Christos Kokkotis

Dr. Christos Kokkotis

Department of Physical Education and Sport Science, Democritus University of Thrace, Komotini, Greece

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
4 May 2020 in Osteoarthritis and Cartilage Open
Verified
Journal Article
Open access
Christos KokkotisChristos Kokkotis
Christos Kokkotis
SMS. Moustakidis
S. Moustakidis
Elpiniki PapageorgiouElpiniki Papageorgiou
Elpiniki Papageorgiou
GGG. Giakas
G. Giakas
DTD.E. Tsaopoulos
D.E. Tsaopoulos
The purpose of present review paper is to introduce the reader to key directions of Machine Learning techniques on the diagnosis and predictions of knee osteoarthritis. This survey was based on research articles published between 2006 and 2019. The articles were divided into four categories, namely (i) predictions/regression, (ii) classification, (iii) optimum post-treatment planning techniques and (iv) segmentation. The grouping was based on the application domain of each study. The survey findings are reported outlining the main characteristics of the proposed learning algorithms, the application domains, the data sources investigated and the quality of the results. Knee osteoarthritis is a big data problem in terms of data complexity, heterogeneity and size as it has been commonly considered in the literature. Machine Learning has attracted significant interest from the scientific community to cope with the aforementioned challenges and thus lead to new automated pre- or post-treatment solutions that utilize data from the greatest possible variety of sources.

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.

24 March 2021 in JMIR Serious Games
Verified
Journal Article
Open access
Mary HassandraMary Hassandra
Mary Hassandra
EGEvangelos Galanis
Evangelos Galanis
Antonis HatzigeorgiadisAntonis Hatzigeorgiadis
Antonis Hatzigeorgiadis
MGMarios Goudas
Marios Goudas
CMChristos Mouzakidis
Christos Mouzakidis
YTYannis Theodorakis
Yannis Theodorakis
Background: Therapeutic virtual reality (VR) has emerged as an effective treatment modality for cognitive and physical training in people with mild cognitive impairment (MCI). However, to replace existing nonpharmaceutical treatment training protocols, VR platforms need significant improvement if they are to appeal to older people with symptoms of cognitive decline and meet their specific needs. Objective: This study aims to design and test the acceptability, usability, and tolerability of an immersive VR platform that allows older people with MCI symptoms to simultaneously practice physical and cognitive skills on a dual task. Methods: On the basis of interviews with 20 older people with MCI symptoms (15 females; mean age 76.25, SD 5.03 years) and inputs from their health care providers (formative study VR1), an interdisciplinary group of experts developed a VR system called VRADA (VR Exercise App for Dementia and Alzheimer’s Patients). Using an identical training protocol, the VRADA system was first tested with a group of 30 university students (16 females; mean age 20.86, SD 1.17 years) and then with 27 older people (19 females; mean age 73.22, SD 9.26 years) who had been diagnosed with MCI (feasibility studies VR2a and VR2b). Those in the latter group attended two Hellenic Association Day Care Centers for Alzheimer’s Disease and Related Disorders. Participants in both groups were asked to perform a dual task training protocol that combined physical and cognitive exercises in two different training conditions. In condition A, participants performed a cycling task in a lab environment while being asked by the researcher to perform oral math calculations (single-digit additions and subtractions). In condition B, participants performed a cycling task in the virtual environment while performing calculations that appeared within the VR app. Participants in both groups were assessed in the same way; this included questionnaires and semistructured interviews immediately after the experiment to capture perceptions of acceptability, usability, and tolerability, and to determine which of the two training conditions each participant preferred. Results: Participants in both groups showed a significant preference for the VR condition (students: mean 0.66, SD 0.41, t29=8.74, P<.001; patients with MCI: mean 0.72, SD 0.51, t26=7.36, P<.001), as well as high acceptance scores for intended future use, attitude toward VR training, and enjoyment. System usability scale scores (82.66 for the students and 77.96 for the older group) were well above the acceptability threshold (75/100). The perceived adverse effects were minimal, indicating a satisfactory tolerability. Conclusions: The findings suggest that VRADA is an acceptable, usable, and tolerable system for physical and cognitive training of older people with MCI and university students. Randomized controlled trial studies are needed to assess the efficacy of VRADA as a tool to promote physical and cognitive health in patients with MCI.

31 January 2022 in Physical and Engineering Sciences in Medicine
Verified
Journal Article
Closed access
PDF file
Christos KokkotisChristos Kokkotis
Christos Kokkotis
CNCharis Ntakolia
Charis Ntakolia
SMSerafeim Moustakidis
Serafeim Moustakidis
GGGiannis Giakas
Giannis Giakas
DTDimitrios Tsaopoulos
Dimitrios Tsaopoulos

22 April 2022 in Scientific Reports
Verified
Journal Article
Open access
PDF file
Christos KokkotisChristos Kokkotis
Christos Kokkotis
SMSerafeim Moustakidis
Serafeim Moustakidis
TTThemistoklis Tsatalas
Themistoklis Tsatalas
CNCharis Ntakolia
Charis Ntakolia
GCGeorgios Chalatsis
Georgios Chalatsis
DTDimitrios Tsaopoulos
Dimitrios Tsaopoulos
Anterior cruciate ligament (ACL) deficient and reconstructed knees display altered biomechanics during gait. Identifying significant gait changes is important for understanding normal and ACL function and is typically performed by statistical approaches. This paper focuses on the development of an explainable machine learning (ML) empowered methodology to: (i) identify important gait kinematic, kinetic parameters and quantify their contribution in the diagnosis of ACL injury and (ii) investigate the differences in sagittal plane kinematics and kinetics of the gait cycle between ACL deficient, ACL reconstructed and healthy individuals. For this aim, an extensive experimental setup was designed in which three-dimensional ground reaction forces and sagittal plane kinematic as well as kinetic parameters were collected from 151 subjects. The effectiveness of the proposed methodology was evaluated using a comparative analysis with eight well-known classifiers. Support Vector Machines were proved to be the best performing model (accuracy of 94.95%) on a group of 21 selected biomechanical parameters. Neural Networks accomplished the second best performance (92.89%). A state-of-the-art explainability analysis based on SHapley Additive exPlanations (SHAP) and conventional statistical analysis were then employed to quantify the contribution of the input biomechanical parameters in the diagnosis of ACL injury. Features, that would have been neglected by the traditional statistical analysis, were identified as contributing parameters having significant impact on the ML model’s output for ACL injury during gait.

27 November 2021 in Sensors
Verified
Journal Article
Open access
PDF file
Charis NtakoliaCharis Ntakolia
Charis Ntakolia
Christos KokkotisChristos Kokkotis
Christos Kokkotis
PKPatrik Karlsson
Patrik Karlsson
SMSerafeim Moustakidis
Serafeim Moustakidis
Global competition among businesses imposes a more effective and low-cost supply chain allowing firms to provide products at a desired quality, quantity, and time, with lower production costs. The latter include holding cost, ordering cost, and backorder cost. Backorder occurs when a product is temporarily unavailable or out of stock and the customer places an order for future production and shipment. Therefore, stock unavailability and prolonged delays in product delivery will lead to additional production costs and unsatisfied customers, respectively. Thus, it is of high importance to develop models that will effectively predict the backorder rate in an inventory system with the aim of improving the effectiveness of the supply chain and, consequentially, the performance of the company. However, traditional approaches in the literature are based on stochastic approximation, without incorporating information from historical data. To this end, machine learning models should be employed for extracting knowledge of large historical data to develop predictive models. Therefore, to cover this need, in this study, the backorder prediction problem was addressed. Specifically, various machine learning models were compared for solving the binary classification problem of backorder prediction, followed by model calibration and a post-hoc explainability based on the SHAP model to identify and interpret the most important features that contribute to material backorder. The results showed that the RF, XGB, LGBM, and BB models reached an AUC score of 0.95, while the best-performing model was the LGBM model after calibration with the Isotonic Regression method. The explainability analysis showed that the inventory stock of a product, the volume of products that can be delivered, the imminent demand (sales), and the accurate prediction of the future demand can significantly contribute to the correct prediction of backorders.