Search

Introduction: There is a tendency toward nonoperative management of appendicitis resulting in an increasing need for preoperative diagnosis and classification. For medical purposes, simple conceptual decision-making models that can learn are widely used. Decision trees are reliable and effective techniques which provide high classification accuracy. We tested if we could detect appendicitis and differentiate uncomplicated from complicated cases using machine learning algorithms., Materials and Methods: We analyzed all cases admitted between 2010 and 2016 that fell into the following categories: healthy controls (Group 1); sham controls (Group 2); sham disease (Group 3), and acute abdomen (Group 4). The latter group was further divided into four groups: false laparotomy; uncomplicated appendicitis; complicated appendicitis without abscess, and complicated appendicitis with abscess. Patients with comorbidities and whose complete blood count and/or pathology results were lacking were excluded. Data were collected for demographics, preoperative blood analysis, and postoperative diagnosis. Various machine learning algorithms were applied to detect appendicitis patients., Results: There were 7244 patients with a mean age of 6.84 ± 5.31 years, of whom 82.3% (5960/7244) were male. Most algorithms tested, especially linear methods, provided similar performance measures. We preferred the decision tree model due to its easier interpretability. With this algorithm, we detected appendicitis patients with 93.97% area under the curve (AUC), 94.69% accuracy, 93.55% sensitivity, and 96.55% specificity, and uncomplicated appendicitis with 79.47% AUC, 70.83% accuracy, 66.81% sensitivity, and 81.88% specificity., Conclusions: Machine learning is a novel approach to prevent unnecessary operations and decrease the burden of appendicitis both for patients and health systems., Levels of Evidence: III.

The tendency of non-operative management of appendicitis let us explore the natural history of appendiceal carcinoids, compare them with appendicitis patients, and determine the possibility of deciding the extent of the surgery and post-operative follow-up on behalf of the intraoperative findings. A retrospective review was performed of patients with appendicitis between 2009 and 2017. Of 2781 patients, 10 (0.36%) were diagnosed with appendiceal carcinoids. Sixty percent were female with an average age of 13.10 ± 1.73. The mean tumor size was 0.97 ± 0.34 cm with 70% located at the tip. Majority had an insular pattern (n = 9), six had subserosal fat tissue invasion, one had extension to mesoappendix, one had vascular invasion, and two had lymphatic invasion. The average mitotic index was 3.20 ± 1.40/50HPF, and Ki 67 activity was 3 ± 1.7%. The mean follow-up period was 66.40 ± 25.92 months. Patients were further evaluated with ultrasonography (n = 10), CT (n = 3), and MRI (n = 10). Serum markers including chromogranin (n = 9), NSE (n = 6), and 5-HIAA (n = 6) were normal. None required further treatment and had any symptoms of carcinoid syndromes or recurrences post-operatively.Conclusion: Other than appendectomy, no additional surgery or follow-up is required in appendiceal carcinoids less than 1.5 cm in size, regardless of the lymphoid or vascular invasion. What is Known: • The treatment of patients with a 1-2-cm tumor is not clear in both the pediatric and adult populations, and additional resection is needed. • Patients are monitored post-operatively with radiological and/or biochemical testing. What is New: • Appendectomy is curative for tumors less than 2 cm. • No additional surgery or follow-up is required in appendiceal carcinoids less than 1.5 cm in size regardless of the lymphoid or vascular invasion.