The Application of Computer Technology to Clinical Practice Guideline Implementation: A Scoping Review.

Implementation of clinical practice guidelines (CPG) is a complex and challenging task. Computer technology, including artificial intelligence (AI), has been explored to promote the CPG implementation. This study has reviewed the main domains where computer technology and AI has been applied to CPG implementation. PubMed, Embase, Web of science, the Cochrane Library, China National Knowledge Infrastructure database, WanFang DATA, VIP database, and China Biology Medicine disc database were searched from inception to December 2021. Studies involving the utilization of computer technology and AI to promote the implementation of CPGs were eligible for review. A total of 10429 published articles were identified, 117 met the inclusion criteria. 21 (17.9%) focused on the utilization of AI techniques to classify or extract the relative content of CPGs, such as recommendation sentence, condition-action sentences. 47 (40.2%) focused on the utilization of computer technology to represent guideline knowledge to make it understandable by computer. 15 (12.8%) focused on the utilization of AI techniques to verify the relative content of CPGs, such as conciliation of multiple single-disease guidelines for comorbid patients. 34 (29.1%) focused on the utilization of AI techniques to integrate guideline knowledge into different resources, such as clinical decision support systems. We conclude that the application of computer technology and AI to CPG implementation mainly concentrated on the guideline content classification and extraction, guideline knowledge representation, guideline knowledge verification, and guideline knowledge integration. The AI methods used for guideline content classification and extraction were pattern-based algorithm and machine learning. In guideline knowledge representation, guideline knowledge verification, and guideline knowledge integration, computer techniques of knowledge representation were the most used.

Towards a better negative sampling strategy for dynamic graphs.

As dynamic graphs have become indispensable in numerous fields due to their capacity to represent evolving relationships over time, there has been a concomitant increase in the development of Temporal Graph Neural Networks (TGNNs). When training TGNNs for dynamic graph link prediction, the commonly used negative sampling method often produces starkly contrasting samples, which can lead the model to overfit these pronounced differences and compromise its ability to generalize effectively to new data. To address this challenge, we introduce an innovative negative sampling approach named Enhanced Negative Sampling (ENS). This strategy takes into account two pervasive traits observed in dynamic graphs: (1) Historical dependence, indicating that nodes frequently reestablish connections they held in the past, and (2) Temporal proximity preference, which posits that nodes are more inclined to connect with those they have recently interacted with. Specifically, our technique employs a designed scheduling function to strategically control the progression of difficulty of the negative samples throughout the training. This ensures that the training progresses in a balanced manner, becoming incrementally challenging, and thereby enhancing TGNNs' proficiency in predicting links within dynamic graphs. In our empirical evaluation across multiple datasets, we discerned that our ENS, when integrated as a modular component, notably augments the performance of four SOTA baselines. Additionally, we further investigated the applicability of ENS in handling dynamic graphs of varied attributes. Our code is available at https://github.com/qqaazxddrr/ENS.

Graph explicit pooling for graph-level representation learning.

Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selecting top-ranked nodes and discarding the remaining to construct coarsened graph representations. However, this paper highlights two key issues with these methods: (1) The process of selecting nodes to discard frequently employs additional Graph Convolutional Networks or Multilayer Perceptrons, lacking a thorough evaluation of each node's impact on the final graph representation and subsequent prediction tasks. (2) Current graph pooling methods tend to directly discard the noise segment (dropped) of the graph without accounting for the latent information contained within these elements. To address the first issue, we introduce a novel Graph explicit Pooling (GrePool) method, which selects nodes by explicitly leveraging the relationships between the nodes and final representation vectors crucial for classification. The second issue is addressed using an extended version of GrePool (i.e., GrePool+), which applies a uniform loss on the discarded nodes. This addition is designed to augment the training process and improve classification accuracy. Furthermore, we conduct comprehensive experiments across 12 widely used datasets to validate our proposed method's effectiveness, including the Open Graph Benchmark datasets. Our experimental results uniformly demonstrate that GrePool outperforms 14 baseline methods for most datasets. Likewise, implementing GrePool+ enhances GrePool's performance without incurring additional computational costs. The code is available at https://github.com/LiuChuang0059/GrePool.

Ontology of clinical practice guidelines for Integrated Traditional Chinese and Western Medicine.

OBJECTIVE: Clinical practice guidelines (CPGs) for Integrated Traditional Chinese and Western Medicine (TCM and WM) are important medical documents used to assist medical decision-making and are of great significance for standardizing clinical pathways. However, due to the constraints of text format, it is difficult for Integrated TCM and WM CPGs to play a real role in medical practice. In addition, how to standardize the structure and semantic relationships between Integrated TCM and WM CPG knowledge, and realize the construction of computable, sharable and reliable CPGs, remains an urgent issue to be addressed. Therefore, we are proposing an ontology of CPGs for Integrated TCM and WM. METHODS: We first initialized domain concepts and relationships to ensure the accuracy of the ontology knowledge structure. We then screened CPGs that meet the standards for Integrated TCM and WM, analyzed and classified the contents, and extracted the common structures. Based on the seven-step ontology construction method combined with inference-complement, referring to the representation methods and hierarchical relationships of terms and concepts in MeSH, ICD-10, SNOMED-CT, and other ontologies and terminology sets, we formed the concept structure and semantic relationship tables for the ontology. We also achieved the matching and mapping between the ontology and reference ontologies and term sets. Next, we defined the aspects and constraints of properties, selected multiple Integrated TCM and WM CPGs as instances to populate, and used ontology reasoning tools and formulated defined inference rules to reason and extend the ontology. Finally, we evaluated the performance of the ontology. RESULTS: The content of the Integrated TCM and WM CPGs is divided into nine parts: basic information, background, development method, clinical question, recommendation, evidence, conclusion, result, and reason for recommendations. The Integrated TCM and WM CPG ontology has 152 classes and defines 90 object properties and 114 data properties, with a maximum classification depth of 4 layers. The terms of disease, drug and examination item names in the ontology have been standardized. CONCLUSIONS: This study proposes an Integrated TCM and WM CPG ontology. The ontology adopts a modular design, which has both sharing and scaling ability, and can express rich guideline knowledge. It provides important support for the semantic processing and computational application of guideline documents.

Thickness-dependent transport channels in topological insulator Bi2Se3 thin films grown by magnetron sputtering.

We study the low-temperature transport properties of Bi2Se3 thin films grown by magnetron sputtering. A positive magnetoresistance resulting from the weak antilocalization (WAL) effect is observed at low temperatures. The observed WAL effect is two dimensional in nature. Applying the Hikami-Larkin-Nagaoka theory, we have obtained the dephasing length. It is found that the temperature dependence of the dephasing length cannot be described only by the Nyquist electron-electron dephasing, in conflict with prevailing experimental results. From the WAL effect, we extract the number of the transport channels, which is found to increase with increasing the thickness of the films, reflecting the thickness-dependent coupling between the top and bottom surface states in topological insulator. On the other hand, the electron-electron interaction (EEI) effect is observed in temperature-dependent conductivity. From the EEI effect, we also extract the number of the transport channel, which shows similar thickness dependence with that obtained from the analysis of the WAL effect. The EEI effect, therefore, can be used to analyze the coupling effect between the top and bottom surface states in topological insulator like the WAL effect.