OBJECTIVE: Up to 50% of ultrasounds (USs) for suspected pediatric appendicitis are nondiagnostic. While the validated low-risk clinical pediatric Appendicitis Risk Calculator (pARC) score < 15% and the low-risk US with nonvisualized appendix and no periappendiceal inflammation carry relatively low appendicitis risks, the contribution of the combination of both characteristics to this risk has never been assessed. The primary objective was to determine the proportion of children with the low-risk US-low-risk pARC combination with appendicitis. We hypothesized that this proportion would be 2.5% (upper 95% CI ≤ 5%).
METHODS: A retrospective cohort study of 448 previously healthy children 4-17 years old at a pediatric ED with suspected appendicitis, nondiagnostic US, and persistent clinical concern about appendicitis. Two investigators abstracted demographic, clinical, and imaging data. Based on published criteria, USs were classified as low-risk or high-risk. The pARC includes seven demographic, clinical, and laboratory variables and is quantified according to the published formula. The primary outcome was appendicitis, based on the histological evidence. All nonoperated patients underwent a 1-month-follow-up to exclude delayed appendicitis diagnoses.
RESULTS: Sixty of the 448 (13.4%) patients had appendicitis; 269 (60%) had low-risk US, 262 (58.4%) had low-risk pARC, and 163 (36.4%) had both characteristics. The appendicitis rates with low-risk pARC alone and low-risk US alone were 14/262 (5.4%) and 21/269 (7.8%), respectively. A total of 2/163 children (1.2%) with low-risk pARC and low-risk US had appendicitis (95% CI 0%-4.4%). Higher-risk US increased the appendicitis odds 5 (95% CI 1.54-20.55) to 11 times (95% CI 2.41-51.10) across pARC levels. The low-risk combination had sensitivity of 96.7% (95% CI 88.5%-99.6%), specificity of 41.5%, positive predictive value of 20.4%, and negative predictive value of 98.8% (95% CI 95.6%-99.9%).
CONCLUSIONS: The children with low-risk pARC and low-risk US combination are unlikely to have appendicitis and can be discharged home. The presence of higher-risk US-pARC score combinations substantially increases the appendicitis risk and warrants reassessment or interval imaging.

Appendicitis is the most common cause of acute abdominal pain requiring surgical intervention; however, it is extremely rare in infants. Its diagnosis and treatment are challenging due to nonspecific clinical signs and symptoms. As a result, delayed or missed diagnosis is common in young children and is associated with an increased risk of perforation and peritonitis. We reported a case of a 4-month-old healthy male child. The patient presented with abdominal distention and fever. After ruling out other possible causes, he was diagnosed with acute appendicitis, which was confirmed by a CT scan. A gangrenous appendix, dilated bowel loops, and free fluid in the abdomen were discovered during surgery. An appendectomy was performed. The appendix in infants has an average length of 4.5 cm compared with 9.5 cm in adults. Infantile appendicitis is considered rare but cases have been documented also in neonates, misdiagnosis rates are high due to rarity in this age group in addition to nonspecific signs and symptoms, which led to a high perforation rate. Ultrasonography can diagnose appendicitis in children with a sensitivity and specificity of 90%-95% without subjecting the child to radiation. A physician should always keep the diagnosis of appendicitis in mind in the infant age group, even though it is rare, as a delay in diagnosis and treatment has been associated with an increased risk of complications including appendicular perforation and peritonitis.

OBJECTIVE: Data science approaches personalizing pediatric appendicitis management are hampered by small datasets and unstructured electronic medical records (EMR). Artificial intelligence (AI) chatbots based on large language models can structure free-text EMR data. We compare data extraction quality between ChatGPT-4 and human data collectors.
METHODS: To train AI models to grade pediatric appendicitis preoperatively, several data collectors extracted detailed preoperative and operative data from 2100 children operated for acute appendicitis. Collectors were trained for the task based on satisfactory Kappa scores. ChatGPT-4 was prompted to structure free text from 103 random anonymized ultrasound and operative records in the dataset using the set variables and coding options, and to estimate appendicitis severity grade from the operative report. A pediatric surgeon then adjudicated all data, identifying errors in each method.
RESULTS: Within the 44 ultrasound (42.7%) and 32 operative reports (31.1%) discordant in at least one field, 98% of the errors were found in the manual data extraction. The appendicitis grade was erroneously assigned manually in 29 patients (28.2%), and by ChatGPT-4 in 3 (2.9%). Across datasets, the use of the AI chatbot was able to avoid misclassification in 59.2% of the records including both reports and extracted data approximately 40 times faster.
CONCLUSIONS: AI chatbot significantly outperformed manual data extraction in accuracy for ultrasound and operative reports, and correctly assigned the appendicitis grade. While wider validation is required and data safety concerns must be addressed, these AI tools show significant promise in improving the accuracy and efficiency of research data collection.
METHODS: Level III.

BACKGROUND: Appendicitis is one of the most common causes of acute abdominal pain and remains the most common abdominal-related emergency seen in emergency room that needs urgent surgery (Yang et al. in J Emerg Med 43:980-2, 2012. 10.1016/j.jemermed.2010.11.056, Wickramasinghe et al. in World J Surg 45:1999-2008, 2021. 10.1007/s00268-021-06077-5). The characteristic presentation is a vague epigastric or periumbilical discomfort or pain that migrates to the lower right quadrant in 50% of cases. Other related symptoms, such as nausea, anorexia, vomiting, and change in bowel habits, occur in varying percentages. The diagnosis is usually reached through comprehensive history, physical examination, laboratory tests, and radiological investigations as needed. Nowadays, computed tomography of the abdomen and pelvis is considered the modality of choice for definitive assessment of patients being evaluated for possible appendicitis. Anatomical variations or an ectopic appendix are rarely reported or highlighted in literature.
METHODS: Left-sided appendicitis is a rare (Hu et al. in Front Surg 2022. 10.3389/fsurg.2022.896116) and atypical presentation and has rarely been reported. The majority of these cases are associated with congenital midgut malrotation, situs inversus, or an extremely long appendix (Akbulut et al. in World J Gastroenterol 16:5598-5602, 2010. 10.3748/wjg.v16.i44.5598). This case is of significance to raise awareness regarding an anatomical variation of the appendix that might delay or mislead diagnosis of appendicitis and to confirm safety of a laparoscopic approach in dealing with a left-sided appendicitis case (Yang et al. in J Emerg Med 43:980-2, 2012. 10.1016/j.jemermed.2010.11.056). We report a case of left-sided appendicitis in a 12-year-old child managed successfully via a laparoscopic approach.
CONCLUSIONS: Appendicitis remains the most common abdominal-related emergency that needs urgent surgery (Akbulut et al. in World J Gastroenterol 16:5598-5602, 2010. 10.3748/wjg.v16.i44.5598). Left-sided appendicitis is a rare (Hu et al. in Front Surg 2022. 10.3389/fsurg.2022.896116, Hu et al. in Front Surg 9:896116, 2022. 10.3389/fsurg.2022.896116) and atypical presentation and has rarely been reported. Awareness regarding an anatomical variation of the appendix and diagnostic modalities on a computed tomography scan help avoid delay in diagnosis and management of such a rare entity (Vieira et al. in J Coloproctol 39(03):279-287, 2019. 10.1016/j.jcol.2019.04.003). A laparoscopic approach is a safe approach for management of left-sided appendicitis (Yang et al. in J Emerg Med 43:980-2, 2012. 10.1016/j.jemermed.2010.11.056, Hu et al. in Front Surg 9:896116, 2022. 10.3389/fsurg.2022.896116).

Accurate diagnosis of paediatric appendicitis remains a challenge due to its diverse clinical presentations and reliance on subjective assessments. The integration of artificial intelligence (AI) with an expert\'s \'\'clinical sense\'\' has the potential to improve diagnostic accuracy. In this study, we aimed to evaluate the effectiveness of the Artificial Intelligence Pediatric Appendicitis Decision-tree (AiPAD) model in enhancing the diagnostic capabilities of trainees and compare their performance with that of an expert supervisor. Between March 2019 and October 2022, we included paediatric patients aged 0-12 years who were referred for suspected appendicitis. Trainees collected clinical findings using five predefined parameters before ordering any imaging studies. The AiPAD model, which was blinded to the surgical team, made predictions from the supervisor\'s and trainees\' findings independently. The diagnosis verdicts of the supervisor and the trainees were statistically evaluated in comparison to the prediction of the AI model, taking into account the revealed correct diagnosis. A total of 136 cases were included, comprising 58 cases of acute appendicitis (AA) and 78 cases of non-appendicitis (NA). The supervisor\'s correct verdict showed 91% accuracy compared to an average of 70% for trainees. However, if trainees were enabled with AiPAD, their accuracy would improve significantly to an average of 97%. Significantly, a strong association was observed between the expert\'s clinical sense and the predictions generated by AiPAD.
CONCLUSIONS:  The utilisation of the AiPAD model in diagnosing paediatric appendicitis has significant potential to improve trainees\' diagnostic accuracy, approaching the level of an expert supervisor. This hybrid approach combining AI and expert knowledge holds promise for enhancing diagnostic capabilities, reducing medical errors and improving patient outcomes.
BACKGROUND: • Sharpening clinical judgement for pediatric appendicitis takes time and seasoned exposure. Traditional training leaves junior doctors yearning for a faster path to diagnostic mastery.
BACKGROUND: • AI-generated models unlock the secrets of expert intuition, crafting an explicit guide for juniors to rapidly elevate their diagnostic skills. This leapfrog advancement empowers young doctors, democratizing medical expertise and paving the way for brighter outcomes in clinical training.

Appendicitis is among the most frequent reasons for pediatric abdominal surgeries. Previous decision support systems for appendicitis have focused on clinical, laboratory, scoring, and computed tomography data and have ignored abdominal ultrasound, despite its noninvasive nature and widespread availability. In this work, we present interpretable machine learning models for predicting the diagnosis, management and severity of suspected appendicitis using ultrasound images. Our approach utilizes concept bottleneck models (CBM) that facilitate interpretation and interaction with high-level concepts understandable to clinicians. Furthermore, we extend CBMs to prediction problems with multiple views and incomplete concept sets. Our models were trained on a dataset comprising 579 pediatric patients with 1709 ultrasound images accompanied by clinical and laboratory data. Results show that our proposed method enables clinicians to utilize a human-understandable and intervenable predictive model without compromising performance or requiring time-consuming image annotation when deployed. For predicting the diagnosis, the extended multiview CBM attained an AUROC of 0.80 and an AUPR of 0.92, performing comparably to similar black-box neural networks trained and tested on the same dataset.

Background Acute appendicitis (AA) is the most common surgical emergency worldwide. Delay in diagnosis of disease often leads to serious complications such as perforation appendicitis (PA) and gangrenous appendicitis (GA). Aims and objectives The purpose of the study is to document clinicopathological outcomes in pediatric age group patients in a tertiary health care center. Material and method This study was a prospective observation study of 50 patients with pediatric appendicitis who had undergone emergency appendectomy from January 2022 to December 2022. All pediatric patients below 15 years of age with a diagnosis of AA were included. Institute ethical permission was granted before the study, and parent consent was taken for the surgery and also for inclusion in the study. After proper resuscitation, all patients underwent appendectomy, and necessary specimens were sent for histological examination. Based on histopathology reports, all patients were classified into four groups: AA, PA, GA, and normal appendix (NA). Results Out of 50 patients, 33 (66%) patients were males and 17 (34%) patients were females. The mean age of the patients was 10.22 ± 2.73 years. The mean age of AA, PA, GA, and NA patients were 10.25 ± 2.6 years, 9.78 ± 2.99 years, 10.00 ± 4.6 years, and 12.00 ± 2.8 years, respectively. The mean duration of symptoms at the time of hospital admission was 2.42 ± 0.97 days for histopathologically proven AA patients, 4.67 ± 2.1 days for GA patients, 2.8 ± 0.83 for PA patients, and one day for NA patients. Overall clinical presentation was right iliac fossa (RIF) pain in 36 (72%) patients, migration of pain in 31 (62%) patients, anorexia in 37 (74%) patients, nausea and vomiting in 43 (86%) patients fever in 26 (52%) patients, RIF tenderness in 50 (100%) patients, rebound tenderness in 39 (78%) patients, guarding in 19 (38%) patients, Psoas\'s sign in nine (18% patients), and Rovsing\'s sign in 19 (38%) patients. On histopathological examination of the sent specimen, AA was found in 36 (72%) patients, PA was found in nine (18%) patients, GA was found in three (6%) patients, and NA was found in two (4%) patients. Wound infection was the most common complication and was found in five (10%) patients. The average duration of hospital stay for AA, PA, GA, and NA was 4.33 ± 1.04 days, 9.56 ± 4.2 days, 12.33 ± 8.5 days, and 3.50 ± 0.71 days, respectively. Conclusion The appendicular disease is common in teenage male children. Fever, dehydration, and rebound tenderness at the RIF are clinically significant findings. Duration of symptoms at the time of diagnosis, post-appendectomy complication, and duration of hospital stay significantly correlated with histopathological findings.

BACKGROUND: Acute appendicitis is the leading cause of emergency pediatric surgical admissions in the world. The diagnosis is may be difficult and is often dependent on clinical parameters. This study was aimed at reviewing the clinical presentations, the management and outcomes in children with inflamed and phlegmonous appendicitis with reference to the operative findings.
METHODS: The records of 211 children 5 to 15 years of age who were operated for acute appendicitis with intra operative findings of inflamed or phlegmonous appendicitis who met inclusion criteria were entered and analyzed using SPSS (IBM) V.26. Descriptive and regression tests were done with p < 0.05 considered statistically significant.
RESULTS: Of 211 children with inflamed and phlegmonous appendicitis, the M: F was 1.48:1 with a median age of 11 years. 58.3% of them presented within 24 h with the commonest symptoms being right lower abdominal pain, anorexia, and vomiting (96.2%,96.2%, 85.3%,) respectively. 96.7% of them had right lower abdominal tenderness. 73% had neutrophils ≥ 75%, and of 171 patients who had abdominal ultrasound scan, 97.7% showed appendiceal diameter ≥ 6 mm. Intraoperatively 56.4% of them were found to have phlegmonous appendicitis. In a retrospective Pediatric Appendiceal Score, only 52.6% of patients fall into the high-risk category, who could be confirmed on preoperative clinical assessment. Postoperatively 90% of them discharged improved with a mean hospital stay of 2.26(SD = 0.9) days. There was no association between the sex of the child and the intraoperative finding of inflamed or phlegmonous appendicitis (p = 0.77).
CONCLUSIONS: Pediatric appendicitis affects more male children in their second decade of life. Most had phlegmonous appendicitis and presented within 24 h. Duration of illness has little effect on the progress of appendicitis. Surgical management is safe for inflamed and phlegmonous appendicitis with a reasonable hospital stay and a low rate of complications.

Missed diagnosis (MD) of acute appendicitis is associated with increased risk of appendiceal perforation. This study aimed to investigate whether racial/ethnic disparities exist in the diagnosis of pediatric appendicitis by comparing rates of MD versus single-encounter diagnosis (SED) between racial/ethnic groups.
Patients 0-18 y-old admitted for acute appendicitis from February 2017 to December 2021 were identified in the Pediatric Health Information System (PHIS). International Classification of Diseases, 10th Revision, Clinical Modification diagnosis codes for Emergency Department visits within 7 d prior to diagnosis were evaluated to determine whether the encounter represented MD. Generalized mixed models were used to assess the association between MD and patient characteristics. A similar model assessed independent predictors of perforation.
51,164 patients admitted for acute appendicitis were included; 50,239 (98.2%) had SED and 925 (1.8%) had MD. Compared to non-Hispanic White patients, patients of non-Hispanic Black (odds ratio 2.5, 95% confidence interval 2.0-3.1), Hispanic (2.1, 1.8-2.5), and other race/ethnicity (1.6, 1.2-2.1) had higher odds of MD. There was a significant interaction between race/ethnicity and imaging (P < 0.0001). Among patients with imaging, race/ethnicity was not significantly associated with MD. Among patients without imaging, there was an increase in strength of association between race/ethnicity and MD (non-Hispanic Black 3.6, 2.7-4.9; Hispanic 3.3, 2.6-4.1; other 2.0, 1.4-2.8). MD was associated with increased risk of perforation (2.5, 2.2-2.8).
Minority children were more likely to have MD. Future efforts should aim to mitigate the risk of MD, including implementation of algorithms to standardize the workup of abdominal pain to reduce potential consequences of implicit bias.

The management of pediatric appendicitis continues to advance with the development of evidence-based treatment algorithms and a recent shift toward patient-centered treatment approaches. Further research should focus on development of standardized institution-specific diagnostic algorithms to minimize rates of missed diagnosis and appendiceal perforation and refinement of evidence-based clinical treatment pathways that reduce complication rates and minimize health care resource utilization.