Search Results (83)

Background/Objectives: Recurrent meningiomas remain difficult to manage due to the absence of effective systemic therapies and comparatively high treatment failure rates, particularly in high-grade tumors. Stereotactic radiosurgery (SRS) offers a minimally-invasive and precise option, particularly for tumors in surgically complex locations. However, the risks associated with re-irradiation, and recent changes in the WHO classification of CNS tumors highlight the need for more personalized and strategic treatment approaches. This systematic review evaluates the safety, efficacy, and clinical considerations for use of SRS for recurrent meningiomas. Methods: In accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a systematic literature search was conducted using the PubMed, Scopus, and Web of Science databases for studies reporting outcomes of SRS in recurrent, pathologically confirmed intracranial meningiomas. Studies were excluded if they were commentaries, reviews, case reports with fewer than three cases, or had inaccessible full text. The quality and risk of bias of the included studies were assessed using the modified Newcastle-Ottawa Scale. Data on patient and tumor characteristics, SRS treatment parameters, clinical outcomes, adverse effects, and statistical analysis results were extracted. Results: Sixteen studies were included. For WHO Grade I tumors, 3- to 5-year progression-free survival (PFS) ranged from 85% to 100%. Grade II meningiomas demonstrated more variable outcomes, with 3-year PFS ranging from 23% to 100%. Grade III tumors had consistently poorer outcomes, with reported 1-year and 2-year PFS rates as low as 0% and 46%, respectively. SRS performed after surgery alone was associated with superior outcomes, with local control rates of 79% to 100% and 5-year PFS ranging from 40.4% to 91%. In contrast, tumors previously treated with radiotherapy, with or without surgery, showed substantially poorer outcomes, with 3- to 5-year PFS ranging from 26% to 41% and local control rates as low as 31%. Among patients with prior radiotherapy, outcomes were particularly poor in Grade II and III recurrent tumors. Toxicity rates ranged from 3.7% to 37%, and were generally higher for patients with prior radiation. Predictors of worse PFS included prior radiation, older age, and Grade III histology. Conclusions: SRS may represent a reasonable salvage option for carefully selected patients with recurrent meningioma, particularly following surgery alone. Outcomes were notably worse in high-grade recurrent meningiomas following prior radiotherapy, emphasizing the prognostic significance of both histological grade and treatment history. Notably, the lack of molecular and genetic data in most existing studies represents a key limitation in the current literature. Future prospective studies incorporating molecular profiling may improve risk stratification and support more personalized treatment strategies. Full article

Background: Motor imagery (MI) is defined as the cognitive ability to simulate motor movements while suppressing muscular activity. The electroencephalographic (EEG) signals associated with lower limb MI have become essential in brain–computer interface (BCI) research aimed at assisting individuals with motor disabilities. Objective: This systematic review aims to evaluate methodologies for acquiring and processing EEG signals within brain–computer interface (BCI) applications to accurately identify lower limb MI. Methods: A systematic search in Scopus and IEEE Xplore identified 287 records on EEG-based lower-limb MI using artificial intelligence. Following PRISMA guidelines (non-registered), 35 studies met the inclusion criteria after screening and full-text review. Results: Among the selected studies, 85% applied machine or deep learning classifiers such as SVM, CNN, and LSTM, while 65% incorporated multimodal fusion strategies, and 50% implemented decomposition algorithms. These methods improved classification accuracy, signal interpretability, and real-time application potential. Nonetheless, methodological variability and a lack of standardization persist across studies, posing barriers to clinical implementation. Conclusions: AI-based EEG analysis effectively decodes lower-limb motor imagery. Future efforts should focus on harmonizing methods, standardizing datasets, and developing portable systems to improve neurorehabilitation outcomes. This review provides a foundation for advancing MI-based BCIs. Full article

Background: The U.S. Medicare Annual Wellness Visit (AWV) offers a structured opportunity for cognitive screening and personalized prevention planning among older adults. Yet, implementation of AWVs, particularly for individuals with cognitive impairment, remains inconsistent across primary care or other diverse care settings. Methods: We conducted a scoping review using the Consolidated Framework for Implementation Research (CFIR) to explore multilevel factors influencing the implementation of the Medicare AWV’s cognitive screening component, with a focus on how these processes support the detection and management of cognitive impairment among older adults. We searched four databases and screened peer-reviewed studies published between 2011 and March 2025. Searches were conducted in Ovid MEDLINE, PubMed, EBSCOhost, and CINAHL databases. The initial search was completed on 3 January 2024 and updated monthly through 30 March 2025. All retrieved citations were imported into EndNote 21, where duplicates were removed. We screened titles and abstracts for relevance using the predefined inclusion criteria. Full-text articles were then reviewed and scored as either relevant (1) or not relevant (0). Discrepancies were resolved through consensus discussions. To assess the methodological quality of the included studies, we used the Joanna Briggs Institute critical appraisal tools appropriate to each study design. These tools evaluate rigor, trustworthiness, relevance, and risk of bias. We extracted the following data from each included study: Author(s), year, title, and journal; Study type and design; Data collection methods and setting; Sample size and population characteristics; Outcome measures; Intervention details (AWV delivery context); and Reported facilitators, barriers, and outcomes related to AWV implementation. The first two authors independently coded and synthesized all relevant data using a table created in Microsoft Excel. The CFIR guided our data analysis, thematizing our findings into facilitators and barriers across its five domains, viz: (1) Intervention Characteristics, (2) Outer Setting, (3) Inner Setting, (4) Characteristics of Individuals, and (5) Implementation Process. Results: Among 19 included studies, most used quantitative designs and secondary data. Our CFIR-based synthesis revealed that AWV implementation is shaped by interdependent factors across five domains. Key facilitators included AWV adaptability, Electronic Health Record (EHR) integration, team-based workflows, policy alignment (e.g., Accountable Care Organization participation), and provider confidence. Barriers included vague Centers for Medicare and Medicaid Services (CMS) guidance, limited reimbursement, staffing shortages, workflow misalignment, and provider discomfort with cognitive screening. Implementation strategies were often poorly defined or inconsistently applied. Conclusions: Effective AWV delivery for older adults with cognitive impairment requires more than sound policy and intervention design; it demands organizational readiness, structured implementation, and engaged providers. Tailored training, leadership support, and integrated infrastructure are essential. These insights are relevant not only for U.S. Medicare but also for global efforts to integrate dementia-sensitive care into primary health systems. Our study has a few limitations that should be acknowledged. First, our scoping review synthesized findings predominantly from quantitative studies, with only two mixed-method studies and no studies using strictly qualitative methodologies. Second, few studies disaggregated findings by race, ethnicity, or geography, reducing our ability to assess equity-related outcomes. Moreover, few studies provided sufficient detail on the specific cognitive screening instruments used or on the scope and delivery of educational materials for patients and caregivers, limiting generalizability and implementation insights. Third, grey literature and non-peer-reviewed sources were not included. Fourth, although CFIR provided a comprehensive analytic structure, some studies did not explicitly fit in with our implementation frameworks, which required subjective mapping of findings to CFIR domains and may have introduced classification bias. Additionally, although our review did not quantitatively stratify findings by year, we observed that studies from more recent years were more likely to emphasize implementation facilitators (e.g., use of templates, workflow integration), whereas earlier studies often highlighted systemic barriers such as time constraints and provider unfamiliarity with AWV components. Finally, while our review focused specifically on AWV implementation in the United States, we recognize the value of comparative analysis with international contexts. This work was supported by a grant from the National Institute on Aging, National Institutes of Health (Grant No. 1R01AG083102-01; PIs: Tzeng, Kuo, & Raji). Full article

The operational roles of artificial intelligence in energy security remain inconsistently defined across the scientific literature. To address this gap, the present review examines 165 peer-reviewed abstracts published between 2021 and 2025 using a triangulated methodology that combines trigram frequency analysis, manual qualitative coding, and semantic clustering with sentence embeddings. Eight core roles were identified: forecasting and prediction, optimisation of energy systems, renewable energy integration, monitoring and anomaly detection, grid management and stability, energy market operations/trading, cybersecurity, and infrastructure and resource planning. According to the results, the most frequently identified roles, based on the average distribution across all three methods, are forecasting and prediction, optimisation of energy systems, and energy market operations/trading. Roles such as cybersecurity and infrastructure and resource planning appear less frequently and are primarily detected through manual interpretation and semantic clustering. Trigram analysis alone failed to capture these functions due to terminological ambiguity or diffuse expression. However, correlation coefficients indicate high concordance between manual and semantic methods (Spearman’s ρ = 0.91), confirming the robustness of the classification. A structured typology of AI roles supports the development of more coherent analytical frameworks in energy research. Future research incorporating full texts, policy taxonomies, and real-world use cases may help integrate AI more effectively into energy security planning and decision support environments. Full article

Background/Objectives: The rapid development of artificial intelligence is transforming the face of medicine. Due to the large number of imaging studies (pre-, intra-, and postoperative) combined with histopathological and molecular findings, its impact may be particularly significant in neurosurgery. We aimed to perform a scoping review of recent applications of deep learning in MRI-based diagnostics of brain tumors relevant to neurosurgical practice. Methods: We conducted a systematic search of scientific articles available in the PubMed database. The search was performed on 22 April 2024, using the following query: ((MRI) AND (brain tumor)) AND (deep learning). We included original studies that applied deep-learning methods to brain tumor diagnostics using MRI, with potential relevance to neuroradiology or neurosurgery. A total of 893 records were retrieved, and after title/abstract screening and full-text assessment by two independent reviewers, 229 studies met the inclusion criteria. The study was not registered and received no external funding. Results: Most included articles were published after 1 January 2022. The studies primarily focused on developing models to differentiate between specific CNS tumors. With improved radiological analysis, deep-learning technologies can support surgical planning through enhanced visualization of cerebral vessels, white matter tracts, and functional brain areas. Over half of the papers (52%) focused on gliomas, particularly their detection, grading, and molecular characterization. Conclusions: Recent advancements in artificial intelligence methods have enabled differentiation between normal and abnormal CNS imaging, identification of various pathological entities, and, in some cases, precise tumor classification and molecular profiling. These tools show promise in supporting both diagnosis and treatment planning in neurosurgery. Full article

The ship waterjet propulsion system is a crucial power unit for high-performance vessels, and the operational state of its core component, the waterjet pump, is directly related to navigation safety and mission reliability. To enhance the intelligence and accuracy of pump fault diagnosis, this paper proposes a novel diagnostic framework that integrates a supervised autoencoder (SAE) with a large language model (LLM). This framework first employs an SAE to perform task-oriented feature learning on raw vibration signals collected from the pump’s guide vane casing. By jointly optimizing reconstruction and classification losses, the SAE extracts deep features that both represent the original signal information and exhibit high discriminability for different fault classes. Subsequently, the extracted feature vectors are converted into text sequences and fed into an LLM. Leveraging the powerful sequential information processing and generalization capabilities of LLM, end-to-end fault classification is achieved through parameter-efficient fine-tuning. This approach aims to avoid the traditional dependence on manually extracted time-domain and frequency-domain features, instead guiding the feature extraction process via supervised learning to make it more task-specific. To validate the effectiveness of the proposed method, we compare it with a baseline approach that uses manually extracted features. In two experimental scenarios, direct diagnosis with full data and transfer diagnosis under limited-data, cross-condition settings, the proposed method significantly outperforms the baseline in diagnostic accuracy. It demonstrates excellent performance in automated feature extraction, diagnostic precision, and small-sample data adaptability, offering new insights for the application of large-model techniques in critical equipment health management. Full article

Driven by the rapid development of e-commerce and intelligent logistics, the volume of express delivery services has surged, making the efficient and accurate identification of shipping information a core requirement for automatic sorting systems. However, traditional Optical Character Recognition (OCR) technology struggles to meet the accuracy and real-time demands of complex logistics scenarios due to challenges such as image distortion, uneven illumination, and field overlap. This paper proposes a three-level collaborative recognition method based on deep learning that facilitates structured information extraction through regional normalization, dual-path parallel extraction, and a dynamic matching mechanism. First, the geometric distortion associated with contour detection and the lightweight direction classification model has been improved. Second, by integrating the enhanced YOLOv5s for key area localization with the upgraded PaddleOCR for full-text character extraction, a dual-path parallel architecture for positioning and recognition has been constructed. Finally, a dynamic space–semantic joint matching module has been designed that incorporates anti-offset IoU metrics and hierarchical semantic regularization constraints, thereby enhancing matching robustness through density-adaptive weight adjustment. Experimental results indicate that the accuracy of this method on a self-constructed dataset is 89.5%, with an F1 score of 90.1%, representing a 24.2% improvement over traditional OCR methods. The dynamic matching mechanism elevates the average accuracy of YOLOv5s from 78.5% to 89.7%, surpassing the Faster R-CNN benchmark model while maintaining a real-time processing efficiency of 76 FPS. This study offers a lightweight and highly robust solution for the efficient extraction of order information in complex logistics scenarios, significantly advancing the intelligent upgrading of sorting systems. Full article

Background/Objectives: Endometriosis can present as ovarian endometriosis in 15–25% of the cases. While chronic pelvic pain and dysmenorrhea dominate its clinical presentation, acute complications, such as spontaneous OMA rupture, are rare (<3%), often mimicking acute abdominal pain and necessitating emergency surgery. Diagnostic delays persist due to the condition’s rarity and overlapping symptoms with ovarian torsion or appendicitis. This study investigates the clinical features of ruptured OMAs to enhance preoperative suspicion and optimize management. Methods: From February 2011 to August 2023, 14 patients with spontaneous rupture of histologically confirmed endometriomas underwent emergency laparoscopy for acute abdominal pain in the University Hospital of Bern, Switzerland. The clinical data of these patients were analyzed to find common patterns of spontaneous endometrioma ruptures. We also conducted a literature search in PubMed, Scopus, ScienceDirect, Cochrane, and Embase databases from inception to December 2023 in order to identify other possible confounding factors. The search was based on the keywords “ruptured endometrioma”. All English full-text prospective and retrospective observational and interventional studies with at least five patients that described the clinical features and findings of women diagnosed with ruptured endometrioma and treated surgically were included. Results: The median age at operation was 37.4 (23–49) years old, and all cases presented with acute abdominal pain, with/without peritonitis. Only 3/14 patients presented with fever, while the most common laboratory finding was an elevated CRP level of 45.6 mg/L (3–100 mg/L), while leukocytosis was less pronounced, with a median of 12.2 G/L (6.04–21.4 G/L). Notably, 64.3% (9 out of 14) of the patients reported experiencing dysmenorrhea, while for the remaining 5 individuals, the presence or absence of dysmenorrhea could not be obtained. Interestingly, only one patient had undergone hormonal treatment, with a combined oral contraceptive (COC) of Ethinylestradiol (0.02 mg) and Desogestrel (0.15 mg), while the other patients either lacked awareness of their endometriosis or expressed reluctance towards hormonal downregulation therapy. The median endometrioma size was 7 cm (3.5–18 cm), and 78.57% of the cases (11 out of 14 patients) had only ovarian endometriosis, while only 3 patients had involvement of compartment A, B, or C according to the # ENZIAN classification. Conclusions: Though rare, spontaneous OMA rupture should be considered in acute abdomen cases, especially with cysts > 5 cm. Hormonal therapy may reduce rupture risk, but more research is needed to confirm this and refine diagnostic strategies. Full article

Background/Objectives: Pathogenic variants in the growth differentiation factor 2 (GDF2) gene have been linked to a hereditary hemorrhagic telangiectasia (HHT)-like syndrome, yet their clinical significance remains under investigation. This study reports seven pediatric patients with GDF2 variants from a single center. Methods: We identified children with GDF2 pathogenic variants and variants of uncertain significance (VUS) from the Children’s Hospital of Philadelphia Comprehensive HHT Program and cross-referenced the list with a full-text query by GDF2 gene name on >53,000,000 visits to ensure complete ascertainment. Medical records were reviewed retrospectively, and variables of interest were abstracted. Results: The median age at genetic testing was 12 years (range 1.75–16). Reasons for genetic testing included telangiectasias, pulmonary hypertension, familial testing, respiratory symptoms, seizures, developmental disabilities, and lung arteriovenous malformations (AVMs). Four patients had missense VUS, including two novel VUS (c.34C>G; p.Leu12Val, c.41C>T; p.Ser14Phe), while three had pathogenic deletions. All patients experienced epistaxis, starting at a median age of 6 years (range 2–12). Three had telangiectasias. One patient had both a GDF2 VUS and a de novo partial endoglin (ENG) gene deletion. While this patient’s symptoms of HHT are likely related to her ENG variant, synergy cannot be excluded, and two first-degree family members with clinically significant epistaxis also have the same GDF2 VUS. Notably, two patients had visceral AVMs—one with a lung AVM and another with a vein of Galen malformation. Conclusions: Interpretation of GDF2 VUS and their relationship to clinical symptoms is challenging given the rarity of these genetic variants and the inadequate diagnostic utility of the current clinical criteria for HHT in the pediatric population. Further research with larger cohorts is necessary to improve the genotype–phenotype correlation in GDF2-related HHT. Carefully collected clinical information with longitudinal follow-up may also assist in refining classification of GDF2 VUS as benign or pathogenic in the future. Full article

With the increasing adoption of digital governance and big data analytics, the quality of government hotline data significantly affects urban governance and public service efficiency. However, existing methods for assessing data record standards focus predominantly on structured data, exhibiting notable inadequacies in handling the complexities inherent in unstructured or semi-structured textual hotline records. To address these shortcomings, this study develops a comprehensive scoring method tailored for evaluating multi-dimensional data record standards in government hotline data. By integrating advanced deep learning models, we systematically analyze six evaluation indicators: classification predictability, dispatch accuracy, record correctness, address accuracy, adjacent sentence similarity, and full-text similarity. Empirical analysis reveals a significant positive correlation between improved data record standards and higher work order completion rates, particularly highlighting the crucial role of semantic-related indicators (classification predictability and adjacent sentence similarity). Furthermore, the results indicate that the work order field strengthens the positive impact of data standards on completion rates, whereas variations in departmental data-handling capabilities weaken this relationship. This study addresses existing inadequacies by proposing a novel scoring method emphasizing semantic measures and provides practical recommendations—including standardized language usage, intelligent analytic support, and targeted staff training—to effectively enhance urban governance. Full article

Due to the poor quality of current water consumption data and the frequent absence of industry information, accurately calculating the water consumption for different industries is difficult. Therefore, we propose a BERT-GCN model based on a strong link graph for classification within the water industry. First, we constructed a co-word relation graph based on the typical industry characteristics keywords extracted by the TF-IDF and extracted co-word relation features using a graph convolutional network (GCN). Then the web crawler was utilized to collect the main business data of the enterprise as additional information, and the semantic features were extracted from the supplementary information by the pre-trained language model BERT. Finally, we connected the semantic features with the co-word relation features to obtain the enhanced feature vector of the enterprise for the classification of the enterprise through the full connection layer. The experimental results in Xiuzhou District and Zhuji City show that compared with TextCNN, BERT-FC, TextGCN and Word2Vec-GCN models, the BERT-GCN has the best performance in classification evaluation indicators of precision, recall and F1-score. The relevant research provides technical and theoretical guidance for the government to carry out dynamic, rapid and accurate management of the water conservancy industry. Full article

Thyroid Cancer (TC) is one of the most prevalent endocrine malignancies, with early detection being critical for patient management. The motivation for integrating Machine Learning (ML) in thyroid cancer research stems from the limitations of conventional diagnostic and monitoring approaches, as ML offers transformative potential for reducing human errors and improving prediction outcomes for diagnostic accuracy, risk stratification, treatment options, recurrence prognosis, and patient quality of life. This scoping review maps existing literature on ML applications in TC, particularly those leveraging clinical data, Electronic Medical Records (EMRs), and synthesized findings. This study analyzed 1231 papers, evaluated 203 full-text articles, selected 21 articles, and detailed three themes: (1) malignancy prediction and nodule classification; (2) other metastases derived from TC prediction; and (3) recurrence and survival prediction. This work examined the case studies’ characteristics and objectives and identified key trends and challenges in ML-driven TC research. Finally, this scoping review addressed the limitations of related and highlighted directions to enhance the clinical potential of ML in this domain while emphasizing its capability to transform TC patient care into advanced precision medicine. Full article

Background: Kidney transplantation (KTx) is a safe procedure that improves the life expectancy and quality of life of patients requiring it. However, despite the known benefits for patients who receive a kidney transplant, non-adherence to immunosuppressive medication is an unsolved problem, reflected mainly by graft rejection. Objective: The aim of this study is to systematically review the existing literature on adherence factors to medication after renal transplantation. Methods: A systematic literature review of studies published since 2010 was conducted in three databases. Records for the search were limited to publications from 2010 to 2024, available in full-text. The search was carried out in July 2024. In total, 2632 abstracts were downloaded from the different databases. Inclusion criteria were papers of any type (quantitative or qualitative) whose objective was the identification of predictors of adherence for patients who were prescribed immunosuppressive medication after kidney transplantation. Results: The predictors of adherence to treatment found in the systematic review were grouped into the following categories of the World Health Organization classification: socio-economic factors, factors related to the treatment/therapy, patient-related factors, disease-related factors, and health care system factors. Most of the studies were excluded, and in the end, 30 were included in the final analysis. According to these studies, a set of strong predictors was identified, but discrepancies among the variables of gender in young patients, pre-emptive transplantation, and the time of the transplantation were detected. Conclusions: In this study, we identified specific predictors and directions for the association of those predictors with adherence to immunosuppressive medication for patients after KTx. Further research should consider conducting reviews for different patient sub-groups on medication adherence and the development and validation of a screening instrument for adherence/non-adherence factors that clinicians could use as a detection tool for subjects at risk of low adherence. Full article

Dietary choices, especially vegetarianism, have attracted much attention lately due to their potential effects on the environment, human health, and morality. Despite this, public discourse on vegetarianism in Russian-language contexts remains underexplored. This paper introduces VegRuCorpus, a novel, manually annotated dataset of Russian-language social media texts expressing opinions on vegetarianism. Through extensive experimentation, we demonstrate that contrastive learning significantly outperforms traditional machine learning and fine-tuned transformer models, achieving the best classification performance for distinguishing pro- and anti-vegetarian opinions. While traditional models perform competitively using syntactic and semantic representations and fine-tuned transformers show promise, our findings highlight the need for task-specific data to unlock their full potential. By providing a new dataset and insights into model performance, this work advances opinion mining and contributes to understanding nutritional health discourse in Russia. Full article

Prompt tuning is a mainstream technique for fine-tuning large language models (LLMs), offering minimal parameter adjustments by learning task-specific prompt vectors. However, it suffers from training costs due to network-wide backpropagation and weaker performance compared to methods like adapters and LoRA, likely due to the limited capacity of soft prompts to encode task-specific information. This study introduces Late Inception Prompt Tuning (LIPT), a novel approach to soft prompt learning that enhances performance and efficiency by shortening backpropagation paths and employing a multidimensional bottleneck network with greater capacity. LIPT surpasses existing prompt tuning techniques on various benchmark tasks, delivering a 1.3% gain over LPT and a 5% improvement compared to standard prompt tuning when applied to RoBERTa-large, while converging more rapidly. It achieves an average accuracy of 90% across ten benchmark datasets. Notably, in certain scenarios, LIPT’s performance approaches that of full-parameter fine-tuning methods. To evaluate parameter-efficient fine-tuning (PEFT) comprehensively, we propose an Efficiency Indicator (EI) that balances accuracy and cost. LIPT is well suited for natural language understanding tasks, like sentiment analysis and text classification, with potential extensions to larger-scale models and tasks like text generation. This framework advances the scalability and practicality of fine-tuning methods for diverse applications. Full article