This study aimed to develop and validate an artificial intelligence model using machine learning (ML) to predict hospital mortality in patients with acute mesenteric ischemia (AMI). A total of 122 patients diagnosed with AMI at Sakarya University Training and Research Hospital between January 2011 and June 2023 were included in the study. These patients were divided into a training cohort (n=97) and a validation cohort (n=25), and further categorized as survivors and non-survivors during hospitalization. Serum-based laboratory results served as features. Hyperfeatures were eliminated using Recursive Feature Elimination (RFE) in Python to optimize outcomes. ML algorithms and data analyses were performed using Python (version 3.7). Of the patients, 56.5% were male (n=69) and 43.5% were female (n=53). The mean age was 71.9 years (range 39-94 years). The mortality rate during hospitalization was 50% (n=61). To achieve optimal results, the model incorporated features such as age, red cell distribution width (RDW), C-reactive protein (CRP), D-dimer, lactate, globulin, and creatinine. Success rates in test data were as follows: logistic regression (LG), 80%; random forest (RF), 60%; k-nearest neighbor (KN), 52%; multilayer perceptron (MLP), 72%; and support vector classifier (SVC), 84%. A voting classifier (VC), aggregating votes from all models, achieved an 84% success rate. Among the models, SVC (sensitivity 1.0, specificity 0.77, area under the curve (AUC) 0.90, Confidence Interval (95%): (0.83-0.84)) and VC (sensitivity 1.0, specificity 0.77, AUC 0.88, Confidence Interval (95%): (0.83-0.84)) were noted for their effectiveness. Independent risk factors for mortality were identified in patients with AMI. An efficient and rapid method using various ML models to predict mortality has been developed.

Indroduction: 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. Aim: 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. Materials and methods: 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. Results: 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%. Conclusions: 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.

Background. Many scoring systems have been developed for acute appendicitis, which is the most common emergent disorder in surgical practice. Considering the physiological changes and chronic diseases occurring with advancing age, an applied scoring system may not produce the same score in similar patients in all age groups. Objectives. We aimed to compare the predictive values of scoring systems in different age groups. Methods. In this prospective study, the patients operated on in our clinic with a prediagnosis of acute appendicitis between March 2020 and March 2021 were included. We divided them into three age groups as 1845 years (group 1), 4665 years (group 2), and >65 years (group 3). We compared the scores of the nine acute appendicitis scoring systems most commonly used in the literature for these age groups. Results. A total of 203 patients were included in our study. The Alvarado scoring system yielded the most accurate results for group 1, whereas the FenyoLinberg scoring system was the most accurate system for group 2 and the Eskelinen scoring system for group 3. Conclusion. Age should be considered as a major parameter during the selection of the scoring system to be applied for patients with prediagnosis of acute appendicitis. Our study revealed the Alvarado and the FenyoLindberg scoring systems as the most accurate systems for the differential diagnosis of appendicitis in the 1845 and 4665 years age groups, respectively. Although we found the Eskelinen scoring system as the most accurate one in the >65 years age group, the confidence intervals indicated that it may not be appropriate for use alone in this group.

Rectal cancer (RC) is a significant global health burden with distinct anatomical and prognostic challenges compared to colon cancer. Despite advancements in treatment, postoperative recurrence and poor survival rates remain prevalent, particularly in advanced-stage cases. This study aims to evaluate the prognostic value of systemic inflammatory biomarkers, including hemoglobin, albumin, lymphocyte, and platelet, LCR, prognostic nutritional index, CAR, NLR, and SII, in predicting long-term survival outcomes in RC patients. A retrospective cohort study was conducted on 637 patients who underwent low anterior resection for RC at Sakarya Training and Research Hospital between 2015 and 2023. Inclusion criteria were adult patients with complete clinicopathological and follow-up data. Inflammatory biomarkers were calculated using standard biochemical parameters. Overall survival (OS) was assessed through Kaplan–Meier analysis, and the prognostic significance of variables was determined via Cox regression and ROC analysis. Age, follow-up duration, hemoglobin, albumin, CRP levels, and inflammatory markers significantly influenced survival (P < .05). Elevated CRP/Albumin ratios, NLR, and SII values correlated with poor prognosis, while higher hemoglobin, albumin, lymphocyte, and platelet and prognostic nutritional index scores were associated with improved outcomes. Advanced tumor stage (T3/T4) and lymph node metastasis significantly reduced OS (P = .002). ROC analysis identified optimal biomarker cutoffs, with AUC values ranging from 0.7 to 0.9, indicating moderate to good predictive accuracy. Inflammation-based biomarkers provide valuable prognostic insights in RC, facilitating personalized treatment planning and follow-up. Future multicenter studies are needed to validate these findings and refine biomarker utility in clinical practice.