Stavros Pitoglou

Dr. Stavros Pitoglou

Biomedical Engineering Laboratory, National Technical University of Athens, Athens, Attikí, Greece
+1
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 April 2018 in International Journal of Reliable and Quality E-Healthcare
Verified
Journal Article
Closed access
PDF file
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
Machine Learning, closely related to Artificial Intelligence and standing at the intersection of Computer Science and Mathematical Statistical Theory, comes in handy when the truth is hiding in a place that the human brain has no access to. Given any prediction or assessment problem, the more complicated this issue is, based on the difficulty of the human mind to understand the inherent causalities/patterns and apply conventional methods towards an acceptable solution, Machine Learning can find a fertile field of application. This article's purpose is to give a general non-technical definition of Machine Learning, provide a review of its latest implementations in the Healthcare domain and add to the ongoing discussion on this subject. It suggests the active involvement of entities beyond the already active academic community in the quest for solutions that “exploit” existing datasets and can be applied in the daily practice, embedded inside the software processes that are already in use.

1 December 2018
Verified
Conference Paper
Closed access
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
YKYiannis Koumpouros
Yiannis Koumpouros
AAAthanasios Anastasiou
Athanasios Anastasiou
Objectives: Administrative HIS (Hospital Information System) and EHR (Electronic Health Record) data are characterized by lower privacy sensitivity, thus easier portability and handling, as well as higher information quality. In this paper we test the hypothesis that the application of machine learning techniques on data of this nature can be used to address prediction/forecasting problems in the Health IT domain. The novelty of this approach consists in that medical data (test results, diagnoses, doctors' notes etc.) are not included in the predictors' dataset. Moreover, there is limited need for separation of patient cohorts based on specific health conditions. Methods: We experiment with the prediction of the probability of early readmission at the time of a patient's discharge. We extract real HIS data and perform data processing techniques. We then apply a series of machine learning algorithms (Logistic Regression, Support Vector Machine, Gaussian Naïve Bayes, K-Nearest Neighbors and Deep Multilayer Neural Network) and measure the performance of the emergent models. Results: All applied methods performed well above random guessing, even with minimal hyper-parameter tuning. Conclusions: Given that the experiments provide evidence in favor of the underlying hypothesis, future experimentation on more fine-tuned (thus more robust) models could result in applications suited for productive environments.

22 November 2024
Verified
Book Chapter
Open access
PDF file
GEORGIOS FERETZAKISGEORGIOS FERETZAKIS
GEORGIOS FERETZAKIS
AAAthanasios Anastasiou
Athanasios Anastasiou
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
EPEVGENIA PAXINOU
EVGENIA PAXINOU
AGAris Gkoulalas-Divanis
Aris Gkoulalas-Divanis
VVVassilios S. Verykios
Vassilios S. Verykios
In Generative Artificial Intelligence (AI), Large Language Models (LLMs) like GPT-4, Gemini, Claude, and Llama, significantly impact healthcare by aiding in patient care, medical research, and administrative tasks. AI-powered chatbots offer real-time responses and manage chronic diseases, improving patient outcomes and operational efficiency. However, these models pose security and ethical challenges, necessitating robust data privacy, adversarial training, and ethical guidelines. This paper proposes a secure, ethical pipeline for deploying AI healthcare chatbots, integrating advanced privacy-preserving techniques and continuous security assessments to enhance data privacy, resilience, and user trust.

1 January 2022 in International Journal of Reliable and Quality E-Healthcare
Verified
Journal Article
Open access
PDF file
AAAthanasios Anastasiou
Athanasios Anastasiou
ANAngeliki Nikaki
Angeliki Nikaki
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
YKYiannis Koumpouros
Yiannis Koumpouros
The paper presents the design approach of a low power stretchable wearable epidermal electronic device as part of an advanced athlete performance management framework to perform multi-parametric, multi-modal measurements of vital physiological parameters through the skin and via sweat analysis. It can be used to seamlessly monitor athletes, to prevent serious health complications and injuries during training, sudden death and complications related to overtraining. The proposed framework allows real-time physiological monitoring, tracking, prediction and quantification of athletic performance and estimation of recovery time after an injury, an illness or the overtraining syndrome. It is based on low-cost and clean room-based fabrication techniques and interconnects and readout electronics based on commercially available off-the-shelf components and application-specific integrated circuits. A data analytics platform incorporates real-time monitoring to identify the susceptibility to sudden death, health complications or injury, for the athlete, executing a personalized prediction model

1 September 2022 in Frontiers in Digital Health
Verified
Journal Article
Open access
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
AFArianna Filntisi
Arianna Filntisi
AAAthanasios Anastasiou
Athanasios Anastasiou
GMGeorge K. Matsopoulos
George K. Matsopoulos
DKDimitrios Koutsouris
Dimitrios Koutsouris
Introduction: Electronic Health Records (EHRs) are essential data structures, enabling the sharing of valuable medical care information for a diverse patient population and being reused as input to predictive models for clinical research. However, issues such as the heterogeneity of EHR data and the potential compromisation of patient privacy inhibit the secondary use of EHR data in clinical research.Objectives: This study aims to present the main elements of the MODELHealth project implementation and the evaluation method that was followed to assess the efficiency of its mechanism.Methods: The MODELHealth project was implemented as an Extract-Transform-Load system that collects data from the hospital databases, performs harmonization to the HL7 FHIR standard and anonymization using the k-anonymity method, before loading the transformed data to a central repository. The integrity of the anonymization process was validated by developing a database query tool. The information loss occurring due to the anonymization was estimated with the metrics of generalized information loss, discernibility and average equivalence class size for various values of k.Results: The average values of generalized information loss, discernibility and average equivalence class size obtained across all tested datasets and k values were 0.008473 ± 0.006216252886, 115,145,464.3 ± 79,724,196.11 and 12.1346 ± 6.76096647, correspondingly. The values of those metrics appear correlated with factors such as the k value and the dataset characteristics, as expected.Conclusion: The experimental results of the study demonstrate that it is feasible to perform effective harmonization and anonymization on EHR data while preserving essential patient information.

10 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Stavros PitoglouStavros Pitoglou
Stavros Pitoglou
AFArianna Filntisi
Arianna Filntisi
AAAthanasios Anastasiou
Athanasios Anastasiou
George K. MatsopoulosGeorge K. Matsopoulos
George K. Matsopoulos
Dimitris Dionissios KoutsourisDimitris Dionissios Koutsouris
Dimitris Dionissios Koutsouris
The object of this paper was the application of machine learning to a clinical dataset that was anonymized using the Mondrian algorithm. (1) Background: The preservation of patient privacy is a necessity rising from the increasing digitization of health data; however, the effect of data anonymization on the performance of machine learning models remains to be explored. (2) Methods: The original EHR derived dataset was subjected to anonymization by applying the Mondrian algorithm for various k values and quasi identifier (QI) set attributes. The logistic regression, decision trees, k-nearest neighbors, Gaussian naive Bayes and support vector machine models were applied to the different dataset versions. (3) Results: The classifiers demonstrated different degrees of resilience to the anonymization, with the decision tree and the KNN models showing remarkably stable performance, as opposed to the Gaussian naïve Bayes model. The choice of the QI set attributes and the generalized information loss value played a more important role than the size of the QI set or the k value. (4) Conclusions: Data anonymization can reduce the performance of certain machine learning models, although the appropriate selection of classifier and parameter values can mitigate this effect.