A different way to diagnosis acute appendicitis: machine learning

<b><br>Indroduction:</b> Machine learning is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns, and make decisions with minimal human intervention.</br> <b><br>Aim:</b> Our aim is to predict acute appendicitis, which is the most common indication for emergency surgery, using machine learning algorithms with an easy and inexpensive method.</br> <b><br>Materials and methods:</b> Patients who were treated surgically with a prediagnosis of acute appendicitis in a single center between 2011 and 2021 were analyzed. Patients with right lower quadrant pain were selected. A total of 189 positive and 156 negative appendectomies were found. Gender and hemogram were used as features. Machine learning algorithms and data analysis were made in Python (3.7) programming language.</br> <b><br>Results:</b> Negative appendectomies were found in 62% (n = 97) of the women and in 38% (n = 59) of the men. Positive appendectomies were present in 38% (n = 72) of the women and 62% (n = 117) of the men. The accuracy in the test data was 82.7% in logistic regression, 68.9% in support vector machines, 78.1% in k-nearest neighbors, and 83.9% in neural networks. The accuracy in the voting classifier created with logistic regression, k-nearest neighbor, support vector machines, and artificial neural networks was 86.2%. In the voting classifier, the sensitivity was 83.7% and the specificity was 88.6%.</br> <b><br>Conclusions:</b> The results of our study show that machine learning is an effective method for diagnosing acute appendicitis. This study presents a practical, easy, fast, and inexpensive method to predict the diagnosis of acute appendicitis.</br>.

Isolated recto-vaginal septum injury during parturition: Single-center experience

BACKGROUND

Traumatic rectal injuries are uncommon and can originate due to various causes. Rectal injuries have a high mor-bidity, regardless of cause, and detection at the time of occurrence is important to prevent fistula formation and/or stoma. In this article, treatment approaches in patients with isolated rectovaginal septum injury without perineal and sphincter injury during sponta-neous vaginal delivery are presented and the current literature is reviewed.

METHODS

The records of spontaneous vaginal deliveries that resulted in live births between January 2015 and January 2020 were analyzed retrospectively at our center. The records of patients with isolated rectovaginal septum injury were evaluated in terms of demographic and obstetric data, trauma, classification of injury, and early and late results.

RESULTS

Isolated septum injuries were detected 12 women (0.06%). Of the isolated rectovaginal septum injuries, 9 (75%) were clas-sified as Type III, 2 (16.6%) as Type IV, and 1 (8.3%) as a Type V injury according to the Rosenshein classification. Transvaginal repair was performed because all of the injuries underwent early surgical intervention, were limited, and exploration through the vagina was possible.

CONCLUSION

Rectal examination should be performed simultaneously with a detailed perineal examination after vaginal delivery. For birth-related rectal injuries detected early in appropriate patients, a primary repair without diversion stoma may be the best option.