Article
Mathematics, Applied
Monika Petelczyc, Zbigniew Czechowski
Summary: Stochastic models of time series can be nonlinear equations with a built-in memory mechanism. The generated time series can be characterized by certain features such as non-stationarity, irreversibility, irregularity, multifractality, and distribution type. This paper systematically analyzes the relationship between measures of irreversibility, irregularity, and non-stationarity and the degree of nonlinearity and persistence using a modified nonlinear Langevin equation. The results show that changes in nonlinearity affect irregularity and non-stationarity markers significantly, while a synergy of non-linearity and persistence is needed for greater changes in irreversibility.
Article
Physics, Multidisciplinary
Lina Zhao, Jianqing Li, Xiangkui Wan, Shoushui Wei, Chengyu Liu
Summary: The study introduced a new entropy-based AF detection method, Entropy(AF), with high accuracy in classifying AF and non-AF rhythms. The determination of parameters r and n is crucial for the classification, with smaller values leading to better detection accuracy. The best AUC value for AF detection was 98.15%, achieved with specific parameter combinations for Entropy(AF).
Article
Mathematics, Interdisciplinary Applications
Chen Diao, Ning Cai
Summary: In this study, an improved second-order difference plot is proposed to analyze the variability of heart rate variability. The temporal variation measure analysis is introduced to quantitatively describe the distribution patterns of scatter points and extract the acceleration information of heart rate variability. Experimental results demonstrate the effectiveness of the temporal variation measure analysis.
Article
Health Care Sciences & Services
Justin C. Niestroy, J. Randall Moorman, Maxwell A. Levinson, Sadnan Al Manir, Timothy W. Clark, Karen D. Fairchild, Douglas E. Lake
Summary: New vital sign measures were discovered through highly comparative time-series analysis to identify newborns in the Neonatal Intensive Care Unit (NICU) at the highest risk of death.
NPJ DIGITAL MEDICINE
(2022)
Article
Psychology, Multidisciplinary
Yotam Sahar, Tomer Elbaum, Michael Wagner, Oren Musicant, Tehila Hirsh, Shraga Shoval
Summary: Driver performance is crucial for road safety, and there is a relationship between performance and stress levels. The study explores grip force as a potential measure of stress in driving tasks, showing significant correlations with heart rate and heart rate variability. Initial evidence suggests that grip force can be a useful tool for measuring stress in driving tasks.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Environmental Sciences
Minna Tang, Yu He, Xiaochun Zhang, Huichu Li, Chang Huang, Cuiping Wang, Ya Gao, Yinliang Li, Haidong Kan, Jialu Hu, Renjie Chen
Summary: The study found that temperature variability is negatively associated with heart rate variability, especially on the same day. The exposure-response relationships were almost linear for most parameters. The increase in temperature variability is significantly associated with the decrease in heart rate variability, with females being more affected.
ENVIRONMENTAL RESEARCH
(2021)
Article
Mathematics, Interdisciplinary Applications
Bhabesh Deka, Dipen Deka
Summary: The assessment of dynamical complexity is vital in various fields such as medical diagnostics, mechanical system fault analysis, and astrophysics. Traditional entropy measures are limited by short data length and sensitive predetermined parameters. Distribution entropy (DistEn) is a robust complexity estimator, but it fails to distinguish noise and chaotic signals while underestimating their complexity at higher scales. To overcome these limitations, an improved distribution entropy (ImDistEn) is proposed, which utilizes embedded vectors' orientation, ordinality, and l(1)-norm distance information. Simulation results demonstrate that ImDistEn can accurately assess the complexity of different types of signals.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Physics, Multidisciplinary
Lina Zhao, Peng Li, Jianqing Li, Chengyu Liu
Summary: The study found that different numbers of ectopic beats affect HRV parameters, with the degree of influence increasing as the number of ectopic beats increases. Among the four indices, Pt-SampEn shows better robustness to ectopic beats.
Article
Computer Science, Interdisciplinary Applications
M. Moya-Ramon, M. Mateo-March, I. Pena-Gonzalez, M. Zabala, A. Javaloyes
Summary: The validity and reliability of short and ultra-short HRV measurements in elite cyclists were assessed using different smartphone applications. Both Elite HRV and Welltory showed good correlation with electrocardiogram measurements and can be implemented to monitor HRV. There were no differences between short and ultra-short measurement lengths.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Multidisciplinary Sciences
Ruitao Gao, Huachao Yan, Zhou Yang
Summary: This paper investigates the impact of tractor field operations vibration on driver comfort and health through physiological indicators collection experiments. The study proposes a vibration comfort evaluation method based on multiple physiological parameters and uses an artificial neural network model to predict discomfort with an accuracy rate of 88.9%. The effectiveness of physiological signals changing with human body vibration is verified by changing vibration conditions with a shock-absorbing suspension on a tractor, providing a basis for structural design optimization.
Article
Engineering, Biomedical
Bella Eszter Ajtay, Szabolcs Beres, Laszlo Hejjel
Summary: The present study examined the beat-to-beat pulse arrival time (PAT) and analyzed the relationship between pulse rate variability (PRV) and heart rate variability (HRV). The results showed that PAT had the minimum relative precision (RP%) at the 1/2 amplitude point and the maximum RP% at the base point. The observed fine oscillation of PAT was associated with breathing. The instantaneous slope of photoplethysmogram (PPG) rise was inversely proportional to the corresponding PAT. Comparisons of PRV and HRV parameters showed excellent agreement in most of the analysis. The difference between HRV and PRV is caused by the difference between two consecutive PATs.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Szabolcs Beres, Laszlo Hejjel
Summary: The study found that a sampling frequency of 5 Hz may be sufficient for monitoring average heart rate in healthy subjects, while accurate HRV analysis requires higher sampling rates. Interpolation techniques can improve HRV accuracy from lower temporal resolution PPG signals.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Chemistry, Multidisciplinary
Raquel Cervigon, Brian McGinley, Darren Craven, Martin Glavin, Edward Jones
Summary: This study investigates the effects of ECG signal compression on an entropy-based AF detection algorithm, demonstrating that compression ratios of up to 90 can be obtained while maintaining a detection accuracy of at least 0.9.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Biomedical
Vincenzo Catrambone, Gaetano Valenza
Summary: This study proposes an analysis framework to estimate the directional information flow between whole-brain and heartbeat dynamics. The experimental results demonstrate that there is a bidirectional increase in brain-heart interplay during cognitive workload and an increase in descending interplay during an autonomic maneuver. These changes cannot be detected by isolated cortical and heartbeat dynamics.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Hiroatsu Hatsukawa, Masaaki Ishikawa
Summary: Pupillary light reflex (PLR) and heart rate variability (HRV) parameters can serve as objective indicators of chronic rhinosinusitis (CRS) status. Adjusting among-individual variability can improve model fit when analyzing CRS-specific quality of life, leading to robust conclusions.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Artificial Intelligence
Andre M. Carrington, Douglas G. Manuel, Paul W. Fieguth, Tim Ramsay, Venet Osmani, Bernhard Wernly, Carol Bennett, Steven Hawken, Olivia Magwood, Yusuf Sheikh, Matthew McInnes, Andreas Holzinger
Summary: This paper proposes a new method called deep ROC analysis to evaluate the performance of binary classifiers and diagnostic tests. It provides more detailed information compared to traditional performance measures. The method measures the performance in multiple groups and allows comparisons between groups. The paper also offers a new interpretation of AUC as balanced average accuracy, relevant to individuals.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Rehabilitation
Martina Pigliautile, Theresa Koenig, Christopher C. Mayer, Matteo Colombo, Anna Giulia Guazzarini, Markus Muellner-Rieder, Oscar Aguila, Christophoros Christophorou, Argyris Constantinides, Rosario Curia, Maria Stillo, Jon Arambarri, Christian Schueler, Elisabeth Stoegmann, Patrizia Mecocci
Summary: Assistive technologies have the potential to support people with memory complaints in daily life. User-centered interaction design research helps developers create systems suitable for users. Results from the usability test of the first Memento prototype, involving users from Italy, Austria and Spain, showed design, technical problems, target-group-related challenges and users' perception of usability, with suggestions for improvement highlighted by users.
DISABILITY AND REHABILITATION-ASSISTIVE TECHNOLOGY
(2023)
Article
Biochemical Research Methods
Andreas Holzinger, Katharina Keiblingera, Petr Holub, Kurt Zatloukal, Heimo Mueller
Summary: Due to the successes of AI, such as ChatGPT, and the combination of biotechnology, new potential solutions have emerged to address global problems and contribute to sustainability.
Article
Radiology, Nuclear Medicine & Medical Imaging
Gabriel Adelsmayr, Michael Janisch, Heimo Mueller, Andreas Holzinger, Emina Talakic, Elmar Janek, Simon Streit, Michael Fuchsjaeger, Helmut Schoellnast
Summary: This study aimed to investigate whether CT texture analysis can differentiate between different types of lung cancers and tumors. The study included 133 patients who underwent CT-guided biopsy of the lung. The results showed significant differences in texture features between different entities, and the use of a HU threshold affected the results of the analysis. Rating: 7/10
EUROPEAN JOURNAL OF RADIOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Federico Cabitza, Andrea Campagner, Gianclaudio Malgieri, Chiara Natali, David Schneeberger, Karl Stoeger, Andreas Holzinger
Summary: This paper presents a framework for defining different types of explanations of AI systems and criteria for evaluating their quality. It proposes a structural view of constructing explanations and suggests a typology based on the explanandum, explanantia, and their relationship. The paper highlights the importance of epistemological and psychological perspectives in defining quality criteria and aims to support clear inventories, verification criteria, and validation methods for AI explainability.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Letter
Peripheral Vascular Disease
Andrie G. Panayiotou, Chloe Park, Rachel E. Climie, Christopher C. Mayer, Giacomo Pucci, Elisabetta Bianchini, Thomas Weber, Areti Triantafyllou
JOURNAL OF HYPERTENSION
(2023)
Article
Biophysics
Theresa Letz, Carina Hoerandtner, Matthias C. Braunisch, Peter Gundel, Julia Matschkal, Martin Bachler, Georg Lorenz, Andrea Koerner, Carolin Schaller, Moritz Lattermann, Andreas Holzinger, Uwe Heemann, Siegfried Wassertheurer, Christoph Schmaderer, Christopher C. Mayer
Summary: The aim of this study is to compare automatic to manual measurements of left ventricular hypertrophy (LVH) parameters and investigate their predictive value for cardiovascular and all-cause mortality in patients with end-stage kidney disease (ESKD). The study found that automatic algorithms can be as reliable as manual measurements in assessing LVH parameters and predicting risk in ESKD patients.
PHYSIOLOGICAL MEASUREMENT
(2023)
Editorial Material
Physiology
Janos Nemcsik, Christopher Clemens Mayer, Andrea Guala, Dimitrios Terentes-Printzios, Bart Spronck
FRONTIERS IN PHYSIOLOGY
(2023)
Review
Pathology
Markus Plass, Michaela Kargl, Tim-Rasmus Kiehl, Peter Regitnig, Christian Geissler, Theodore Evans, Norman Zerbe, Rita Carvalho, Andreas Holzinger, Heimo Mueller
Summary: The development of digital pathology allows pathologists to utilize AI-based computer programs for advanced analysis of whole slide images. However, the best-performing AI algorithms for image analysis are considered black boxes, making it unclear why they produce specific results. This article addresses the issue of explainability in digital pathology and discusses the necessity of explainable AI (XAI) techniques to enhance transparency and causal understanding. The authors argue for the development of user interfaces that enable contextual understanding and interactive questioning to bridge the gap between AI processes and medical experts' knowledge.
JOURNAL OF PATHOLOGY CLINICAL RESEARCH
(2023)
Article
Mathematics, Interdisciplinary Applications
Claire Jean-Quartier, Katharina Bein, Lukas Hejny, Edith Hofer, Andreas Holzinger, Fleur Jeanquartier
Summary: In response to socioeconomic development, this study focuses on the transparency and sustainability aspects of artificial intelligence in terms of energy consumption. The research measures carbon emissions and energy consumption of Python algorithms and tests the impact of explainability on algorithmic energy consumption. The results can guide the selection of tools to measure algorithmic energy consumption and raise awareness of emission-based model optimization by highlighting the sustainability of explainable artificial intelligence.
Review
Cardiac & Cardiovascular Systems
Jordi Alastruey, Peter H. Charlton, Vasiliki Bikia, Birute Paliakaite, Bernhard Hametner, Rosa Maria Bruno, Marijn P. Mulder, Samuel Vennin, Senol Piskin, Ashraf W. Khir, Andrea Guala, Christopher C. Mayer, Jonathan Mynard, Alun D. Hughes, Patrick Segers, Berend E. Westerhof
Summary: Arterial pulse waves (PWs), such as blood pressure and photoplethysmogram (PPG) signals, are rich sources of information for assessing vascular age and identifying individuals at elevated cardiovascular risk. This review explores the possibilities and limitations of reduced-order biophysical models and theoretical and empirical methods for analyzing PW signals and extracting clinically relevant information. Detailed mathematical derivations are provided, demonstrating the relationships between these models and methods. Suggestions for future research are also outlined to fully utilize the potential of modeling and analyzing PW signals for accurate vascular age assessment.
AMERICAN JOURNAL OF PHYSIOLOGY-HEART AND CIRCULATORY PHYSIOLOGY
(2023)
Article
Health Care Sciences & Services
Julian Matschinske, Julian Spaeth, Mohammad Bakhtiari, Niklas Probul, Mohammad Mahdi Kazemi Majdabadi, Reza Nasirigerdeh, Reihaneh Torkzadehmahani, Anne Hartebrodt, Balazs-Attila Orban, Sandor-Jozsef Fejer, Olga Zolotareva, Supratim Das, Linda Baumbach, Josch K. Pauling, Olivera Tomasevic, Bela Bihari, Marcus Bloice, Nina C. Donner, Walid Fdhila, Tobias Frisch, Anne-Christin Hauschild, Dominik Heider, Andreas Holzinger, Walter Hoetzendorfer, Jan Hospes, Tim Kacprowski, Markus Kastelitz, Markus List, Rudolf Mayer, Monika Moga, Heimo Mueller, Anastasia Pustozerova, Richard Roettger, Christina C. Saak, Anna Saranti, Herald H. H. W. Schmidt, Christof Tschohl, Nina K. Wenke, Jan Baumbach
Summary: Machine learning and artificial intelligence have achieved promising results in various fields, driven by the increasing availability of data. However, these data are often distributed across different institutions and cannot be easily shared due to strict privacy regulations. Federated learning (FL) enables the training of distributed machine learning models without sharing sensitive data. However, implementing FL is time-consuming and requires advanced programming skills and complex technical infrastructures.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Editorial Material
Transplantation
Maximilian Waller, Simon Krenn, Sebastian Mussnig, Michael Schmiedecker, Janosch Niknam-Saeidi, Christopher C. Mayer, Peter Wabel, Daniel Schneditz, Charles Chazot, Manfred Hecking
Summary: This article provides a video link to watch the related content.
NEPHROLOGY DIALYSIS TRANSPLANTATION
(2023)
Review
Computer Science, Artificial Intelligence
Andreas Holzinger, Anna Saranti, Alessa Angerschmid, Bettina Finzel, Ute Schmid, Heimo Mueller
Summary: Artificial intelligence has made significant progress in standard pattern recognition tasks, but there is still a significant gap between AI and human-level concept learning. To analyze current approaches and drive progress, experimental environments and diagnostic/benchmark datasets are needed for explainable machine intelligence. This paper provides an overview of current AI solutions for benchmarking concept learning, reasoning, and generalization, discusses state-of-the-art diagnostic/benchmark datasets, and explores future research directions in this exciting field.