Diagnosis of mental disorders using machine learning: Literature review and bibliometric mapping from 2012 to 2023.

Background: Mental disorders (MDs) are becoming a leading burden in non-communicable diseases (NCDs). As per the World Health Organization's 2022 assessment report, there was a steep increase of 25 % in MDs during the COVID-19 pandemic. Early diagnosis of MDs can significantly improve treatment outcome and save disability-adjusted life years (DALYs). In recent times, the application of machine learning (ML) and deep learning (DL)) has shown promising results in the diagnosis of MDs, and the field has witnessed a huge research output in the form of research publications. Therefore, a bibliometric mapping along with a review of recent advancements is required. Methods: This study presents a bibliometric analysis and review of the research, published over the last 10 years. Literature searches were conducted in the Scopus database for the period from January 1, 2012, to June 9, 2023. The data was filtered and screened to include only relevant and reliable publications. A total of 2811 journal articles were found. The data was exported to a comma-separated value (CSV) format for further analysis. Furthermore, a review of 40 selected studies was performed. Results: The popularity of ML techniques in diagnosing MDs has been growing, with an annual research growth rate of 17.05 %. The Journal of Affective Disorders published the most documents (n = 97), while Wang Y. (n = 64) has published the most articles. Lotka's law is observed, with a minority of authors contributing the majority of publications. The top affiliating institutes are the West China Hospital of Sichuan University followed by the University of California, with China and the US dominating the top 10 institutes. While China has more publications, papers affiliated with the US receive more citations. Depression and schizophrenia are the primary focuses of ML and deep learning (DL) in mental disease detection. Co-occurrence network analysis reveals that ML is associated with depression, schizophrenia, autism, anxiety, ADHD, obsessive-compulsive disorder, and PTSD. Popular algorithms include support vector machine (SVM) classifier, decision tree classifier, and random forest classifier. Furthermore, DL is linked to neuroimaging techniques such as MRI, fMRI, and EEG, as well as bipolar disorder. Current research trends encompass DL, LSTM, generalized anxiety disorder, feature fusion, and convolutional neural networks.

Comprehensive assessment of machine learning methods for diagnosing gastrointestinal diseases through whole metagenome sequencing data.

The gut microbiome, linked significantly to host diseases, offers potential for disease diagnosis through machine learning (ML) pipelines. These pipelines, crucial in modeling diseases using high-dimensional microbiome data, involve selecting profile modalities, data preprocessing techniques, and classification algorithms, each impacting the model accuracy and generalizability. Despite whole metagenome shotgun sequencing (WMS) gaining popularity for human gut microbiome profiling, a consensus on the optimal methods for ML pipelines in disease diagnosis using WMS data remains elusive. Addressing this gap, we comprehensively evaluated ML methods for diagnosing Crohn's disease and colorectal cancer, using 2,553 fecal WMS samples from 21 case-control studies. Our study uncovered crucial insights: gut-specific, species-level taxonomic features proved to be the most effective for profiling; batch correction was not consistently beneficial for model performance; compositional data transformations markedly improved the models; and while nonlinear ensemble classification algorithms typically offered superior performance, linear models with proper regularization were found to be more effective for diseases that are linearly separable based on microbiome data. An optimal ML pipeline, integrating the most effective methods, was validated for generalizability using holdout data. This research offers practical guidelines for constructing reliable disease diagnostic ML models with fecal WMS data.

Unpaired fundus image enhancement based on constrained generative adversarial networks.

Fundus photography (FP) is a crucial technique for diagnosing the progression of ocular and systemic diseases in clinical studies, with wide applications in early clinical screening and diagnosis. However, due to the nonuniform illumination and imbalanced intensity caused by various reasons, the quality of fundus images is often severely weakened, brings challenges for automated screening, analysis, and diagnosis of diseases. To resolve this problem, we developed strongly constrained generative adversarial networks (SCGAN). The results demonstrate that the quality of various datasets were more significantly enhanced based on SCGAN, simultaneously more effectively retaining tissue and vascular information under various experimental conditions. Furthermore, the clinical effectiveness and robustness of this model were validated by showing its improved ability in vascular segmentation as well as disease diagnosis. Our study provides a new comprehensive approach for FP and also possesses the potential capacity to advance artificial intelligence-assisted ophthalmic examination.

Design of application-oriented disease diagnosis model using a meta-heuristic algorithm.

BACKGROUND: Healthcare is crucial to patient care because it provides vital services for maintaining and restoring health. As healthcare technology evolves, cutting-edge tools facilitate faster diagnosis and more effective patient treatment. In the present age of pandemics, the Internet of Things (IoT) offers a potential solution to the problem of patient safety monitoring by creating a massive quantity of data about the patient through the linked devices around them and then analyzing it to estimate the patient's current status. Utilizing the IoT-based meta-heuristic algorithm allows patients to be remotely monitored, resulting in timely diagnosis and improved care. Meta-heuristic algorithms are successful, resilient, and effective in solving real-world enhancement, clustering, predicting, and grouping. Healthcare organizations need an efficient method for dealing with big data since the prevalence of such data makes it challenging to analyze for diagnosis. The current techniques used in medical diagnostics have limitations due to imbalanced data and the overfitting issue. OBJECTIVE: This study introduces the particle swarm optimization and convolutional neural network to be used as a meta-heuristic optimization method for extensive data analysis in the IoT to monitor patients' health conditions. METHOD: Particle Swarm Optimization is used to optimize the data used in the study. Information for a diabetes diagnosis model that includes cardiac risk forecasting is collected. Particle Swarm Optimization and Convolutional Neural Networks (PSO-CNN) results effectively make illness predictions. Support Vector Machine has been used to predict the possibility of a heart attack based on the classification of the collected data into projected abnormal and normal ranges for diabetes. RESULTS: The results of the simulations reveal that the PSO-CNN model used to predict diabetic disease increased in accuracy by 92.6%, precision by 92.5%, recall by 93.2%, F1-score by 94.2%, and quantization error by 4.1%. CONCLUSION: The suggested approach could be applied to identify cancer cells.

A Comprehensive Review of AI Diagnosis Strategies for Age-Related Macular Degeneration (AMD).

The rapid advancement of computational infrastructure has led to unprecedented growth in machine learning, deep learning, and computer vision, fundamentally transforming the analysis of retinal images. By utilizing a wide array of visual cues extracted from retinal fundus images, sophisticated artificial intelligence models have been developed to diagnose various retinal disorders. This paper concentrates on the detection of Age-Related Macular Degeneration (AMD), a significant retinal condition, by offering an exhaustive examination of recent machine learning and deep learning methodologies. Additionally, it discusses potential obstacles and constraints associated with implementing this technology in the field of ophthalmology. Through a systematic review, this research aims to assess the efficacy of machine learning and deep learning techniques in discerning AMD from different modalities as they have shown promise in the field of AMD and retinal disorders diagnosis. Organized around prevalent datasets and imaging techniques, the paper initially outlines assessment criteria, image preprocessing methodologies, and learning frameworks before conducting a thorough investigation of diverse approaches for AMD detection. Drawing insights from the analysis of more than 30 selected studies, the conclusion underscores current research trajectories, major challenges, and future prospects in AMD diagnosis, providing a valuable resource for both scholars and practitioners in the domain.

Analysis of optical properties and response mechanism of H2S fluorescent probe based on rhodamine derivatives.

H2S plays a crucial role in numerous physiological and pathological processes. In this project, a new fluorescent probe, SG-H2S, for the detection of H2S, was developed by introducing the recognition group 2,4-dinitrophenyl ether. The combination of rhodamine derivatives can produce both colorimetric reactions and fluorescence reactions. Compared with the current H2S probes, the main advantages of SG-H2S are its wide pH range (5-9), fast response (30 min), and high selectivity in competitive species (including biological mercaptan). The probe SG-H2S has low cytotoxicity and has been successfully applied to imaging in MCF-7 cells, HeLa cells, and BALB/c nude mice. We hope that SG-H2S will provide a vital method for the field of biology.

Non-invasive hepatic fat quantification: Can multi-echo Dixon help?

Objective: To evaluate the diagnostic accuracy of multi-echo Dixon magnetic resonance imaging (MRI) in hepatic fat quantification, in comparison with that of magnetic resonance spectroscopy (MRS), on 3.0-T MRI. Materials and Methods: Fifty-five adults with no known liver disease underwent MRI in a 3.0-T scanner for determination of the hepatic fat fraction, with two techniques: multi-echo Dixon, in a manually drawn region of interest (ROI) and in the entire liver parenchyma (automated segmentation); and MRS. The diagnostic accuracy and cutoff value for multi-echo Dixon were determined, with MRS being used as the reference standard. Results: The mean fat fraction obtained by multi-echo Dixon in the manually drawn ROI and in the entire liver was 5.2 ± 5.8% and 6.6 ± 5.2%, respectively, whereas the mean hepatic fat fraction obtained by MRS was 5.7 ± 6.4%. A very strong positive correlation and good agreement were observed between MRS and multi-echo Dixon, for the ROI (r = 0.988, r2 = 0.978, p < 0.001) and for the entire liver parenchyma (r = 0.960, r2 = 0.922, p < 0.001). A moderate positive correlation was observed between the hepatic fat fraction and body mass index of the participants, regardless of the fat estimation technique employed. Conclusion: For hepatic fat quantification, multi-echo Dixon MRI demonstrated a very strong positive correlation and good agreement with MRS (often considered the gold-standard noninvasive technique). Because multi-echo Dixon MRI is more readily available than is MRS, it can be used as a rapid tool for hepatic fat quantification, especially when the hepatic fat distribution is not homogeneous.

Objetivo: Avaliar a acurácia diagnóstica da técnica multieco Dixon na quantificação da gordura hepática em comparação com a espectroscopia por ressonância magnética (ERM), em exames de RM 3.0-T. Materiais e Métodos: Cinquenta e cinco participantes adultos sem doença hepática conhecida foram submetidos a RM 3.0-T para determinação da fração de gordura hepática, usando duas técnicas: multieco Dixon (em ROI desenhada manualmente e em segmentação automatizada para todo o parênquima hepático) e ERM. A precisão diagnóstica e o valor de corte para multieco Dixon foram determinados usando a ERM como padrão de referência. Resultados: A fração de gordura média usando multieco Dixon na ROI desenhada manualmente e na segmentação automatizada do fígado inteiro foi 5,2 ± 5,8% e 6,6 ± 5,2%, respectivamente. A fração de gordura hepática média usando ERM foi 5,7 ± 6,4%. Correlação positiva muito alta e forte concordância foram observadas entre ERM e multieco Dixon, tanto para ROI (r = 0,988, r2 = 0,978, p < 0,001) quanto para todo o parênquima hepático (r = 0,960, r2 = 0,922, p < 0,001). Correlação positiva moderada foi observada entre a fração de gordura hepática e o índice de massa corpórea dos participantes usando ambas as técnicas de estimativa de gordura. Conclusão: Multieco Dixon demonstrou correlação positiva muito alta e concordância com a ERM (muitas vezes considerada padrão de referência não invasivo) para quantificação de gordura hepática. Uma vez que o multieco Dixon está mais prontamente disponível do que a ERM, pode ser usado como uma ferramenta rápida para a quantificação da gordura hepática, especialmente na distribuição não homogênea da gordura.

Artificial Intelligence in Metabolomics: A Current Review.

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

RPA-CRISPR/Cas12a-mediated isothermal amplification for rapid detection of Phytopythium helicoides.

Phytopythium helicoides, which belongs to the algae (Chromista), Oomycota, Pythiales, Pythiaceae and Phytophthora, is a quarantine pathogen that causes brown rot of fruits, stem rot and root rot, along with other symptoms that can damage several tree species in urban landscaping. Therefore, disease management requires rapid and accurate diagnosis. The present study used recombinase polymerase amplification (RPA) in conjunction with the CRISPR/Cas12a system to identify P. helicoides. The test exhibited high specificity and sensitivity and could detect 10 pg.µL-1 of P. helicoides genomic DNA at 37 ℃ within 20 minutes. The test results were visible by excitation of fluorophores by blue light. This groundbreaking test is able to detect P. helicoides in artificially inoculated Rhododendron leaves. The RPA-CRISPR/Cas12a detection assay developed in this study is characterized by its sensitivity, efficiency, and convenience. Early detection and control of P. helicoides is crucial for the protection of urban green cover species.

Direct and Rapid Visualization of the Spatial Distribution of Cholesterol in Alzheimer's and Cancer Tissue via MALDI Mass Spectrometry Imaging.

Cholesterol is a vital component of the central nervous system and tissues, and understanding its spatial distribution is crucial for biology, pathophysiology, and diagnostics. However, direct imaging of cholesterol using matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) remains challenging and time-consuming due to the difficulty in ionizing the sterol molecule. To tackle this issue, a MALDI-MSI method is established for direct and rapid analysis of the spatial distribution of cholesterol in Alzheimer's disease (AD), different cancer tissues and organs via MALDI-MSI. This excellent imaging performance depends on the study and systemic optimization of various conditions that affect the imaging of MALDI-MSI. In this case, we report the distribution and levels of cholesterol across specific structures of the AD mouse brain and different tumor tissue and organs. According to the results, the content of cholesterol in the AD mouse cerebellum, especially in the arborvitae, was significantly higher than that in the wild type (WT) model. Furthermore, we successfully visualize the distribution of cholesterol in other organs, such as the heart, liver, spleen, kidney, pancreas, as well as tumor tissues parenchyma and interstitium using MALDI-MSI. Notably, the attribution of cholesterol MS/MS hydrocarbon fragments was systematically investigated. Our presented optimization strategy and established MALDI-MSI method can be easily generalized for different animal tissues or live samples, thereby facilitating the potential for applications of MALDI-MSI in clinical, medical and biological research.

Extended dipeptide composition framework for accurate identification of anticancer peptides.

The identification of anticancer peptides (ACPs) is crucial, especially in the development of peptide-based cancer therapy. The classical models such as Split Amino Acid Composition (SAAC) and Pseudo Amino Acid Composition (PseAAC) lack the incorporation of feature representation. These advancements improve the predictive accuracy and efficiency of ACP identification. Thus, the effort of this research is to propose and develop an advanced framework based on feature extraction. Thus, to achieve this objective herein we propose an Extended Dipeptide Composition (EDPC) framework. The proposed EDPC framework extends the dipeptide composition by considering the local sequence environment information and reforming the CD-HIT framework to remove noise and redundancy. To measure the accuracy, we have performed several experiments. These experiments were employed using four famous machine learning (ML) algorithms named; Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and K Nearest Neighbor (KNN). For comparisons, we have used accuracy, specificity, sensitivity, precision, recall, and F1-Score as evaluation criteria. The reliability of the proposed framework is further evaluated using statistical significance tests. As a result, the proposed EDPC framework exhibited enhanced performance than SAAC and PseAAC, where the SVM model delivered the highest accuracy of 96. 6% and significant enhancements in specificity, sensitivity, precision, and F1-score over multiple datasets. Due to the incorporation of enhanced feature representation and the incorporation of local and global sequence profiles proposed EDPC achieves higher classification performance. The proposed frameworks can deal with noise and also duplicating features. These are accompanied by a wide range of feature representations. Finally, our proposed framework can be used for clinical applications where ACP identification is essential. Future works will include extending to a larger variety of datasets, incorporating tertiary structural information, and using deep learning techniques to improve the proposed EDPC.

Advances in Vascular Imaging: A Comparative Analysis of Doppler Ultrasound and Multidetector CT for Lower Limb Peripheral Arterial Disease Diagnosis.

Background This study explores the comparison between Doppler ultrasound and multidetector CT angiography (MDCTA) in diagnosing peripheral arterial disease (PAD), emphasizing the urgent need for precise and minimally invasive methodologies in vascular medicine. PAD, stemming from atherosclerosis, manifests as reduced blood flow and symptoms, such as claudication, requiring timely and accurate diagnosis for optimal treatment outcomes. Doppler ultrasound emerges as an option, offering a non-invasive and cost-effective approach. Conversely, MDCTA provides intricate images, albeit with associated risks, such as radiation exposure and potential complications from contrast agents. This research rigorously evaluates the efficacy, safety, and cost-efficiency of these modalities, aiming to provide clinicians with valuable insights for informed decision-making, ultimately enhancing standards of patient care. Methodology In this prospective study conducted at Saveetha Medical College, Chennai, 34 patients diagnosed with PAD were enrolled to compare the efficacy of duplex ultrasound and MDCTA in identifying arterial lesions. Statistical analysis comprised kappa statistics and contingency tables to evaluate the concordance between the modalities, with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) being calculated. Exclusions were made for patients with contraindications to MDCTA, those under 18 years of age, severe renal impairment, and allergies to contrast agents. This research examined the diagnostic accuracy of both imaging techniques, aiming to provide valuable insights into their effectiveness in identifying arterial lesions associated with PAD. Statistical analysis This investigation studied the efficacy of Doppler ultrasound and MDCTA in diagnosing PAD, with a particular focus on comparing the accuracy of Doppler ultrasonography (DUS) against MDCTA using sensitivity, specificity, and Cohen's kappa coefficient. Through segmental analysis, valuable insights were garnered into the diagnostic precision of DUS across various arterial segments. The results underscored the significance of DUS as a safe, cost-effective, and non-invasive alternative that complements the utility of MDCTA. This comprehensive assessment sheds light on the comparative strengths of both modalities, offering invaluable guidance for clinicians in selecting optimal diagnostic approaches for PAD assessment. Statistical analysis was conducted using the Statistical Package for the Social Sciences (IBM SPSS Statistics for Windows, IBM Corp., Version 24.0, Armonk, NY). Results The sensitivity of ultrasonography (USG) arterial Doppler in evaluating the supra-inguinal, femoropopliteal segments, and infrapopliteal segments was 87.5%, 100%, and 75.32%, respectively. The specificity in evaluating supra-inguinal, femoropopliteal segments, and infrapopliteal segments was 100%, 96.01%, and 83.06%, respectively. The agreement between the two modalities (USG arterial Doppler and CT angiography) obtained by Cohen's kappa analysis with respect to the aortoiliac region and femoropopliteal region was very good (0.91). For infrapopliteal vessels, it was only moderate (0.76). Conclusion Duplex ultrasound emerges as an indispensable tool in the investigation of PAD, offering safety, affordability, and non-invasiveness alongside high diagnostic accuracy and substantial concordance with MDCTA.

Ensemble approach of transfer learning and vision transformer leveraging explainable AI for disease diagnosis: An advancement towards smart healthcare 5.0.

Smart healthcare has advanced the medical industry with the integration of data-driven approaches. Artificial intelligence and machine learning provided remarkable progress, but there is a lack of transparency and interpretability in such applications. To overcome such limitations, explainable AI (EXAI) provided a promising result. This paper applied the EXAI for disease diagnosis in the advancement of smart healthcare. The paper combined the approach of transfer learning, vision transformer, and explainable AI and designed an ensemble approach for prediction of disease and its severity. The result is evaluated on a dataset of Alzheimer's disease. The result analysis compared the performance of transfer learning models with the ensemble model of transfer learning and vision transformer. For training, InceptionV3, VGG19, Resnet50, and Densenet121 transfer learning models were selected for ensembling with vision transformer. The result compares the performance of two models: a transfer learning (TL) model and an ensemble transfer learning (Ensemble TL) model combined with vision transformer (ViT) on ADNI dataset. For the TL model, the accuracy is 58 %, precision is 52 %, recall is 42 %, and the F1-score is 44 %. Whereas, the Ensemble TL model with ViT shows significantly improved performance i.e., 96 % of accuracy, 94 % of precision, 90 % of recall and 92 % of F1-score on ADNI dataset. This shows the efficacy of the ensemble model over transfer learning models.

Extracellular Vesicle Preparation and Analysis: A State-of-the-Art Review.

In recent decades, research on Extracellular Vesicles (EVs) has gained prominence in the life sciences due to their critical roles in both health and disease states, offering promising applications in disease diagnosis, drug delivery, and therapy. However, their inherent heterogeneity and complex origins pose significant challenges to their preparation, analysis, and subsequent clinical application. This review is structured to provide an overview of the biogenesis, composition, and various sources of EVs, thereby laying the groundwork for a detailed discussion of contemporary techniques for their preparation and analysis. Particular focus is given to state-of-the-art technologies that employ both microfluidic and non-microfluidic platforms for EV processing. Furthermore, this discourse extends into innovative approaches that incorporate artificial intelligence and cutting-edge electrochemical sensors, with a particular emphasis on single EV analysis. This review proposes current challenges and outlines prospective avenues for future research. The objective is to motivate researchers to innovate and expand methods for the preparation and analysis of EVs, fully unlocking their biomedical potential.

Revised criteria for diagnosis and staging of Alzheimer's disease: Alzheimer's Association Workgroup.

The National Institute on Aging and the Alzheimer's Association convened three separate work groups in 2011 and single work groups in 2012 and 2018 to create recommendations for the diagnosis and characterization of Alzheimer's disease (AD). The present document updates the 2018 research framework in response to several recent developments. Defining diseases biologically, rather than based on syndromic presentation, has long been standard in many areas of medicine (e.g., oncology), and is becoming a unifying concept common to all neurodegenerative diseases, not just AD. The present document is consistent with this principle. Our intent is to present objective criteria for diagnosis and staging AD, incorporating recent advances in biomarkers, to serve as a bridge between research and clinical care. These criteria are not intended to provide step-by-step clinical practice guidelines for clinical workflow or specific treatment protocols, but rather serve as general principles to inform diagnosis and staging of AD that reflect current science. HIGHLIGHTS: We define Alzheimer's disease (AD) to be a biological process that begins with the appearance of AD neuropathologic change (ADNPC) while people are asymptomatic. Progression of the neuropathologic burden leads to the later appearance and progression of clinical symptoms. Early-changing Core 1 biomarkers (amyloid positron emission tomography [PET], approved cerebrospinal fluid biomarkers, and accurate plasma biomarkers [especially phosphorylated tau 217]) map onto either the amyloid beta or AD tauopathy pathway; however, these reflect the presence of ADNPC more generally (i.e., both neuritic plaques and tangles). An abnormal Core 1 biomarker result is sufficient to establish a diagnosis of AD and to inform clinical decision making throughout the disease continuum. Later-changing Core 2 biomarkers (biofluid and tau PET) can provide prognostic information, and when abnormal, will increase confidence that AD is contributing to symptoms. An integrated biological and clinical staging scheme is described that accommodates the fact that common copathologies, cognitive reserve, and resistance may modify relationships between clinical and biological AD stages.

Artificial intelligence in retinal screening using OCT images: A review of the last decade (2013-2023).

BACKGROUND AND OBJECTIVES: Optical coherence tomography (OCT) has ushered in a transformative era in the domain of ophthalmology, offering non-invasive imaging with high resolution for ocular disease detection. OCT, which is frequently used in diagnosing fundamental ocular pathologies, such as glaucoma and age-related macular degeneration (AMD), plays an important role in the widespread adoption of this technology. Apart from glaucoma and AMD, we will also investigate pertinent pathologies, such as epiretinal membrane (ERM), macular hole (MH), macular dystrophy (MD), vitreomacular traction (VMT), diabetic maculopathy (DMP), cystoid macular edema (CME), central serous chorioretinopathy (CSC), diabetic macular edema (DME), diabetic retinopathy (DR), drusen, glaucomatous optic neuropathy (GON), neovascular AMD (nAMD), myopia macular degeneration (MMD) and choroidal neovascularization (CNV) diseases. This comprehensive review examines the role that OCT-derived images play in detecting, characterizing, and monitoring eye diseases. METHOD: The 2020 PRISMA guideline was used to structure a systematic review of research on various eye conditions using machine learning (ML) or deep learning (DL) techniques. A thorough search across IEEE, PubMed, Web of Science, and Scopus databases yielded 1787 publications, of which 1136 remained after removing duplicates. Subsequent exclusion of conference papers, review papers, and non-open-access articles reduced the selection to 511 articles. Further scrutiny led to the exclusion of 435 more articles due to lower-quality indexing or irrelevance, resulting in 76 journal articles for the review. RESULTS: During our investigation, we found that a major challenge for ML-based decision support is the abundance of features and the determination of their significance. In contrast, DL-based decision support is characterized by a plug-and-play nature rather than relying on a trial-and-error approach. Furthermore, we observed that pre-trained networks are practical and especially useful when working on complex images such as OCT. Consequently, pre-trained deep networks were frequently utilized for classification tasks. Currently, medical decision support aims to reduce the workload of ophthalmologists and retina specialists during routine tasks. In the future, it might be possible to create continuous learning systems that can predict ocular pathologies by identifying subtle changes in OCT images.

[Clinical Evaluation of Dural (Spinal) Membrane Repair Materials].

Objective: To select high-quality and cost-effective dural (spinal) membrane repair materials, in order to reduce the cost of consumables procurement, save medical insurance funds, and optimize hospital operation and management. Methods: Taking the BS06B disease group (spinal cord and spinal canal surgery without extremely severe or severe complications and comorbidities, mainly diagnosed as congenital tethered cord syndrome) as an example, a retrospective analysis was conducted on the relevant data of surgical treatment for congenital tethered cord syndrome conducted in our hospital from January 2021 to June 2023. Safety and efficacy indicators in clinical application (incidence of postoperative epidural hemorrhage, incidence of postoperative purulent cerebrospinal meningitis, incidence of cerebrospinal fluid leakage, surgical duration, and postoperative hospital stay) were compared. Results: There was no difference in safety and effectiveness between different brands of dura mater repair materials. Conclusion: For the repair of small incisions in dura mater surgery, high-quality and cost-effective dura mater repair materials can be selected to reduce hospital costs and control expenses for the disease group.

Diffuse and focal liver fat: advanced imaging techniques and diagnostic insights.

The fatty liver disease represents a complex, multifaceted challenge, requiring a multidisciplinary approach for effective management and research. This article uses conventional and advanced imaging techniques to explore the etiology, imaging patterns, and quantification methods of hepatic steatosis. Particular emphasis is placed on the challenges and advancements in the imaging diagnostics of fatty liver disease. Techniques such as ultrasound, CT, MRI, and elastography are indispensable for providing deep insights into the liver's fat content. These modalities not only distinguish between diffuse and focal steatosis but also help identify accompanying conditions, such as inflammation and fibrosis, which are critical for accurate diagnosis and management.

Federated learning using model projection for multi-center disease diagnosis with non-IID data.

Multi-center disease diagnosis aims to build a global model for all involved medical centers. Due to privacy concerns, it is infeasible to collect data from multiple centers for training (i.e., centralized learning). Federated Learning (FL) is a decentralized framework that enables multiple clients (e.g., medical centers) to collaboratively train a global model while retaining patient data locally for privacy. However, in practice, the data across medical centers are not independently and identically distributed (Non-IID), causing two challenging issues: (1) catastrophic forgetting at clients, i.e., the local model at clients will forget the knowledge received from the global model after local training, causing reduced performance; and (2) invalid aggregation at the server, i.e., the global model at the server may not be favorable to some clients after model aggregation, resulting in a slow convergence rate. To mitigate these issues, an innovative Federated learning using Model Projection (FedMoP) is proposed, which guarantees: (1) the loss of local model on global data does not increase after local training without accessing the global data so that the performance will not be degenerated; and (2) the loss of global model on local data does not increase after aggregation without accessing local data so that convergence rate can be improved. Extensive experimental results show that our FedMoP outperforms state-of-the-art FL methods in terms of accuracy, convergence rate and communication cost. In particular, our FedMoP also achieves comparable or even higher accuracy than centralized learning. Thus, our FedMoP can ensure privacy protection while outperforming centralized learning in accuracy and communication cost.

Portable hydrogel kit based on Michael addition reaction for (E)-2-hexenal gas detection.

Plants exhibit rapid responses to biotic and abiotic stresses by releasing a range of volatile organic compounds (VOCs). Monitoring changes in these VOCs holds the potential for the early detection of plant diseases. This study proposes a method for identifying late blight in potatoes based on the detection of (E)-2-hexenal, one of the major VOC markers released during plant infection by Phytophthora infestans. By combining the Michael addition reaction with cysteine-mediated etching of aggregation-induced emission gold nanoclusters (Au NCs), we have developed a portable hydrogel kit for on-site detection of (E)-2-hexenal. The Michael addition reaction between (E)-2-hexenal and cysteine effectively alleviates the etching of cysteine-mediated Au NCs, leading to a distinct fluorescence color change in the Au NCs, enabling a detection limit of 0.61 ppm. Utilizing the superior loading and diffusion characteristics of the three-dimensional structure of agarose hydrogel, our sensor demonstrated exceptional performance in terms of sensitivity, selectivity, reaction time, and ease of use. Moreover, quantitative measurement of (E)-2-hexenal was made easier by using ImageJ software to transform fluorescent images from the hydrogel kit into digital data. Such method was effectively used for the early detection of potato late blight. This study presents a low-cost, portable fluorescent analytical tool, offering a new avenue for on-site detection of plant diseases.