Mortality predictors in earthquake victims admitted to intensive care unit in Kahramanmaras earthquakes.

BACKGROUND: The purpose of this study is to report the data for patients followed-up in our intensive care unit due to the 6th February 2023, earthquake in Kahramanmaras, Türkiye, and to investigate parameters affecting mortality. METHODS: The demographic characteristics of patients followed-up in intensive care due to trauma following the earthquake, the treatments administered, developing complications, lengths of stay in the hospital and intensive care, and laboratory data were scanned retrospectively and recorded. These data were then compared between the surviving and non-surviving patients. RESULTS: Twenty-six patients, 13 (50 %) male, were followed-up in our intensive care, 24 (92 %) due to being buried under earthquake debris, and 2 (8 %) due to falling from heights. Increased Sequential Organ Failure Assessment (SOFA) (p = 0.027), higher initial serum potassium (p = 0.043), higher initial serum phosphorus (p = 0.035), higher initial and peak serum magnesium (p = 0.004 and p = 0.001), lower initial and peak bicarbonate (p = 0.021 and p = 0.012) and higher initial and peak serum base deficit values (p = 0.012 and p = 0.009) were associated with mortality. In the subgroup with crush injuries, higher initial and peak serum potassium (p = 0.001 and p = 0.025), higher initial and peak serum magnesium (p = 0.005 and p = 0.004), lower initial and peak bicarbonate (p = 0.019 and p = 0.021) and higher initial and peak serum base deficit values (p = 0.017 and p = 0.025) were associated with mortality. Multiorgan dysfunction failure developed in nine patients, sepsis in seven, dissemine intravascular coagulation in four, and acute respiratory distress syndrome in two. Fasciotomy was performed on 2 (8 %) patients and amputation on 8 (31 %). Extremity injuries were most frequently observed. 10 (38.5 %) of the 12 (46 %) patients developing acute kidney injury required renal replacement therapy. 7 (27 %) patients died during follow-up. In logistic regression analysis, higher SOFA scores, lower initial bicarbonate and BE levels, higher serum initial potassium and magnesium levels were a risk factor for mortality. Higher SOFA scores, lower initial bicarbonate and base deficit and higher initial phosphorus values affected mortality in patients with crush syndrome. CONCLUSION: Not only increased SOFA, serum potassium, serum phosphorus, and serum magnesium, but also decreased bicarbonate, and base deficit were associated with mortality in earthquake victims with crush syndrome in ICU.

Prediction of Perforated and Nonperforated Acute Appendicitis Using Machine Learning-Based Explainable Artificial Intelligence.

BACKGROUND: The primary aim of this study was to create a machine learning (ML) model that can predict perforated and nonperforated acute appendicitis (AAp) with high accuracy and to demonstrate the clinical interpretability of the model with explainable artificial intelligence (XAI). METHOD: A total of 1797 patients who underwent appendectomy with a preliminary diagnosis of AAp between May 2009 and March 2022 were included in the study. Considering the histopathological examination, the patients were divided into two groups as AAp (n = 1465) and non-AAp (NA; n = 332); the non-AAp group is also referred to as negative appendectomy. Subsequently, patients confirmed to have AAp were divided into two subgroups: nonperforated (n = 1161) and perforated AAp (n = 304). The missing values in the data set were assigned using the Random Forest method. The Boruta variable selection method was used to identify the most important variables associated with AAp and perforated AAp. The class imbalance problem in the data set was resolved by the SMOTE method. The CatBoost model was used to classify AAp and non-AAp patients and perforated and nonperforated AAp patients. The performance of the model in the holdout test set was evaluated with accuracy, F1- score, sensitivity, specificity, and area under the receiver operator curve (AUC). The SHAP method, which is one of the XAI methods, was used to interpret the model results. RESULTS: The CatBoost model could distinguish AAp patients from non-AAp individuals with an accuracy of 88.2% (85.6-90.8%), while distinguishing perforated AAp patients from nonperforated AAp individuals with an accuracy of 92% (89.6-94.5%). According to the results of the SHAP method applied to the CatBoost model, it was observed that high total bilirubin, WBC, Netrophil, WLR, NLR, CRP, and WNR values, and low PNR, PDW, and MCV values increased the prediction of AAp biochemically. On the other hand, high CRP, Age, Total Bilirubin, PLT, RDW, WBC, MCV, WLR, NLR, and Neutrophil values, and low Lymphocyte, PDW, MPV, and PNR values were observed to increase the prediction of perforated AAp. CONCLUSION: For the first time in the literature, a new approach combining ML and XAI methods was tried to predict AAp and perforated AAp, and both clinical conditions were predicted with high accuracy. This new approach proved successful in showing how well which demographic and biochemical parameters could explain the current clinical situation in predicting AAp and perforated AAp.

Explainable artificial intelligence model for identifying COVID-19 gene biomarkers.

AIM: COVID-19 has revealed the need for fast and reliable methods to assist clinicians in diagnosing the disease. This article presents a model that applies explainable artificial intelligence (XAI) methods based on machine learning techniques on COVID-19 metagenomic next-generation sequencing (mNGS) samples. METHODS: In the data set used in the study, there are 15,979 gene expressions of 234 patients with COVID-19 negative 141 (60.3%) and COVID-19 positive 93 (39.7%). The least absolute shrinkage and selection operator (LASSO) method was applied to select genes associated with COVID-19. Support Vector Machine - Synthetic Minority Oversampling Technique (SVM-SMOTE) method was used to handle the class imbalance problem. Logistics regression (LR), SVM, random forest (RF), and extreme gradient boosting (XGBoost) methods were constructed to predict COVID-19. An explainable approach based on local interpretable model-agnostic explanations (LIME) and SHAPley Additive exPlanations (SHAP) methods was applied to determine COVID-19- associated biomarker candidate genes and improve the final model's interpretability. RESULTS: For the diagnosis of COVID-19, the XGBoost (accuracy: 0.930) model outperformed the RF (accuracy: 0.912), SVM (accuracy: 0.877), and LR (accuracy: 0.912) models. As a result of the SHAP, the three most important genes associated with COVID-19 were IFI27, LGR6, and FAM83A. The results of LIME showed that especially the high level of IFI27 gene expression contributed to increasing the probability of positive class. CONCLUSIONS: The proposed model (XGBoost) was able to predict COVID-19 successfully. The results show that machine learning combined with LIME and SHAP can explain the biomarker prediction for COVID-19 and provide clinicians with an intuitive understanding and interpretability of the impact of risk factors in the model.

A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs.

The study aims to evaluate the diagnostic performance of an artificial intelligence system based on deep learning for the segmentation of occlusal, proximal and cervical caries lesions on panoramic radiographs. The study included 504 anonymous panoramic radiographs obtained from the radiology archive of Inonu University Faculty of Dentistry's Department of Oral and Maxillofacial Radiology from January 2018 to January 2020. This study proposes Dental Caries Detection Network (DCDNet) architecture for dental caries segmentation. The main difference between DCDNet and other segmentation architecture is that the last part of DCDNet contains a Multi-Predicted Output (MPO) structure. In MPO, the final feature map split into three different paths for detecting occlusal, proximal and cervical caries. Extensive experimental analyses were executed to analyze the DCDNet network architecture performance. In these comparison results, while the proposed model achieved an average F1-score of 62.79%, the highest average F1-score of 15.69% was achieved with the state-of-the-art segmentation models. These results show that the proposed artificial intelligence-based model can be one of the indispensable auxiliary tools of dentists in the diagnosis and treatment planning of carious lesions by enabling their detection in different locations with high success.

Evaluation of the relationship between nasal septal deviation and development of facial asymmetry with anthropometric measurements depending on age.

AIM: It was aimed to determine the change of facial asymmetry resulting from nasal septal deviation (SD) depending on age, gender, degree of deviation and the affected area besides the effect of SD on somatotype and craniofacial morphology. MATERIALS AND METHODS: 171 volunteers (90 males, 81 females), 27 individuals aged 9-13, 44 individuals aged 14-18, 44 individuals aged 19-23 and 56 individuals in control group participated in the study conducted in otorhinolaryngology polyclinic.11 photometric, 16 anthropometric measurements were taken from the participants. RESULTS: SD affects facial asymmetry formation, although not statistically significant compared to healthy individuals asymmetry rates (p˃0.05). It was determined that the degree of SD affected asymmetry only between the ages of 14-18 (in adolescence) and the development of asymmetry in all SD patients was not statistically dependent on age and gender (p˃0.05). Photometric measurements demonstrated asymmetries in horizontally-extending parameters of 1/3 middle part of face. There was no statistically significant difference in the cranial anthropometric measurements of the upper and lower 1/3 of the face compared to the control group (p˃0.05). The order of the most asymmetrical parameters is Alare-Zygion, Alare-Subnasale, Cheilion-Gonion, Exocanthion-Cheilion, Midsagittal plane-Zygion, Zygion-Cheilion, Zygion-Gonion, Subalare-Cheilion, Glabella-Exocanthion. In all participants were determined that endomorph somatotype was dominant in female and mesomorph somatotype was dominant in male besides SD did not affect somatotype and somatotype did not alter with age. CONCLUSION: The development of facial asymmetry due to SD is not affected by age and gender furthermore SD does not affect craniofacial asymmetry and somatotype.

Preoperative evaluation of liver volume in living donor liver transplantation.

OBJECTIVE: The aim of the present study was to retrospectively evaluate the difference between the preoperative estimated volume and the actual intraoperative graft volume determined in donor right hepatectomies and to evaluate the possible effect of age, gender, and body mass index on the difference. METHODS: A total of 225 donor hepatectomies performed at the center between 2016 and 2017 were evaluated for the study. Left hepatectomies and left lateral segmentectomies were excluded from the analysis. As a result, 174 donor right hepatectomies were included in the study. Volumetric analysis was performed with dynamic hepatic computed tomography (CT), including non-contrast analysis, followed by non-ionic, contrast-enhanced arterial, portal, and hepatic-phase, thin-slice scanning. Volumetric analysis was performed based on the CT images using automatic volume calculating software. RESULTS: The mean preoperatively estimated graft volume was 800±112 g and the mean intraoperatively measured actual graft volume was 750±131 g. There was a statistically significant difference (p=0.003). Age and body mass index had a significant impact on the discrepancy between the predicted and actual graft volume, while gender did not. CONCLUSION: A thorough preoperative evaluation of the donor graft volume should be performed in order to prevent donor morbidity and mortality, as well as small-for-size and large-for-size phenomena in the implanted grafts. Physicians working in the field of transplantation should be aware of the fact that a difference of 10% between the predicted and the actual graft volume is usually encountered.