Georgios Giarmatzis

Dr. Georgios Giarmatzis

Patras University
orcid

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
19 February 2015 in Journal of Bone and Mineral Research
Verified
Journal Article
Closed access
PDF file
GGGeorgios Giarmatzis
Georgios Giarmatzis
IJIlse Jonkers
Ilse Jonkers
MWMariska Wesseling
Mariska Wesseling
SRSam Van Rossom
Sam Van Rossom
SVSabine Verschueren
Sabine Verschueren

1 October 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
Christos KokkotisChristos Kokkotis
Christos Kokkotis
GGGeorgios Giarmatzis
Georgios Giarmatzis
EGErasmia Giannakou
Erasmia Giannakou
SMSerafeim Moustakidis
Serafeim Moustakidis
THEMISTOKLIS TSATALASTHEMISTOKLIS TSATALAS
THEMISTOKLIS TSATALAS
NANikolaos Aggelousis
Nikolaos Aggelousis
Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients’ class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.

4 December 2020 in Sensors
Verified
Journal Article
Open access
PDF file
GGGeorgios Giarmatzis
Georgios Giarmatzis
Evangelia I. ZacharakiEvangelia I. Zacharaki
Evangelia I. Zacharaki
Konstantinos  MoustakasKonstantinos Moustakas
Konstantinos Moustakas
Conventional biomechanical modelling approaches involve the solution of large systems of equations that encode the complex mathematical representation of human motion and skeletal structure. To improve stability and computational speed, being a common bottleneck in current approaches, we apply machine learning to train surrogate models and to predict in near real-time, previously calculated medial and lateral knee contact forces (KCFs) of 54 young and elderly participants during treadmill walking in a speed range of 3 to 7 km/h. Predictions are obtained by fusing optical motion capture and musculoskeletal modeling-derived kinematic and force variables, into regression models using artificial neural networks (ANNs) and support vector regression (SVR). Training schemes included either data from all subjects (LeaveTrialsOut) or only from a portion of them (LeaveSubjectsOut), in combination with inclusion of ground reaction forces (GRFs) in the dataset or not. Results identify ANNs as the best-performing predictor of KCFs, both in terms of Pearson R (0.89–0.98 for LeaveTrialsOut and 0.45–0.85 for LeaveSubjectsOut) and percentage normalized root mean square error (0.67–2.35 for LeaveTrialsOut and 1.6–5.39 for LeaveSubjectsOut). When GRFs were omitted from the dataset, no substantial decrease in prediction power of both models was observed. Our findings showcase the strength of ANNs to predict simultaneously multi-component KCF during walking at different speeds—even in the absence of GRFs—particularly applicable in real-time applications that make use of knee loading conditions to guide and treat patients.

4 April 2018 in PLOS ONE
Verified
Journal Article
Open access
PDF file
PPPim Pellikaan
Pim Pellikaan
GGGeorgios Giarmatzis
Georgios Giarmatzis
JSJos Vander Sloten
Jos Vander Sloten
SVSabine Verschueren
Sabine Verschueren
IJIlse Jonkers
Ilse Jonkers
The current study aimed to assess the potential of different exercises triggering an osteogenic response at the femoral neck in a group of postmenopausal women. The osteogenic potential was determined by ranking the peak hip contact forces (HCFs) and consequent peak tensile and compressive strains at the superior and inferior part of the femoral neck during activities such as (fast) walking, running and resistance training exercises. Results indicate that fast walking (5–6 km/h) running and hopping induced significantly higher strains at the femoral neck than walking at 4 km/h which is considered a baseline exercise for bone preservation. Exercises with a high fracture risk such as hopping, need to be considered carefully especially in a frail elderly population and may therefore not be suitable as a training exercise. Since superior femoral neck frailness is related to elevated hip fracture risk, exercises such as fast walking (above 5 km/h) and running can be highly recommended to stimulate this particular area. Our results suggest that a training program including fast walking (above 5 km/h) and running exercises may increase or preserve the bone mineral density (BMD) at the femoral neck.

5 March 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Dimitar StanevDimitar Stanev
Dimitar Stanev
KFKonstantinos Filip
Konstantinos Filip
DBDimitrios Bitzas
Dimitrios Bitzas
SZSokratis Zouras
Sokratis Zouras
GGGeorgios Giarmatzis
Georgios Giarmatzis
Konstantinos  MoustakasKonstantinos Moustakas
Konstantinos Moustakas
This study aims to explore the possibility of estimating a multitude of kinematic and dynamic quantities using subject-specific musculoskeletal models in real-time. The framework was designed to operate with marker-based and inertial measurement units enabling extensions far beyond dedicated motion capture laboratories. We present the technical details for calculating the kinematics, generalized forces, muscle forces, joint reaction loads, and predicting ground reaction wrenches during walking. Emphasis was given to reduce computational latency while maintaining accuracy as compared to the offline counterpart. Notably, we highlight the influence of adequate filtering and differentiation under noisy conditions and its importance for consequent dynamic calculations. Real-time estimates of the joint moments, muscle forces, and reaction loads closely resemble OpenSim’s offline analyses. Model-based estimation of ground reaction wrenches demonstrates that even a small error can negatively affect other estimated quantities. An application of the developed system is demonstrated in the context of rehabilitation and gait retraining. We expect that such a system will find numerous applications in laboratory settings and outdoor conditions with the advent of predicting or sensing environment interactions. Therefore, we hope that this open-source framework will be a significant milestone for solving this grand challenge.

14 March 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RBRemco Baggen
Remco Baggen
Jaap Van DieenJaap Van Dieen
Jaap Van Dieen
EREvelien Van Roie
Evelien Van Roie
SVSabine M. Verschueren
Sabine M. Verschueren
GGGeorgios Giarmatzis
Georgios Giarmatzis
NDNadia Dominici
Nadia Dominici
The aim of this study was to explore the underlying age-related differences in dynamic motor control during different step ascent conditions using muscle synergy analysis. Eleven older women (67.0 y ± 2.5) and ten young women (22.5 y ± 1.6) performed stepping in forward and lateral directions at step heights of 10, 20 and 30 cm. Surface electromyography was obtained from 10 lower limb and torso muscles. Non-negative matrix factorization was used to identify sets of (n) synergies across age groups and stepping conditions. In addition, variance accounted for (VAF) by the detected number of synergies was compared to assess complexity of motor control. Finally, correlation coefficients of muscle weightings and between-subject variability of the temporal activation patterns were calculated and compared between age groups and stepping conditions. Four synergies accounted for >85% VAF across age groups and stepping conditions. Age and step height showed a significant negative correlation with VAF during forward stepping but not lateral stepping, with lower VAF indicating higher synergy complexity. Muscle weightings showed higher similarity across step heights in older compared to young women. Neuromuscular control of young and community-dwelling older women could not be differentiated based on the number of synergies extracted. Additional analyses of synergy structure and complexity revealed subtle age- and step-height-related differences, indicating that older women rely on more complex neuromuscular control strategies.