OBJECTIVE:Left ventricular hypertrophy (LVH) is classified as concentric or eccentric based on left ventricle relative wall thickness. Using machine learning techniques on basic clinical parameters and features from a single-lead electrocardiogram (ECG), we detected LVH in a hypertensive population without cardiovascular disease. METHODS:We enrolled 812 subjects with hypertension with no indications of cardiovascular disease. Based on left ventricular mass index and relative wall thickness, the subjects were classified into two groups; i) normal geometry and concentric remodeling were classified as no-LVH, whereas ii) concentric and eccentric hypertrophy were classified as having LVH. We trained a Random Forest to distinguish between the two categories. For comparison, we also trained a logistic regression and a convolutional neural network model. We performed feature importance and interaction analysis using SHAP to interpret the model's predictions for feature importance and feature interactions. RESULTS:Our model was able to distinguish subjects with no-LVH from the ones with LVH, with an ROC/AUC of 0.82 (95% CI: 0.71-0.91) and an average precision of 0.61. At threshold 0.3, specificity is 81% and sensitivity is 58%. Age, corrected QT interval, T wave duration, and being female were the most important features that contributed to the model's predictions. CONCLUSION:Using an analysis of single-lead ECG combined with clinical data, we demonstrated strong performance in detecting LVH. The identification of key ECG features, such as corrected QT interval and T wave morphology, underscores the clinical value of single-lead ECG analysis. These findings are particularly important in the era of wearable devices, where accessible, noninvasive screening for cardiac conditions such as LVH can be integrated into everyday health monitoring.
Background and Objectives: Dermatology relies on a complex terminology encompassing lesion types, distribution patterns, colors, and specialized sites such as hair and nails, while dermoscopy adds an additional descriptive framework, making interpretation subjective and challenging. Our study aims to evaluate the ability of a chatbot (Gemini 2) to generate dermatology descriptions across multiple languages and image types, and to assess the influence of prompt language on readability, completeness, and terminology consistency. Our research is based on the concept that non-English prompts are not mere translations of the English prompts but are independently generated texts that reflect medical and dermatological knowledge learned from non-English material used in the chatbot’s training. Materials and Methods: Five macroscopic and five dermoscopic images of common skin lesions were used. Images were uploaded to Gemini 2 with language-specific prompts requesting short paragraphs describing visible features and possible diagnoses. A total of 2400 outputs were analyzed for readability using LIX score and CLEAR (comprehensiveness, accuracy, evidence-based content, appropriateness, and relevance) assessment, while terminology consistency was evaluated via SNOMED CT mapping across English, French, German, and Greek outputs. Results: English and French descriptions were found to be harder to read and more sophisticated, while SNOMED CT mapping revealed the largest terminology mismatch in German and the smallest in French. English texts and macroscopic images achieved the highest accuracy, completeness, and readability based on CLEAR assessment, whereas dermoscopic images and non-English texts presented greater challenges. Conclusions: Overall, partial terminology inconsistencies and cross-lingual variations highlighted that the language of the prompt plays a critical role in shaping AI-generated dermatology descriptions.
Abstract Background Health professionals in Greece face barriers in assessing child and adolescent mental health conditions due to the lack of instruments with evidence of validity in local samples. This study addresses this gap by evaluating the psychometric properties and establishing common norms for six globally recognized mental health tools in Greece: the Child and Adolescent Trauma Screen-2 (CATS-2), Pediatric Symptoms Checklist-17 (PSC-17), Revised Children’s Anxiety and Depression Scale-25 (RCADS-25), Swanson, Nolan, and Pelham Scale (SNAP-IV), Modified Checklist for Autism in Toddlers-Revised (MCHAT-R/F), and Child Autism Spectrum Test (CAST). Methodology We drew on a nationwide Greek survey comprising 1,756 caregivers and 1,201 children and adolescents (age groups: 1 to 18 years). Using Item Response Theory, we assessed internal consistency and factor models according to Consensus-based Standards for the Selection of Health Measurement Instruments’ (COSMIN) criteria for unidimensionality, local independence, monotonicity, and global model fit. Normative references were calculated using standardized metrics recommended by the Patient-Reported Outcomes Measurement Information System (PROMIS). Results Final sample sizes ranged from 1,356 (PSC-17, caregiver version) to 198 (CATS-2, caregiver version). Internal consistency was rated as good to excellent across all scales. Factor analyses supported all scales except the ones assessing autism spectrum disorder: MCHAT-R/F (failing monotonicity) and CAST (failing monotonicity and unidimensionality). Local normative references were usually consistent with international samples. Conclusion This toolkit provides essential evidence-based resources for child and adolescent mental health in Greece, offering a scalable model for other underserved settings. Further research with national probabilistic samples is recommended to enhance risk stratification accuracy.
PurposeDespite extensive research, it remains unclear which patient-ventilator asynchronies are reliably detectable in clinical practice, most clinically relevant, and how they rank in severity.MethodsMultiple-choice questions and 5-point Likert-scale statements were used in iterative Delphi rounds. Feedback was incorporated until stable consensus or dissensus was reached for all items. First series of rounds focused on identifying and classifying patient-ventilator asynchronies detectable from ventilator waveforms, second series assessed their associations with outcomes in three patient groups, and in the final rounds, asynchronies were ranked by severity within these patient groups and across three scenarios.ResultsIn total, 11 panelists completed nine rounds. Consensus classified ineffective triggering, reverse triggering, double triggering, auto-triggering, insufficient flow, premature cycling, and delayed cycling as clinically relevant patient-ventilator asynchronies. Of these, auto-triggering and delayed cycling were deemed unlikely to be detectable using ventilator waveforms alone. Across all three patient groups, the panelists reached consensus that double triggering and ineffective triggering were the most clinically relevant. In acute respiratory distress syndrome, double triggering, ineffective triggering, and reverse triggering were all judged clinically relevant. In patients without acute respiratory distress syndrome and after cardiac surgery, asynchronies were classified as severe or mild and combined into two composite groups.ConclusionThis Delphi study provides a consensus-based framework for identifying and ranking patient-ventilator asynchronies at the bedside, highlighting those most likely to be clinically relevant and offering a structured approach to support monitoring, intervention, and future research.
