Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 8 appraisals
BMJ health & care informatics
Routine data are not 'dirty' data: how to approach using routine data for research.
The rise of electronic patient records has led to an abundance of routine healthcare data, and the development of NHS Secure Data Environments (SDEs) is transforming their potential for research. However, routine data differ fundamentally from research data; they are generated to support care processes rather than answer predefined research questions. This creates challenges when they are analysed without understanding the context in which they were produced.Using real examples from practice, this paper illustrates the variety of ways routine data can be shaped and how this leads to misinterpretation if treated as merely 'dirty' research data. These examples underpin practical strategies for researchers, including analysis at or by source and working closely with local data providers to understand how a dataset was created.We argue that SDEs must foster strong links between data users and creators to preserve data provenance and support accurate interpretation. By approaching routine data as meaningful records of healthcare processes-rather than flawed research datasets-researchers can fully realise their potential to drive healthcare improvement.
1 June 2026
Read appraisal →Molecular genetics and genomics : MGG
Comparison between a conventional tool and deep learning models for RNA velocity analysis of scRNA-Seq data
Single-cell RNA sequencing (scRNA-Seq) enables analysis of gene expression at single-cell resolution. RNA velocity analysis infers the temporal dynamics of transcriptional states from the relative abundances of spliced/unspliced mRNA quantified via scRNA-Seq. Classical RNA velocity approaches, such as scVelo, implement gene-specific kinetic modeling. Deep learning methods including DeepVelo, VeloVI, LatentVelo, SymVelo, and scTour are based on variational autoencoders (VAEs), which allow to enhance the robustness and accuracy by leveraging nonlinear latent representations. Here, we systematically evaluated the performance of deep learning RNA velocity tools by comparing with the scVelo dynamical model to access the possible advantages of VAE-base methods. For this purpose, public datasets (GSE149689 and GSE203233) were initially processed using a standard scRNA-Seq pipeline. Comparisons among results of selected velocity tools were conducted using cosine similarity of velocity vectors to assess directional concordance, and by mean squared error analysis of trajectory continuity for the deep learning models. Overall, VAE methods produced significant, richer, and more directionally coherent and consistent velocity fields than the classical model. Our findings indicate that deep learning models provide more consistent and biologically plausible cell-state trajectories, although at the expense of higher computational demands and reliance on accurate splicing quantification. Altogether, our results underscore the relevance of VAE-based frameworks to advance RNA velocity analysis while highlighting the need for careful preprocessing.
14 May 2026
Read appraisal →PloS one
Data fusion-based traffic prediction and software decision support for recreational suburban roads
Predicting traffic flow on mountainous suburban roads is challenging due to highly variable environmental, temporal, and traffic-related conditions. This study focuses on Kandovan Road, a critical route with complex behavioral patterns influenced by weather conditions, calendar events, and road-specific characteristics. To improve forecasting accuracy, eight machine learning and deep learning models were implemented, including Deep LSTM, Random Forest Regressor, XGBRegressor, Transformer, ST-ResNet, Conv-LSTM, Bidirectional LSTM, and LSTM-GAN. The models were trained and evaluated using traffic, weather, and event datasets from 2017 to 2023, with performance measured through MAE, RMSE, MSE, and MAPE metrics. Among the evaluated models, the Random Forest Regressor achieved the highest accuracy with an R² score of 0.88 and a low average error. This result demonstrates its strong ability to model non-linear and dynamic traffic patterns. The results indicate that integrating diverse data sources significantly enhances traffic prediction performance on mountain roads. Additionally, a dedicated traffic forecasting software system was developed to visualize real-time predictions and provide an operational decision-support tool for traffic authorities. The outcomes of this work support more efficient traffic management, improved road safety, and sustainable transportation planning in challenging terrains.
11 May 2026
Read appraisal →Neural networks : the official journal of the International Neural Network Society
Semi-supervised classification and projection with adaptive flexible structure optimal graph
Graph-based semi-supervised learning (GSSL) has received more attention in recent years. Many existing methods obtain a fixed similarity graph based on the original data. Affected by the redundant information and noise of the original data, the obtained similarity graph is not optimal, which greatly affects the subsequent work. And the similarity graphs obtained by these methods are fully connected, so the local structure information of the data cannot be preserved. Moreover, many GSSL methods project the original data into a low-dimensional space through a linear mapping function. However, linear functions may not be appropriate for data embedded in a nonlinear manifold. In order to overcome these shortcomings mentioned above, we relax the linear mapping function and impose a ℓ0-norm constraint on the similarity graph to gain an adaptive flexible structure optimal graph. Furthermore, incorporating the principle of maximum separability, an efficient GSSL method is proposed, named semi-supervised classification and projection with adaptive flexible structure optimal graph (SAFSG). Combining the construction of similarity graphs and label propagation, SAFSG can simultaneously get an adaptive flexible structure optimal graph, a label prediction matrix and a projection matrix. In addition, an efficient iterative algorithm for optimizing SAFSG is proposed. Finally, we conduct experiments on more than ten benchmark datasets, and the experimental results show that SAFSG performs satisfactorily in both classification and projection.
9 May 2026
Read appraisal →PloS one
A load forecasting method based on edge graph attention network.
Given the increasing demand for high-accuracy power load forecasting, traditional load forecasting methods can capture long-term dependencies in time series, but cannot fully capture the complex relationships between multi-dimensional features. This paper proposes an innovative method to convert time series data into graph features. By constructing a graph structure based on time nodes, the time series forecasting problem is transformed into a graph-based load forecasting problem. On this basis, the Edge Graph Attention Network (EGAT) is used to combine the feature information of nodes and edges to further enhance the ability to represent feature interactions and improve the accuracy of load forecasting. This paper compares the EGAT model with common load forecasting methods, including gated recurrent units (GRU), multi-layer perceptron networks (MLP) and long short-term memory (LSTM). The results show that EGAT is effective at finding important features and understanding complex time patterns, which means it shows strong potential in predicting energy demand. A limitation of the proposed approach is its increased computational cost introduced by graph construction and attention-based aggregation, which may raise training time and memory usage for large-scale graphs. In addition, the forecasting performance can be influenced by the design of the time-series graph (e.g., connectivity patterns) and the availability/quality of edge features.
27 Apr 2026
Read appraisal →International journal of medical informatics
Rule-augmented constraint learning for semantic error detection in MIMIC-III knowledge graph
High-quality, error-free data is essential for developing reliable data-driven models, particularly in clinical decision support systems where inaccurate predictions can have serious consequences. While KGs offer a structured and semantically rich representation for clinical data, ensuring their consistency and correctness remains a challenge. Existing rule mining techniques provide solutions for the automatic extraction of logical constraints from KGs, but they often produce redundant or clinically irrelevant rules, especially when dealing with numeric or categorical literals such as age or lab values. KG constraints-rules intended to capture implausible or conflicting facts in the KG-can be used to spot semantic errors: facts that might conform to the underlying schema but contradict domain knowledge. In this work, we propose a novel framework for constraint learning in clinical KGs that identifies and transforms high-confidence rules into clinically plausible constraints. We propose two approaches, based on class disjointness and literal clustering combined with rule mining. We validate the clinical relevance of these generated rules using expert-curated constraints and large language models (LLMs). The results on the MIMIC-III clinical dataset show that rule filtering based constraint learning effectively preserves clinically meaningful rules that align with established medical knowledge. For numeric data, we achieve reliable value groupings through our clustering-based method, and the rules derived from these groupings were validated by LLMs. Their outputs confirm the clinical relevance of a portion of those discovered rules. By providing interpretable and scalable solutions to semantic inconsistencies in KGs, this study contributes to increasing the KG trustworthiness and its clinical usability.
17 Apr 2026
Read appraisal →Journal of chemical information and modeling
zERExtractor: An Automated Platform for Enzyme-Catalyzed Reaction Data Extraction from Scientific Literature
The rapid expansion of enzyme reaction literature has created a major bottleneck in database curation, leaving vast amounts of enzyme-substrate-condition relationships unstructured and inaccessible for DL-driven modeling. How to fully utilize the enzymatic reaction data has been an important task for future accurate enzyme activity prediction models. Current deep learning (DL)-based data extraction models heavily rely on large language models (LLMs) without a fidelity check and the ability to continuously evolve. To address these issues, we developed zERExtractor (Zelixir's Enzyme Reaction Data Extractor), an accuracy-oriented and extensible platform for extracting enzyme-catalyzed reaction data from scientific publications. This system offers a unified multimodal information extraction framework (covering molecular reaction diagrams, tables, and texts) to integrate enzymatic reaction descriptors into structured storage. We employ fine-tuned large LLMs together with DL in a human-in-the-loop pipeline that evolves through data fidelity validation by experts and active learning. Also, zERExtractor achieves 89.9% accuracy in table recognition and over 98% accuracy in molecular image recognition on synthetic data sets, outperforming the strongest baseline by more than 2% and consistently maintaining above 95% on realistic benchmarks. zERExtractor bridges the data gap in enzyme reaction data with a scalable framework for accurate multimodal extraction, advancing DL-driven enzyme modeling and enabling future applications in computational enzymology and biotechnology. The platform is publicly accessible online at https://zpaper.zelixir.com/.
14 Apr 2026
Read appraisal →Analytical chemistry
SIBioX: A Matrix Based Bioinformatics Analysis Tool Based on Swarm Intelligence Algorithm
Biological matrix data are essential for computational analysis, providing a structured framework to identify patterns and relationships in biological systems. Many other biological data types, including sequences, networks, and images, can be transformed into matrix representations through feature extraction and encoding. However, their high dimensionality complicates analysis, leading to increased computational complexity and the risk of overfitting, known as the curse of dimensionality. To address these challenges, we developed SIBioX, a matrix-based bioinformatics tool powered by swarm intelligence algorithms. It integrates 54 swarm intelligence methods, 5 conventional feature selection techniques, and 17 machine learning models, enabling comprehensive analysis of biological matrix data. With a user-friendly graphical interface, it supports operations such as feature normalization, selection, classification, clustering, statistical analysis, and data visualization. Additionally, it converts nonmatrix biological data, like gene and protein sequences, into matrix formats for further study. Experimental results demonstrate that SIBioX not only attains high accuracy in feature selection but also effectively reduces dimensionality, thereby streamlining bioinformatics workflows and promoting greater efficiency in biomedical research.
10 Apr 2026
Read appraisal →