Objective Basis Research Articles

Biomarkers: The Key to Enhancing Deep Brain Stimulation Treatment for Psychiatric Conditions

Background: Deep brain stimulation (DBS) is currently a promising technique for psychiatric patients with severe and treatment-resistant symptoms. However, the results to date have been quite heterogeneous, and the indications for psychosurgery with DBS remain in an experimental phase. One of the major challenges limiting the advancement of DBS in psychiatric disorders is the lack of objective criteria for diagnosing certain conditions, which are often based more on clinical scales rather than measurable biological markers. Additionally, there is a limited capacity to objectively assess treatment outcomes. Methods: This overview examines the literature on the available biomarkers in psychosurgery in relation to DBS, as well as other relevant biomarkers in psychiatry with potential applicability for this treatment modality. Results: There are five types of biomarkers: clinical/behavioral, omic, neuroimaging, electrophysiological, and neurobiochemical. The information provided by each biomarker within these categories is highly variable and may be relevant for diagnosis, response prediction, target selection, program adjustment, etc. Conclusions: A better understanding of biomarkers and their applications would allow DBS in psychosurgery to advance on a more objective basis, guided by the information provided by them and within the context of precision psychiatry.

Chinese-English Translation Strategies for Metaphors Based on Domestication and Foreignization

As an essential rhetorical device in language expression, metaphor deeply reflects the cultural background and social cognition. Metaphor translation needs to convey the meaning of language as well as the cultural connotations behind the metaphor. This study found that when the metaphorical images contain the same symbolic meaning in Chinese and English cultures, applying foreignization to reproduce the original metaphorical images can maintain the uniqueness and writing style of the source text and avoid the loss of cultural connotations in the translation process. Instead, in the case of different metaphorical images, using domestication to replace or omit the original symbolic images in the target language can improve the readability and acceptance of the translation. However, no studies explore applying metaphor translation strategies based on comparing the similarities and differences of metaphors in different languages and cultures, causing subjectivity in selecting metaphor translation strategies. This study compares the symbolic meanings of metaphors in Chinese and English cultures and provides a reliable and objective basis for selecting domestication and foreignization for metaphor translation, which help to achieve more effective faithfulness and cultural transmission. This analysis provides practical references for translation strategies of metaphors and promotes the depth of cross-cultural communication.

Analysis of mRNA expression profile in the treatment of diabetic foot ulcer healing by tibial cortex transverse distraction

To investigate mRNA Expression profile and associated signaling pathways in the treatment of diabetic foot ulcer healing by tibial cortex transverse distraction. Tissue samples were collected from the wound edge before and after the surgery. After reference genome transcriptome sequencing and subsequent bioinformatics analysis, the differentially expressed genes and related pathways were explored, and functional analysis of important genes and pathways was conducted. qRT-PCR was used to verify the significantly expressed genes-HLA-DRB1, HLA-DRB5, CXCL5 and IGFL1. There were 2441 significantly up-regulated and 3904 significantly down-regulated genes in the postoperative group. The qRT-PCR results showed the expression of HLA-DRB1, HLA-DRB5 and CXCL5 was consistent with the transcriptional sequencing results. CXCL5 and CXCL6 differentially up-regulated genes are involved in the process of neovascularization, and HLA-DRB1 is involved in the improvement of the degree of diabetic peripheral nerve degeneration. Pathway analysis showed that differential genes were most significantly enriched in Adherens junction, Inflammatory mediator regulation of TRP channels and Wnt signaling pathway. Inflammatory mediator regulation of TRP channels is involved in the improvement of peripheral neurodegeneration, VEGF signaling pathway is involved in the process of neovascularization, and Wnt signaling pathway is involved in the process of bone healing. Significantly up-regulated CXCL5 and CXCL6 and enriched VEGF signaling pathway analyzed are involved in postoperative lower limb neovascularization. The HLA-DRB1 and the enriched Inflammatory mediator regulation of TRP channels may be related to the improvement of postoperative peripheral neurodegeneration. The differentially expressed genes and related pathways can provide objective basis for further mechanism study.

Diffusion tensor imaging in cerebral small vessel disease applications: opportunities and challenges.

Cerebral small vessel disease (CSVD) is a syndrome of pathology, imaging, and clinical manifestations caused primarily by a variety of functional or structural lesions in the small blood vessels of the brain. CSVD contributes to approximately 45% of dementia and 25% of ischemic strokes worldwide and is one of the most important causes of disability. The disease progresses insidiously, and patients often have no typical symptoms in the early stages, but have an increased risk of stroke, death, and poor long-term prognosis. Therefore, early diagnosis of CSVD is particularly important. Neuroimaging is the most important diagnostic tool used for CSVD. Therefore, it is important to explore the imaging mechanisms of CSVD for its early diagnosis and precise treatment. In this article, we review the principles and analysis methods of DTI, analyze the latest DTI studies on CSVD, clarify the disease-lesion mapping relationships between cerebral white matter (WM) microstructural damage and CSVD, explore the pathogenic mechanisms and preclinical imaging features of CSVD, and summarize the latest research directions of CSVD and research methods to provide a comprehensive and objective imaging basis for the diagnosis and treatment of CSVD.

The value of amide proton transfer imaging in assessing brain damage in patients with obstructive sleep apnea

ObjectiveTo investigate the application value of amide proton transfer (APT) magnetic resonance imaging in evaluating brain damage in patients with obstructive sleep apnea (OSA). Materials and methods49 OSA patients and 25 healthy individuals matched for age and sex were included as case and control groups. All study participants underwent conventional 3D T1WI and APT imaging of the head. The APT values were measured in each of the brain regions of interest (ROI). To compare the differences in APT values of each brain region between the case and control groups, to compare the differences in the efficacy of APT values of each brain region in diagnosing OSA, and to investigate the correlation between APT values of each brain region and Apnea Hypopnea Index (AHI) and minimum blood oxygen saturation. ResultsCompared to the control group, patients with OSA had elevated APT values in several brain regions (P < 0.05), and the diagnostic efficacy of the combined diagnosis of OSA by multiple brain regions is better than that by each brain region alone.Left frontal APT values were positively correlated with AHI in the case group (r = 0.33, P = 0.020).In the case group, the APT values of bilateral frontal lobe, parietal lobe, occipital lobe, left temporal lobe, right thalamus, left internal capsule, left lenticular nucleus, right cerebellar hemisphere and splenium of corpus callosum were negatively correlated with the minimum blood oxygen saturation, and the APT values for each of the above ROIs were positively correlated. ConclusionAPT imaging has a certain value in evaluating brain damage in OSA patients, which may provide a new objective imaging basis for the clinical diagnosis of OSA.

Food allergy in children: treatment challenges and outcome standardization

Relevance. Food allergy (FA) is an important public health concern, particularly among children, with an increasing prevalence. It is associated with a significant decrease in the quality of life for patients and their families due to the need to avoid allergens and the risk of severe allergic reactions, such as anaphylaxis. Despite active research, the primary treatment remains elimination diets, which limit patients’ options and highlight the need for new therapeutic solutions.Aim of the review. This review aims to summarize the current treatment methods for food allergy, discuss the challenges in evaluating the effectiveness of interventions, and highlight the importance of standardizing outcomes in clinical trials to improve comparability and practical relevance.Content. The review discusses modern therapeutic approaches for food allergy, such as oral, epicutaneous, and sublingual immunotherapies, which have shown positive results in achieving tolerance to allergens. Special attention is given to safety concerns, particularly for children, emphasizing the need for further research. The potential use of biological agents, such as omalizumab, in food allergy treatment is also explored. The review addresses challenges in choosing and standardizing endpoints in clinical trials, where most focus on desensitization and immunological markers, while patient-centered outcomes, such as quality of life, remain under-researched. The implementation of “core outcome sets” is highlighted as an important step toward improving data comparability and forming a more objective basis for clinical recommendations.Conclusions. The review emphasizes significant progress in food allergy treatment but notes the need for further research to ensure the safety of new therapies, particularly for children. Standardizing outcomes in clinical trials plays a key role in improving the quality and comparability of research, which will, in turn, help develop more effective clinical guidelines and improve patients’ quality of life.

Using 2D U-Net convolutional neural networks for automatic acetabular and proximal femur segmentation of hip MRI images and morphological quantification: a preliminary study in DDH

BackgroundDevelopmental dysplasia of the hip (DDH) is a common pediatric orthopedic condition characterized by varying degrees of acetabular dysplasia and hip dislocation. Current 2D imaging methods often fail to provide sufficient anatomical detail for effective treatment planning, leading to higher rates of misdiagnosis and missed diagnoses. MRI, with its advantages of being radiation-free, multi-planar, and containing more anatomical information, can provide the crucial morphological and volumetric data needed to evaluate DDH. However, manual techniques for measuring parameters like the center–edge angle (CEA) and acetabular index (AI) are time-consuming. Automating these processes is essential for accurate clinical assessments and personalized treatment strategies.MethodsThis study employed a U-Net-based CNN model to automate the segmentation of hip MRI images in children. The segmentation process was validated using a leave-one-out method during training. Subsequently, the segmented hip joint images were utilized in clinical settings to perform automated measurements of key angles: AI, femoral neck angle (FNA), and CEA. This automated approach aimed to replace manual measurements and provide an objective reference for clinical assessments.ResultsThe U-Net-based network demonstrates high effectiveness in hip segmentation compared to manual radiologist segmentations. In test data, it achieves average DSC values of 0.9109 (acetabulum) and 0.9244 (proximal femur), with a 91.76% segmentation success rate. The average ASD values are 0.3160 mm (acetabulum) and 0.6395 mm (proximal femur) in test data, with Ground Truth (GT) edge points and predicted segmentation maps having a mean distance of less than 1 mm. Using automated segmentation models for clinical hip angle measurements (CEA, AI, FNA) shows no statistical difference compared to manual measurements (p > 0.05).ConclusionUtilizing U-Net-based image segmentation and automated measurement of morphological parameters significantly enhances the accuracy and efficiency of DDH assessment. These methods improve precision in automatic measurements and provide an objective basis for clinical diagnosis and treatment of DDH.

The Inarticulate Few: Agrarian voices during the modernisation of agriculture in Leicestershire 1935–1955

Abstract Leicestershire experienced a uniquely pronounced shift from pastoral to mixed arable agriculture during the Second World War, with changes to farming practice being overseen and enforced by the County War Agricultural Executive Committee. The invasive powers of such Committees have led them to be criticised in recent historiography as an affront to individual freedoms. Opposition and resentment towards these policies would surely be most pronounced where they caused the greatest change – in Leicestershire. This article studies oral testimonies, alongside corresponding farm surveys from the period to provide a more objective basis for comparison, to reveal contemporary farmers did not share the negative historiographical characterisation of wartime policy. By the mid-1950s, agriculture in Leicestershire had embraced the ‘modern’ scientific methods demanded by the committees, but farmers’ recollections of the committee appear to span from favourable to, at worst, ambivalent. They considered the committee’s demands and methods necessary and for the most part, entirely reasonable.

Meta-Reinforcement Learning in Nonstationary and Nonparametric Environments.

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning (meta-RL) addresses this challenge by leveraging knowledge learned from training tasks to perform well in previously unseen tasks. However, current meta-RL approaches limit themselves to narrow parametric and stationary task distributions, ignoring qualitative differences and nonstationary changes between tasks that occur in the real world. In this article, we introduce a Task-Inference-based meta-RL algorithm using explicitly parameterized Gaussian variational autoencoders (VAEs) and gated Recurrent units (TIGR), designed for nonparametric and nonstationary environments. We employ a generative model involving a VAE to capture the multimodality of the tasks. We decouple the policy training from the task-inference learning and efficiently train the inference mechanism on the basis of an unsupervised reconstruction objective. We establish a zero-shot adaptation procedure to enable the agent to adapt to nonstationary task changes. We provide a benchmark with qualitatively distinct tasks based on the half-cheetah environment and demonstrate the superior performance of TIGR compared with state-of-the-art meta-RL approaches in terms of sample efficiency (three to ten times faster), asymptotic performance, and applicability in nonparametric and nonstationary environments with zero-shot adaptation. Videos can be viewed at https://videoviewsite.wixsite.com/tigr.

Association of miR-499 rs3746444, miR-149 rs2292832 polymorphisms and their expression levels with helicobacter pylori-related gastric diseases and Traditional Chinese Medicine syndromes.

To provide an objective experimental basis for the gastric mucosa pathological evolution and the transformation of different Traditional Chinese Medicine (TCM) syndromes in helicobacter pylori (H. pylori)-related gastric diseases (HPGD) patients, based on the combination of TCM syndrome differentiation, molecular biology and histopathology. A total of 203 participants were enrolled in this study. The expressions of miR-499/miR-149 and H. pylori infection in the gastric tissues from all participants were detected. The genotyping for miR-499 rs3746444 and miR-149 rs2292832 was performed. In H. pylori positive subjects, the proportion of precancerous gastric lesions (PGL) in liver-stomach disharmony syndrome (LSDS) group was higher than in spleen Qi deficiency syndrome (SQDS) group (P <0.001); The proportion of gastric cancer (GC) in SQDS group was higher than in spleen-stomach damp-heat syndrome (SSDHS) group and LSDS group (all P <0.001). We also found C allele of miR-149 rs2292832 was linked to lower risk of gastric atrophy [miR-149 rs2292832 C vs T: adjusted odds ratio = 0.207; 95% confidence interval (0.043-0.989); P = 0.048]. Compared with healthy control (HC) group, the expression of miR-499 was significantly increased in GC group, while the expression of miR-149 was significantly decreased in chronic inflammation group, PGL group and GC group (all P < 0.05). Test for trend showed that GC risk was on a rising trend with the increasing expression of miR-499 and decreasing expression of miR-149 (both P for trend < 0.05). The C allele of miR-149 rs2292832 may be a protective factor for gastric mucosal atrophy. H. pylori may participate in the evolution of benign to malignant gastric mucosa lesions by inducing the overexpression of miR-499 and down regulation of miR-149. In addition, patients with H. pylori infection combined SQDS or LSDS may have higher risk of gastric mucosal malignant lesions.

The combination of 18F-fluorodeoxyglucose and 18F 9-fluoropropyl-(+)-dihydrotetrabenazine positron emission tomography for distinguishing between early-onset and late-onset idiopathic Parkinson disease and analyzing influencing factors.

The classification of Parkinson disease by age of onset has proven to be a valuable method for subtyping, given its practical application in clinical settings. However, the interactions between the metabolic brain changes, dopaminergic dysfunction, and clinical manifestations in patients with early-onset (early-iPD) and late-onset (late-iPD) idiopathic Parkinson disease have not been adequately evaluated. Therefore, this study aimed to investigate the difference in cerebral metabolism and presynaptic dopaminergic function between patients with early-iPD and those with late-onset disease using 18F-fluorodeoxyglucose (18F-FDG) and [18F] 9-fluoropropyl-(+)-dihydrotetrabenazine (18F-FP-DTBZ) positron emission tomography (PET). Furthermore, the goal was to further explore the correlation between imaging measurements and clinical manifestations in the early and late idiopathic patients with Parkinson disease. This cross-sectional study included 80 patients with idiopathic Parkinson disease and 29 healthy control participants who underwent 18F-FDG and18F-FP-DTBZ PET imaging at Xuanwu Hospital, Capital Medical University from August 2022 to August 2023. The patients were categorized into early-iPD (n=27) and late-iPD (n=53) groups based on an age threshold of 50 years. The mean standardized uptake value of 18F-FDG and the standardized uptake value ratio (SUVR) of 18F-FP-DTBZ were compared between the early-iPD and late-iPD groups using unpaired Student t-tests. Furthermore, pairwise correlations among cerebral metabolism, dopaminergic function, and corresponding clinical ratings in all patients were conducted using Pearson correlation analysis. Patients with late-iPD exhibited a significant metabolic decrease in the frontal, parietal, and temporal cortex, along with the globus pallidus, putamen, thalamus, and cerebellum, compared to those with early-iPD in 18F-FDG PET imaging (all P values <0.05). Furthermore, the 18F-FP-DTBZ binding potential was significantly lower in the contralateral caudate and anterior putamen of patients with late-iPD compared to those with early-iPD (contralateral caudate: 3.16±1.2 vs. 2.63±0.7, P=0.020; contralateral anterior putamen: 2.49±1.2 vs. 2.05±0.7, P=0.040). Further analysis of the correlations between imaging clinical features revealed that glucose metabolism increases and dopaminergic function decreases with higher motor ratings. 18F-FDG and 18F-FP-DTBZ PET offer an objective molecular imaging basis for distinguishing between early-onset and late-onset idiopathic with Parkinson disease. Additionally, correlation analysis between imaging and clinical data represents a new approach for exploring the potential applications in future studies involving patients with early-iPD and late-iPD.

Research on Construction of Knowledge Base for MRI Equipment Maintenance Based on Knowledge Graph

To improve the level of modern hospital management and establish a scientific and effective medical equipment maintenance guarantee system, this paper proposes the construction of a dynamic interactive fault repair knowledge base system for magnetic resonance imaging (MRI) equipment based on knowledge graph technology. This innovative application of intelligent management for large medical equipment involves collecting and organizing actual maintenance data. The paper constructs the medical equipment maintenance knowledge base, with MRI equipment as a case study, and initially implements functions such as fault information retrieval, technical guidance, and training and learning for MRI equipment. These functions aim to provide an objective decision-making basis for the maintenance and management of large medical equipment, enhance the efficiency of fault repair and maintenance, and elevate the construction level of intelligent hospitals.

From onset to blindness: a comprehensive analysis of RPGR-associated X-linked retinopathy in a large cohort in China

BackgroundVariants in the RPGR are the leading cause of X-linked retinopathies (XLRPs). Further in-depth investigation is needed to understand the natural history.MethodsReview of all case records, molecular genetic testing results,...

Analysing group‐ and metatechnology efficiencies and technology gap of airlines for a sustainable future

AbstractAirline performance evaluation, which involves incorporating sustainable concepts, provides stakeholders and managers with an objective basis for decision‐making. This evaluation considers not only conventional metrics but also environmental impacts, contributing to the advancement of sustainable development goals. This study incorporates a two‐stage network of airline operations, which implies that airlines utilise limited resources to meet their service capacity in the first stage and generate passenger and cargo services alongside carbon emissions in the second stage. The study proposes a union dynamic network data envelopment analysis model, which integrates group technology and meta‐technology into a unified model. This model not only solves the unreasonable technology gap ratio problem but also accounts for the technological heterogeneity (whether or not to participate in a strategic alliance) and the dynamic efficiency of different airlines in the network structure during different operation periods. A sample of 24 global airlines from 2017 to 2019 is used in the study. The empirical results show that the dynamic total meta‐efficiency of the alliance group is significantly greater than that of the nonalliance group over the 3 years. This suggests that joining a strategic alliance has a positive effect on airlines' operational efficiency while reinforcing their commitment to sustainability initiatives.

Analysis Methods for Landscapes and Features of Traditional Villages Based on Digital Technology—The Example of Puping Village in Zhangzhou

Many traditional villages have been degraded to a certain extent due to urbanization and out-of-control management. In addition, due to the lack of recognition and continuation of spatial texture in some village conservation and planning that, in turn, resulting in the gradual disappearance of their distinctive landscape feature. Studying the spatial form of traditional villages helps preserve the authenticity of traditional villages as cultural landscape and inherits traditional historical characteristics. Using Puping Village in Zhangzhou City, Fujian Province as an example, this paper obtains the integrated information data of the village through UAV oblique photography, classifies and extracts the spatial constitution of the traditional village using digital technology, quantitatively analyses it from macroscopic to microscopic, and summarizes the spatial morphology analysis method of the traditional village. The results demonstrate that digital technology can effectively and accurately complete data collection and can provide an objective basis for zoning conservation of traditional villages based on the distinction between new and historic buildings. In addition, digital information collection on the traditional villages landscape features will prepare for the establishment of a database and comparative analysis in the future. We further suggest that digital technology analysis needs to be combined with traditional methods to have a deeper understanding of the formation process of village spatial morphology. The results of the practice in Puping Village show that the use of digital technology can provide a scientific basis for the protection and planning of traditional villages, and that this method is adaptable, which can help to efficiently collect and analyze data on landscape characteristics of other similar villages in China, and support innovative methodologies and technologies for China’s rural revitalization efforts.

Development and internal validation of an artificial intelligence-assisted bowel sounds auscultation system to predict early enteral nutrition-associated diarrhoea in acute pancreatitis: a prospective observational study.

Aims/Background An artificial intelligence-assisted prediction model for enteral nutrition-associated diarrhoea (ENAD) in acute pancreatitis (AP) was developed utilising data obtained from bowel sounds auscultation. This model underwent validation through a single-centre, prospective observational study. The primary objective of the model was to enhance clinical decision-making by providing a more precise assessment of ENAD risk. Methods The study enrolled patients with AP who underwent early enteral nutrition (EN). Real-time collection and analysis of bowel sounds were conducted using an artificial intelligence bowel sounds auscultation system. Univariate analysis, multicollinearity analysis, and logistic regression analysis were employed to identify risk factors associated with ENAD. The random forest algorithm was utilised to establish the prediction model, and partial dependence plots were generated to analyse the impact of risk factors on ENAD risk. Validation of the model was performed using the optimal model Bootstrap resampling method. Predictive performance was assessed using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and an area under the receiver operating characteristic (ROC) curve. Results Among the 133 patients included in the study, the incidence of ENAD was 44.4%. Six risk factors were identified, and the model's accuracy was validated through Bootstrap iterations. The prediction accuracy of the model was 81.10%, with a sensitivity of 84.30% and a specificity of 77.80%. The positive predictive value was 82.60%, and the negative predictive value was 80.10%. The area under the ROC curve was 0.904 (95% confidence interval: 0.817-0.997). Conclusion The artificial intelligence bowel sounds auscultation system enhances the assessment of gastrointestinal function in AP patients undergoing EN and facilitates the construction of an ENAD predictive model. The model demonstrates good predictive efficacy, offering an objective basis for precise intervention timing in ENAD management.

Nomogram model for the diagnosis of solitary nodular pulmonary mucinous adenocarcinoma

The objective of this study was to develop a nomogram model based on the natural progression of tumor and other radiological features to discriminate between solitary nodular pulmonary mucinous adenocarcinoma and non-mucinous adenocarcinomas. A retrospective analysis was conducted on 15,655 cases of lung adenocarcinoma diagnosed at our institution between January 2010 and June 2023. Primary nodular invasive mucinous adenocarcinomas and non-mucinous adenocarcinomas with at least two preoperative CT scans were included. These patients were randomly assigned to training and validation sets. Univariate and multivariate analyses were employed to compare tumor growth rates and clinical radiological characteristics between the two groups in the training set. A nomogram model was constructed based on the results of multivariate analysis. The diagnostic value of the model was evaluated in both the training and validation sets using calibration curves and receiver operating characteristic curves (ROC). The study included 174 patients, with 58 cases of mucinous adenocarcinoma and 116 cases of non-mucinous adenocarcinoma. The nomogram model incorporated the maximum tumor diameter, the consolidation/tumor ratio (CTR), and the specific growth rate (SGR) to generate individual scores for each patient, which were then accumulated to obtain a total score indicative of the likelihood of developing mucinous or non-mucinous adenocarcinoma. The model demonstrated excellent discriminative ability with an area under the receiver operating characteristic curve of 0.784 for the training set and 0.833 for the testing set. The nomogram model developed in this study, integrating SGR with other radiological and clinical parameters, provides a valuable and accurate tool for differentiating between solitary nodular pulmonary mucinous adenocarcinoma and non-mucinous adenocarcinomas. This prognostic model offers a robust and objective basis for personalized management of patients with pulmonary adenocarcinomas.

RGB Color Model: Effect of Color Change on a User in a VR Art Gallery Using Polygraph.

This paper presents computer and color vision research focusing on human color perception in VR environments. A VR art gallery with digital twins of original artworks is created for this experiment. In this research, the field of colorimetry and the application of the L*a*b* and RGB color models are applied. The inter-relationships of the two color models are applied to create a color modification of the VR art gallery environment using C# Script procedures. This color-edited VR environment works with a smooth change in color tone in a given time interval. At the same time, a sudden change in the color of the RGB environment is defined in this interval. This experiment aims to record a user's reaction embedded in a VR environment and the effect of color changes on human perception in a VR environment. This research uses lie detector sensors that record the physiological changes of the user embedded in VR. Five sensors are used to record the signal. An experiment on the influence of the user's color perception in a VR environment using lie detector sensors has never been conducted. This research defines the basic methodology for analyzing and evaluating the recorded signals from the lie detector. The presented text thus provides a basis for further research in the field of colors and human color vision in a VR environment and lays an objective basis for use in many scientific and commercial areas.

A fourfold-objective-based cloud privacy preservation model with proposed association rule hiding and deep learning assisted optimal key generation

ABSTRACT Numerous studies have been conducted in an attempt to preserve cloud privacy, yet the majority of cutting-edge solutions fall short when it comes to handling sensitive data. This research proposes a “privacy preservation model in the cloud environment”. The four stages of recommended security preservation methodology are “identification of sensitive data, generation of an optimal tuned key, suggested data sanitization, and data restoration”. Initially, owner’s data enters the Sensitive data identification process. The sensitive information in the input (owner’s data) is identified via Augmented Dynamic Itemset Counting (ADIC) based Associative Rule Mining Model. Subsequently, the identified sensitive data are sanitized via the newly created tuned key. The generated tuned key is formulated with new fourfold objective-hybrid optimization approach-based deep learning approach. The optimally tuned key is generated with LSTM on the basis of fourfold objectives and the new hybrid MUAOA. The created keys, as well as generated sensitive rules, are fed into the deep learning model. The MUAOA technique is a conceptual blend of standard AOA and CMBO, respectively. As a result, unauthorized people will be unable to access information. Finally, comparative evaluation is undergone and proposed LSTM+MUAOA has achieved higher values on privacy about 5.21 compared to other existing models.

Predicting TCM patterns in PCOS patients: An exploration of feature selection methods and multi-label machine learning models

BackgroundTraditional Chinese Medicine (TCM) offers individualized treatment for Polycystic Ovary Syndrome (PCOS) through pattern differentiation, but the subjectivity of TCM diagnoses can lead to inconsistent outcomes. Integrating machine learning (ML) offers an objective basis to support TCM diagnoses. This study aims to evaluate various feature selection techniques and multi-label ML algorithms to develop an effective predictive model for classifying TCM patterns in PCOS patients, thereby enhancing diagnostic standardization and treatment personalization. MethodsThe study utilized a dataset comprising 432 patients with PCOS, exhibiting one or more of five TCM patterns. Feature selection began with Variance Thresholding (VT), followed by a comparison of five advanced techniques: Statistical Analysis Test, Recursive Feature Elimination with Cross-Validation (RFECV), Least Absolute Shrinkage and Selection Operator Regression, BorutaShap, and ReliefF. To ascertain the most effective model for predicting PCOS TCM patterns, four ML algorithms—Support Vector Machine, Logistic Regression, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks—were evaluated against the identified feature set. ResultsVT reduced the feature count from 224 to 174. RFECV emerged as the most effective feature selection method, identifying 67 key features. XGBoost emerged as the top-performing model, demonstrating superior testing accuracy (0.7870), F1 score (0.9519), and Hamming loss (0.0481) with RFECV-optimized features. ConclusionsThe RFECV-XGBoost model proved effective for classifying TCM patterns in PCOS. It emphasizes the necessity of precise feature selection and the significant capabilities of ML in advancing TCM pattern diagnostics, marking a significant step toward enhancing precise and personalized healthcare in biomedical studies.