Hand, Foot and Mouth Disease (HFMD) is a highly contagious paediatric disease showing up symptoms like fever, diarrhoea, oral ulcers and rashes on the hands and foot, and even in the mouth. This disease has become an epidemic with several outbreaks in many Asian-Pacific countries with the basic reproduction number $R_{0} > 1$ . HFMD’s diagnosis is very challenging as its lesion pattern may appear quite similar to other skin diseases such as herpangina, aseptic meningitis, and poliomyelitis. Therefore, clinical symptoms are essential besides skin lesion’s pattern and position for precise diagnose of this disease. A deep learning-based HFMD detection system can play a significant role in the digital diagnosis of this disease. Various machine learning and deep learning architectures have been proposed for skin disease diagnosis and classification. However, these models are limited to the image classification problem. The diagnosis of similar appearing skin diseases using the image classification approach may result in misclassification or misdiagnosis of the disease. Parallel integration of clinical symptoms and images can improve disease diagnosis and classification performance. However, no deep learning architecture has been developed to diagnose HFMD disease from images and clinical data. This paper has proposed a novel Hybrid Deep Neural Networks integrating Multi-Layer Perceptron (MLP) network and Convolutional Neural Network into a single framework for the diagnosis of HFMD using the integrated features from clinical and image data. The proposed Hybrid Deep Neural Networks is particularly a multi branched model comprising of Multi-Layer Perceptron (MLP) network in the first branch to extract the clinical features and the modified pre-trained CNN architecture: MobileNet or NasNetMobile in the second branch to extract the features from skin disease lesion images. The features learnt from both the branches are merged to form an integrated feature from clinical data and images, which is fed to the subsequent classification network. We conducted several experiments employing image data only, clinical data only and both sources of data. The analyses compared and evaluated the performance of a typical MLP model and CNN model with our proposed Hybrid Deep Neural Networks. The novel approach promotes the existing image classification model and clinical symptoms based disease classification model, particularly the MLP model. From the cross-validated experiments, the results reveal that the proposed Hybrid Deep Neural Networks can diagnose the disease 99%-100% accurately.
The rapid evolution of AI has facilitated innovative solutions in analysing different biomedical imaging modalities. By leveraging the complementary information from each modality, multimodal AI solutions have shown a huge potential to go beyond human capabilities and offer advances in bioimaging. At the same time, new foundation models and transformer-based architectures are now poised to address unsolved challenges in this field. This review aims to explore and discuss the state-of-the-art AI techniques applied in multimodal biomedical imaging, presenting the key challenges and future directions. We discuss several integration strategies to combine multiple biomedical imaging data types. We also focus on methods to overcome the open challenges related to data quality, model interpretability, and ethical implications.
4 March 2021 in Computational and Mathematical Methods in Medicine
Hand, foot, and mouth disease (HFMD) is a highly contagious disease with several outbreaks in Asian-Pacific countries, including Thailand. With such epidemic characteristics and potential economic impact, HFMD is a significant public health issue in Thailand. Generally, contagious/infectious diseases’ transmission dynamics vary across geolocations due to different socioeconomic situations, demography, and lifestyles. Hence, a nationwide comprehensive model of the disease’s epidemic dynamics can provide information to understand better and predict a potential outbreak of this disease and efficiently and effectively manage its impact. However, there is no nationwide and comprehensive (i.e., the inclusion of reinfections in the model) model of HFDM dynamics for Thailand. This paper has endeavoured to promote nationwide comprehensive modelling of HFMD’s epidemic dynamics and comprehend the reinfection cases. We have formulated the SEIRS epidemiological model with dynamic vitals, including reinfections, to explore this disease’s prevalence. We also introduced periodic seasonality to reproduce the seasonal effect. The pattern of spread of this disease is uneven across the provinces in Thailand, so we used -means clustering algorithm to cluster those provinces into three groups (i.e., highly, moderately, and least affected levels). We also analysed health records collected from district hospitals, which suggest significant reinfection cases. For example, we found that 11% (approximately) of infectious patients return for repeat treatment within the study period. We also performed sensitivity analysis which indicates that the basic reproduction number () is sensitive to the rate of transmission () and the rate at which infected people recover (). By fitting the model with HFMD confirmed data for the provinces in each cluster, the basic reproduction number () was estimated to be 2.643, 1.91, and 3.246 which are greater than 1. Based on this high , this study recommends that this disease will persist in the coming years under identical cultural and environmental conditions.
18 October 2025 in Computers in Biology and Medicine
Due to tumour heterogeneity, cellular metabolic activities and tumour proliferation rates can vary across patients, limiting the predictive and prognostic power of population-based metabolic biomarkers. Genome-scale metabolic models have been developed to address this challenge. These models can simulate patient-specific metabolic reaction rates and mechanistically elucidate cellular metabolic alterations. Simultaneously, phenotypes and other omics data can be integrated to provide valuable insights into specific tumour behaviour and molecular mechanisms underlying cancer biology. However, integrative approaches that combine multiple data modalities with metabolic modelling remain largely undeveloped. We propose a unified framework based on interpretable multi-modal machine learning, integrating different data modalities, including transcriptomics, clinical data, and genome-scale metabolic modelling, to stratify breast cancer patients. By integrating validation analysis across data scales, from bulk to single-cell and spatial data, our framework combines mechanistic knowledge from metabolic modelling with machine learning to characterise molecular and metabolic dysregulations across breast cancer risk groups. This unique mechanistic interpretation approach, combining data-driven and biologically-driven knowledge, provides a comprehensive understanding of breast cancer biology to improve personalised cancer therapy and reveal key biomarkers across multiple scales, including patient-specific, cell-specific, and spot-specific prognostic signatures.
Science is losing knowledge it cannot afford to lose. Negative results go unpublished, hard-won expertise walks out the door with departing researchers, and preservation efforts remain fragmented. The consequences are wasted resources, duplicated effort, and missed discoveries. In this perspective, we argue that the research community can act now by embracing alternative dissemination channels, improving documentation best practices, and building sustainable digital infrastructure. We envision moderated platforms for sharing null results and practical know-how, community-driven standards, and AI-powered tools that lower barriers to implementation. With coordinated effort, science can become more open, efficient, and resilient for future generations.
Optimisation of the design-build-test-learn cycle remains a bottleneck for developing and efficiently manufacturing the next generation of bioproducts. To address this challenge, research has traditionally focused on either data-driven or mechanistic modelling, but the emerging consensus in the field highlights that their strategic integration, often termed hybrid modelling, offers significant advantages, particularly for complex systems where data is sparse. Here, we introduce a hybrid framework where these two methodological lineages are combined to frame development parameters within the metabolism of a production system, therefore achieving mechanism-informed predictions for follow-up experiments. We present three scenarios that exemplify how this framework can be leveraged to guide and accelerate the development of novel bioprocesses, even with small datasets available. We validate our framework by applying it to two heterologous peptide production scenarios in Escherichia coli, explored through commonly relevant experimental factors such as inducer concentration and production strain. Using our framework, we identify key metabolic pathways and reactions that contribute to productivity and whose activity is modified by individual experimental factors like temperature and plasmid used. Furthermore, we show that the biological patterns extracted from this hybrid approach can complement the experimental design, informing predictive models of process performance. Our approach is general and can be tailored to a large array of processes, and thus holds potential for boosting both proof-of-concept and industrial projects, contributing to more efficient and sustainable biomanufacturing.