Journal of Research in Medical Sciences
Volume:29 Issue: 12, Dec 2024

The initial assessment of trauma is a time?consuming and challenging task. The purpose of this research is to examine the diagnostic effectiveness and usefulness of machine learning models paired with radiomics features to identify blunt traumatic liver injury in abdominal computed tomography (CT) images.

In this study, 600 CT scan images of people with mild and severe liver damage due to trauma and healthy people were collected from the Kaggle dataset. The axial images were segmented by an experienced radiologist, and radiomics features were extracted from each region of interest. Initially, 30 machine learning models were implemented, and finally, three machine learning models were selected including Light Gradient?Boosting Machine (LGBM), Ridge Classifier, and Extreme Gradient Boosting (XGBoost), and their performance was examined in more detail.

The two criteria of precision and specificity of LGBM and XGBoost models in diagnosing mild liver injury were calculated to be 100%. Only 6.00% of cases were misdiagnosed by the LGBM model. The LGBM model achieved 100% sensitivity and 99.00% accuracy in diagnosing severe liver injury. The area under the receiver operating characteristic curve value and precision of this model were also calculated to be 99.00% and 98.00%, respectively.

The artificial intelligence models used in this study have great potential to improve patient care by assisting radiologists and other physicians in diagnosing and staging trauma?related liver injuries. These models can help prioritize positive studies, allow more rapid evaluation, and identify more severe injuries thatmay require immediate intervention.

Accurate and timely assessment of tumor response after chemotherapy is crucial in clinical settings. The aim of this study was to explore the feasibility of Gemstone Spectral Imaging (GSI) for early assessment of chemotherapy responses in patients with colorectal cancer liver metastasis (CRCLM).

From October 2012 to October 2018, 46 patients (28 malesand 18 females) with CRCLM received GSI followed by chemotherapy were retrospectively reviewed. The patients were divided into a response group (n = 32) and a nonresponse group (n = 14) according to the tumor response to chemotherapy. The iodine concentration images and virtual monoenergetic images (VMIs) with an optimal contrast?to?noise ratio at the arterial phase (AP) and portal venous phase (PVP) were obtained by GSI viewer. The iodine concentration value and computed tomography (CT) value on VMIs and slope of spectral attenuation curves of all lesions were compared. A logistic regression analysis was used to determine the predictor of chemotherapy response.

The difference of extrahepatic metastasis (P = 0.001), CT value on 68 keV VMIs at the AP (P = 0.005) and PVP (P = 0.001), slope of CT value attenuation curves at the AP (P = 0.013) and PVP (P = 0.001), and iodine concentration value at PVP (P = 0.003) between the response and nonresponse groups were statistically significant. The CT value of the 68 keV VMIs (OR: 1.206; 95% confidence interval [CI]: 1.021–1.425, P = 0.027) and the iodine concentration value at PVP (OR: 1.952; 95% CI: 1.034–3.684, P = 0.039) were independent prognostic factors for predicting chemotherapy response.

Baseline GSI may help predict the response to chemotherapy and provide a good tumor?response indicator through single?energy CT value of 68 keV at the PVP and iodine concentration.

The data on the association between alcohol intake and sleep quality in a community?based setting are lacking. This study examined overall sleep difficulty according to alcohol habits among Korean adults.

We analyzed data from 4937 adults who responded to questions about sleep difficulty and drinking habits from the 2019 Korea National Health and Nutrition Examination Survey. Multivariate logistic regression analyses were used to calculate the odds ratios (ORs) and 95% confidence intervals (CIs) for substantial sleep difficulty based on the frequency or amount of alcohol consumption in total and age? and sex?stratified subgroup analyses.

Approximately 8.5% of the study population had substantial sleep difficulty.Individuals who drank <1 per week (frequency) or 1–2 cups per time (amount) had the lowest prevalence of substantial sleep difficulty, even compared with nondrinkers. Among drinkers, the association between alcohol use and sleep difficulty was significant in a dose?dependent manner (P for trend: 0.003 in frequency and < 0.001 in amount). Subgroup analysis revealed that significant linear relationships were robust for adults aged <50 years ([ORs] 1.20 [95% CIs 1.03–1.40] for frequency and 1.25 [1.10–1.42] for amount) and females (1.26 [1.10–1.44] for amount).

Alcohol consumption is associated with increased sleep difficulties, especially in younger adults and women, underscoring the need for targeted interventions and in?depth research on the effects of alcohol on sleep.

Diabetic cardiomyopathy (DCM) is a severe complication among patients with Type 2 diabetes, significantly increasing heart failure risk and mortality. Despite various implicated mechanisms, effective DCM treatments remain elusive. This study aimed to construct a comprehensive competing endogenous RNA (ceRNA) network in DCM using bioinformatics analysis.

Three expression profiles datasets (GSE161827, GSE161931, and GSE241166) were collected from gene expression omnibus database and then integrated for the identification of differentially expressed genes (DEGs). Gene Ontology, Kyoto Encyclopedia of Gene and Genome pathway analysis, and Gene set enrichment analysis (GSEA) were employed for functional analysis. Protein?proteininteraction (PPI) network and hub genes were also identified. The ceRNA regulatory networks were constructed based on interaction between long noncoding RNA (lncRNA) and DEGs, microRNA (miRNA) and DEGs, as predicted by public available databases.

A total of 105 DEGs, including 44 upregulated and 61 downregulated genes were identified to be associated with DCM. Functional enrichment analysis showed that fatty acid metabolism pathway and inflammatory responses were significantly enriched in DCM. A total of 56 interactions between miRNA with DEGs, and 27 interactions between lncRNA with miRNA was predicted. Besides, a ceRNA network includes 9 mRNA, 17 miRNA and 10 lncRNA was constructed, among which Cdh20 and Cacna2d2 were hub genes in PPI network.

The identified hub genes and ceRNA network components provide valuable insights into DCM biology and offer potential diagnostic biomarkers and therapeutic targets for further investigation. Further experimental validation and clinical studies are warranted to translate these findings into clinical applications.

The tricuspid annular plane systolic excursion (TAPSE) (transthoracic apical two?chamber stretch) and pulmonary artery systolic pressure (PASP) ratio is a measure of cardiac function that is used to assess left ventricular systolic function. PASP is typically measured using a catheterization procedure, in which a small tube is inserted into a blood vessel and advanced to the pulmonary artery. A TAPSE/PASP ratio higher than 0.36 mm/mmHg has been shown in several studies to be a good sign of normal or generally well?maintained right ventricular function. It is important to note that the TAPSE/PASP ratio should be interpreted in the context of other clinical findings and should not be used as the sole indicator of cardiac function. A decreasein the TAPSEpulmonary arterial systolic pressure (PASP) ratio (i.e., (RV)?arterial uncoupling), which quantitatively depicts the function of the RV, was detected in patients with heart failure. In pulmonary arterial hypertension patients, TAPSE/PASPis linked to hemodynamics and functional class. In diseases impacting right cardiac function, the TAPSE/PASP may also be beneficial. The purpose of this review is to demonstrate how the TAPSE/PASP impacts how the (RV) functions. We believe thatthis is the first review on the topic written.