Cogn Neurodyn. 2025 Dec;19(1):70. doi: 10.1007/s11571-025-10253-x. Epub 2025 May 5.

ABSTRACT

One of the areas where artificial intelligence (AI) technologies are used is the detection and diagnosis of mental disorders. AI approaches, including machine learning and deep learning models, can identify early signs of bipolar disorder, schizophrenia, autism spectrum disorder, depression, suicidality, and dementia by analyzing speech patterns, behaviors, and physiological data. These approaches increase diagnostic accuracy and enable timely intervention, which is crucial for effective treatment. This paper presents a comprehensive literature review of AI approaches applied to mental disorder detection using various data sources, such as survey, Electroencephalography (EEG) signal, text and image. Applications include predicting anxiety and depression levels in online games, detecting schizophrenia from EEG signals, detecting autism spectrum disorder, analyzing text-based indicators of suicidality and depression, and diagnosing dementia from magnetic resonance imaging images. eXtreme Gradient Boosting (XGBoost), light gradient-boosting machine (LightGBM), random forest (RF), support vector machine (SVM), K-nearest neighbor were designed as machine learning models, and convolutional neural networks (CNN), long short-term memory (LSTM) and gated recurrent unit (GRU) models suitable for the dataset were designed as deep learning models. Data preprocessing techniques such as wavelet transforms, normalization, clustering were used to optimize model performances, and hyperparameter optimization and feature extraction were performed. While the LightGBM technique had the highest performance with 96% accuracy for anxiety and depression prediction, the optimized SVM stood out with 97% accuracy. Autism spectrum disorder classification reached 98% accuracy with XGBoost, RF and LightGBM. The LSTM model achieved a high accuracy of 83% in schizophrenia diagnosis. The GRU model showed the best performance with 93% accuracy in text-based suicide and depression detection. In the detection of dementia, LSTM and GRU models have demonstrated their effectiveness in data analysis by reaching 99% accuracy. The findings of the study highlight the effectiveness of LSTM and GRU for sequential data analysis and their applicability in medical imaging or natural language processing. XGBoost and LightGBM are noted to be highly accurate ML tools for clinical diagnoses. In addition, hyperparameter optimization and advanced data pre-processing approaches are confirmed to significantly improve model performance. The results obtained with this study have revealed the potential to improve clinical decision support systems for mental disorders with AI, facilitating early diagnosis and personalized treatment strategies.

PMID:40330715 | PMC:PMC12052716 | DOI:10.1007/s11571-025-10253-x

Cogn Neurodyn. 2025 Dec;19(1):68. doi: 10.1007/s11571-025-10251-z. Epub 2025 May 3.

ABSTRACT

Schizophrenia remains a challenging neuropsychiatric disorder with complex diagnostic processes. Current clinical approaches often rely on subjective assessments, highlighting the critical need for objective, quantitative diagnostic methods. This study aimed to develop a robust classification approach for schizophrenia using EEG microstate analysis and advanced machine learning techniques. We analyzed EEG signals from 14 healthy individuals and 14 patients with schizophrenia during a 15-min resting-state session across 19 EEG channels. A data augmentation strategy expanded the dataset to 56 subjects in each group. The signals were preprocessed and segmented into five frequency bands (delta, theta, alpha, beta, gamma) and five microstates (A, B, C, D, E) using k-means clustering. Five key features were extracted from each microstate: duration, occurrence, standard deviation, coverage, and frequency. A Deep Neural Network (DNN) model, along with other machine learning classifiers, was developed to classify the data. A comprehensive fivefold cross-validation approach evaluated model performance across various EEG channels, frequency bands, and feature combinations. Significant alterations in microstate transition probabilities were observed, particularly in higher frequency bands. The gamma band showed the most pronounced differences, with a notable disruption in D → A transitions (absolute difference = 0.100). The Random Forest classifier achieved the highest accuracy of 99.94% ± 0.12%, utilizing theta band features from the F8 frontal channel. The deep neural network model demonstrated robust performance with 98.31% ± 0.68% accuracy, primarily in the occipital region. Feature size 2 consistently provided optimal classification across most models. Our study introduces a novel, high-precision EEG microstate analysis approach for schizophrenia diagnosis, offering an objective diagnostic tool with potential applications in neuropsychiatric disorders. The findings reveal critical insights into neural dynamics associated with schizophrenia, demonstrating the potential for transforming clinical diagnostic practices through advanced machine learning and neurophysiological feature extraction.

PMID:40330714 | PMC:PMC12049357 | DOI:10.1007/s11571-025-10251-z

Plant Direct. 2025 May 4;9(5):e70076. doi: 10.1002/pld3.70076. eCollection 2025 May.

ABSTRACT

Sustainable agriculture holds the key in meeting food production requirements for a rapidly growing population without exacerbating environmental degradation. Plant leaf diseases pose a critical threat to crop yield and quality. Existing inspection methods are labor-intensive and prone to human errors, while lacking support for large-scale agriculture. This research aims to enhance plant health by developing advanced deep learning models for the detection and classification of plant diseases across a variety of species. A deep learning model based on the paradigm of the MobileNet architecture is proposed, which employs a dedicated design through deeper convolutional layers, dropout regularization, and fully connected layers. This results in significant improvements in disease classification in tomato, bean, and chili plants, with accuracy rates of 97.90%, 98.12%, and 97.95%, respectively. Moreover, Grad-CAM is used to shed light on the decision-making process of the proposed model. The work contributes to the advancement of precision farming and sustainable agricultural practices, supporting timely and accurate plant disease diagnosis.

PMID:40330704 | PMC:PMC12050364 | DOI:10.1002/pld3.70076

Evol Appl. 2025 May 4;18(5):e70101. doi: 10.1111/eva.70101. eCollection 2025 May.

ABSTRACT

DNA methylation has fundamental implications for vertebrate genome evolution by influencing the mutational landscape, particularly at CpG dinucleotides. Methylation-induced mutations drive a genome-wide depletion of CpG sites, creating a dinucleotide composition bias across the genome. Examination of the standard genetic code reveals CpG to be the only facultative dinucleotide; it is however unclear what specific implications CpG bias has on protein coding DNA. Here, we use theoretical considerations of the genetic code combined with empirical genome-wide analyses in six vertebrate species-human, mouse, chicken, great tit, frog, and stickleback-to investigate how CpG content is shaped and maintained in protein-coding genes. We show that protein-coding sequences consistently exhibit significantly higher CpG content than noncoding regions and demonstrate that CpG sites are enriched in genes involved in regulatory functions and stress responses, suggesting selective maintenance of CpG content in specific loci. These findings have important implications for evolutionary applications in both natural and managed populations: CpG content could serve as a genetic marker for assessing adaptive potential, while the identification of CpG-free codons provides a framework for genome optimization in breeding and synthetic biology. Our results underscore the intricate interplay between mutational biases, selection, and epigenetic regulation, offering new insights into how vertebrate genomes evolve under varying ecological and selective pressures.

PMID:40330995 | PMC:PMC12050414 | DOI:10.1111/eva.70101

Front Med (Lausanne). 2025 Apr 22;12:1576583. doi: 10.3389/fmed.2025.1576583. eCollection 2025.

ABSTRACT

Human Metapneumovirus (hMPV) is a common cause of acute respiratory viral infection in humans, typically occurring in children and causing no serious complications. However, the severity of the disease can be exacerbated by certain bacterial pathogens that lead to severe illness and even death. This report details a fulminant case of dual infection with hMPV and group A Streptococcus (Streptococcus pyogenes) in a three-year-old child. The whole genome sequencing of isolated clinical S. pyogenes strains was conducted, followed by an analysis of the genomic characteristics of the pathogen. Also, potential viral and bacterial pathogens were identified by qPCR and 16S rRNA metagenomic sequencing in any autopsy materials obtained from the patient. Children who had contact with the patient and began to exhibit symptoms of a cold were also tested and confirmed to have uncomplicated hMPV infection. The S. pyogenes strain has been found to contain five genes for various streptococcal exotoxins (speA, speB, speJ, speG and smeZ). In addition, the speA gene is situated in close proximity to the prophage, which may suggest that it is encoded and transferred specifically by the bacteriophage. We hypothesize that it was the cumulative effects of different streptococcal exotoxins that led to the patient's death.

PMID:40330784 | PMC:PMC12052555 | DOI:10.3389/fmed.2025.1576583

Curr Res Food Sci. 2025 Apr 5;10:101043. doi: 10.1016/j.crfs.2025.101043. eCollection 2025.

ABSTRACT

Analyzing bitterness is challenging because of the diverse range of bitter compounds, the variability in sensory perception, and its complex interaction with other tastes. To address this, we developed an untargeted approach to deconvolute the taste and molecular composition of complex plant extracts. We applied our methodology to an ethanolic extract of Swertia chirayita (Roxb.) H.Karst., a plant recognized for its distinctive bitterness. Chemical characterization was performed through nuclear magnetic resonance spectroscopy experiments together with untargeted liquid chromatography-high resolution tandem mass spectrometry analysis coupled to a charged aerosol detector. After clustering the fractions based on chemical similarity, we performed free sensory analysis and classical descriptive analysis on each cluster. Our results confirmed the attribution of bitterness to iridoids and highlighted the role of other important compounds in the overall taste. This method provides a systematic approach for analyzing and potentially enhancing the taste profiles of plant-based beverages.

PMID:40330506 | PMC:PMC12051061 | DOI:10.1016/j.crfs.2025.101043

PNAS Nexus. 2025 Apr 25;4(5):pgaf120. doi: 10.1093/pnasnexus/pgaf120. eCollection 2025 May.

ABSTRACT

Circadian clocks regulate biological activities, providing organisms with a fitness advantage under diurnal conditions by enabling anticipation and adaptation to recurring external changes. Three proteins, KaiA, KaiB, and KaiC, constitute the circadian clock in the cyanobacterial model Synechococcus elongatus PCC 7942. Several techniques established to measure circadian output in Synechococcus yielded comparably weak signals in Synechocystis sp. PCC 6803, a strain important for biotechnological applications. We applied an approach that does not require genetic modifications to monitor the circadian rhythms in Synechococcus and Synechocystis. We placed batch cultures in shake flasks on a sensor detecting backscattered light via noninvasive online measurements. Backscattering oscillated with a period of ∼24 h around the average growth. Wavelet and Fourier transformations are applied to determine the period's significance and length. In Synechocystis, oscillations fulfilled the circadian criteria of temperature compensation and entrainment by external stimuli. Remarkably, dilution alone synchronized oscillations. Western blotting revealed that the backscatter was ∼6.5 h phase-delayed in comparison to KaiC3 phosphorylation.

PMID:40330109 | PMC:PMC12053491 | DOI:10.1093/pnasnexus/pgaf120

J Biomol Tech. 2025 Mar 24;36(1):3fc1f5fe.0f37be73. doi: 10.7171/3fc1f5fe.0f37be73. eCollection 2025 Apr 30.

ABSTRACT

Recent advances in massively parallel DNA sequencing have enabled researchers to study new areas of extreme environments. Of particular interest to many researchers are areas of the Arctic that have yet to be comprehensively examined using DNA techniques. These modern approaches to microbial profiling provide new critical data on systems biology not yet seen before from Arctic samples. The discovery of new microbes, microbial biochemical pathways, and biosynthetic gene clusters are critically important when characterizing the Arctic snow microbiome and can provide insights to discovering valuable biosynthetic gene clusters. In this study, 2 L of snow was collected from 15 sites 12 km east outside of Ilulissat, Greenland, using DNA-free sterile techniques. Snow was allowed to melt and immediately concentrated using the InnovaPrep CP sample concentrator. Whole genome DNA sequencing was performed on extracts using both Illumina and Nanopore sequencing as well as psychrophilic culturing. Individual cultures were also sequenced to determine whole genome content and species identity. The results showed a wide-ranging microbiome across the snow fields, including bacteria, yeast, and fungi, with Granulicella, Methylobabcterium, Nostoc, Sphingomonas, and Streptomyces being consistently detected at higher levels across the majority of sites and sequencing platforms, while Belnapia, Chlorogloea, Hymenobacter, Mesorhizobium, Narcardioides, Pseudomonas, Pseudonocardia, Roseomonas, and Solirubrobacter at comparatively lower abundances. The results of culture data for snow sites reveal Pseudomanas sp., Pseudomonas fluorescens Group, unknown Microbacteriaceae sp., Variovorax sp., Robbsia andropogonis, and low concentrations of Aureobasidium sp., Stylodothis sp., Sphingomonas sp., Hymenobacter sp., Caballeronia sordidicola, and two unknown species of yeast and one unknown species of bacteria.

PMID:40329984 | PMC:PMC12051450 | DOI:10.7171/3fc1f5fe.0f37be73

Adv Sci (Weinh). 2025 May 7:e2414507. doi: 10.1002/advs.202414507. Online ahead of print.

ABSTRACT

Facial morphology is a distinctive biometric marker, offering invaluable insights into personal identity, especially in forensic science. In the context of high-throughput sequencing, the reconstruction of 3D human facial images from DNA is becoming a revolutionary approach for identifying individuals based on unknown biological specimens. Inspired by artificial intelligence techniques in text-to-image synthesis, it proposes Difface, a multi-modality model designed to reconstruct 3D facial images only from DNA. Specifically, Difface first utilizes a transformer and a spiral convolution network to map high-dimensional Single Nucleotide Polymorphisms and 3D facial images to the same low-dimensional features, respectively, while establishing the association between both modalities in the latent features in a contrastive manner; and then incorporates a diffusion model to reconstruct facial structures from the characteristics of SNPs. Applying Difface to the Han Chinese database with 9,674 paired SNP phenotypes and 3D facial images demonstrates excellent performance in DNA-to-3D image alignment and reconstruction and characterizes the individual genomics. Also, including phenotype information in Difface further improves the quality of 3D reconstruction, i.e. Difface can generate 3D facial images of individuals solely from their DNA data, projecting their appearance at various future ages. This work represents pioneer research in de novo generating human facial images from individual genomics information.

PMID:40329800 | DOI:10.1002/advs.202414507

Pigment Cell Melanoma Res. 2025 May;38(3):e70022. doi: 10.1111/pcmr.70022.

ABSTRACT

Pigment cells not only are intrinsic factors to determine animal patterns, but also play vital roles in numerous behavioral and physiological processes as well as health, such as melanomas originating from melanocytes. Model organisms are commonly used to study pigment cell development and the mechanisms underlying related diseases, with zebrafish and mice, and Xenopus being well-established examples. Xenopus tropicalis, a diploid amphibian model, offers advantages such as high fecundity and easily observable pigment cell development. Recent advancements in gene-editing techniques have increased its prominence in research on pigment cell biology and melanoma pathogenesis. Here, we compare the skin pigment cell distribution as well as the skin structure in X. tropicalis, zebrafish, mice, and humans and point out the potential value of using X. tropicalis to model human skin diseases, such as melanoma.

PMID:40329555 | DOI:10.1111/pcmr.70022

Rom J Ophthalmol. 2025 Jan-Mar;69(1):3-9. doi: 10.22336/rjo.2025.02.

ABSTRACT

OBJECTIVES: The primary aim of this article is to present cystoid macular oedema as one of the side effects of Paclitaxel (Taxol) chemotherapy. Paclitaxel is used as a treatment option in patients with different types of solid carcinomas. The potential loss of vision, already altered by the disease, further compromises their quality of life, a contributing factor to overall psychological and mental decline.

CASE PRESENTATION: A 69-year-old woman developed a drop in visual acuity that was painless, bilateral, and accompanied by wavy lines. This occurred six months after starting Paclitaxel chemotherapy for metastatic breast cancer. The diagnosis of cystoid macular oedema caused by Paclitaxel was made. The visual acuity significantly improved after Paclitaxel was discontinued, and the symptoms subsided.

DISCUSSION: Paclitaxel is a chemotherapy drug used to treat various types of cancers and has been associated with cystoid macular oedema (CMO) in rare cases. CMO is thought to result from the disruption of the normal blood-retinal barrier. The specific mechanism remains incompletely understood, and multiple mechanisms have been postulated. In typical CMO, leakage from parafoveal capillaries is demonstrated on fluorescein angiograms in a classic petaloid pattern. However, in Taxane-Drug Induced CMO (TDICMO), there is no evidence of fluorescein leakage on angiography. TDICMO is a rare drug side effect of breast cancer treatment, described just 14 times in the English literature.

CONCLUSION: It is crucial to reiterate that if a patient undergoing Paclitaxel treatment experiences any vision changes, it is imperative to consult an ophthalmologist for a thorough evaluation and appropriate management. This step is essential for the patient's well-being and to ensure the best possible outcome.

PMID:40330966 | PMC:PMC12049643 | DOI:10.22336/rjo.2025.02

AME Case Rep. 2025 Apr 17;9:65. doi: 10.21037/acr-24-114. eCollection 2025.

ABSTRACT

BACKGROUND: Omalizumab is a monoclonal humanized antibody used as a third-line treatment for chronic spontaneous urticaria (CSU). While it has shown significant efficacy in controlling urticaria symptoms, it is also associated with various adverse effects. Cutaneous side effects of omalizumab have been reported, but the mechanisms underlying these reactions are not fully understood. This case report describes a patient who developed a maculopapular rash after receiving the 8th dose of omalizumab, which has not been previously reported.

CASE DESCRIPTION: The patient in this case was a 46-year-old male with CSU who had been receiving omalizumab injections every four weeks. After the 8th dose, he developed a generalized itchy erythematous skin eruption six days after the injection. The rash progressively worsened over a two-week period. Interestingly, the patient had experienced a milder skin reaction after the 6th dose, which resolved on its own. A skin biopsy showed mild interstitial edema in the dermis with a mild perivascular infiltrate of lymphocytes and eosinophils, consistent with a drug-induced eruption. The patient was advised to hold the next dose of omalizumab and was managed with topical steroids. Significant improvement and resolution of the lesions were observed, and no recurrence or relapse was reported after the patient resumed omalizumab.

CONCLUSIONS: This case adds to the existing literature by reporting a pityriasis rosea-like eruption as an adverse reaction to omalizumab, which has not been extensively documented. The delayed onset and progressive nature of the rash after the 8th dose, as well as the milder previous reaction after the 6th dose, highlight the importance of considering omalizumab as a potential cause of various cutaneous reactions. Physicians should be vigilant in monitoring patients receiving omalizumab for any signs of skin eruptions or other adverse effects. Further research is needed to understand the mechanisms underlying cutaneous reactions to omalizumab and to establish guidelines for their management. This case emphasizes the need for ongoing attention to potential side effects or reactions in patients receiving omalizumab.

PMID:40330944 | PMC:PMC12053656 | DOI:10.21037/acr-24-114

Cureus. 2025 Apr 3;17(4):e81663. doi: 10.7759/cureus.81663. eCollection 2025 Apr.

ABSTRACT

We report the case of a 30-year-old male patient who presented with a pruritic, irregular, 4x3 cm scaly purple-red plaque with surrounding papules on his lateral face, scalp, and chin after the introduction of semaglutide (Ozempic). Discoid lupus erythematosus (DLE) was suspected. A punch biopsy of a scalp lesion showed interface changes with loss of pilosebaceous units and follicular plugging, findings consistent with DLE. A complete blood count, antinuclear antibody (ANA), anti-double stranded DNA (dsDNA), and extractable nuclear antigen (ENA) panel was quantified along with erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), complement levels, creatinine, and glomerular filtration rate, ruling out systemic lupus erythematosus (SLE). The patient's condition improved with drug discontinuation as well as topical treatment, including tacrolimus 0.1% ointment and clobetasol lotion. Hydroxychloroquine 200 mg daily was trialed but discontinued due to the patient's concerns about ocular side effects. Follow-up after four months showed improvement, with less scale and erythema. Although semaglutide has been widely used for glycemic control and weight loss, cutaneous adverse effects are seldom reported. This case highlights the potential for drug-induced cutaneous lupus erythematosus (DICLE) associated with immune-modulating medications such as semaglutide, a glucagon-like peptide-1 receptor agonist (GLP-1 RA).

PMID:40330408 | PMC:PMC12051072 | DOI:10.7759/cureus.81663

Rev Med Interne. 2025 May;46(5):287-292. doi: 10.1016/j.revmed.2025.03.424. Epub 2025 May 5.

ABSTRACT

This review describes the role of real-world data (RWD) at each step of drug development for rare diseases like immune thrombocytopenia (ITP) and autoimmune hemolytic anemia (AIHA). We also describe the main sources of RWD in rare diseases and how the generation of real-world evidence (RWE) is crucial for decisions of regulatory health agencies regarding drugs for rare disease.

PMID:40328530 | DOI:10.1016/j.revmed.2025.03.424

JAMA Netw Open. 2025 May 1;8(5):e256908. doi: 10.1001/jamanetworkopen.2025.6908.

ABSTRACT

IMPORTANCE: Current therapeutic approaches are inaccessible to many people with chronic pain and frequently fail to address emotion dysregulation as a key factor in psychological comorbidity and pain intensity. An effective and accessible emotion regulation-focused intervention is needed.

OBJECTIVES: To compare the efficacy of online dialectical behavioral therapy for chronic pain plus treatment as usual (iDBT-Pain) with only treatment as usual on emotion dysregulation in people with chronic pain.

DESIGN, SETTING, AND PARTICIPANTS: This 2-arm randomized clinical trial was conducted from March 2023 to September 2024 in Australia. Participants were adults with chronic pain (lasting ≥3 months) and weekly pain intensity of 3 or higher out of 10 (10 indicating worst pain), without psychotic or personality disorders, and without dementia. Eligible participants were randomly assigned (1:1 ratio) to receive either iDBT-Pain for 9 weeks or treatment as usual only. Intention-to-treat data analyses were performed between August and September 2024.

INTERVENTIONS: The iDBT-Pain group received 8 group-based 90-minute therapist-guided online sessions as well as an app and a handbook for self-learning. Content focused on DBT skills training, including pain science education. Participants in the treatment-as-usual group continued usual care, which consisted of treatment options that can be accessed in the community.

MAIN OUTCOMES AND MEASURES: The primary outcome was emotion dysregulation at 9 weeks after randomization. The Difficulties in Emotion Regulation Scale (score range: 18-90, with higher scores indicating higher emotion dysregulation) was used in assessment.

RESULTS: Among 89 participants (mean [SD] age, 51.5 [14.2] years; 74 females [83%]), 44 (49%) were randomly assigned to the treatment-as-usual group and 45 (51%) were randomly assigned to the iDBT-Pain group. Overall, 79 participants (89%) completed the 9-week assessment. Between-group difference in emotion dysregulation over time favored iDBT-Pain over treatment as usual at 9 weeks (-4.88; 95% CI, -9.20 to -0.55; P = .03; Cohen d = -0.46 [95% CI, -0.87 to -0.08]).

CONCLUSIONS AND RELEVANCE: In this randomized clinical trial, the iDBT-Pain intervention, delivered through a self-learning and therapist-guided hybrid approach, resulted in sustained improvements in emotion dysregulation in people with chronic pain.

TRIAL REGISTRATION: Anzctr.org.au Identifier: ACTRN12622000113752.

PMID:40327344 | PMC:PMC12056567 | DOI:10.1001/jamanetworkopen.2025.6908

Orphanet J Rare Dis. 2025 May 6;20(1):215. doi: 10.1186/s13023-025-03715-2.

ABSTRACT

BACKGROUND: Onasemnogene abeparvovec (OA) is an adeno-associated virus vector-based gene therapy indicated for the treatment of paediatric patients with spinal muscular atrophy(SMA) with biallelic mutations in the survival motor neuron 1 (SMN1) gene. This study focused on analysis of the postmarketing adverse events(AEs) of onasemnogene abeparvovec (OA) reported in the US Food and Drug Administration public data open project (openFDA) database to assess the safety of OA in the real world and to provide a reference for the rational use of this drug in the clinic.

RESULTS: In total, 1,959 AEs were reported with "onasemnogene abeparvovec" as the primary suspected drug. The top 5 most frequent AEs were pyrexia (461 cases), vomiting (434 cases), aspartate aminotransferase increase (284 cases), alanine aminotransferase increase (260 cases), and hepatic enzyme increase (237 cases). A total of 77 alert signals were generated, 60 of which were not included in the drug label. The top 5 signals included troponin I increase ( ROR of 895.21, 95% CI: 734.43-1091.18), troponin T increase ( ROR of 313.30, 95% CI:220.85-444.44), rhinovirus infection ( ROR of 175.80, 95% CI:130.86-236.17), troponin increase ( ROR of 143.49, 95% CI:114.96-179.10), and increased bronchial secretion ( ROR of 142.71, 95% CI:96.63-210.77). Further analysis of AEs associated with gender and age differences identified 14 high-risk signals related to gender and 10 high-risk signals related to age. Female patients should be vigilant for vomiting, thrombotic microangiopathy, increased troponin T, proteinuria, haematuria, haemolytic anaemia, urinary tract infection, generalised oedema, and atypical haemolytic uraemic syndrome. Male patients should be alert to increased hepatic enzyme, increased bronchial secretion, respiratory tract infection, pallor, and increased blood creatine phosphokinase MB. Patients under 2 years of age should be vigilant for lethargy, increased monocyte count, decreased blood creatinine, and decreased neutrophil count. Patients over 2 years of age should be alert to hypertension, haematuria, rhinovirus infection, increased blood creatine phosphokinase, headache, and malaise.

CONCLUSIONS: Mining of OA alert signals using the openFDA database provides supplementary information on AEs not included in the drug label. Clinical attention should be focused on common, strong-signal, and label-unmentioned AEs to optimise medication regimens and control risks in clinical use.

PMID:40329332 | DOI:10.1186/s13023-025-03715-2

Sci Rep. 2025 May 6;15(1):15760. doi: 10.1038/s41598-025-00231-y.

ABSTRACT

This study employs a comprehensive approach to systematically identify drugs associated with Drug-Induced Erectile Dysfunction (DIED) risk and constructs a DIED risk assessment platform. Utilizing the FAERS database, we identified "Erectile Dysfunction," "Organic Erectile Dysfunction," and "Psychogenic Erectile Dysfunction" as relevant Preferred Terms (PTs) for DIED. After excluding patients diagnosed with Erectile Dysfunction (ED), drugs suspected as primary suspects (PS) in ≥ 10 DIP events were selected as target drugs. Through disproportionality analysis, we identified positive signals for these drugs using ROR, PRR, BCPNN, and EBGM. We further assessed the independent effects of positive drugs by adjusting for confounding factors such as age using multivariate logistic regression. Subsequently, we obtained the median onset time and outcome events of DIED for target drugs and compared them by age. The DIED platform is accessible for free at http://116.196.73.86:3838/ADR-DATABASE/DIED/. A total of 67 target drugs were identified as PS in DIED events with 10 or more cases. Based on disproportionality analysis, we further identified 28 drugs with DIED risk signals. Multivariate logistic regression revealed that 23 of these drugs were independent risk factors for DIED (OR > 1 and P < 0.05). Analysis of outcome events showed a significant difference in the median onset time of DIED between different age groups. This study identified 28 drugs associated with DIED risk. We also found some previously unreported DIP risk drugs, including omeprazole, antihypertensive drugs, etc., which should be of clinical concern.

PMID:40328828 | DOI:10.1038/s41598-025-00231-y

Diabetes Res Clin Pract. 2025 May 4:112221. doi: 10.1016/j.diabres.2025.112221. Online ahead of print.

ABSTRACT

Diabetes mellitus (DM) is a highly prevalent chronic condition with significant health and economic impacts; therefore, an accurate diagnosis is essential for the effective management and prevention of its complications. This review explores the latest advances in artificial intelligence (AI) focusing on machine learning (ML) and deep learning (DL) for the diagnosis of diabetes. Recent developments in AI-driven diagnostic tools were analyzed, with an emphasis on breakthrough methodologies and their real-world clinical applications. This review also discusses the role of various data sources, datasets, and preprocessing techniques in enhancing diagnostic accuracy. Key advancements in integrating AI into clinical workflows and improving early detection are highlighted along with challenges related to model interpretability, ethical considerations, and practical implementation. By offering a comprehensive overview of these advancements and their implications, this review contributes significantly to the understanding of how AI technologies can enhance the diagnosis of diabetes and support their integration into clinical practice, thereby aiming to improve patient outcomes and reduce the burden of diabetes.

PMID:40328407 | DOI:10.1016/j.diabres.2025.112221

Radiother Oncol. 2025 May 4:110914. doi: 10.1016/j.radonc.2025.110914. Online ahead of print.

ABSTRACT

PURPOSES: This study aimed to develop a computed tomography (CT)-based multi-organ segmentation model for delineating organs-at-risk (OARs) in pediatric upper abdominal tumors and evaluate its robustness across multiple datasets.

MATERIALS AND METHODS: In-house postoperative CTs from pediatric patients with renal tumors and neuroblastoma (n = 189) and a public dataset (n = 189) with CTs covering thoracoabdominal regions were used. Seventeen OARs were delineated: nine by clinicians (Type 1) and eight using TotalSegmentator (Type 2). Auto-segmentation models were trained using in-house (Model-PMC-UMCU) and a combined dataset of public data (Model-Combined). Performance was assessed with Dice Similarity Coefficient (DSC), 95 % Hausdorff Distance (HD95), and mean surface distance (MSD). Two clinicians rated clinical acceptability on a 5-point Likert scale across 15 patient contours. Model robustness was evaluated against sex, age, intravenous contrast, and tumor type.

RESULTS: Model-PMC-UMCU achieved mean DSC values above 0.95 for five of nine OARs, while the spleen and heart ranged between 0.90 and 0.95. The stomach-bowel and pancreas exhibited DSC values below 0.90. Model-Combined demonstrated improved robustness across both datasets. Clinical evaluation revealed good usability, with both clinicians rating six of nine Type 1 OARs above four and six of eight Type 2 OARs above three. Significant performance differences were only found across age groups in both datasets, specifically in the left lung and pancreas. The 0-2 age group showed the lowest performance.

CONCLUSION: A multi-organ segmentation model was developed, showcasing enhanced robustness when trained on combined datasets. This model is suitable for various OARs and can be applied to multiple datasets in clinical settings.

PMID:40328363 | DOI:10.1016/j.radonc.2025.110914