With a massive influx of multimodality data, the role of data analytics in health informatics has grown rapidly in the last decade. This has also prompted increasing interests in the generation of analytical, data driven models based on machine learning in health informatics. Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reshape the future of artificial intelligence. Rapid improvements in computational power, fast data storage, and parallelization have also contributed to the rapid uptake of the technology in addition to its predictive power and ability to generate automatically optimized high-level features and semantic interpretation from the input data. This article presents a comprehensive up-to-date review of research employing deep learning in health informatics, providing a critical analysis of the relative merit, and potential pitfalls of the technique as well as its future outlook. The paper mainly focuses on key applications of deep learning in the fields of translational bioinformatics, medical imaging, pervasive sensing, medical informatics, and public health.

The aging population, prevalence of chronic diseases, and outbreaks of infectious diseases are some of the major challenges of our present-day society. To address these unmet healthcare needs, especially for the early prediction and treatment of major diseases, health informatics, which deals with the acquisition, transmission, processing, storage, retrieval, and use of health information, has emerged as an active area of interdisciplinary research. In particular, acquisition of health-related information by unobtrusive sensing and wearable technologies is considered as a cornerstone in health informatics. Sensors can be weaved or integrated into clothing, accessories, and the living environment, such that health information can be acquired seamlessly and pervasively in daily living. Sensors can even be designed as stick-on electronic tattoos or directly printed onto human skin to enable long-term health monitoring. This paper aims to provide an overview of four emerging unobtrusive and wearable technologies, which are essential to the realization of pervasive health information acquisition, including: 1) unobtrusive sensing methods, 2) smart textile technology, 3) flexible-stretchable-printable electronics, and 4) sensor fusion, and then to identify some future directions of research.

After decades of evolution, measuring instruments for quantitative gait analysis have become an important clinical tool for assessing pathologies manifested by gait abnormalities. However, such instruments tend to be expensive and require expert operation and maintenance besides their high cost, thus limiting them to only a small number of specialized centers. Consequently, gait analysis in most clinics today still relies on observation-based assessment. Recent advances in wearable sensors, especially inertial body sensors, have opened up a promising future for gait analysis. Not only can these sensors be more easily adopted in clinical diagnosis and treatment procedures than their current counterparts, but they can also monitor gait continuously outside clinics – hence providing seamless patient analysis from clinics to free-living environments. The purpose of this paper is to provide a systematic review of current techniques for quantitative gait analysis and to propose key metrics for evaluating the existing, as well as emerging methods for qualifying the gait features extracted from wearable sensors. It aims to highlight key advances in this rapidly evolving research field and outline potential future directions for both research and clinical applications.

The increasing popularity of wearable devices in recent years means that a diverse range of physiological and functional data can now be captured continuously for applications in sports, wellbeing, and healthcare. This wealth of information requires efficient methods of classification and analysis where deep learning is a promising technique for large-scale data analytics. While deep learning has been successful in implementations that utilize high-performance computing platforms, its use on low-power wearable devices is limited by resource constraints. In this paper, we propose a deep learning methodology, which combines features learned from inertial sensor data together with complementary information from a set of shallow features to enable accurate and real-time activity classification. The design of this combined method aims to overcome some of the limitations present in a typical deep learning framework where on-node computation is required. To optimize the proposed method for real-time on-node computation, spectral domain preprocessing is used before the data are passed onto the deep learning framework. The classification accuracy of our proposed deep learning approach is evaluated against state-of-the-art methods using both laboratory and real world activity datasets. Our results show the validity of the approach on different human activity datasets, outperforming other methods, including the two methods used within our combined pipeline. We also demonstrate that the computation times for the proposed method are consistent with the constraints of real-time on-node processing on smartphones and a wearable sensor platform.

Large AI models, or foundation models, are models recently emerging with massive scales both parameter-wise and data-wise, the magnitudes of which can reach beyond billions. Once pretrained, large AI models demonstrate impressive performance in various downstream tasks. A prime example is ChatGPT, whose capability has compelled people's imagination about the far-reaching influence that large AI models can have and their potential to transform different domains of our lives. In health informatics, the advent of large AI models has brought new paradigms for the design of methodologies. The scale of multi-modal data in the biomedical and health domain has been ever-expanding especially since the community embraced the era of deep learning, which provides the ground to develop, validate, and advance large AI models for breakthroughs in health-related areas. This article presents a comprehensive review of large AI models, from background to their applications. We identify seven key sectors in which large AI models are applicable and might have substantial influence, including 1) bioinformatics; 2) medical diagnosis; 3) medical imaging; 4) medical informatics; 5) medical education; 6) public health; and 7) medical robotics. We examine their challenges, followed by a critical discussion about potential future directions and pitfalls of large AI models in transforming the field of health informatics.

Epilepsy seizure prediction paves the way of timely warning for patients to take more active and effective intervention measures. Compared to seizure detection that only identifies the inter-ictal state and the ictal state, far fewer researches have been conducted on seizure prediction because the high similarity makes it challenging to distinguish between the pre-ictal state and the inter-ictal state. In this paper, a novel solution on seizure prediction is proposed using common spatial pattern (CSP) and convolutional neural network (CNN). Firstly, artificial pre-ictal EEG signals based on the original ones are generated by combining the segmented pre-ictal signals to solve the trial imbalance problem between the two states. Secondly, a feature extractor employing wavelet packet decomposition and CSP is designed to extract the distinguishing features in both the time domain and the frequency domain. It can improve overall accuracy while reducing the training time. Finally, a shallow CNN is applied to discriminate between the pre-ictal state and the inter-ictal state. Our proposed solution is evaluated on 23 patient's data from Boston Children's Hospital-MIT scalp EEG dataset by employing a leave-one-out cross-validation, and it achieves a sensitivity of 92.2% and false prediction rate of 0.12/h. Experimental result demonstrates that the proposed approach outperforms most state-of-the-art methods.