Guest Editorial: Special issue on “Artificial Intelligence in Health Informatics”

Siuly Siuly, Uwe Aickelin, Enamul Kabir, Zhisheng Huang, Yanchun ZhangHealth Information Science and Systems 2021 · DOI · OpenAlex

Artificial Intelligence (AI) has transitioned from a futuristic concept to a robust, fast-growing pillar of Health Informatics (HI). By mimicking human perception, learning, and decision-making, AI systems are now essential tools for managing the vast complexities of modern healthcare. This special issue of Health Information Science and Systems curates 16 peer-reviewed papers that explore the cutting edge of AI applications in clinical and public health settings.

Addressing the Healthcare Knowledge Explosion

Modern medicine faces a significant challenge: the "knowledge explosion." Clinicians are inundated with data from electronic health records, medical imaging, and real-time physiological sensors. Synthesizing this information to solve complex problems—such as identifying disease patterns or forecasting health trends—is increasingly difficult for human minds alone.

AI serves as a vital bridge in this gap. It is no longer merely an automation tool but a necessity for improving diagnostic accuracy, optimizing therapeutic decisions, and predicting clinical outcomes. The research presented in this issue addresses the practical application of AI in solving real-world HI problems, moving beyond theoretical models to actionable clinical aids.

Methodological Frontiers

The special issue highlights a diverse methodological toolkit. One of the most innovative trends is the "image-ification" of medical signals. Researchers have successfully converted 1D audio signals, such as heart and lung sounds, into 2D spectrograms. This allows them to utilize powerful pre-trained computer vision models like AlexNet and VGG for high-accuracy classification.

Other key technical advancements include:

  • Multimodal Fusion: Integrating disparate data types, such as combining functional near-infrared spectroscopy (fNIR) and electroencephalography (EEG) signals, to enhance Brain-Computer Interface (BCI) performance.
  • Natural Language Processing (NLP): Leveraging neural attention mechanisms and character-level embeddings to mine social media (e.g., Twitter) for public health surveillance, effectively handling the informal language and typos inherent in such data.
  • Knowledge Representation: Using Fuzzy Cognitive Maps (FCM) to visualize causal relationships in traditional medicine and Heterogeneous Information Graphs (HIG) for patient status prediction.
  • Advanced Signal Processing: Implementing techniques like Tunable-Q Factor Wavelet Transform (TQWT) to refine raw physiological data before analysis.

Diverse Data Sources and Real-World Impact

The research spans a wide array of datasets, from global clinical databases like ICBHI 2017 (lung sounds) to regional studies in Iran and India. This diversity underscores the global reach of AI in HI.

Key Results and Insights

  • Enhanced Diagnostics: Spectrogram-based CNN architectures have significantly outperformed traditional methods in detecting heart and lung ailments.
  • Operational Efficiency: Data mining models have successfully identified critical factors affecting hospital Length of Stay (LOS), providing administrators with tools to optimize resource allocation.
  • Data Resilience: Several papers address the challenge of imperfect data, using machine learning for imputation (filling missing values) in breast cancer datasets and semi-supervised clustering for unlabeled patient records.
  • Explainability: By using Fuzzy Cognitive Maps, researchers are making AI more "interpretable," showing clinicians the underlying logic behind suggested treatment paths—a crucial step for clinical adoption.

The Path Forward

While the results are promising, the editorial identifies key areas for future growth. There is a pressing need to validate these models across more diverse global populations to ensure generalizability. Furthermore, the transition from "research lab" to "real-time clinical workflow" remains a hurdle. Finally, the scarcity of high-quality, annotated medical datasets continues to be a bottleneck for training the next generation of robust AI models.

This special issue demonstrates that AI is not just simulating human intelligence; it is augmenting it, providing the tools necessary to navigate the complexities of 21st-century medicine.

Summary updated

Abstract

Globally, Artificial intelligence (AI) has been playing a robust and the fastest growing role in Health Informatics (HI) the last few decades. AI enables computers and machines to mimic the perception, learning, problem-solving, and decision-making capabilities of the human mind. Generally, AI refers to the simulation of human intelligence processes by machines, especially computer systems that are programmed to think like humans and mimic their actions. Modern health treatments are faced with the challenge of acquiring, analysing and applying the large amount of knowledge necessary to solve complex problems. In HI, AI can help manage and analyze data, make decisions, and identify and forecasting the upcoming health problems. The greatest application of AI technologies is delivering huge effort in the fields of health to effectively identify diseases and advance medical diagnosis and improve the efficiency of treatments, and avoid the risks of false diagnosis, the making of therapeutic decisions and the prediction of outcome in many clinical scenarios.
BibTeX
@inproceedings{siuly2021guest,
  author = {Siuly Siuly and Uwe Aickelin and Enamul Kabir and Zhisheng Huang and Yanchun Zhang},
  title = {{Guest Editorial: Special issue on “Artificial Intelligence in Health Informatics”}},
  booktitle = {Health Information Science and Systems},
  year = {2021},
  doi = {10.1007/s13755-021-00155-7},
}
Figure