Search

Background and objectives: Liver cirrhosis is a chronic, progressive condition characterized by fibrosis and architectural distortion of the liver, leading to impaired liver function and severe complications. Accurately predicting these complications is crucial to the improvement of patient outcomes. Therefore, this study aimed to evaluate the accuracy of various non-invasive biomarkers and clinical scores in assessing the risk of complications among cirrhotic patients. Materials and methods: We conducted an observational retrospective study involving 236 cirrhotic patients from two tertiary care hospitals in Italy and Romania, in a timespan ranging from January 2021 to March 2024. Data on clinical characteristics, liver function tests, hematological indices, various non-invasive biomarkers, and clinical scores were collected and analyzed. Receiver operating characteristic analysis was performed to assess the accuracy of these biomarkers and clinical scores in predicting complications, including the presence of varices and hepato-renal syndrome. Results: The Child-Pugh score showed the highest accuracy for cirrhosis-related complications, with an area under curve (AUC) = 0.667. The red cell distribution width coefficient of variation followed closely with an AUC = 0.646. While the Child-Pugh score had a high specificity (85.42%), its sensitivity was low (37.97%). In patients with varices, non-invasive scores such as platelet distribution width (PDW) and the RDW-to-platelet ratio (RPR) showed modest predictive ability, with an AUC = 0.594. For hepato-renal syndrome, the Model for End-Stage Liver Disease (MELD) score showed the highest diagnostic accuracy with an AUC = 0.758. Conclusions: The most reliable biomarkers for detecting complications, varices, and hepato-renal syndrome, are, respectively, the Child-Pugh Score, PDW along with RPR, and the MELD score. However, while these scores remain valuable, the moderate diagnostic accuracy of other indices suggests the need for a more integrated approach to risk stratification. Future research should focus on validating these tools across different populations and incorporating emerging biomarkers to enhance predictive accuracy and inform more effective clinical decision-making.

Background and Objectives: Pulmonary fibrosis, including idiopathic pulmonary fibrosis (IPF) and secondary pulmonary fibrosis (SPF), is a progressive lung disease that significantly impairs respiratory function. Accurate differentiation between IPF and SPF is crucial for effective management. This study explores the association between pulmonary fibrosis and hepatic conditions, evaluating the utility of various hemogram-derived ratios and hepatic fibrosis scores in distinguishing between IPF and SPF. Materials and Methods: We conducted a retrospective study involving patients diagnosed with IPF or SPF at the "Leon Daniello" Clinical Hospital of Pneumology in Cluj-Napoca, Romania. Pulmonary fibrosis was confirmed via imaging techniques, and hepatic steatosis and fibrosis were assessed using non-invasive scores. We analyzed clinical, laboratory, and pulmonary function data, focusing on hemogram-derived ratios and hepatic scores. Statistical analyses, including ROC curves, were used to evaluate the effectiveness of these biomarkers in differentiating IPF from SPF. Results: We included a total of 38 patients with IPF and 28 patients with SPF. Our findings revealed that IPF patients had a significantly higher FIB-4 score compared to SPF patients, suggesting increased hepatic fibrosis risk in IPF, as well as an increased RDW/PLT ratio. Conversely, SPF patients exhibited elevated PLR, PNR, and SII, reflecting a more pronounced inflammatory profile. PLR and PNR demonstrated the highest discriminatory ability between IPF and SPF, while traditional hepatic fibrosis scores showed limited differentiation capabilities. No significant differences in pulmonary function tests were observed across hepatic fibrosis risk categories. Conclusions: The study highlights the value of biomarkers like PLR and PNR in differentiating between IPF and SPF, offering additional diagnostic insights beyond traditional imaging. Integrating hepatic assessments into the management of pulmonary fibrosis could improve diagnostic accuracy and patient care.

Background/Objectives: To develop a deep learning model for esophageal motility disorder diagnosis using high-resolution manometry images with the aid of Gemini. Methods: Gemini assisted in developing this model by aiding in code writing, preprocessing, model optimization, and troubleshooting. Results: The model demonstrated an overall precision of 0.89 on the testing set, with an accuracy of 0.88, a recall of 0.88, and an F1-score of 0.885. It presented better results for multiple categories, particularly in the panesophageal pressurization category, with precision = 0.99 and recall = 0.99, yielding a balanced F1-score of 0.99. Conclusions: This study demonstrates the potential of artificial intelligence, particularly Gemini, in aiding the creation of robust deep learning models for medical image analysis, solving not just simple binary classification problems but more complex, multi-class image classification tasks.

Background and Objectives : The threshold for ineffective esophageal motility (IEM) diagnosis was changed in Chicago v4.0. Our aim was to determine IEM prevalence using the new criteria and the differences between patients with definite IEM versus "inconclusive diagnosis". Materials and Methods : We retrospectively selected IEM and fragmented peristalsis (FP) patients from the high-resolution esophageal manometries (HREMs) database. Clinical, demographic data and manometric parameters were recorded. Results : Of 348 HREMs analyzed using Chicago v3.0, 12.3% of patients had IEM and 0.86% had FP. Using Chicago v4.0, 8.9% of patients had IEM (IEM-4 group). We compared them with the remaining 16 with an inconclusive diagnosis of IEM (borderline group). Dysphagia (77% vs. 44%, Z-test = 2.3, p = 0.02) and weight loss were more commonly observed in IEM-4 compared to the borderline group. The reflux symptoms were more prevalent in the borderline group (87.5% vs. 70.9%, p = 0.2). Type 2 or 3 esophagogastric junction morphology was more prevalent in the borderline group (81.2%) vs. 64.5% in IEM-4 ( p = 0.23). Distal contractile integral (DCI) was lower in IEM-4 vs. the borderline group, and resting lower esophageal sphincter (LES) pressure and mean integrated relaxation pressure (IRP) were similar. The number of ineffective swallows and failed swallows was higher in IEM-4 compared to the borderline group. Conclusions : Using Chicago v4.0, less than 10% of patients had a definite diagnosis of IEM. The dominant symptom was dysphagia. Only DCI and the number of failed and inefficient swallows were different between definite IEM patients and borderline cases.

Background and Objectives : It is crucial to quickly identify those patients who need immediate treatment in order to avoid the various complications related to acute diverticulitis (AD). Although several studies evaluated the neutrophil-to-lymphocyte ratio (NLR) suggesting its predictive value in assessing the severity of AD, results have been inconclusive. Therefore, we aimed to assess the relationship between the neutrophil-to-lymphocyte ratio (NLR), the platelet-to-lymphocyte ratio (PLR), the monocyte-to-lymphocyte ratio (MLR), and systemic immune inflammation (SII) with the severity of AD, the ability to predict the presence or absence of complications, and the recurrence rate, based on the values of inflammatory markers. Materials and Methods : We retrospectively reviewed 147 patients diagnosed with AD between January 2012 to February 2023. Patients were divided into 2 groups, uncomplicated and complicated AD. The characteristics and full blood count between both groups were compared. Results: A total of 65 (44.22%) patients were classified as having complicated AD. The area under the ROC curve (AUROC) defining a Hinchey score ≥ 1b was as follows: SII, 0.812 (95% confidence interval (CI), 0.73 -0.888); NLR, 0.773 (95% CI, 0.676-0.857); PLR, 0.725 (95% CI, 0.63-0.813); MLR: 0.665 (95% CI, 0.542 -0.777). An SII cutoff value of > 1200 marked the highest yield for diagnosing complicated AD, with a sensitivity of 82% and a specificity of 76%. The cumulative recurrence rate was not significantly different in the groups of SII ≥ median vs. SII < median ( p = 0.35), NLR ≥ median vs. NLR < median ( p = 0.347), PLR ≥ median vs. PLR < median ( p = 0.597), and MLR ≥ median vs. MLR < median ( p = 0.651). Conclusions : Our study indicates that SII, NLR, and PLR are statistically significant and clinically useful classifying ratios to predict higher Hinchey scores. However, they cannot predict recurrences.

Diverticular disease (DD) is the most frequent condition in the Western world that affects the colon. Although chronic mild inflammatory processes have recently been proposed as a central factor in DD, limited information is currently available regarding the role of inflammatory cytokines, such as tumor necrosis factor-alpha (TNF-α). Therefore, we conducted a systematic review and meta-analysis aiming to assess the mucosal TNF-α levels in DD. We conducted a systematic literature search using PubMed, Embase, and Scopus to identify observational studies assessing the TNF-α levels in DD. Full-text articles that satisfied our inclusion and exclusion criteria were included, and a quality assessment was performed using the Newcastle-Ottawa Scale (NOS). The principal summary outcome was the mean difference (MD). The results were reported as MD (95% confidence interval (CI)). A total of 12 articles involving 883 subjects were included in the qualitative synthesis, out of which 6 studies were included in our quantitative synthesis. We did not observe statistical significance related to the mucosal TNF-α levels in symptomatic uncomplicated diverticular disease (SUDD) vs. the controls (0.517 (95% CI -1.148-2.182)), and symptomatic vs. asymptomatic DD patients (0.657 (95% CI -0.883-2.196)). However, the TNF-α levels were found to be significantly increased in DD compared to irritable bowel disease (IBS) patients (27.368 (95% CI 23.744-30.992)), and segmental colitis associated with diverticulosis (SCAD) vs. IBS patients (25.303 (95% CI 19.823-30.784)). Between SUDD and the controls, as well as symptomatic and asymptomatic DD, there were no significant differences in the mucosal TNF-α levels. However, the TNF-α levels were considerably higher in DD and SCAD patients than IBS patients. Our findings suggest that TNF-α may play a key role in the pathogenesis of DD in specific subgroups and could potentially be a target for future therapies.

The goal of this paper is to provide a Machine Learning-based solution that can be utilized to automate the Chicago Classification algorithm, the state-of-the-art scheme for esophageal motility disease identification. First, the photos were preprocessed by locating the area of interest-the precise instant of swallowing. After resizing and rescaling the photos, they were utilized as input for the Deep Learning models. The InceptionV3 Deep Learning model was used to identify the precise class of the IRP. We used the DenseNet201 CNN architecture to classify the images into 5 different classes of swallowing disorders. Finally, we combined the results of the two trained ML models to automate the Chicago Classification algorithm. With this solution we obtained a top-1 accuracy and f1-score of 86% with no human intervention, automating the whole flow, from image preprocessing until Chicago classification and diagnosis.

High-resolution esophageal manometry is used for the study of esophageal motility disorders, with the help of catheters with up to 36 sensors. Color pressure topography plots are generated and analyzed and using the Chicago algorithm a final diagnosis is established. One of the main parameters in this algorithm is integrated relaxation pressure (IRP). The procedure is time consuming. Our aim was to firstly develop a machine learning based solution to detect probe positioning failure and to create a classifier to automatically determine whether the IRP is in the normal range or higher than the cut-off, based solely on the raw images. The first step was the preprocessing of the images, by finding the region of interest-the exact moment of swallowing. Afterwards, the images were resized and rescaled, so they could be used as input for deep learning models. We used the InceptionV3 deep learning model to classify the images as correct or failure in catheter positioning and to determine the exact class of the IRP. The accuracy of the trained convolutional neural networks was above 90% for both problems. This work is just the first step in fully automating the Chicago Classification, reducing human intervention.