Beyond grassland degradation: Pathways to resilience for pastoralist households in alpine grassland ecosystems.

Sustaining the development of rural and pastoral communities' hinges on livelihood resilience. Pastoralist household resilience relies on resource availability and decision-making abilities. Despite extensive studies on pastoralist livelihoods, a significant knowledge gap remains in understanding the nuanced adaptive capacities of diverse households, particularly amid grassland degradation. Thus, this study investigates the household-based livelihood resilience of pastoralists in China's Three-River Headwater Region, offering policy recommendations for resilient livelihoods. Using stratified random sampling, 758 pastoralist household heads underwent semi-structured interviews to collect data. Five household characteristics, encompassing age, gender, energy use, well-being perception, and multi-household grazing participation, were evaluated. Looking ot the nature of data, descriptive statistics and non-parametric tests were performed in this study to draw the valid inferences. The results revealed a positive correlation (p < 0.05) between household head age and livelihood resilience, with divergent resilience across age groups. Varied energy usage yielded distinct impacts; households employing solar or mixed energy sources exhibited heightened resilience (p < 0.05). Household well-being emerged as an invariant variable concerning resilience. Furthermore, engagement in multi-household grazing (an informal institution) significantly (p < 0.05) influenced pastoralist livelihood resilience. These insights advocate targeted support for young household heads and the adoption of clean energy. Exploring the deeper strategies and mechanisms of multi-household grazing can enhance understanding and policy integration, guiding eco-friendly progress within rustic landscapes for pastoral communities.

Improving Global Generalization and Local Personalization for Federated Learning.

Federated learning aims to facilitate collaborative training among multiple clients with data heterogeneity in a privacy-preserving manner, which either generates the generalized model or develops personalized models. However, existing methods typically struggle to balance both directions, as optimizing one often leads to failure in another. To address the problem, this article presents a method named personalized federated learning via cross silo prototypical calibration (pFedCSPC) to enhance the consistency of knowledge of clients by calibrating features from heterogeneous spaces, which contributes to enhancing the collaboration effectiveness between clients. Specifically, pFedCSPC employs an adaptive aggregation method to offer personalized initial models to each client, enabling rapid adaptation to personalized tasks. Subsequently, pFedCSPC learns class representation patterns on clients by clustering, averages the representations within each cluster to form local prototypes, and aggregates them on the server to generate global prototypes. Meanwhile, pFedCSPC leverages global prototypes as knowledge to guide the learning of local representation, which is beneficial for mitigating the data imbalanced problem and preventing overfitting. Moreover, pFedCSPC has designed a cross-silo prototypical calibration (CSPC) module, which utilizes contrastive learning techniques to map heterogeneous features from different sources into a unified space. This can enhance the generalization ability of the global model. Experiments were conducted on four datasets in terms of performance comparison, ablation study, in-depth analysis, and case study, and the results verified that pFedCSPC achieves improvements in both global generalization and local personalization performance via calibrating cross-source features and strengthening collaboration effectiveness, respectively.

Hybrid multimodal fusion for graph learning in disease prediction.

Graph neural networks (GNNs) have gained significant attention in disease prediction where the latent embeddings of patients are modeled as nodes and the similarities among patients are represented through edges. The graph structure, which determines how information is aggregated and propagated, plays a crucial role in graph learning. Recent approaches typically create graphs based on patients' latent embeddings, which may not accurately reflect their real-world closeness. Our analysis reveals that raw data, such as demographic attributes and laboratory results, offers a wealth of information for assessing patient similarities and can serve as a compensatory measure for graphs constructed exclusively from latent embeddings. In this study, we first construct adaptive graphs from both latent representations and raw data respectively, and then merge these graphs via weighted summation. Given that the graphs may contain extraneous and noisy connections, we apply degree-sensitive edge pruning and kNN sparsification techniques to selectively sparsify and prune these edges. We conducted intensive experiments on two diagnostic prediction datasets, and the results demonstrate that our proposed method surpasses current state-of-the-art techniques.

A Comprehensive Review of the Global Epidemiology, Clinical Management, Socio-Economic Impacts, and National Responses to Long COVID with Future Research Directions.

Background: Long COVID, characterized by a persistent symptom spectrum following SARS-CoV-2 infection, poses significant health, social, and economic challenges. This review aims to consolidate knowledge on its epidemiology, clinical features, and underlying mechanisms to guide global responses; Methods: We conducted a literature review, analyzing peer-reviewed articles and reports to gather comprehensive data on long COVID's epidemiology, symptomatology, and management approaches; Results: Our analysis revealed a wide array of long COVID symptoms and risk factors, with notable demographic variability. The current understanding of its pathophysiology suggests a multifactorial origin yet remains partially understood. Emerging diagnostic criteria and potential therapeutic strategies were identified, highlighting advancements in long COVID management; Conclusions: This review highlights the multifaceted nature of long COVID, revealing a broad spectrum of symptoms, diverse risk factors, and the complex interplay of physiological mechanisms underpinning the condition. Long COVID symptoms and disorders will continue to weigh on healthcare systems in years to come. Addressing long COVID requires a holistic management strategy that integrates clinical care, social support, and policy initiatives. The findings underscore the need for increased international cooperation in research and health planning to address the complex challenges of long COVID. There is a call for continued refinement of diagnostic and treatment modalities, emphasizing a multidisciplinary approach to manage the ongoing and evolving impacts of the condition.

Medicine Package Recommendation via Dual-Level Interaction Aware Heterogeneous Graph.

Medicine package recommendation aims to assist doctors in clinical decision-making by recommending appropriate packages of medicines for patients. Current methods model this task as a multi-label classification or sequence generation problem, focusing on learning relationships between individual medicines and other medical entities. However, these approaches uniformly overlook the interactions between medicine packages and other medical entities, potentially resulting in a lack of completeness in recommended medicine packages. Furthermore, medicine commonsense knowledge considered by current methods is notably limited, making it challenging to delve into the decision-making processes of doctors. To solve these problems, we propose DIAGNN, a Dual-level Interaction Aware heterogeneous Graph Neural Network for medicine package recommendation. Specifically, DIAGNN explicitly models interactions of medical entities within electronic health records(EHRs) at two levels, individual medicine and medicine package, leveraging a heterogeneous graph. A dual-level interaction aware graph convolutional network is utilized to capture semantic information in the medical heterogeneous graph. Additionally, we incorporate medication indications into the medical heterogeneous graph as medicine commonsense knowledge. Extensive experimental results on real-world datasets validate the effectiveness of the proposed method.

ResDeepSurv: A Survival Model for Deep Neural Networks Based on Residual Blocks and Self-attention Mechanism.

Survival analysis, as a widely used method for analyzing and predicting the timing of event occurrence, plays a crucial role in the medicine field. Medical professionals utilize survival models to gain insight into the effects of patient covariates on the disease, and the correlation with the effectiveness of different treatment strategies. This knowledge is essential for the development of treatment plans and the enhancement of treatment approaches. Conventional survival models, such as the Cox proportional hazards model, require a significant amount of feature engineering or prior knowledge to facilitate personalized modeling. To address these limitations, we propose a novel residual-based self-attention deep neural network for survival modeling, called ResDeepSurv, which combines the benefits of neural networks and the Cox proportional hazards regression model. The model proposed in our study simulates the distribution of survival time and the correlation between covariates and outcomes, but does not impose strict assumptions on the basic distribution of survival data. This approach effectively accounts for both linear and nonlinear risk functions in survival data analysis. The performance of our model in analyzing survival data with various risk functions is on par with or even superior to that of other existing survival analysis methods. Furthermore, we validate the superior performance of our model in comparison to currently existing methods by evaluating multiple publicly available clinical datasets. Through this study, we prove the effectiveness of our proposed model in survival analysis, providing a promising alternative to traditional approaches. The application of deep learning techniques and the ability to capture complex relationships between covariates and survival outcomes without relying on extensive feature engineering make our model a valuable tool for personalized medicine and decision-making in clinical practice.

A Survey on Federated Recommendation Systems.

Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models by collecting the intermediate parameters instead of the real user data, which greatly enhances user privacy. In addition, federated recommendation systems (FedRSs) can cooperate with other data platforms to improve recommendation performance while meeting the regulation and privacy constraints. However, FedRSs face many new challenges such as privacy, security, heterogeneity, and communication costs. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this article, we: 1) summarize some common privacy mechanisms used in FedRSs and discuss the advantages and limitations of each mechanism; 2) review several novel attacks and defenses against security; 3) summarize some approaches to address heterogeneity and communication costs problems; 4) introduce some realistic applications and public benchmark datasets for FedRSs; and 5) present some prospective research directions in the future. This article can guide researchers and practitioners understand the research progress in these areas.

Multi-Granularity Graph Convolution Network for Major Depressive Disorder Recognition.

Major depressive disorder (MDD) is the most common psychological disease. To improve the recognition accuracy of MDD, more and more machine learning methods have been proposed to mining EEG features, i.e. typical brain functional patterns and recognition methods that are closely related to depression using resting EEG signals. Most existing methods typically utilize threshold methods to filter weak connections in the brain functional connectivity network (BFCN) and construct quantitative statistical features of brain function to measure the BFCN. However, these thresholds may excessively remove weak connections with functional relevance, which is not conducive to discovering potential hidden patterns in weak connections. In addition, statistical features cannot describe the topological structure features and information network propagation patterns of the brain's different functional regions. To solve these problems, we propose a novel MDD recognition method based on a multi-granularity graph convolution network (MGGCN). On the one hand, this method applies multiple sets of different thresholds to build a multi-granularity functional neural network, which can remove noise while fully retaining valuable weak connections. On the other hand, this method utilizes graph neural network to learn the topological structure features and brain saliency patterns of changes between brain functional regions on the multi-granularity functional neural network. Experimental results on the benchmark datasets validate the superior performance and time complexity of MGGCN. The analysis shows that as the granularity increases, the connectivity defects in the right frontal(RF) and right temporal (RT) regions, left temporal(LT) and left posterior(LP) regions increase. The brain functional connections in these regions can serve as potential biomarkers for MDD recognition.

EAPR: explainable and augmented patient representation learning for disease prediction.

Patient representation learning aims to encode meaningful information about the patient's Electronic Health Records (EHR) in the form of a mathematical representation. Recent advances in deep learning have empowered Patient representation learning methods with greater representational power, allowing the learned representations to significantly improve the performance of disease prediction models. However, the inherent shortcomings of deep learning models, such as the need for massive amounts of labeled data and inexplicability, limit the performance of deep learning-based Patient representation learning methods to further improvements. In particular, learning robust patient representations is challenging when patient data is missing or insufficient. Although data augmentation techniques can tackle this deficiency, the complex data processing further weakens the inexplicability of patient representation learning models. To address the above challenges, this paper proposes an Explainable and Augmented Patient Representation Learning for disease prediction (EAPR). EAPR utilizes data augmentation controlled by confidence interval to enhance patient representation in the presence of limited patient data. Moreover, EAPR proposes to use two-stage gradient backpropagation to address the problem of unexplainable patient representation learning models due to the complex data enhancement process. The experimental results on real clinical data validate the effectiveness and explainability of the proposed approach.

Navigating the landscape of global sustainable livelihood research: past insights and future trajectory.

Sustainable livelihoods (SL) have emerged as a crucial area of focus in global environmental change research, aligning with the Sustainable Development Goals (SDGs). This field is rapidly gaining prominence in sustainability science and has become one of the primary research paradigms. In our study, we conducted scientometrics analysis using the ISI Web of Science core collection database to examine research patterns and frontier areas in SL research. We selected 6441 papers and 265,759 references related to SL published from 1991 to 2020. To achieve this, we employed advanced quantitative analysis tools such as CiteSpace and VOSviewer to quantitatively analyze and visualize the evolution of literature in the SL research field. Our overarching objectives were to understand historical research characteristics, identify the knowledge base, and determine future research trends. The results revealed an exponential increase in SL research documentation since 1991, with the Consortium of International Agricultural Research Center (CGIAR) contributing the highest volume of research documents and citations. Key journals in this field included World Development, Global Environmental Change, Ecological Economics, and Ecology and Society. Notably, Singh RK and Shackleton CM emerged as prolific authors in SL research. Through our analysis, we identified six primary clusters of research areas: livelihoods, conservation, food security, management, climate change, and ecosystem services. Additionally, we found that tags such as rural household, agricultural intensification, cultural intensification, and livelihoods vulnerability remained relevant and represented active research hotspots. By analyzing keyword score relevance, we identified frontier areas in SL research, including mass tourism, solar home systems, artisanal and small-scale mining, forest quality, marine-protected areas, agricultural sustainability, sustainable rangeland management, and indigenous knowledge. These findings provide valuable insights to stakeholders regarding the historical, current, and future trends in SL research, offering strategic opportunities to enhance the sustainability of livelihoods for farmers and rural communities in alignment with the SDGs.

Micro- and nanoplastics in soil: Linking sources to damage on soil ecosystem services in life cycle assessment.

Soil ecosystems are crucial for providing vital ecosystem services (ES), and are increasingly pressured by the intensification and expansion of human activities, leading to potentially harmful consequences for their related ES provision. Micro- and nanoplastics (MNPs), associated with releases from various human activities, have become prevalent in various soil ecosystems and pose a global threat. Life Cycle Assessment (LCA), a tool for evaluating environmental performance of product and technology life cycles, has yet to adequately include MNPs-related damage to soil ES, owing to factors like uncertainties in MNPs environmental fate and ecotoxicological effects, and characterizing related damage on soil species loss, functional diversity, and ES. This study aims to address this gap by providing as a first step an overview of the current understanding of MNPs in soil ecosystems and proposing a conceptual approach to link MNPs impacts to soil ES damage. We find that MNPs pervade soil ecosystems worldwide, introduced through various pathways, including wastewater discharge, urban runoff, atmospheric deposition, and degradation of larger plastic debris. MNPs can inflict a range of ecotoxicity effects on soil species, including physical harm, chemical toxicity, and pollutants bioaccumulation. Methods to translate these impacts into damage on ES are under development and typically focus on discrete, yet not fully integrated aspects along the impact-to-damage pathway. We propose a conceptual framework for linking different MNPs effects on soil organisms to damage on soil species loss, functional diversity loss and loss of ES, and elaborate on each link. Proposed underlying approaches include the Threshold Indicator Taxa Analysis (TITAN) for translating ecotoxicological effects associated with MNPs into quantitative measures of soil species diversity damage; trait-based approaches for linking soil species loss to functional diversity loss; and ecological networks and Bayesian Belief Networks for linking functional diversity loss to soil ES damage. With the proposed conceptual framework, our study constitutes a starting point for including the characterization of MNPs-related damage on soil ES in LCA.

MolFPG: Multi-level fingerprint-based Graph Transformer for accurate and robust drug toxicity prediction.

Drug toxicity prediction is essential to drug development, which can help screen compounds with potential toxicity and reduce the cost and risk of animal experiments and clinical trials. However, traditional handcrafted feature-based and molecular-graph-based approaches are insufficient for molecular representation learning. To address the problem, we developed an innovative molecular fingerprint Graph Transformer framework (MolFPG) with a global-aware module for interpretable toxicity prediction. Our approach encodes compounds using multiple molecular fingerprinting techniques and integrates Graph Transformer-based molecular representation for feature learning and toxic prediction. Experimental results show that our proposed approach has high accuracy and reliability in predicting drug toxicity. In addition, we explored the relationship between drug features and toxicity through an interpretive analysis approach, which improved the interpretability of the approach. Our results highlight the potential of Graph Transformers and multi-level fingerprints for accelerating the drug discovery process by reliably, effectively alarming drug safety. We believe that our study will provide vital support and reference for further development in the field of drug development and toxicity assessment.

MVIL6: Accurate identification of IL-6-induced peptides using multi-view feature learning.

Interleukin-6 (IL-6) is a potential therapeutic target for many diseases, and it is of great significance in accurately predicting IL-6-induced peptides for IL-6 research. However, the cost of traditional wet experiments to detect IL-6-induced peptides is huge, and the discovery and design of peptides by computer before the experimental stage have become a promising technology. In this study, we developed a deep learning model called MVIL6 for predicting IL-6-inducing peptides. Comparative results demonstrated the outstanding performance and robustness of MVIL6. Specifically, we employ a pre-trained protein language model MG-BERT and the Transformer model to process two different sequence-based descriptors and integrate them with a fusion module to improve the prediction performance. The ablation experiment demonstrated the effectiveness of our fusion strategy for the two models. In addition, to provide good interpretability of our model, we explored and visualized the amino acids considered important for IL-6-induced peptide prediction by our model. Finally, a case study presented using MVIL6 to predict IL-6-induced peptides in the SARS-CoV-2 spike protein shows that MVIL6 achieves higher performance than existing methods and can be useful for identifying potential IL-6-induced peptides in viral proteins.

Heterogeneous Collaborative Learning for Personalized Healthcare Analytics via Messenger Distillation.

The Healthcare Internet-of-Things (IoT) framework aims to provide personalized medical services with edge devices. Due to the inevitable data sparsity on an individual device, cross-device collaboration is introduced to enhance the power of distributed artificial intelligence. Conventional collaborative learning protocols (e.g., sharing model parameters or gradients) strictly require the homogeneity of all participant models. However, real-life end devices have various hardware configurations (e.g., compute resources), leading to heterogeneous on-device models with different architectures. Moreover, clients (i.e., end devices) may participate in the collaborative learning process at different times. In this paper, we propose a Similarity-Quality-based Messenger Distillation (SQMD) framework for heterogeneous asynchronous on-device healthcare analytics. By introducing a preloaded reference dataset, SQMD enables all participant devices to distill knowledge from peers via messengers (i.e., the soft labels of the reference dataset generated by clients) without assuming the same model architecture. Furthermore, the messengers also carry important auxiliary information to calculate the similarity between clients and evaluate the quality of each client model, based on which the central server creates and maintains a dynamic collaboration graph (communication graph) to improve the personalization and reliability of SQMD under asynchronous conditions. Extensive experiments on three real-life datasets show that SQMD achieves superior performance.

SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning.

BACKGROUND: Cell-penetrating peptides (CPPs) have received considerable attention as a means of transporting pharmacologically active molecules into living cells without damaging the cell membrane, and thus hold great promise as future therapeutics. Recently, several machine learning-based algorithms have been proposed for predicting CPPs. However, most existing predictive methods do not consider the agreement (disagreement) between similar (dissimilar) CPPs and depend heavily on expert knowledge-based handcrafted features. RESULTS: In this study, we present SiameseCPP, a novel deep learning framework for automated CPPs prediction. SiameseCPP learns discriminative representations of CPPs based on a well-pretrained model and a Siamese neural network consisting of a transformer and gated recurrent units. Contrastive learning is used for the first time to build a CPP predictive model. Comprehensive experiments demonstrate that our proposed SiameseCPP is superior to existing baseline models for predicting CPPs. Moreover, SiameseCPP also achieves good performance on other functional peptide datasets, exhibiting satisfactory generalization ability.

Towards Personalized Federated Learning.

In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.

HealthNet: A Health Progression Network via Heterogeneous Medical Information Fusion.

Numerous electronic health records (EHRs) offer valuable opportunities for understanding patients' health status at different stages, namely health progression. Extracting the health progression patterns allows researchers to perform accurate predictive analysis of patient outcomes. However, most existing works on this task suffer from the following two limitations: 1) the diverse dependencies among heterogeneous medical entities are overlooked, which leads to the one-sided modeling of patients' status and 2) the extraction granularity of patient's health progression patterns is coarse, limiting the model's ability to accurately infer the patient's future status. To address these challenges, a pretrained Health progression network via heterogeneous medical information fusion, HealthNet, is proposed in this article. Specifically, a global heterogeneous graph in HealthNet is built to integrate heterogeneous medical entities and the dependencies among them. In addition, the proposed health progression network is designed to model hierarchical medical event sequences. By this method, the fine-grained health progression patterns of patients' health can be captured. The experimental results on real disease datasets demonstrate that HealthNet outperforms the state-of-the-art models for both diagnosis prediction task and mortality prediction task.

Lung Cancer Subtype Diagnosis by Fusing Image-Genomics Data and Hybrid Deep Networks.

Accurate diagnosis of cancer subtypes is crucial for precise treatment, because different cancer subtypes are involved with different pathology and require different therapies. Although deep learning techniques have made great success in computer vision and other fields, they do not work well on Lung cancer subtype diagnosis, due to the distinction of slide images between different cancer subtypes is ambiguous. Furthermore, they often over-fit to high-dimensional genomics data with limited samples, and do not fuse the image and genomics data in a sensible way. In this paper, we propose a hybrid deep network based approach LungDIG for Lung cancer subtype Diagnosis by fusing Image-Genomics data. LungDIG first tiles the tissue slide image into small patches and extracts the patch-level features by fine-tuning an Inception-V3 model. Since the patches may contain some false positives in non-diagnostic regions, it further designs a patch-level feature combination strategy to integrate the extracted patch features and maintain the diversity between different cancer subtypes. At the same time, it extracts the genomics features from Copy Number Variation data by an attention based nonlinear extractor. Next, it fuses the image and genomics features by an attention based multilayer perceptron (MLP) to diagnose cancer subtype. Experiments on TCGA lung cancer data show that LungDIG can not only achieve higher accuracy for cancer subtype diagnosis than state-of-the-art methods, but also have a high authenticity and good interpretability.

Exploring the frontiers of sustainable livelihoods research within grassland ecosystem: A scientometric analysis.

Grassland degradation has become a global social-ecological problem, which seriously limits the sustainability of indigenous people's livelihoods. Bibliometrics, a type of analysis based on the Science Citation Index-Expanded (SCI-E), was therefore performed to explore the research trends and focus areas of studies on sustainable livelihoods (SLs). We conducted an in-depth analysis of 489 research publications and their 25,144 references from 1991 to 2020. The results show that only few papers have been published, but the number of countries and research institutions involved shows an overall imbalance. We identified eight main clusters based on keyword co-occurrence, these being studies the content of which is an important representation of current research directions in this topic. The document co-citation analysis revealed 10 research clusters, representing the frontiers of research. Clusters included the following topics: NPP (Net Primary Productivity) dynamics, global change, ecological restoration, risk indicators, livelihood strategies, smallholder systems, drought relief, sustainable land management and common pool resources. We reviewed and interpreted these clusters in depth with a view to provide an up-to-date account of the dynamics of this research. As the first scientometric evaluation of research on sustainable livelihoods in grassland ecosystems, this study provides several theoretical and practical implications for global poverty eradication research, which are of great scientific value for global sustainable development.

A Novel Multi-view Bi-clustering method for identifying abnormal Co-occurrence medical visit behaviors.

Abnormal co-occurrence medical visit behavior is a form of medical insurance fraud. Specifically, an organized gang of fraudsters hold multiple medical insurance cards and purchase similar drugs frequently at the same time and the same location in order to siphon off medical insurance funds. Conventional identification methods to identify such behaviors rely mainly on manual auditing, making it difficult to satisfy the needs of identifying the small number of fraudulent behaviors in the large-scale medical data. On the other hand, the existing single-view bi-clustering algorithms only consider the features of the time-location dimension while neglecting the similarities in prescriptions and neglecting the fact that fraudsters may belong to multiple gangs. Therefore, in this paper, we present a multi-view bi-clustering method for identifying abnormal co-occurrence medical visit behavioral patterns, which performs cluster analysis simultaneously on the large-scale, complex and diverse visiting record dimension and prescription dimension to identify bi-clusters with similar time-location features. The proposed method constructs a matrix view of patients and visit records as well as a matrix view of patients and prescriptions, while decomposing multiple data matrices into sparse row and column vectors to obtain a consistent patient population across views. Subsequently the proposed method identifies the corresponding abnormal co-occurrence medical visit behavior and may greatly facilitate the safe operations and the sustainability of medical insurance funds. The experimental results show that our proposed method leads to more efficient and more accurate identifications of abnormal co-occurrence medical visit behavior, demonstrating its high efficiency and effectiveness.