Tibor Maximilian Szikszay

Tibor Maximilian Szikszay

Auto-generated profile, based on publicly available information

Tibor Maximilian Szikszay

Institute of Health Sciences, Department of Physiotherapy, Pain and Exercise Research Luebeck (P.E.R.L.), University of Luebeck, Lübeck, Germany

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2021 in Sensors
Verified
Journal Article
Open access
PDF file
PGPhilip Gouverneur
Philip Gouverneur
FLFrédéric Li
Frédéric Li
WAWacław M. Adamczyk
Wacław M. Adamczyk
TSTibor M. Szikszay
Tibor M. Szikszay
KLKerstin Luedtke
Kerstin Luedtke
MGMarcin Grzegorzek
Marcin Grzegorzek
While even the most common definition of pain is under debate, pain assessment has remained the same for decades. But the paramount importance of precise pain management for successful healthcare has encouraged initiatives to improve the way pain is assessed. Recent approaches have proposed automatic pain evaluation systems using machine learning models trained with data coming from behavioural or physiological sensors. Although yielding promising results, machine learning studies for sensor-based pain recognition remain scattered and not necessarily easy to compare to each other. In particular, the important process of extracting features is usually optimised towards specific datasets. We thus introduce a comparison of feature extraction methods for pain recognition based on physiological sensors in this paper. In addition, the PainMonit Database (PMDB), a new dataset including both objective and subjective annotations for heat-induced pain in 52 subjects, is introduced. In total, five different approaches including techniques based on feature engineering and feature learning with deep learning are evaluated on the BioVid and PMDB datasets. Our studies highlight the following insights: (1) Simple feature engineering approaches can still compete with deep learning approaches in terms of performance. (2) More complex deep learning architectures do not yield better performance compared to simpler ones. (3) Subjective self-reports by subjects can be used instead of objective temperature-based annotations to build a robust pain recognition system.

31 July 2022 in The Journal of Pain
Verified
Journal Article
Open access
WAWaclaw M. Adamczyk
Waclaw M. Adamczyk
TSTibor M. Szikszay
Tibor M. Szikszay
HNHadas Nahman-Averbuch
Hadas Nahman-Averbuch
JSJacek Skalski
Jacek Skalski
JNJakub Nastaj
Jakub Nastaj
KLKerstin Luedtke
Kerstin Luedtke
To calibrate or not to calibrate? This question is raised by almost everyone designing an experimental pain study with supra-threshold stimulation. The dilemma is whether to individualize stimulus intensity to the pain threshold / supra-threshold pain level of each participant or whether to provide the noxious stimulus at a fixed intensity so that everyone receives the identical input. Each approach has unique pros and cons which need to be considered to i) accurately design an experiment, ii) enhance statistical inference in the given data and, iii) reduce bias and the influence of confounding factors in the individual study e.g., body composition, differences in energy absorption and previous experience. Individualization requires calibration, a procedure already irritating the nociceptive system but allowing to match the pain level across individuals. It leads to a higher variability of the stimulus intensity, thereby influencing the encoding of "noxiousness" by the central nervous system. Results might be less influenced by statistical phenomena such as ceiling/floor effects and the approach does not seem to rise ethical concerns. On the other hand, applying a fixed (standardized) intensity reduces the problem of intensity encoding leading to a large between-subjects variability in pain responses. Fixed stimulation intensities do not require pre-exposure. It can be proposed that one method is not preferable over another, however the choice depends on the study aim and the desired level of external validity. This paper discusses considerations for choosing the optimal approach for experimental pain studies and provides recommendations for different study designs. PERSPECTIVE: To calibrate pain or not? This dilemma is related to almost every experimental pain research. The decision is a trade-off between statistical power and greater control of stimulus encoding. The article decomposes both approaches and presents the pros and cons of either approach supported by data and simulation experiment.

9 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
PGPhilip Gouverneur
Philip Gouverneur
FLFrédéric Li
Frédéric Li
KSKimiaki Shirahama
Kimiaki Shirahama
LLLuisa Luebke
Luisa Luebke
WAWacław M. Adamczyk
Wacław M. Adamczyk
MGMarcin Grzegorzek
Marcin Grzegorzek
Artificial intelligence and especially deep learning methods have achieved outstanding results for various applications in the past few years. Pain recognition is one of them, as various models have been proposed to replace the previous gold standard with an automated and objective assessment. While the accuracy of such models could be increased incrementally, the understandability and transparency of these systems have not been the main focus of the research community thus far. Thus, in this work, several outcomes and insights of explainable artificial intelligence applied to the electrodermal activity sensor data of the PainMonit and BioVid Heat Pain Database are presented. For this purpose, the importance of hand-crafted features is evaluated using recursive feature elimination based on impurity scores in Random Forest (RF) models. Additionally, Gradient-weighted class activation mapping is applied to highlight the most impactful features learned by deep learning models. Our studies highlight the following insights: (1) Very simple hand-crafted features can yield comparative performances to deep learning models for pain recognition, especially when properly selected with recursive feature elimination. Thus, the use of complex neural networks should be questioned in pain recognition, especially considering their computational costs; and (2) both traditional feature engineering and deep feature learning approaches rely on simple characteristics of the input time-series data to make their decision in the context of automated pain recognition.

26 June 2018 in The Journal of Headache and Pain
Verified
Journal Article
Open access
PDF file
KLKerstin Luedtke
Kerstin Luedtke
WAWaclaw Adamczyk
Waclaw Adamczyk
KMKatrin Mehrtens
Katrin Mehrtens
IMInken Moeller
Inken Moeller
LRLouisa Rosenbaum
Louisa Rosenbaum
BWBettina Wollesen
Bettina Wollesen
Chronic pain including migraine is associated with structural and functional changes in the somatosensory cortex. Previous reports proposed two-point discrimination (TPD) as a measurement for cortical alterations. Limited evidence exists for tactile acuity in the neck and no data is available for migraine. To introduce a standardized protocol for the measurement of TPD in the upper cervical spine, 51 healthy participants were investigated with a newly developed paradigm which was evaluated for intra-rater reliability. The same protocol was applied by two further examiners to 28 migraine patients and 21 age-, and gender-matched healthy controls to investigate inter-rater reliability and between group differences. Results indicated excellent intra-rater (right ICC(2,4) = 0.82, left ICC(2,4) = 0.83) and good inter-rater reliability (right ICC(2,4) = 0.70, left ICC(2,4) = 0.75). Migraine patients had larger TPD thresholds (26.86 ± 7.21) than healthy controls (23.30 ± 6.17) but these became only statistically significant for the right side of the neck (p = 0.02). There was a significant, moderate association with age for the right side (r = 0.42 p = 0.002, n = 51), and less strong association for the left side (r = 0.34, p = 0.14) in healthy individuals. TPD did not correlate with headache days per month or the dominant headache side in migraine patients. Surprisingly, migraine patients showed increased TPD thresholds in the upper cervical spine interictally. Although a body of evidence supports that hypersensitivity is part of the migraine attack, the current report indicates that interictally, migraine patients showed worse tactile acuity similar to other chronic pain populations. This has been hypothesized to indicate structural and functional re-organisation of the somatosensory cortex.

31 July 2018 in Journal of Manual & Manipulative Therapy
Verified
Journal Article
Open access
TSTibor M. Szikszay
Tibor M. Szikszay
KLKerstin Luedtke
Kerstin Luedtke
HPHarry von Piekartz
Harry von Piekartz
Objectives: To investigate differences in pressure pain thresholds (PPTs) and longitudinal mechanosensitivity of the greater occipital nerve (GON) between patients with side-dominant head and neck pain (SDHNP) and healthy controls. Evaluation of neural sensitivity is not a standard procedure in the physical examination of headache patients but may influence treatment decisions. Methods: Two blinded investigators evaluated PPTs on two different locations bilaterally over the GON as well as the occipitalis longsitting-slump (OLSS) in subjects with SDHNP (n = 38)) and healthy controls (n = 38). Results: Pressure pain sensitivity of the GON was lower at the occiput in patients compared to controls (p = 0.001). Differences in pressure sensitivity of the GON at the nucheal line, or between the dominant headache side and the non-dominant side were not found (p > 0.05). The OLSS showed significant higher pain intensity in SDHNP (p < 0.001). In comparison to the non-dominant side, the dominant side was significantly more sensitive (p = 0.004). Discussion: Palpation of the GON at the occiput and the OLSS may be potentially relevant tests in SDHNP. One explanation for an increased bilateral sensitivity may be sensitization mechanisms. Future research should investigate the efficacy of neurodynamic techniques directed at the GON. Level of Evidence: 3b.

15 February 2021 in Pain Medicine
Verified
Journal Article
Closed access
PDF file
TSTibor M Szikszay
Tibor M Szikszay
JLJuliette L M Lévénez
Juliette L M Lévénez
JSJanne von Selle
Janne von Selle
WAWaclaw M Adamczyk
Waclaw M Adamczyk
KLKerstin Luedtke
Kerstin Luedtke
Endogenous pain modulation can be quantified using various paradigms. Commonly used paradigms include conditioned pain modulation (CPM), offset analgesia (OA), spatial summation (SSP) and temporal summation of pain (TSP) which reflect spatial and temporal aspects of pro- and antinociceptive processing. Although these paradigms are regularly used and are of high clinical relevance, the underlying physiological mechanisms are not fully understood. The aim of this study is therefore to assess the association between these paradigms using comparable protocols and methodological approaches. University Campus. Healthy and pain-free volunteers (n = 48) underwent psychophysical assessment of CPM, OA, SSP and TSP (random order) at the same body area (volar non-dominant forearm) with individualized noxious stimuli. CPM included heat stimuli before, during and after a noxious cold-water bath, while for OA, three heat stimuli were applied: baseline trial, offset trial and constant trial. For the SSP paradigm, two differently sized heat stimulation areas were evaluated, while for TSP, the first and last stimulus of ten consecutive short heat stimuli were assessed. A computerized visual analogue scale was used to continuously evaluate pain intensity. Using Spearman's correlation, the magnitudes of all association between all paradigm pairs were analyzed and individual influencing factors were assessed with a multivariate linear regression model. Weak to moderate correlations between all four paradigms was found (p>0.05) and no distinct influencing factors were identified. A limited association between pain modulation paradigms suggests that CPM, OA, SSP and TSP assess distinct aspects of endogenous analgesia with different underlying physiological mechanisms