Christina Koufopoulou

Background/Objectives: Assessment of Internet Gaming Disorder (IGD) relies on retrospective self-reports and clinical interviews, which may be affected by recall and social desirability biases and may be insensitive to behavioral change. This study evaluated an artificial intelligence (AI)-enabled, privacy-preserving digital phenotyping framework for personalized IGD risk stratification under controlled simulation assumptions. Methods: A synthetic dataset of 1000 virtual user profiles was generated with a 20% elevated-risk prevalence and 5% balanced stochastic label noise. Four aggregated telemetry features were modeled: average session duration, sessions per week, Late-Night Index, and application-switching rate. Random Forest, Logistic Regression, and Gradient Boosting classifiers were evaluated using a stratified 80:20 hold-out split, five-fold cross-validation, playtime-only baselines, label-noise sensitivity analysis, and 200 synthetic realizations. Results: The primary Random Forest model achieved a balanced accuracy of 0.850, a sensitivity of 0.800, a specificity of 0.900, an area under the receiver operating characteristic curve (ROC-AUC) of 0.909, an average precision (AP) of 0.779, and a Brier score of 0.089. As an internal consistency check under the pre-specified synthetic signal structure, all-feature models showed higher performance than playtime-only baselines, and feature importance analyses recovered the encoded signal hierarchy. Performance declined with increasing label noise. Across 200 realizations, mean ROC-AUC values for the three all-feature models ranged from 0.888 to 0.904, with overlapping empirical 95% intervals. Conclusions: The framework demonstrates the methodological feasibility of transforming aggregated telemetry into interpretable risk signals while avoiding content-level monitoring. These findings are hypothesis-generating and do not establish clinical validity or diagnostic performance. Longitudinal validation in clinically characterized cohorts is required before deployment.

Background/Objectives: Assessment of Internet Gaming Disorder (IGD) relies largely on retrospective self-report and clinical interviews, which may be affected by recall bias, social desirability bias, and limited sensitivity to within-person behavioral change. This study evaluated an AI-enabled, privacy-preserving digital phenotyping framework for personalized IGD risk stratification under controlled simulation assumptions. Methods: A reproducible synthetic dataset of 1,000 virtual user profiles was generated; 20% were assigned to an elevated-risk class, and 5% balanced stochastic label noise was introduced to approximate imperfect ground truth. Four aggregated telemetry features were modeled: average session duration, sessions per week, Late-Night Index, and application-switching rate. Random Forest, Logistic Regression, and Gradient Boosting classifiers were evaluated against playtime-only baselines using a stratified 80:20 train–test split. Results: In the primary Random Forest model, accuracy was 0.880, balanced accuracy was 0.850, sensitivity was 0.800, specificity was 0.900, area under the receiver operating characteristic curve (ROC-AUC) was 0.909, area under the precision–recall curve (PR-AUC) was 0.779, and the Brier score was 0.089. All-feature models substantially outperformed playtime-only baselines. Feature-importance analyses recovered the known signal hierarchy encoded in the synthetic data-generating process, with application-switching rate and Late-Night Index showing the largest Gini-based and permutation-importance values. Performance degraded progressively as label noise increased from 0% to 20%. Conclusions: The framework demonstrates the methodological feasibility of transforming aggregated, privacy-preserving behavioral telemetry into interpretable simulated risk signals for IGD. The findings are hypothesis-generating and do not establish clinical validity or diagnostic performance. Longitudinal validation in clinically characterized cohorts using validated psychometric instruments and person-level calibration is required before practical deployment.

Antimicrobial resistance (AMR) is a critical and growing worldwide public health issue compromising effective disease prevention and management strategies in a range of bacterial, parasitic, viral, and fungal diseases. Despite efforts to counteract excessive use and overreliance on antibiotics, cases of resistant infection rise, and an imperative for accelerated development in diagnostics, disease surveillance, and therapeutic approaches arises. In this chapter, an intersection of technological advances in genomics, machine learning (ML) technology, and personalized approaches will be discussed in relation to countering AMR. With integration of genomic data and sophisticated computational algorithms, medical professionals and scientists stand to make rapid inferences about resistant trends and tailor individualized, specific courses of therapy. There is a critical need to move such techniques out of laboratory settings and into real-life practice to minimize dissemination of resistant pathogens, improve patient care, and mitigate worldwide consequences of AMR.

The study explores the application of automated machine learning (AutoML) using the MIMIC-IV-ED database to enhance decision-making in emergency department (ED) triage. We developed a predictive model that utilizes triage data to forecast hospital admissions, aiming to support medical staff by providing an advanced decision-support system. The model, powered by H2O.ai’s AutoML platform, was trained on approximately 280,000 preprocessed records from the Beth Israel Deaconess Medical Center collected between 2011 and 2019. The selected Gradient Boosting Machine (GBM) model demonstrated an AUC ROC of 0.8256, indicating its efficacy in predicting patient dispositions. Key variables such as acuity and waiting hours were identified as significant predictors, emphasizing the model’s capability to integrate critical triage metrics into its predictions. However, challenges related to the complexity and heterogeneity of medical data, privacy concerns, and the need for model interpretability were addressed through the incorporation of Explainable AI (XAI) techniques. These techniques ensure the transparency of the predictive processes, fostering trust and facilitating ethical AI use in clinical settings. Future work will focus on external validation and expanding the model to include a broader array of variables from diverse healthcare environments, enhancing the model’s utility and applicability in global emergency care contexts.

(1) Background: Predictive modeling is becoming increasingly relevant in healthcare, aiding in clinical decision making and improving patient outcomes. However, many of the most potent predictive models, such as deep learning algorithms, are inherently opaque, and their decisions are challenging to interpret. This study addresses this challenge by employing Shapley Additive Explanations (SHAP) to facilitate model interpretability while maintaining prediction accuracy. (2) Methods: We utilized Gradient Boosting Machines (GBMs) to predict patient outcomes in an emergency department setting, with a focus on model transparency to ensure actionable insights. (3) Results: Our analysis identifies “Acuity”, “Hours”, and “Age” as critical predictive features. We provide a detailed exploration of their intricate interactions and effects on the model’s predictions. The SHAP summary plots highlight that “Acuity” has the highest impact on predictions, followed by “Hours” and “Age”. Dependence plots further reveal that higher acuity levels and longer hours are associated with poorer patient outcomes, while age shows a non-linear relationship with outcomes. Additionally, SHAP interaction values uncover that the interaction between “Acuity” and “Hours” significantly influences predictions. (4) Conclusions: We employed force plots for individual-level interpretation, aligning with the current shift toward personalized medicine. This research highlights the potential of combining machine learning’s predictive power with interpretability, providing a promising route concerning a data-driven, evidence-based healthcare future.

Background: The purpose of this study was to compare the immediate and long-term complications that are associated with the utilized techniques for the insertion of indwelling central venous catheters, that is the open surgical technique, the ultrasound-guided technique, and the transcutaneous technique based on external anatomical landmarks in the right internal jugular vein, to a pediatric population. Methods: This was a prospective randomized trial based on a pediatric patient population under 16 years of age of a tertiary pediatric-oncological hospital. The procedure was performed by a medical team with varying experience regarding the percutaneous and open insertion methods. We studied the outcome of our procedure, based on the immediate and delayed complication rate, as well as the needed time in order to complete the procedure and mean duration of line use. Results: The patients that were inserted in our protocol were divided into three subgroups based on the selected technique for the insertion of the central venous catheter. A total number of 88 insertions (25.4%) (out of 346) were based on the technique that was using external anatomical landmarks, 121 insertions were based on the ultrasound-guided transcutaneous technique (34.9%), whereas in 137 cases (39.5%) the open surgical technique was preferred. All cases that were related to catheter re-insertion were excluded from our study. We performed a statistical analysis regarding the catheter dwell time between the three subgroups of patients and no significant difference was recorded. Moreover, the development of thrombosis was investigated, and we noted that a higher percentage of this complication was related to the transcutaneous external landmark and open surgical technique. Also, the incidence of infection was taken into consideration, which manifested an increased incidence when the transcutaneous technique based on external landmarks was used. Conclusions: Ultrasound-guided percutaneous insertion was considered to be a safe and effective technique for the insertion of central venous catheters. Our study also demonstrated a decrease in operating times when performed by operators with increasing expertise, increased preservation of the diameter of the venous lumen, and no increase in complication rates when the ultrasound-guided technique was selected.

Background: The purpose of this study was to compare the immediate and long-term complications that are associated with the utilized techniques for the insertion of indwelling central venous catheters, that is the open surgical technique, the ultrasound-guided technique and the transcutaneous technique based on external anatomical landmarks in the right internal jugular vein, to a pediatric population. Methods: This was a prospective randomized trial based on a pediatric patient population, under 16 years of age, of a tertiary pediatric-oncological hospital. Procedure was performed by a medical team with varying experience regarding the percutaneous and open insertion methods. We studied the outcome of our procedure, based on the immediate and delayed complication rate, as well as the needed time in order to complete the procedure and mean duration of line use. Results: The patients that were inserted in our protocol were divided into three subgroups, based on the selected technique for the insertion of the central venous catheter. A total number of 88 insertions (25.4%) (out of 346) were based on the technique that was using external anatomical landmarks, 121 insertions were based on the ultrasound-guided transcutaneous technique (34,9%), whereas in 137 cases (39.5%) the open surgical technique was preferred. All cases that were related to catheter re-insertion were excluded from our study. We performed a statistical analysis regarding the catheter dwell time between the three subgroups of patients and no significant difference was recorded. Moreover, the development of thrombosis was investigated, and we mentioned that the higher percentage of this complication was related with the transcutaneous external landmark and open surgical technique. Also, the incidence of infection was taken into consideration, which manifested an increased incidence when the transcutaneous technique based on external landmarks was used. Conclusions: Ultrasound guided percutaneous insertion was considered to be a safe and effective technique for the insertion of central venous catheters. Our study also demonstrated a decrease in operating times, when performed by operators with increasing expertise, increased preservation of the diameter of the venous lumen, and no increase in complication rates when the ultrasound-guided technique was selected.

Machine learning (ML) algorithms are increasingly applied in medical research and in healthcare, gradually improving clinical practice. Among various applications of these novel methods, their usage in the combat against antimicrobial resistance (AMR) is one of the most crucial areas of interest, as increasing resistance to antibiotics and management of difficult-to-treat multidrug-resistant infections are significant challenges for most countries worldwide, with life-threatening consequences. As antibiotic efficacy and treatment options decrease, the need for implementation of multimodal antibiotic stewardship programs is of utmost importance in order to restrict antibiotic misuse and prevent further aggravation of the AMR problem. Both supervised and unsupervised machine learning tools have been successfully used to predict early antibiotic resistance, and thus support clinicians in selecting appropriate therapy. In this paper, we reviewed the existing literature on machine learning and artificial intelligence (AI) in general in conjunction with antimicrobial resistance prediction. This is a narrative review, where we discuss the applications of ML methods in the field of AMR and their value as a complementary tool in the antibiotic stewardship practice, mainly from the clinician’s point of view.