Talha Üstüntaş

1. Tigecycline represents a distinctive member of the glycylcycline class of antimicrobial agents, exerting its bacteriostatic effect through the selective inhibition of bacterial protein synthesis...

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

To examine factors associated with severe respiratory disease at initial presentation in pediatric hMPV-associated LRTIs. We analyzed patients aged 1 month to 18 years with PCR-confirmed hMPV-associated LRTI (January 2018–January 2024). Clinical severity was stratified via the Modified Tal Score at admission (mild ≤ 5, moderate 6–10, severe ≥ 11). Each patient contributed one episode. Multivariable binary logistic regression identified risk factors for severe respiratory disease; ROC analysis evaluated biomarker diagnostic accuracy. A total of 676 hMPV-positive patients were identified; after restricting to one episode per patient, 421 unique episodes were analyzed. Of these, 54.9% were mild, 38.5% moderate, and 6.7% ( n = 28) severe. Comorbidities were present in 67.9% of severe versus 35.5% of mild cases ( p = .004). Viral co-detections occurred in 41.3% but were unrelated to severity ( p = .235). Median CRP was 4.0, 10.0, and 32.0 mg/L in mild, moderate, and severe groups, respectively (p < .001). In multivariable regression, comorbidity was the strongest risk factor (OR 2.96, 95% CI 1.17–7.49, p = 0.022), followed by CRP (OR 1.55 per 1 SD [≈32 mg/L], p = 0.018). No age group retained significance after adjustment (model AUC 0.733). Conclusions : Severe respiratory disease was infrequent (6.7%) and associated primarily with underlying comorbidities, which increased the odds approximately threefold. Age was not independently associated with severity. CRP showed modest diagnostic accuracy (AUC 0.678, negative likelihood ratio 0.59); low levels alone could not reliably exclude severe respiratory disease. What is Known: • hMPV is an established cause of lower respiratory tract infections in children, Ranging from mild illness to severe pneumonia requiring hospitalization and respiratory support. • Infants younger than 12 months and children with comorbidities such as prematurity, chronic lung disease, congenital heart disease, or neurological disorders carry increased risk for severe hMPV infection. What is New: • Multivariable logistic regression identifies underlying comorbidity as the dominant independent risk factor for severe hMPV respiratory disease (OR 2.96, p = 0.022). No age group retains significance after adjustment, indicating that the apparent severity signal in children older than 5 years reflects a comorbidity-driven population shift rather than older age acting as an independent risk factor. • Elevated CRP, decreased lymphocyte counts, and decreased monocyte counts at admission are associated with severe respiratory disease. CRP retained independent association in multivariable analysis, though diagnostic accuracy for all three biomarkers was modest.

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.

Background: Weight changes following gluten‐free diet (GFD) initiation in children with celiac disease remain debated. The diet corrects malabsorption in underweight children but may promote excessive weight gain in those diagnosed at normal weight. We examined whether weight gain on the GFD represents physiological recovery or emerging obesity risk in a Turkish pediatric cohort. Methods: We retrospectively analyzed 117 children diagnosed with celiac disease between 2015 and 2025. Patients were stratified by dietary adherence: strict ( n = 56), partial ( n = 44), and non‐adherent ( n = 17). Adherence was assessed via clinical symptoms, tissue transglutaminase serology, and patient interviews. Body mass index (BMI) and height‐for‐age z ‐scores were calculated at diagnosis and follow‐up (minimum 12 months) per WHO 2007 Growth Reference standards. Results: BMI z ‐scores increased significantly only in the strict adherence group (median Δ +0.27, p = 0.036), while partial adherence ( p = 0.451) and non‐adherence ( p = 0.579) groups showed no significant change. Between‐group comparison was not significant ( p = 0.326). Height‐for‐age z ‐scores showed no significant change in the strict adherence group ( p = 0.247); BMI gains reflected disproportionate weight gain rather than proportional growth recovery. Six patients (5.1%) exceeded the obesity threshold ( z ‐score > +2) during follow‐up. Conclusion: Weight gain occurred primarily with strict GFD adherence. Without corresponding linear growth improvement, BMI increases in strictly adherent children may not represent catch‐up growth alone. Low obesity frequency may reflect traditional Turkish dietary patterns. Dietary counseling for celiac patients should extend beyond gluten avoidance to address overall nutritional balance.

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.