extracting deep image features including primitive, spatial, and overlayed using multilayer fusion of Convolutional Neural Networks(CNNs). Extensive experimentation is performed on standard image datasets benchmarks, including ALOT, Cifar-10, Corel-10k, Tropical Fruits, and Zubud. These datasets cover wide range of categories including shape, color, texture, spatial, and complicated objects. Experimental results demonstrate considerable improvements in precision and recall rates, average retrieval precision and recall, and mean average precision and recall rates across various image semantic groups within versatile datasets. The integration of traditional feature extraction methods fusion with multilevel CNN advances image sensing and retrieval systems, promising more accurate and efficient image retrieval solutions.

PMID:40100801 | DOI:10.1371/journal.pone.0317863

PLoS One. 2025 Mar 18;20(3):e0320337. doi: 10.1371/journal.pone.0320337. eCollection 2025.

NO ABSTRACT

PMID:40100785 | DOI:10.1371/journal.pone.0320337

IEEE Trans Neural Syst Rehabil Eng. 2025 Mar 18;PP. doi: 10.1109/TNSRE.2025.3552530. Online ahead of print.

ABSTRACT

Current surface electromyography (sEMG) methods for locomotion mode prediction face limitations in anticipatory capability due to computation delays and constrained window lengths typically below 500ms-a practice historically tied to stationarity requirements of handcrafted feature extraction. This study investigates whether end-to-end convolutional neural networks (CNNs) processing raw sEMG signals can overcome these constraints through extended window lengths (250ms to 1500 ms). We systematically evaluate six window lengths paired with three prediction horizons (model forecasts 50ms to 150ms ahead) in a continuous locomotion task involving eight modes and 16 transitions. The optimal configuration (1000ms window with 150ms horizon) achieved subject-average accuracies of 96.93% (steady states) and 97.50% (transient states), maintaining 95.03% and 85.53% respectively in real-time simulations. With a net averaged anticipation time of 147.9ms after 2.1ms computation latency, this approach demonstrates that windows covering 74% of the gait cycle can synergize with deep learning to balance the inherent trade-off between extracting richer information and maintaining system responsiveness to changes in activity.

PMID:40100693 | DOI:10.1109/TNSRE.2025.3552530

IEEE J Biomed Health Inform. 2025 Mar 18;PP. doi: 10.1109/JBHI.2025.3551720. Online ahead of print.

ABSTRACT

The intelligent analysis of Whole Slide Images (WSI) in digital pathology is critical for advancing precision medicine, particularly in oncology. However, the availability of WSI datasets is often limited by privacy regulations, which constrains the performance and generalizability of deep learning models. To address this challenge, this paper proposes an improved data augmentation method based on Deep Convolutional Generative Adversarial Network (DCGAN). Our approach leverages self-supervised pretraining with the CTransPath model to extract diverse and representationally rich WSI features, which guide the generation of high-quality synthetic images. We further enhance the model by introducing a least-squares adversarial loss and a frequency domain loss to improve pixel-level accuracy and structural fidelity, while incorporating residual blocks and skip connections to increase network depth, mitigate gradient vanishing, and improve training stability. Experimental results on the PatchCamelyon dataset demonstrate that our improved DCGAN achieves superior SSIM and FID scores compared to traditional models. The augmented datasets significantly enhance the performance of downstream classification tasks, improving accuracy, AUC, and F1 scores.

PMID:40100674 | DOI:10.1109/JBHI.2025.3551720

IEEE Trans Biomed Eng. 2025 Mar 18;PP. doi: 10.1109/TBME.2025.3550842. Online ahead of print.

ABSTRACT

OBJECTIVE: Predicting normative pediatric growth is crucial to identify developmental anomalies. While traditional statistical and computational methods have shown promising results predicting personalized development, they either rely on statistical assumptions that limit generalizability or require longitudinal datasets, which are scarce in children. Recent deep learning methods trained with cross-sectional dataset have shown potential to predict temporal changes but have only succeeded at predicting local intensity changes and can hardly model major anatomical changes that occur during childhood. We present a novel deep learning method for image synthesis that can be trained using only cross-sectional data to make personalized predictions of pediatric development.

METHODS: We designed a new generative adversarial network (GAN) with a novel Siamese cyclic encoder-decoder generator architecture and an identity preservation mechanism. Our design allows the encoder to learn age- and sex-independent identity-preserving representations of patient phenotypes from single images by leveraging the statistical distributions in the cross-sectional dataset. The decoder learns to synthesize personalized images from the encoded representations at any age.

RESULTS: Trained using only cross-sectional head CT images from 2,014 subjects (age 0-10 years), our model demonstrated state-of-the-art performance evaluated on an independent longitudinal dataset with images from 51 subjects.

CONCLUSION: Our method can predict pediatric development and synthesize temporal image sequences with state-of-the-art accuracy without requiring longitudinal images for training.

SIGNIFICANCE: Our method enables the personalized prediction of pediatric growth and longitudinal synthesis of clinical images, hence providing a patient-specific reference of normative development.

PMID:40100672 | DOI:10.1109/TBME.2025.3550842

IEEE Trans Neural Netw Learn Syst. 2025 Mar 18;PP. doi: 10.1109/TNNLS.2025.3540291. Online ahead of print.

ABSTRACT

Protein complex structural data are growing at an unprecedented pace, but its complexity and diversity pose significant challenges for protein function research. Although deep learning models have been widely used to capture the syntactic structure, word semantics, or semantic meanings of polypeptide and protein sequences, these models often overlook the complex contextual information of sequences. Here, we propose interpretable interaction deep learning (IIDL)-peptide-protein interaction (PepPI), a deep learning model designed to tackle these challenges using data-driven and interpretable pragmatic analysis to profile PepPIs. IIDL-PepPI constructs bidirectional attention modules to represent the contextual information of peptides and proteins, enabling pragmatic analysis. It then adopts a progressive transfer learning framework to simultaneously predict PepPIs and identify binding residues for specific interactions, providing a solution for multilevel in-depth profiling. We validate the performance and robustness of IIDL-PepPI in accurately predicting peptide-protein binary interactions and identifying binding residues compared with the state-of-the-art methods. We further demonstrate the capability of IIDL-PepPI in peptide virtual drug screening and binding affinity assessment, which is expected to advance artificial intelligence-based peptide drug discovery and protein function elucidation.

PMID:40100664 | DOI:10.1109/TNNLS.2025.3540291

IEEE Trans Pattern Anal Mach Intell. 2025 Mar 18;PP. doi: 10.1109/TPAMI.2025.3552484. Online ahead of print.

ABSTRACT

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing the scalability and performance. In this paper, we propose a hard-aware instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality and diversity of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. We further enrich the hard class pseudo-labels with inter-image information through a skillfully designed hard-aware pseudo-label augmentation. Besides, we propose the region-adaptive regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. For the non-pseudo-label region, consistency constraint is also constructed to introduce stronger supervision signals during model optimization. Our method is so concise and efficient that it is easy to be generalized to other UDA methods. Experiments on GTA5 Cityscapes, SYNTHIA Cityscapes, and Cityscapes Oxford RobotCar demonstrate the superior performance of our approach compared with the state-of-the-art methods. Our codes are available at https://github.com/bupt-ai-cz/HIAST.

PMID:40100655 | DOI:10.1109/TPAMI.2025.3552484

J Clin Invest. 2025 Mar 18:e181775. doi: 10.1172/JCI181775. Online ahead of print.

ABSTRACT

Tissue regenerative responses involve complex interactions between resident structural and immune cells. Recent reports indicate that accumulation of senescent cells during injury repair contributes to pathological tissue fibrosis. Using tissue-based spatial transcriptomics and proteomics, we identified upregulation of the immune checkpoint protein, cytotoxic T-lymphocyte associated protein 4 (CTLA4) on CD8+ T cells adjacent to regions of active fibrogenesis in human idiopathic pulmonary fibrosis (IPF) and in a murine model of repetitive bleomycin lung injury model of persistent fibrosis. In humanized CTLA4 knock-in mice, treatment with ipilimumab, an FDA-approved drug that targets CTLA4, resulted in accelerated lung epithelial regeneration and diminished fibrosis from repetitive bleomycin injury. Ipilimumab treatment resulted in the expansion of Cd3e+ T cells, diminished accumulation of senescent cells, and robust expansion of type 2 alveolar epithelial cells, facultative progenitor cells of the alveolar epithelium. Ex-vivo activation of isolated CTLA4-expressing CD8+ cells from mice with established fibrosis resulted in enhanced cytolysis of senescent cells, suggesting that impaired immune-mediated clearance of these cells contribute to persistence of lung fibrosis in this murine model. Our studies support the concept that endogenous immune surveillance of senescent cells may be essential in promoting tissue regenerative responses that facilitate the resolution of fibrosis.

PMID:40100323 | DOI:10.1172/JCI181775

PLoS Negl Trop Dis. 2025 Mar 18;19(3):e0012909. doi: 10.1371/journal.pntd.0012909. eCollection 2025 Mar.

ABSTRACT

BACKGROUND: Scrub typhus, traditionally caused by Orientia tsutsugamushi, is a re-emerging public health concern within the Tsutsugamushi Triangle. Despite growing awareness, prevention strategies remain inadequate on Hainan Island, China, where scrub typhus poses a significant threat, especially in field-related environments.

METHODOLOGY/PRINCIPAL FINDINGS: Gene flow analysis of the tsa56 gene and multilocus sequence typing (MLST) were conducted on 156 previously confirmed scrub typhus cases from 2018 to 2021 across Hainan Island. By integrating published datasets, we identified 12 major sub-genotypes and traced their origins, revealing that these sub-genotypes share origins with isolates from Southeast Asia and coastal provinces and island of China, but also demonstrate unique local adaptations across all isolates. Alpha diversity index analysis was applied across administrative regions to identify hotspot regions. This analysis showed that nine out of the detected fourteen administrative regions, particularly along the northern and western coastlines and inland areas, exhibited relatively high genetic diversity, with the highest incidence observed in Qiongzhong, a centrally located city. Related major sequence types were mapped, and distances between locations were estimated, showing that identical MLST sequence types were observed to transfer across distances of 23 to 125 km between different sites on the island. Pathogen density was analyzed using quantitative real-time PCR targeting the tsa56 gene. Without accounting for potential confounding factors or dataset limitations, the Karp_B_2 sub-genotype showed a significant increasing trend in pathogen density with prolonged fever duration, while Gilliam sub-genotypes exhibited a slower or even declining trend.

CONCLUSIONS/SIGNIFICANCE: These findings emphasize the urgent need for targeted public health interventions, particularly focusing on vulnerable populations in rural and agricultural areas of nine key administrative regions where high genetic diversity and pathogen spread were observed. Additionally, this study provides valuable insights into the transmission dynamics and infection progression of scrub typhus, using gene flow analysis and multilocus sequence typing to identify major sub-genotypes.

PMID:40100922 | DOI:10.1371/journal.pntd.0012909

PLoS Biol. 2025 Mar 18;23(3):e3003052. doi: 10.1371/journal.pbio.3003052. eCollection 2025 Mar.

ABSTRACT

Genome sequencing of cancer and normal tissues, alongside single-cell transcriptomics, continues to produce findings that challenge the idea that cancer is a 'genetic disease', as posited by the somatic mutation theory (SMT). In this prevailing paradigm, tumorigenesis is caused by cancer-driving somatic mutations and clonal expansion. However, results from tumor sequencing, motivated by the genetic paradigm itself, create apparent 'paradoxes' that are not conducive to a pure SMT. But beyond genetic causation, the new results lend credence to old ideas from organismal biology. To resolve inconsistencies between the genetic paradigm of cancer and biological reality, we must complement deep sequencing with deep thinking: embrace formal theory and historicity of biological entities, and (re)consider non-genetic plasticity of cells and tissues. In this Essay, we discuss the concepts of cell state dynamics and tissue fields that emerge from the collective action of genes and of cells in their morphogenetic context, respectively, and how they help explain inconsistencies in the data in the context of SMT.

PMID:40100793 | DOI:10.1371/journal.pbio.3003052

Mol Pharm. 2025 Mar 18. doi: 10.1021/acs.molpharmaceut.5c00191. Online ahead of print.

ABSTRACT

Statins have been reported for diverse pleiotropic activities, including antimicrobial and antibiofilm. However, due to the limited understanding of their mode of action, none of the statins have gained approval for antimicrobial or antibiofilm applications. In a recent drug repurposing study, we observed that two statins (i.e., Simvastatin and Lovastatin) interact stably with TasA(28-261), the principal extracellular matrix protein of Bacillus subtilis, and also induce inhibition of biofilm formation. Nevertheless, the underlying mechanism remained elusive. In the present study, we examined the impact of these statins on the physiological activity of TasA(28-261), specifically its interaction with TapA(33-253) and aggregation into the amyloid-like structure using purified recombinant TasA(28-261) and TapA(33-253) in amyloid detection-specific in vitro assays (i.e., CR binding and ThT staining assays). Results revealed that both statins interfered with amyloid formation by the TasA(28-261)-TapA(33-253) complex, while neither statin inhibited amyloid formation by lysozyme, a model amyloid-forming protein. Moreover, neither statin significantly altered the expressions of terminal regulatory genes (viz, sinR, sinI) and terminal effector genes (viz, tasA, tapA, and bslA) involved in biofilm formation by B. subtilis. While the intricate interplay between Simvastatin and Lovastatin with the diverse molecular constituents of B. subtilis biofilm remains to be elucidated conclusively, the findings obtained during the present study suggest that the underlying mechanism for Simvastatin- and Lovastatin-mediated inhibition of B. subtilis biofilm formation is manifested by interfering with the aggregation and amyloid formation by TasA(28-261)-TapA(33-253). These results represent one of the first experimental evidence for the underlying mechanism of antibiofilm activity of statins and offer valuable directions for future research to harness statins as antibiofilm therapeutics.

PMID:40100146 | DOI:10.1021/acs.molpharmaceut.5c00191

ChemMedChem. 2025 Mar 18:e202500084. doi: 10.1002/cmdc.202500084. Online ahead of print.

ABSTRACT

This study explores the anti-cancer potential of N-methylated open-ring derivatives of carborane-substituted diclofenac analogs. By N-methylation, the open-chain form could be trapped and cyclization back to lactam or amidine derivatives was inhibited. A small library of carborane- and phenyl-based secondary and tertiary arylamines bearing carboxylic acid or nitrile groups was synthesized and analyzed for their COX-affinity in vitro and in silico. The compounds were further evaluated against mouse adenocarcinoma (MC38), human colorectal carcinoma (HCT116) and human colorectal adenocarcinoma (HT29) cell lines and showed potent cytotoxicity. Additional biological assessments of the mode of action were performed using flow cytometric techniques and fluorescence microscopy. The data obtained revealed a common antiproliferative effect coupled with the induction of caspase-independent apoptosis and the specific effects of the compound on the phenotype of MC38 cells, resulting in impaired cell viability of MC38 cells and satisfactory selectivity exceeding the antitumor activity of diclofenac.

PMID:40099997 | DOI:10.1002/cmdc.202500084

Per Med. 2025 Mar 18:1-9. doi: 10.1080/17410541.2025.2476392. Online ahead of print.

ABSTRACT

PURPOSE: To investigate patient reactions to and understanding of secondary genomic findings with limited to no medical actionability (LMA-SFs) from diagnostic genome sequencing.

METHODS: We analyzed LMA-SFs returned to 47 adults who elected to receive a broad set of these results from 6 categories. Findings indicated elevated risk (reportable/positive) or not (negative/normal). Most participants (N = 43) also completed surveys to report their distress, decision regret, expected health anxiety, and whether and how they perceived results as reassuring or troubling.

RESULTS: Most participants received some reportable LMA-SFs for common risk, pharmacogenetic, and carrier status variants. Fewer received reportable APOE haplotype or monogenetic condition variants. None received results indicating high risk for severe neurological disease. Overall, participants (76.7% female, 97.7% White) had low distress, decision regret, and expected health anxiety. None described negative/normal findings as troubling. However, their interpretations of reportable/positive results varied. Even within the same result type, some participants found them troubling, while others found them reassuring based on their perception of the results' utility.

CONCLUSION: Participants' short-term well-being was not reduced by receiving LMA-SFs. Their interpretations suggested varied personal utilities and the need for post-test resources to aid understanding of these types of results and their health significance.

PMID:40100039 | DOI:10.1080/17410541.2025.2476392

Clin Pharmacol Ther. 2025 Mar 18. doi: 10.1002/cpt.3642. Online ahead of print.

ABSTRACT

Major depressive disorder is a common disorder in pregnancy. Although citalopram/escitalopram is the second most frequently prescribed antidepressant for pregnant people, information about its pharmacokinetics in pregnancy is limited. We investigated plasma (S)-citalopram concentration to dose (C/D) ratios across pregnancy and postpartum and the effect of pharmacogenetics on its elimination. This prospective observational cohort study enrolled 30 participants with a singleton pregnancy who chose to continue citalopram/escitalopram during pregnancy for a prior diagnosis of major depression. Monthly blood samples were obtained 24 hours post-dose across pregnancy and twice postpartum for measurement of plasma citalopram, desmethylcitalopram, and didesmethylcitalopram enantiomer concentrations. Compared with the 36-week reference, (S)-citalopram C/D ratios were not significantly different throughout pregnancy. However, the mean (S)-citalopram C/D ratio was elevated by 63% (P < 0.001) 6 to 8 weeks after delivery before it decreased to a mean C/D ratio in the later post-birth period that was marginally different than at 36 weeks (1.20 ± 0.64 vs. 0.92 ± 0.46, respectively; P = 0.06). Analyzing the results by cytochrome P 450 (CYP) 2C19 phenotype, the mean late postpartum (S)-citalopram concentration to dose ratio in intermediate metabolizers was approximately twice that in extensive, rapid, or ultrarapid metabolizers. However, at the 36-week reference point, the mean concentration to dose ratio in pregnant CYP2C19 intermediate metabolizers was 35.7% lower than the distant postpartum ratio, while the ratios in extensive and rapid/ultrarapid metabolizers were 15.4% and 18.5% lower, respectively. Without dose adjustment, people with intermediate or poor CYP2C19 activity may be at risk for subtherapeutic S-citalopram concentrations during pregnancy.

PMID:40099712 | DOI:10.1002/cpt.3642

Br J Clin Pharmacol. 2025 Mar 18. doi: 10.1002/bcp.70047. Online ahead of print.

ABSTRACT

Thiopurines are a class of immunosuppressant and antineoplastic agents. They are widely used in the treatment of inflammatory bowel disease, haematological malignancies and autoimmune diseases, but can cause significant toxicity. Inherited gene mutations are now recognized as independent risk factors for severe adverse drug reactions to thiopurines even at 10-fold dose reductions. We present a case of thiopurine toxicity resulting in severe myelosuppression, hepatotoxicity and alopecia in an individual with homozygous *3/*3 loss-of-function alleles in the NUDT15 gene. Our case highlights important differences in gene mutation frequencies between races that can help guide pharmacogenomic testing.

PMID:40099566 | DOI:10.1002/bcp.70047

ACS Appl Mater Interfaces. 2025 Mar 18. doi: 10.1021/acsami.4c20874. Online ahead of print.

ABSTRACT

Bacterial biofilms present significant therapeutic challenges due to their resistance to conventional antimicrobial treatment. Mucins typically serve as a protective barrier against pathogens, yet certain bacteria, such as Pseudomonas aeruginosa (P. aeruginosa), can exploit these glycoproteins as attachment sites for biofilm formation. This study introduces boronic acid-functionalized polyethyleneimine (PEI-BA) as a promising antibiofilm agent that effectively blocks bacterial adhesion to mucin-rich surfaces. Through the multivalent presentation of boronic acid groups, PEI-BA reversibly forms boronate ester bonds with mucin glycans, creating a protective barrier. Our findings show that PEI-BA prevents bacterial attachment through a nonbactericidal mechanism, potentially reducing the risk of resistance development. Notably, PEI-BA synergizes with a conventional antibiotic, tobramycin, significantly enhancing biofilm inhibition compared to either treatment alone. Systematic evaluation of PEI-BA formulations identified optimal functionalization levels, balancing glycan-binding capability with solubility. From a biomaterials design perspective, we demonstrate how rational polymer modification can transform a potent but cytotoxic antimicrobial agent (i.e., PEI) into a safe and effective antibiofilm material, opening further possibilities for managing biofilm-associated infections in clinical settings. This work establishes boronic acid-based nanomaterials as promising candidates for biofilm prevention and antibiotic enhancement, particularly in conditions like cystic fibrosis, where mucin-bacterial interactions contribute to disease progression.

PMID:40099915 | DOI:10.1021/acsami.4c20874

J Med Internet Res. 2025 Mar 18;27:e57358. doi: 10.2196/57358.

ABSTRACT

BACKGROUND: The use of structured electronic health records in health care systems has grown rapidly. These systems collect huge amounts of patient information, including diagnosis codes representing temporal medical history. Sequential diagnostic information has proven valuable for predicting patient outcomes. However, the extent to which these types of data have been incorporated into deep learning (DL) models has not been examined.

OBJECTIVE: This systematic review aims to describe the use of sequential diagnostic data in DL models, specifically to understand how these data are integrated, whether sample size improves performance, and whether the identified models are generalizable.

METHODS: Relevant studies published up to May 15, 2023, were identified using 4 databases: PubMed, Embase, IEEE Xplore, and Web of Science. We included all studies using DL algorithms trained on sequential diagnosis codes to predict patient outcomes. We excluded review articles and non-peer-reviewed papers. We evaluated the following aspects in the included papers: DL techniques, characteristics of the dataset, prediction tasks, performance evaluation, generalizability, and explainability. We also assessed the risk of bias and applicability of the studies using the Prediction Model Study Risk of Bias Assessment Tool (PROBAST). We used the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist to report our findings.

RESULTS: Of the 740 identified papers, 84 (11.4%) met the eligibility criteria. Publications in this area increased yearly. Recurrent neural networks (and their derivatives; 47/84, 56%) and transformers (22/84, 26%) were the most commonly used architectures in DL-based models. Most studies (45/84, 54%) presented their input features as sequences of visit embeddings. Medications (38/84, 45%) were the most common additional feature. Of the 128 predictive outcome tasks, the most frequent was next-visit diagnosis (n=30, 23%), followed by heart failure (n=18, 14%) and mortality (n=17, 13%). Only 7 (8%) of the 84 studies evaluated their models in terms of generalizability. A positive correlation was observed between training sample size and model performance (area under the receiver operating characteristic curve; P=.02). However, 59 (70%) of the 84 studies had a high risk of bias.

CONCLUSIONS: The application of DL for advanced modeling of sequential medical codes has demonstrated remarkable promise in predicting patient outcomes. The main limitation of this study was the heterogeneity of methods and outcomes. However, our analysis found that using multiple types of features, integrating time intervals, and including larger sample sizes were generally related to an improved predictive performance. This review also highlights that very few studies (7/84, 8%) reported on challenges related to generalizability and less than half (38/84, 45%) of the studies reported on challenges related to explainability. Addressing these shortcomings will be instrumental in unlocking the full potential of DL for enhancing health care outcomes and patient care.

TRIAL REGISTRATION: PROSPERO CRD42018112161; https://tinyurl.com/yc6h9rwu.

PMID:40100249 | DOI:10.2196/57358