Clin Transl Med. 2025 Apr;15(4):e70290. doi: 10.1002/ctm2.70290.

ABSTRACT

Single-cell omics has emerged as a powerful tool for elucidating cellular heterogeneity in health and disease. Parallel advances in artificial intelligence (AI), particularly in pattern recognition, feature extraction and predictive modelling, now offer unprecedented opportunities to translate these insights into clinical applications. Here, we propose single-cell -omics-based Disease Predictor through AI (scDisPreAI), a unified framework that leverages AI to integrate single-cell -omics data, enabling robust disease and disease-stage prediction, alongside biomarker discovery. The foundation of scDisPreAI lies in assembling a large, standardised database spanning diverse diseases and multiple disease stages. Rigorous data preprocessing, including normalisation and batch effect correction, ensures that biological rather than technical variation drives downstream models. Machine learning pipelines or deep learning architectures can then be trained in a multi-task fashion, classifying both disease identity and disease stage. Crucially, interpretability techniques such as SHapley Additive exPlanations (SHAP) values or attention weights pinpoint the genes most influential for these predictions, highlighting biomarkers that may be shared across diseases or disease stages. By consolidating predictive modelling with interpretable biomarker identification, scDisPreAI may be deployed as a clinical decision assistant, flagging potential therapeutic targets for drug repurposing and guiding tailored treatments. In this editorial, we propose the technical and methodological roadmap for scDisPreAI and emphasises future directions, including the incorporation of multi-omics, standardised protocols and prospective clinical validation, to fully harness the transformative potential of single-cell AI in precision medicine.

PMID:40170267 | DOI:10.1002/ctm2.70290

Ann Hum Genet. 2025 Apr 2:e12596. doi: 10.1111/ahg.12596. Online ahead of print.

ABSTRACT

Pharmacological responses can vary significantly among patients from different ethnogeographic backgrounds. This variability can, at least in part, be attributed to population-specific genetic patterns in genes involved in drug absorption, distribution, metabolism, and excretion, as well as in genes associated with drug-induced toxicity. Identification of such ethnogeographic variability is thus crucial for the optimization of precise population-specific drug treatments. In this review, we summarize the current knowledge about the clinically actionable pharmacogenetic diversity of genes involved in drug metabolism (CYP2B6, CYP2C8, CYP2C9, CYP2C19, CYP2D6, CYP3A5, DPYD, TPMT, NUDT15, UGT1A1, and NAT2), drug-induced hypersensitivity reactions (HLA-A and HLA-B), and drug-induced acute hemolytic anemia (G6PD). We highlight risk populations with distinct allele frequencies and discuss implications for the customization of treatment. Subsequently, we discuss key challenges and opportunities in population pharmacogenomics, including the importance of considering distinct allele frequency patterns in indigenous or founder populations, interpreting pharmacogenomic response in admixed populations, addressing the investigation bias of the pharmacogenomic literature, and difficulties in including rare and population-specific variants into drug response predictions. The information provided here underscores the critical role of population pharmacogenomics in refining pharmacological treatment strategies and aspires to provide further guidance to maximize the benefits of precision medicine across populations.

PMID:40171627 | DOI:10.1111/ahg.12596

Front Pharmacol. 2025 Mar 18;16:1577547. doi: 10.3389/fphar.2025.1577547. eCollection 2025.

NO ABSTRACT

PMID:40170722 | PMC:PMC11959060 | DOI:10.3389/fphar.2025.1577547

Ann Lab Med. 2025 Apr 2. doi: 10.3343/alm.2024.0652. Online ahead of print.

ABSTRACT

Pharmacogenomics is a rapidly evolving field with a strong foundation in basic science dating back to 1960. Pharmacogenomic findings have been translated into clinical care through collaborative efforts of clinical practitioners, pharmacists, clinical laboratories, and research groups. The methods used have transitioned from targeted genotyping of relatively few variants in individual genes to multiplexed multi-gene panels, and sequencing-based methods are likely on the horizon; however, no system exists for classifying and reporting rare variants identified via sequencing-based approaches. Laboratory testing in pharmacogenomics is complex for several genes, including cytochrome P450 2D6 (CYP2D6), HLA-A, and HLA-B, owing to a high degree of polymorphisms, homology with other genes, and copy-number variation. These loci require specialized methods and familiarity with each gene, which may persist during the transition to next-generation sequencing. Increasing implementation across laboratories and clinical facilities has required cooperative efforts to develop standard testing targets, nomenclature, and reporting practices and guidelines for applying the results clinically. Beyond standardization, harmonization between pharmacogenomics and the broader field of genomic medicine may be essential for facilitating further adoption and realizing the full potential of personalized medicine. In this review, we describe the evolution of clinical laboratory testing for pharmacogenomics, including standardization efforts and the anticipated transition from targeted genotyping to sequencing-based pharmacogenomics. We speculate on potential upcoming developments, including pharmacoepigenetics, improved understanding of the impact of non-coding variants, use of large-scale functional genomics to characterize rare variants, and a renewed interest in polygenic risk or combinatorial approaches, which will drive the progression of the field.

PMID:40170583 | DOI:10.3343/alm.2024.0652

Front Med (Lausanne). 2025 Mar 18;12:1527843. doi: 10.3389/fmed.2025.1527843. eCollection 2025.

ABSTRACT

BACKGROUND: Established morpho-functional chest magnetic resonance imaging (MRI) detects abnormalities in lung morphology and perfusion in people with cystic fibrosis (pwCF) using a dedicated scoring system. Functional assessment is performed using contrast-enhanced (CE) perfusion MRI. Novel matrix pencil decomposition MRI (MP-MRI) is a contrast agent-free alternative, but further validation of this technique is needed.

OBJECTIVES: The aim of this study was to evaluate the applicability of the validated morpho-functional chest MRI score for CE perfusion and MP perfusion MRI in a multireader approach.

METHODS: Twenty-seven pwCF (mean age 20.8 years, range 8.4-45.7 years) underwent morpho-functional MRI including CE perfusion and MP perfusion MRI in the same examination. Nine blinded chest radiologists of different experience levels assessed lung perfusion and applied the validated chest MRI score to CE- and MP-MRI. Inter-reader agreement of perfusion scores in CE- and MP-MRI were compared with each other and with the MRI morphology score. Differences according to the readers' experience were also analyzed.

RESULTS: The CE perfusion scores were overall lower than the MP perfusion scores (6.2 ± 3.3 vs. 6.9 ± 2.0; p < 0.05) with a strong correlation between both perfusion scores (r = 0.74; p < 0.01). The intraclass correlation coefficient (ICC) as measure for inter-reader agreement was good and significant for both perfusion scores, but higher for the CE perfusion score (0.75, p < 0.001) than for MP perfusion scores (0.61, p < 0.001). The Bland-Altman analysis revealed a difference in CE and MP perfusion scores with more extreme values in CE perfusion scores compared to MP perfusion scores (r = 0.62, p < 0.001). The morphology score showed a moderate to good correlation with the CE perfusion score (r = 0.73, p < 0.01) and the MP perfusion score (r = 0.55, p < 0.01). We did not find a difference in scoring according to the radiological experience level.

CONCLUSION: The established chest MRI score can be applied both to validated CE and novel MP perfusion MRI with a good interreader reliability. The remaining difference between CE and MP-MRI scores may be explained by a lack of routine in visual analysis of MP-MRI and may favor an automated analysis for use of MP-MRI as a noninvasive outcome measure.

PMID:40171501 | PMC:PMC11958188 | DOI:10.3389/fmed.2025.1527843

NEJM Catal Innov Care Deliv. 2025 Feb;6(2). doi: 10.1056/CAT.24.0095. Epub 2025 Jan 15.

ABSTRACT

Cystic fibrosis (CF) affects more than 160,000 individuals globally and has seen improved survival rates due to multidisciplinary care models and pharmacotherapy innovations. However, the associated costs remain substantial, prompting the authors to study and evaluate the expense of CF ambulatory care to understand how care structure influences costs. People with CF (PwCF) at large pediatric CF centers in both the United States and Ireland were recruited for parallel observational, prospective studies. Based upon the process of care, the lead clinicians at both sites identified and agreed on three strata of patients (0-11 months, 1-5 years, and 6-17 years of age). Process maps were developed for each of the age cohorts at each site, and the costs of ambulatory care - with emphasis on routine CF clinic visits - were measured utilizing time-driven activity-based costing (TDABC). A dollar-per-minute capacity cost rate (CCR) was calculated for all resources used in the care cycle. The total direct cost was obtained by multiplying the CCR for each resource by the time the resource was used during the patient's care cycle. The cost was summed across all resource types to obtain the cost over the entire care cycle for each site. Service operations were benchmarked to one site and variance analysis was performed. In total, 58 PwCF were included in the analysis (49 in the United States and 9 in Ireland); 4 were 0-11 months, 17 were 1-5 years, and 37 were 6-17 years of age. Physicians (United States) and respiratory consultants (Ireland) had the highest CCRs. Physicians and registered dietitians spent the most time with patients in the United States, compared with the clinical nurse specialists and dietitians in Ireland. The total variance in cost for clinical visits was largest in the 6- to 17-year-old group (28% variance, with 100% in the United States vs. 128% in Ireland). In the 6- to 17-year-old group, the largest drivers in total variance were quantity variance (variance in duration of time spent with patients), which was 108% greater in Ireland); the skill mix variance (variance in clinician type performing service for a given time), which was 49% greater in the United States; and the rate variance (variance in compensation levels across sites), which was 31% greater in the United States. The authors' use of TDABC to characterize the cost of multidisciplinary care during ambulatory clinic visits for PwCF, in combination with variance analysis (the quantitative investigation of the difference between actual and expected costs), provides new and innovative ways to compare costs across similar health care service delivery sites, providing insights into the distinctive features of each. A granular understanding of cost and comparison of resource utilization between centers provides valuable, organizationally relevant insights.

PMID:40171477 | PMC:PMC11960789 | DOI:10.1056/CAT.24.0095

Front Pediatr. 2025 Mar 18;13:1564156. doi: 10.3389/fped.2025.1564156. eCollection 2025.

ABSTRACT

INTRODUCTION: Primary Ciliary Dyskinesia (PCD) is a rare genetic disorder affecting motile cilia, leading to impaired mucociliary clearance and increased susceptibility to respiratory infections. These infections contribute to long-term complications such as bronchiectasis and lung function decline.

OBJECTIVES: This review explores both the acute and long-term impact of respiratory infections in children with PCD, while highlighting the multiple contributors to infection susceptibility. The review also evaluates emerging personalized approaches such as gene and mRNA therapy that hold promise for restoring ciliary function and reducing the burden of acute infections in pediatric PCD.

KEY FINDINGS AND CONCLUSIONS: Acute respiratory infections have a significant impact on morbidity in pediatric PCD, driving progressive airway remodeling. While current treatment strategies focus on managing infections directly, emerging therapies targeting inflammation and genetic causes hold promise for reducing infection burden and improving long-term outcomes. Future advances in personalized medicine could further enhance therapeutic approaches in this population.

PMID:40171169 | PMC:PMC11958984 | DOI:10.3389/fped.2025.1564156

Front Cell Infect Microbiol. 2025 Mar 18;15:1445660. doi: 10.3389/fcimb.2025.1445660. eCollection 2025.

ABSTRACT

Mycobacterium abscessus is a nontuberculous mycobacterium emerging as a significant pathogen in individuals with chronic lung diseases, including cystic fibrosis and chronic obstructive pulmonary disease. Current therapeutics have poor efficacy. Strategies of bacterial control based on host defenses are appealing; however, antimycobacterial immunity remains poorly understood and is further complicated by the appearance of smooth and rough morphotypes, which elicit distinct host responses. We investigated the role of serum components in neutrophil-mediated clearance of M. abscessus morphotypes. M. abscessus opsonization with complement enhanced bacterial killing compared to complement-deficient opsonization. Killing of rough isolates was less reliant on complement. Complement C3 and mannose-binding lectin 2 (MBL2) were deposited on M. abscessus morphotypes in distinct patterns, with a greater association of MBL2 on rough M. abscessus. Killing was dependent on C3; however, depletion and competition experiments indicate that canonical complement activation pathways are not involved. Complement-mediated killing relied on natural IgG and IgM for smooth morphotypes and on IgG for rough morphotypes. Both morphotypes were recognized by complement receptor 3 in a carbohydrate- and calcium-dependent manner. These findings indicate a role for noncanonical C3 activation pathways for M. abscessus clearance by neutrophils and link smooth-to-rough adaptation to complement activation.

PMID:40171164 | PMC:PMC11959001 | DOI:10.3389/fcimb.2025.1445660

Pediatr Pulmonol. 2025 Apr;60(4):e71078. doi: 10.1002/ppul.71078.

ABSTRACT

BACKGROUND: As the life expectancy of people with cystic fibrosis (PwCF) increases, understanding long-term complications, including CF-related bone disease (CFBD), is crucial.

OBJECTIVE: This study aimed to longitudinally characterize CFBD and to compare the bone status of pancreatic sufficient (PS) and pancreatic insufficient (PI) PwCF.

METHODS: This longitudinal analysis included PwCF older than 8 years of age who had at least one dual-energy X-ray absorptiometry test between 2008 and 2021. Data were collected on serum parameters of bone metabolism, nutritional history, habitual activity, and fractures in addition to other demographic and clinical characteristics.

RESULTS: The study included 80 PwCF: 32 (40%) were PS and 48 (60%) PI. Normal dual-energy X-ray absorptiometry results were found in 42 (53%) patients: 16 (50%) in the PS group and 26 (54%) in the PI group (p = 0.72). Three (9%) of the PS group and seven (15%) of the PI group had at least one Z-score below -2 (p = 0.49). The longitudinal bone density decline over a mean of 4.8 years was similar in the two groups. In a logistic regression analysis, pancreatic insufficiency was not found to be a risk factor for CFBD. Female sex was the only significant risk factor for a pathological Z-score.

CONCLUSIONS: The prevalence and severity of CFBD were not found to correlate with pancreatic sufficiency. The similar prevalence of CFBD between patients with PS and PI suggests that screening, and eventually treatment, should be offered to all PwCF, irrespective of pancreatic status.

PMID:40170622 | DOI:10.1002/ppul.71078

Br J Clin Pharmacol. 2025 Apr 2. doi: 10.1002/bcp.70027. Online ahead of print.

ABSTRACT

AIM: Dipeptidyl peptidase-1 (DPP-1) inhibitors have been studied for the treatment of neutrophil-mediated inflammatory diseases including bronchiectasis, bronchial asthma and cystic fibrosis. This study evaluated the pharmacokinetics, pharmacodynamics, safety and tolerability of DPP-1 inhibitor HSK31858 in healthy Chinese volunteers.

METHODS: Volunteers in Part A randomly received single doses of HSK31858 (15, 40, 60 and 80 mg) or placebo in fasted states. The 40-mg cohort also received HSK31858 40 mg or placebo in fed states. In Part B, volunteers randomly received HSK31858 10, 20 and 40 mg or placebo once daily for 28 days in fasted states. The primary endpoints were safety and tolerability of HSK31858.

RESULTS: Among 38 volunteers in Part A and 36 in Part B, HSK31858 was well tolerated; no deaths, serious adverse events, or discontinuations due to adverse events occurred. The median Tmax was 0.75 to 1.0 h and the mean terminal t1/2 was 16.5 to 21.0 h in the fasted state with single doses of HSK31858. Both Cmax and AUC0-t exhibited a dose-dependent rise. Food had no effect on AUC. Multiple doses of HSK31858 demonstrated a similar pharmacokinetics profile, with about 2-fold accumulation in AUC. HSK31858 dose-dependently inhibited neutrophil count-normalized neutrophil elastase (NEnorm) activity. The maximal percentage decrease in NEnorm activity relative to baseline during 28 days of HSK31858 treatments was 13.6% and 76.4% with HSK31858 10 and 40 mg once-daily, respectively.

CONCLUSION: HSK31858 was safe and well tolerated. The pharmacokinetics and pharmacodynamics profile of HSK31858 supports further clinical development for the treatment of neutrophil-mediated inflammatory diseases.

TRIAL REGISTRATION: NCT05663593.

PMID:40170587 | DOI:10.1002/bcp.70027

Ther Adv Respir Dis. 2025 Jan-Dec;19:17534666251329792. doi: 10.1177/17534666251329792. Epub 2025 Apr 1.

NO ABSTRACT

PMID:40170358 | DOI:10.1177/17534666251329792

Front Plant Sci. 2025 Mar 18;16:1498913. doi: 10.3389/fpls.2025.1498913. eCollection 2025.

ABSTRACT

The decline of insect biomass, including pollinators, represents a significant ecological challenge, impacting both biodiversity and ecosystems. Effective monitoring of pollinator habitats, especially floral resources, is essential for addressing this issue. This study connects drone and deep learning technologies to their practical application in ecological research. It focuses on simplifying the application of these technologies. Updating an object detection toolbox to TensorFlow (TF) 2 enhanced performance and ensured compatibility with newer software packages, facilitating access to multiple object recognition models - Faster Region-based Convolutional Neural Network (Faster R-CNN), Single-Shot-Detector (SSD), and EfficientDet. The three object detection models were tested on two datasets of UAV images of flower-rich grasslands, to evaluate their application potential in practice. A practical guide for biologists to apply flower recognition to Unmanned Aerial Vehicle (UAV) imagery is also provided. The results showed that Faster RCNN had the best overall performance with a precision of 89.9% and a recall of 89%, followed by EfficientDet, which excelled in recall but at a lower precision. Notably, EfficientDet demonstrated the lowest model complexity, making it a suitable choice for applications requiring a balance between efficiency and detection performance. Challenges remain, such as detecting flowers in dense vegetation and accounting for environmental variability.

PMID:40171479 | PMC:PMC11959073 | DOI:10.3389/fpls.2025.1498913

Cureus. 2025 Mar 1;17(3):e79871. doi: 10.7759/cureus.79871. eCollection 2025 Mar.

ABSTRACT

Artificial intelligence (AI) has rapidly progressed in the last decade and will inevitably become incorporated into trauma and surgical systems. In such settings, surgeons often need to make high-stakes, time-sensitive, and complex decisions with limited or uncertain information. AI has great potential to augment the pre-operative, intra-operative, and post-operative phases of trauma care. Despite the expeditious advancement of AI, many surgeons lack a foundational understanding of AI terminology, its processes, and potential applications in clinical practice. This narrative review aims to educate general surgeons about the basics of AI, highlight its applications in thoraco-abdominal trauma, and discuss the implications of incorporating its use into the Australian health care system. This review found that studies of AI in trauma care have predominantly focused on machine learning and deep learning applied to diagnostics, risk prediction, and decision-making. Other subfields of AI include natural language processing and computer vision. While AI tools have many potential applications in trauma care, current clinical use is limited. Future prospective, locally validated research is required prior to incorporating AI into clinical practice.

PMID:40171361 | PMC:PMC11958818 | DOI:10.7759/cureus.79871

Front Psychiatry. 2025 Mar 18;16:1452557. doi: 10.3389/fpsyt.2025.1452557. eCollection 2025.

ABSTRACT

Neurological disorders (e.g., Alzheimer's disease and Parkinson's disease) and mental disorders (e.g., depression and anxiety), pose huge challenges to global public health. The pathogenesis of these diseases can usually be attributed to many factors, such as genetic, environmental and socioeconomic status, which make the diagnosis and treatment of the diseases difficult. As research on the diseases advances, so does the body of medical data. The accumulation of such data provides unique opportunities for the basic and clinical study of these diseases, but the vast and diverse nature of the data also make it difficult for physicians and researchers to precisely extract the information and utilize it in their work. A powerful tool to extract the necessary knowledge from large amounts of data is knowledge graph (KG). KG, as an organized form of information, has great potential for the study neurological and mental disorders when it is paired with big data and deep learning technologies. In this study, we reviewed the application of KGs in common neurological and mental disorders in recent years. We also discussed the current state of medical knowledge graphs, highlighting the obstacles and constraints that still need to be overcome.

PMID:40171303 | PMC:PMC11958944 | DOI:10.3389/fpsyt.2025.1452557

Front Oncol. 2025 Mar 18;15:1525650. doi: 10.3389/fonc.2025.1525650. eCollection 2025.

ABSTRACT

In recent years, with the rapid advancement of computer science, artificial intelligence has found extensive applications and has been the subject of significant research within the healthcare industry, particularly in areas such as medical imaging, diagnostics, biomedical engineering, and health data analytics. Artificial intelligence has also made considerable inroads in the diagnosis and treatment of thyroid cancer. This study aims to evaluate the progress, current hotspots, and potential future directions of research on artificial intelligence in the field of thyroid cancer through a bibliometric analysis. This study retrieved literature on the application of artificial intelligence in thyroid cancer from 2004 to 2024 from the Web of Science Core Collection (WoSCC) database. A retrospective bibliometric analysis and visualization study of the filtered data were conducted using VOSviewer, CiteSpace, and the Bibliometrix package in R software. A total of 956 articles from 70 countries/regions were included. China had the highest number of publications, with Shanghai Jiao Tong University (China) being the most prolific research institution. The most prolific author was Wei, X. (n=14), while Haugen, B. R. was the most co-cited author (n=297). The Frontiers in Oncology (35 articles, IF=3.5, Q1) was the most frequently publishing journal, and Thyroid (cited 1,705 times) was the most co-cited journal. Keywords such as 'ultrasound,' 'deep learning,' and 'diagnosis' indicate research hotspots in this field. This study provides a comprehensive exposition of the current advancements, emerging trends, and future directions of artificial intelligence in thyroid cancer research. It serves as a valuable resource for clinicians and researchers, offering a systematic understanding of key focal areas in the field, thereby assisting in the identification and determination of future research trajectories.

PMID:40171256 | PMC:PMC11958942 | DOI:10.3389/fonc.2025.1525650

Front Endocrinol (Lausanne). 2025 Mar 18;16:1485311. doi: 10.3389/fendo.2025.1485311. eCollection 2025.

ABSTRACT

OBJECTIVE: To systematically review and meta-analyze the effectiveness of deep learning algorithms applied to optical coherence tomography (OCT) and retinal images for the detection of diabetic retinopathy (DR).

METHODS: We conducted a comprehensive literature search in multiple databases including PubMed, Cochrane library, Web of Science, Embase and IEEE Xplore up to July 2024. Studies that utilized deep learning techniques for the detection of DR using OCT and retinal images were included. Data extraction and quality assessment were performed independently by two reviewers. Meta-analysis was conducted to determine pooled sensitivity, specificity, and diagnostic odds ratios.

RESULTS: A total of 47 studies were included in the systematic review, 10 were meta-analyzed, encompassing a total of 188268 retinal images and OCT scans. The meta-analysis revealed a pooled sensitivity of 1.88 (95% CI: 1.45-2.44) and a pooled specificity of 1.33 (95% CI: 0.97-1.84) for the detection of DR using deep learning models. All of the outcome of deep learning-based optical coherence tomography ORs ≥0.785, indicating that all included studies with artificial intelligence assistance produced good boosting results.

CONCLUSION: Deep learning-based approaches show high accuracy in detecting diabetic retinopathy from OCT and retinal images, supporting their potential as reliable tools in clinical settings. Future research should focus on standardizing datasets, improving model interpretability, and validating performance across diverse populations.

SYSTEMATIC REVIEW REGISTRATION: https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42024575847.

PMID:40171193 | PMC:PMC11958191 | DOI:10.3389/fendo.2025.1485311

Digit Health. 2025 Mar 31;11:20552076251332999. doi: 10.1177/20552076251332999. eCollection 2025 Jan-Dec.

ABSTRACT

OBJECTIVE: Gait analysis plays a pivotal role in evaluating walking abilities, with recent advancements in digital health stressing the importance of efficient data collection methods. This study aims to classify nine gait types including one normal and eight abnormal gaits, using sequential network-based models and diverse feature combinations obtained from insole sensors.

METHODS: The dataset was collected using insole sensors from subjects performing 15 m walking with designated gait types. The sensors incorporated pressure sensors and inertial measurement units (IMUs), along with the center of pressure engineered from the pressure readings. A number of deep learning architectures were evaluated for their ability to classify the gait types, focusing on feature sets including temporal parameters, statistical features of pressure signals, center of pressure data, and IMU data. Ablation studies were also conducted to assess the impact of combining features from different modalities.

RESULTS: Our results demonstrate that models incorporating IMU features outperform those using different combinations of modalities including individual feature sets, with the top-performing models achieving F1-scores of up to 90% in sample-wise classification and 92% in subject-wise classification. Additionally, an ablation study reveals the importance of considering diverse feature modalities, including temporal parameters, statistical features from pressure signals, center of pressure data, and IMU data, for comprehensive gait classification.

CONCLUSION: Overall, this study successfully developed deep sequential models that effectively classify nine different gait types, with the ablation study underscoring the potential for integrating features from diverse domains to enhance clinical applications, such as intervention for gait-related disorders.

PMID:40171146 | PMC:PMC11960168 | DOI:10.1177/20552076251332999

Front Physiol. 2025 Mar 18;16:1511716. doi: 10.3389/fphys.2025.1511716. eCollection 2025.

ABSTRACT

INTRODUCTION: Lung nodule detection is a crucial task for diagnosis and lung cancer prevention. However, it can be extremely difficult to identify tiny nodules in medical images since pulmonary nodules vary greatly in shape, size, and location. Further, the implemented methods have certain limitations including scalability, robustness, data availability, and false detection rate.

METHODS: To overcome the limitations in the existing techniques, this research proposes the Cnidaria Herd Optimization (CHO) algorithm-enabled Bi-directional Long Short-Term Memory (CHSTM) model for effective lung nodule detection. Furthermore, statistical and texture descriptors extract the significant features that aid in improving the detection accuracy. In addition, the FC2R segmentation model combines the optimized fuzzy C-means clustering algorithm and the Resnet -101 deep learning approach that effectively improves the performance of the model. Specifically, the CHO algorithm is modelled using the combination of the induced movement strategy of krill with the time control mechanism of the cnidaria to find the optimal solution and improve the CHSTM model's performance.

RESULTS: According to the experimental findings of a performance comparison between other established methods, the FC2R + CHSTM model achieves 98.09% sensitivity, 97.71% accuracy, and 97.03% specificity for TP 80 utilizing the LUNA-16 dataset. Utilizing the LIDC/IDRI dataset, the proposed approach attained a high accuracy of 97.59%, sensitivity of 96.77%, and specificity of 98.41% with k-fold validation outperforming the other existing techniques.

CONCLUSION: The proposed FC2R + CHSTM model effectively detects lung nodules with minimum loss and better accuracy.

PMID:40171113 | PMC:PMC11959082 | DOI:10.3389/fphys.2025.1511716

J Appl Crystallogr. 2025 Feb 28;58(Pt 2):513-522. doi: 10.1107/S1600576725000974. eCollection 2025 Apr 1.

ABSTRACT

Recent advancements in X-ray sources and detectors have dramatically increased data generation, leading to a greater demand for automated data processing. This is particularly relevant for real-time grazing-incidence wide-angle X-ray scattering (GIWAXS) experiments which can produce hundreds of thousands of diffraction images in a single day at a synchrotron beamline. Deep learning (DL)-based peak-detection techniques are becoming prominent in this field, but rigorous benchmarking is essential to evaluate their reliability, identify potential problems, explore avenues for improvement and build confidence among researchers for seamless integration into their workflows. However, the systematic evaluation of these techniques has been hampered by the lack of annotated GIWAXS datasets, standardized metrics and baseline models. To address these challenges, we introduce a comprehensive framework comprising an annotated experimental dataset, physics-informed metrics adapted to the GIWAXS geometry and a competitive baseline - a classical, non-DL peak-detection algorithm optimized on our dataset. Furthermore, we apply our framework to benchmark a recent DL solution trained on simulated data and discover its superior performance compared with our baseline. This analysis not only highlights the effectiveness of DL methods for identifying diffraction peaks but also provides insights for further development of these solutions.

PMID:40170972 | PMC:PMC11957406 | DOI:10.1107/S1600576725000974

Stat Biosci. 2025 Apr;17(1):132-150. doi: 10.1007/s12561-023-09394-6. Epub 2023 Oct 28.

ABSTRACT

Estimating treatment effects is of great importance for many biomedical applications with observational data. Particularly, interpretability of the treatment effects is preferable for many biomedical researchers. In this paper, we first provide a theoretical analysis and derive an upper bound for the bias of average treatment effect (ATE) estimation under the strong ignorability assumption. Derived by leveraging appealing properties of the weighted energy distance, our upper bound is tighter than what has been reported in the literature. Motivated by the theoretical analysis, we propose a novel objective function for estimating the ATE that uses the energy distance balancing score and hence does not require the correct specification of the propensity score model. We also leverage recently developed neural additive models to improve interpretability of deep learning models used for potential outcome prediction. We further enhance our proposed model with an energy distance balancing score weighted regularization. The superiority of our proposed model over current state-of-the-art methods is demonstrated in semi-synthetic experiments using two benchmark datasets, namely, IHDP and ACIC, as well as is examined through the study of the effect of smoking on the blood level of cadmium using NHANES.

PMID:40170916 | PMC:PMC11957463 | DOI:10.1007/s12561-023-09394-6