PurposeLarge language models (LLMs) are increasingly used in clinical data workflows, but most clinicians lack the time, training, or support to build predictive models. We evaluated whether a ChatGPT-assisted workflow could enable clinicians to independently construct and execute a basic predictive model using routine perioperative data, using postoperative length of stay (LOS) in pediatric appendicitis as a feasibility use case.MethodsWe conducted a retrospective study of 228 children undergoing laparoscopic appendectomy. Ten routinely available preoperative variables were used. ChatGPT guided preprocessing and generated code for linear regression and random forest models using naïve and structured prompting. Models were trained using an 80/20 split and evaluated using MAE, RMSE, r, and R[2].ResultsNaïve prompting performed poorly, while structured prompting improved model performance (MAE 0.34, RMSE 0.85, r 0.85). On the test set, linear regression achieved MAE 1.00 and random forest 0.77. Identified variables reflected expected clinical patterns. These findings demonstrate internal consistency of the workflow rather than new predictive insight.ConclusionsA structured ChatGPT workflow enabled clinicians to construct standard predictive models using routine data. These findings support feasibility of clinician-directed model development, but not clinical utility, of LLM-enabled workflows.

Acute appendicitis in patients with situs inversus totalis (SIT) represents a diagnostic challenge because the clinical presentation frequently differs from the classic right lower quadrant pain pattern. We present the case of a 37-year-old male with acute appendicitis associated with previously undiagnosed SIT, identified incidentally during diagnostic imaging. The patient presented with left lower quadrant abdominal pain, leukocytosis, and localized tenderness. Computed tomography revealed dextrocardia and left-sided inflammatory changes compatible with acute appendicitis in the setting of SIT. Laparoscopic appendectomy was successfully performed with modified port placement according to the reversed anatomy, with favorable postoperative recovery. This case highlights the importance of considering anatomical anomalies in patients presenting with atypical abdominal pain. Imaging studies, particularly computed tomography, play a crucial role in establishing an early diagnosis and preventing complications such as perforation or generalized peritonitis. Furthermore, laparoscopy offers both diagnostic and therapeutic advantages in patients with situs inversus. Awareness of this uncommon entity is essential for surgeons and emergency physicians in order to avoid delays in diagnosis and treatment.

Meckel's diverticulum is the most common congenital anomaly of the gastrointestinal tract but remains diagnostically challenging in children because of its varied and nonspecific clinical presentation. Concomitant Meckel's diverticulum and acute appendicitis are uncommon and may further obscure diagnosis. We report a 9-year-old boy who presented with chronic periumbilical abdominal pain of 3 months' duration, with acute worsening over 3 days accompanied by vomiting. Physical examination revealed localized right periumbilical tenderness without signs of peritonitis. Laboratory investigations demonstrated mild anemia and eosinophilia, while ultrasonography identified an appendicolith with mesenteric lymphadenitis, raising suspicion for appendiceal pathology. Owing to persistent symptoms and concern for evolving subacute intestinal obstruction, diagnostic laparoscopy was performed. Intraoperatively, acute appendicitis was identified along with a dilated Meckel's diverticulum ~100 cm proximal to the ileocecal junction and associated proximal small-bowel dilatation. Laparoscopic-assisted Meckel's diverticulectomy with appendectomy was successfully performed. Histopathologic examination confirmed acute appendicitis with a fecolith and transmural inflammatory infiltrates. The Meckel's diverticulum demonstrated focal Paneth cell metaplasia and lymphoid aggregates consistent with Peyer patches without ectopic gastric or pancreatic tissue or atypia. The mesenteric lymph node showed reactive lymphoid hyperplasia. The postoperative course was uneventful, and the child remained symptom-free at 2-month follow-up. This case highlights the importance of considering dual intraabdominal pathology in children presenting with prolonged or atypical abdominal pain. Diagnostic laparoscopy plays a pivotal role by enabling comprehensive abdominal evaluation and definitive treatment in a single setting. Furthermore, symptomatic Meckel's diverticulum may occur in the absence of heterotopic mucosa, and uncommon histopathologic findings such as focal Paneth cell metaplasia underscore the value of meticulous examination of resected specimens.

A recurring argument in radiological protection holds that the radiation risk of an imaging examination must be weighed against the clinical risk of not performing it. The argument is applied inconsistently, and evidence on that clinical risk remains sparse compared with the extensive literature on radiation risk. This asymmetry masks an important distinction: the clinical risk of not imaging is not uniformly high. We propose a three-scenario framework for medical imaging, illustrated using computed tomography. In Scenario 1, the harm of withholding or delaying imaging is well documented and substantially exceeds the radiation risk, as in appendicitis, stroke, pulmonary embolism, aortic dissection, and polytrauma. In Scenario 2, imaging is repeated at low incremental yield, exposure accumulates, and guidance on intervals is limited, so radiation risk may outweigh marginal diagnostic gain. In Scenario 3, evidence on both sides is insufficient, and decisions are best supported by clinical decision rules and shared decision making. The framework addresses procedure-level and individual justification, and is confined to the balance between clinical and radiation risk. We suggest that clinical specialty organizations develop guidance on imaging frequency that incorporates review of cumulative exposure, and that ICRP address the place of such exposure within the justification framework.

Non-contrast magnetic resonance imaging (MRI) is the preferred cross-sectional imaging modality for suspected appendicitis in pregnancy, yet its interpretation is uniquely challenging. This pictorial review moves beyond simple appendiceal diameter thresholds to the practical pitfalls encountered in daily practice. We show how the enlarging gravid uterus displaces the appendix and how physiologic changes mask inflammatory signs. We also address the diagnostic uncertainty of the equivocal appendix and the need to recognize subtle secondary features on MRI. We then detail several important entities that may confound interpretation, either by mimicking an inflamed appendix or by obscuring a normal one: pelvic venous engorgement, terminal ileitis, cecal diverticulitis, ovarian torsion, and ectopic pregnancy. For each, we highlight the features that help distinguish them. Finally, we discuss technical limitations such as field inhomogeneity and motion artifacts. We present a stepwise approach to locating the appendix paired with a problem-solving strategy that combines non-fat-suppressed and fat-suppressed T2-weighted sequences. By recognizing these multifaceted pearls and pitfalls, radiologists can improve diagnostic confidence and optimize care in this challenging population.