Today, modern medical research is assisted by various technical sciences. Incentive to develop algorithms of artificial intelligence, fuzzy systems, programming languages, and microelectronics generates innovative solutions in health-care services or both physical and behavioral biometrics. Computer-based medical diagnosis support systems are among the fastest developing fields in biology, medicine, and biometry. This special issue on Intelligent Methods Applied to Health-Care Information Systems focuses on the newest research developments in support of medical treatments, diagnostics, prediction, etc., from an artificial intelligence point of view as well as from mathematics, statistics, and classification systems.
The 21st century represents a unique opportunity for the convergence of engineering and medicine. A greater and more seamless flow of information within a digital health-care structure is created by the implementation of an electronic health record (EHR) in many health-care institutions. Our review article presents the challenges and trends in the EHR area and shows its role in a wide medical environment. Despite significant efforts to develop the knowledge and technological abilities that are essential for addressing problems raised by EHR data availability using artificial intelligence and engineering methods, the optimization of this approach remains a grand challenge. Selected articles identify the topic problems of the EHRs, recommending some standards and further developing directions.
Accordingly, the current issue presents seven research papers dealing with recent aspects of EHR.
Bogusław Cyganek et al. present the selected aspects of EHR analysis from the big data perspective, such as efficient computer system structures, data quality and data privacy, data mining, tensor-based approaches to multidimensional data, cost-sensitive approaches, and, especially, on the nonstationary analysis of the medical data stream.
Tomasz E. Wesołowski et al. focus on EHR security and propose the novel solution for EHR protection by continuous user verification. The introduced approach is based on keystroke dynamics analysis performed by a computer user profiling and an intrusion detection system in which an ensemble of classifiers supported by machine learning methods was used.
Krisztian Buza and Noémi Ágnes Varga examine the presence of hubs in speech data recorded from patients affected by Parkinson’s Disease (PD) and take this property into account in order to increase the accuracy of feedforward neural networks used to estimate the Unified Parkinson’s Disease Rating Scale (UPDRS) score of PD patients.
Robert Czabanski et al. propose the method for retrospective fetal-state assessment using the results of the fuzzy analysis of delivery outcome attributes, aiming to improve the efficiency of the automated assessment of the fetal state with supervised-learning-based methods.
Michal Jezewski et al. concentrate on the application of clustered pairs of prototypes to determine the antecedents of the rules defining the fuzzy classifier that supports the qualitative assessment of the fetal state based on the cardiotocographic signals.
José A. Saéz et al. analyze the usefulness of noise filtering methods in the context of medical data classification. The experiments carried out on several real-world datasets show the importance of noise filtering when class noise affects the data.
In his work, Tomasz Andrysiak uses sparse representation of a signal based on overcomplete dictionaries of base functions, and a QRS detection method using artificial neural network to detect anomalies in the analyzed ECG signals. Performance of the proposed method was tested by means of a widely available database of ECG signals, i.e., the MIT-BIH Arrhythmia Database, and the obtained experimental results confirmed its effectiveness for anomaly detection in the analyzed ECG signals.
To conclude, we would like to thank Prof. Robert Trappl, Editor-in-Chief of Applied Artificial Intelligence, for giving us the opportunity to prepare this special issue and Ms. Karin Vorsteher for her help in preparing the final version of this issue. We would also like to thank the reviewers for contributing to this issue with their work and time, and all the authors who submitted articles to the issue.