Uğur Saraç

Background: Non-benign neonatal arrhythmias (NAs) can constitute a significant clinical burden in neonatal intensive care units (NICUs); however, the impact of prenatal diagnosis and postnatal persistence patterns on clinical outcomes has not been fully elucidated.Objective: To evaluate the clinical burden, acute intensive care requirement, and post-discharge antiarrhythmic treatment need in non-benign NAs according to prenatal arrhythmia history and postnatal persistence pattern.Methods: This retrospective observational study included newborns diagnosed with non-benign arrhythmia during the fetal and/or neonatal period at a tertiary NICU between July 2020 and July 2025. Patients were categorized into three groups: fetal persisting (arrhythmia detected in the fetal period and persisted postnatally), fetal resolved (fetal arrhythmia resolved after birth), and neonatal only (arrhythmia emerged exclusively during the neonatal period). Clinical outcomes, treatment requirements, and adenosine response were compared between groups.Results: Of 9,210 NICU admissions, 35 cases (0.38%) with non-benign NA were identified. Supraventricular tachycardia was the most common arrhythmia type (66.7%) Groups with active postnatal arrhythmia (fetal persisting and neonatal only) demonstrated longer hospitalization, higher comorbidity rates, and greater post-discharge antiarrhythmic treatment requirement (90.9% and 92.3%, respectively) compared to the fetal resolved group (9.1%). Potassium levels were significantly higher in adenosine-resistant cases (median 5.4 vs. 4.3 mEq/L, P = 0.044).Conclusions: In this cohort, active postnatal arrhythmia, whether persistent from the fetal period or emerging only after birth, was associated with greater clinical burden and post-discharge antiarrhythmic treatment requirement than fetal arrhythmia that resolved postnatally. The observed association between higher potassium levels and adenosine resistance should be interpreted cautiously as an exploratory finding.

Objective: Bicuspid aortic valve (BAV) is one of the most common congenital heart defects, yet the electrocardiographic features of isolated BAV in children have not been well characterized. We aimed to evaluate electrocardiographic parameters in pediatric patients with isolated BAV and to investigate whether early electrical changes are detectable before overt valve dysfunction. Materials and Methods: In this retrospective case-control study, 30 children with isolated and hemodynamically uncomplicated BAV were compared with 32 age- and sex-matched healthy controls. Via 12-lead surface electrocardiography, P wave parameters, QT and QTc intervals, QRS duration, axis measurements, and the QRS-T angle were assessed by two blinded investigators. For the ECG parameters, correction for multiple comparisons was applied with the Benjamini-Hochberg method. Results: The study included 30 children with BAV and 32 controls; median age was 142.5 versus 141.5 months, and male sex was present in 70.0% versus 75.0%, respectively. After correction for multiple comparisons, only the minimum duration of the P wave (q=0.005) and the dispersion of the P wave (q=0.008) showed significant differences between the groups; P minimum duration was higher and P wave dispersion was lower in the BAV group. No difference was found between the groups in the PR interval, QRS duration, the parameters of repolarization, and axis measurements. In the BAV group, aortic Z-scores were higher despite preserved systolic function of the left ventricle, and the left ventricular mass index did not reach statistical significance (p=0.058). Conclusion: Isolated pediatric BAV is associated with selective electrocardiographic changes at the level of atrial conduction, in the absence of a hemodynamic burden, while ventricular conduction and repolarization are not affected at this stage.

As participation of children in exercise and organized sports increases worldwide, the health care needs of young athletes differ substantially from those of adults due to age-specific physiological, biomechanical, and psychosocial characteristics related to growth and development. Pediatric Sports Medicine (PSM) is a pediatric-based, multidisciplinary subspecialty that encompasses preparticipation physical evaluation (PPE), exercise prescription, management of sports injuries and overuse syndromes, sport-related concussion, heat-related illnesses, assessment of sudden cardiac event risk, relative energy deficiency in sport (RED-S), planning safe sports participation for children with chronic medical conditions, and safeguarding in sport. In the United States, PSM is formally structured through pediatric-based fellowship training and board certification, whereas Europe lacks a standardized model and relies on heterogeneous approaches integrating pediatrics, sports medicine, and rehabilitation. In Türkiye, sports medicine training remains largely adult-oriented. Given that pediatric subspecialty training is strictly based on prior pediatric specialization and that pediatricians are routinely consulted for comprehensive medical evaluations, the absence of a pediatric-based PSM structure has resulted in notable gaps in pediatric-specific PPE standardization, early sport specialization and load management, RED-S screening, integration of school–club–health care systems, and the health care component of safeguarding policies. This narrative review presents a literature-based synthesis of the conceptual foundations and clinical and public health rationale of PSM, summarizes relevant international guidelines and consensus statements, and proposes a feasible framework for its implementation in Türkiye, where this subspecialty has not yet been established.

Large language models (LLMs) have been explored for clinical applications, yet their reliability in pediatric electrocardiogram (ECG) interpretation remains unclear. We compared the diagnostic accuracy of three general-purpose artificial intelligence (AI) systems-ChatGPT, Gemini, and Copilot-with that of a pediatrician and characterized error patterns across the platforms. A total of 178 children (median age 108 months) underwent standard 12-lead ECG recording at a single center between January 2024 and July 2025. One pediatrician and three LLMs interpreted each ECG using a zero-shot design; responses were compared against a definitive diagnosis established through expert consensus. Rhythms were classified as physiological or pathological, with subgroup analysis for rhythms calling for emergency intervention. The pediatrician achieved the highest accuracy (78.7%), followed by ChatGPT (71.9%), Copilot (66.9%), and Gemini (50.0%). Area under the receiver operating characteristic (ROC) curve confirmed pediatrician superiority (0.79) over ChatGPT (0.70), Copilot (0.63), and Gemini (0.54). Agreement with definitive diagnosis was moderate for the pediatrician (κ = 0.566) and ChatGPT (κ = 0.410), but weak or nonsignificant for Copilot and Gemini. Error profiles differed markedly; Gemini showed a high false negative rate (39.9%), while Copilot showed a high false positive rate (24.7%). The clinician outperformed the LLMs in pediatric ECG interpretation. Diagnostic accuracy varied markedly across the models, with reliability limits particularly evident in high-risk rhythms. In their current form, these systems may serve as supplementary tools under expert oversight rather than independent decision-makers.

Objective: Ebstein’s anomaly is a rare congenital heart defect featuring a varied spectrum of clinical presentation. Anatomical variability in the malformation, together with a frequent association with other cardiac defects and arrhythmias, can complicate diagnosis and long-term management. Methods: Data from a total of 26 patients with Ebstein’s anomaly followed up at two university clinics between 2009 and 2025 were analyzed retrospectively. Cases diagnosed from the prenatal period through adolescent period were included. Results: The cohort consisted of 26 patients; 69.2% (18/26) were males with a median diagnostic age of 8 days. Diagnoses were established prenatally 15.4% (4/26), neonatally 50.0% (13/26), or during later childhood and adolescence 34.6% (9/26). Diagnosis was made during the index NICU admission in 34.6% (9/26) of patients and based on referral for murmur 26.9% (7/26) or cyanosis 7.7% (2/26). Common associated anomalies included atrial-level shunts 61.5% (16/26), mitral regurgitation 23.1% (6/26), and ventricular septal defects 15.4% (4/26). Arrhythmias were documented in 23.1% (6/21) of the cohort; 42.3% (11/26) underwent catheter-based procedures, and 30.8% (8/26) required surgery (median age at first surgery, 8.4 months), with 15.4%(4/26) undergoing reoperation. Over a median 5-year follow-up, mortality was 15.4% (4/26), with no perioperative deaths. Among prenatally diagnosed cases (n=4), three deaths occurred (3/4, 75%). Conclusions: The clinical spectrum of Ebstein’s anomaly is exceptionally broad. Our findings show frequent left heart involvement and a substantial need for catheter-based and surgical interventions, supporting the importance of individualized assessment and follow-up across the disease course.

Pediatric exanthematous diseases pose diagnostic challenges because clinical presentations overlap. To determine whether current artificial intelligence (AI) models achieve diagnostic accuracy within or above the performance distribution of pediatric residents and specialists for common rash-associated diseases. Participants and AI models were evaluated against definitive diagnoses confirmed by clinical features, laboratory findings, and consensus of two pediatric infectious disease specialists. A volunteer sample of 263 pediatric clinicians: 107 residents (years 1 through 4) and 156 specialists. Each clinician completed a blinded multiple-choice questionnaire with a clinical photograph and accompanying clinical data per case. The same cases were presented to three AI models: ChatGPT, Gemini, and Copilot. Among 263 clinicians (107 residents, 156 specialists), specialists scored higher than residents (median, 46 [IQR, 42—50] vs 41 [IQR, 36—46]; P < .001; r = 0.32). ChatGPT correctly diagnosed 53 of 61 cases (86.9%), Gemini 50 (82.0%), and Copilot 44 (72.1%). Both ChatGPT and Gemini exceeded the upper bound of the specialist population median 95% CI (47.17). All three AI models scored above the resident 95% CI upper bound (42.76). Disease-level accuracy ranged from 0% (insect bites, all models) to 100% (9 conditions, all models). Fourth-year residents scored higher than first- and second-year residents ( P = .001; ε ² = 0.13). Conclusions : AI models given clinical data alongside images matched or exceeded specialist-level performance for pediatric exanthems. Accuracy varied by disease; failures clustered in conditions that require contextual reasoning. Physician oversight remains necessary where AI accuracy is lowest. What is Known • Childhood exanthematous diseases pose significant diagnostic challenges due to their overlapping clinical presentations. • Artificial intelligence models are becoming increasingly proficient in accurately diagnosing these conditions. What is New • In this diagnostic accuracy study of 61 cases evaluated by 263 clinicians and 3 artificial intelligence models, ChatGPT (86.9%) and Gemini (82.0%) exceeded the 95% CI upper bound of the specialist population median. Disease-level accuracy ranged from 0 to 100% across models • Artificial intelligence models given clinical data alongside images can match or exceed specialist-level accuracy for common pediatric exanthems, but failures in context-dependent diagnoses require physician oversight

We evaluated three multimodal LLMs, ChatGPT (GPT-5.2), Gemini 3, and Microsoft Copilot, in pediatric ECG interpretation, focusing on clinically significant abnormalities and emergency arrhythmias with likelihood ratios as primary outcome measures. This prospective comparative diagnostic accuracy study (STARD/STARD-AI) included 264 pediatric patients with 12-lead ECGs (November 2024–November 2025). De-identified images were submitted via standardized zero-shot prompt. Three blinded pediatric cardiologists established the reference diagnosis by majority-vote consensus. Cases were classified as Tier 1 (normal), Tier 2 (abnormal, non-urgent), or Tier 3 (urgent). Two binary endpoints were assessed: clinically significant abnormality (Tier 2 + 3 vs Tier 1) and emergency abnormality (Tier 3 vs Tier 1 + 2). Clinically significant abnormalities were present in 54.5% of patients. AUC values ranged from 0.550 to 0.623, reflecting modest discrimination. For the clinically significant endpoint, + LR values were 2.05 (ChatGPT), 1.26 (Gemini), and 1.21 (Copilot); − LR values were 0.68, 0.55, and 0.81, indicating limited rule-in and insufficient rule-out utility. For the emergency endpoint, Gemini achieved 100% sensitivity (95% CI = 85.1–100.0) with − LR 0.07 (95% CI = 0.00–1.12) in a small subgroup ( n = 22); however, specificity of 30.2% and + LR of 1.40 indicate overcalling rather than diagnostic precision. No model achieved clinically meaningful rule-in utility for either endpoint. Conclusions : Current multimodal LLMs showed limited diagnostic utility in pediatric ECG interpretation, with + LR values near 1.0 across both endpoints. Standalone deployment is not supported; these tools may at most serve as adjunctive screening aids under clinician oversight. What is Known: • Deep learning algorithms trained on large ECG datasets perform well in adult populations, but evidence in pediatric ECG interpretation is limited. • General-purpose LLMs show variable accuracy in medical examinations; reliability in subspecialty domains such as pediatric cardiology remains unproven. What is New: • This is the[FCA1] first head-to-head comparative diagnostic accuracy study of multimodal LLMs in pediatric ECG evaluation, using likelihood ratios as primary outcome measures. • All three LLMs showed limited rule-in utility (+LR near 1.0); Gemini achieved potentially meaningful rule-out performance for emergency arrhythmias (−LR = 0.07), but with wide confidence intervals reflecting the small emergency subgroup (n = 22). • Gemini’s 100% sensitivity in the emergency subgroup reflects overcalling (specificity 30.2%) consistent with a triage/screening behavior rather than diagnostic precision.

Aims: This study aimed to to describe clinical and radiological characteristics of cold agglutinin-positive pediatric patients and to evaluate factors associated markers of disease severity, including CT utilization, respiratory support and length of hospitalization, in patients with suspected Mycoplasma pneumonia infection and cold agglutination positivity. Methods: A retrospective analysis was conducted on patients aged 0-18 years who presented to the pediatric clinics of Necmettin Erbakan University between January 2015 and January 2025 and had cold agglutinin positivity. Demographics, presenting symptoms, pulmonary and extrapulmonary findings, imaging results, treatment settings, respiratory support needs, and laboratory parameters were extracted from medical records. Comparative analyses between patients with and without chest CT imaging were performed using appropriate statistical tests. Results: A total of 242 patients (52.9% female; mean age 8.31±4.41 years) were included. The most frequent symptoms were cough (83.5%), nonspecific complaints (42.6%), and fever (38.4%). Abnormal respiratory findings were present in 45.0%, most commonly bilateral crackles. Extrapulmonary manifestations occurred in 20.2% of patients. Chest X-rays showed bilateral involvement in 47.9%. Patients who underwent CT imaging had significantly higher rates of abnormal respiratory findings, increased need for supplemental oxygen or noninvasive support, and longer hospital stays (p

Purpose Differentiating among exanthematous diseases is frequently challenging due to their overlapping symptomatology. We, therefore, aimed to evaluate the diagnostic accuracy of a consultant physician, a resident physician, and various AI models (ChatGPT-5, Gemini, Copilot) in this context. Methods We prospectively enrolled 291 patients treated for exanthematous diseases at our clinic between January 2024 and July 2025. The AI models were first tasked with making a diagnosis based solely on cutaneous images and subsequently with both images and accompanying clinical findings. The diagnoses rendered by the consultant, the resident, and the AI models were then compared against the definitive diagnosis. Results When benchmarked against the definitive diagnosis, the consultant achieved the highest diagnostic accuracy (96.6%), followed by ChatGPT (with clinical data, 86.9%), Copilot (with clinical data, 81.4%), Gemini (with clinical data, 78.7%), and the resident physician (72.5%). In contrast, models without clinical data performed poorly, with the lowest accuracy recorded at 30.6% by Copilot. In ROC analysis against the consultant, the resident (AUC: .875) and AI models with clinical data—ChatGPT (AUC: .898), Gemini (AUC: .856), and Copilot (AUC: .818)—all demonstrated good diagnostic power (p < .001). The ChatGPT model without clinical data showed moderate diagnostic power, whereas the Copilot and Gemini models without data were not statistically significant. Performance metrics (sensitivity, specificity) were: ChatGPT (with data) (89.7%, 90.0%); Copilot (with data) (83.6%, 80.0%); Gemini (with data) (81.1%, 90.0%); the resident (75.1%, 100.0%); ChatGPT (no data) (51.6%, 90.0%); Gemini (no data) (33.5%, 100.0%); and Copilot (no data) (31.7%, 100.0%). The consultant's diagnostic performance was significantly superior to all other interpreters and models (p < .001 for all comparisons). Conclusion: This study establishes the diagnostic utility of AI models in pediatric exanthematous diseases, with ChatGPT-5 demonstrating the greatest accuracy when augmented with clinical data. The findings position these models as powerful assistive tools for clinicians but affirm that they do not yet supplant the indispensable expertise of a consultant physician, who remains the gold standard for diagnosis. What is Known: • Overlapping clinical features of exanthematous diseases often lead to diagnostic uncertainty. • Rash-focused artificial intelligence models frequently perform better when supplemented with clinical context rather than image data alone. What is New: • This study provides the first large-scale, multimodal comparison of three next-generation artificial intelligence models (ChatGPT-5, Gemini, Copilot) specifically in pediatric exanthematous diseases. • The study uniquely demonstrates the diagnostic performance gap between image-only and image-plus-clinical-data modes across multiple artificial intelligence models, quantifying the exact improvement provided by clinical context. • By benchmarking artificial intelligence performance simultaneously against both a consultant and a resident physician, this work introduces a novel dual-reference standard, offering more nuanced insight into real-world clinical use cases.

Evaluation of Patients with Hemolytic Uremic Syndrome - The Journal of Current Pediatrics