Search Results (58)

Background and Objectives: Non-invasive imaging biomarkers for the early detection of chronic kidney allograft injury are needed to improve long-term transplant outcomes. T1 mapping by magnetic resonance imaging (MRI) has emerged as a promising method to assess renal structure and function. This study aimed to determine the potential of MRI as a diagnostic tool for evaluating graft function and structural changes in kidney grafts 1 year after transplantation. Materials and Methods: Thirty-four kidney transplant recipients were prospectively recruited, with 27 completing the follow-up at one year. Renal MRI at 3T was performed to acquire T1, T2, and apparent diffusion coefficient (ADC) maps. Clinical parameters, including estimated glomerular filtration rate (eGFR), albumin-to-creatinine ratio (ACR), protein-to-creatinine ratio (PCR), and histological IF/TA scores, were collected. MRI parameters were compared across the groups stratified by clinical and histological markers. Diagnostic accuracy was assessed using receiver operating characteristic (ROC) analysis. Results: At 1 year, T1 corticomedullary differentiation (CMD) values were significantly higher in patients with elevated ACR (≥3 mg/mmol), PCR (≥15 mg/mmol), and mild to moderate or severe IF/TA, reflecting a reduction in the corticomedullary gradient. T1 CMD demonstrated moderate-to-good diagnostic performance in detecting ACR (AUC 0.791), PCR (AUC 0.730), and IF/TA (AUC 0.839). No significant differences were observed in T2 or ADC values across these groups. T1 CMD also showed a significant positive correlation with ACR but not with eGFR, suggesting a closer association with structural rather than functional deterioration. Conclusions: T1 mapping, particularly T1 CMD, shows promise as a non-invasive imaging biomarker for detecting chronic allograft injury and monitoring renal function 1 year after kidney transplantation. Full article

Objective: Tumor progression is regulated by systemic immune status, nutritional metabolism, and the inflammatory microenvironment. This study aims to investigate inflammatory–nutritional biomarkers associated with metachronous liver metastasis (MLM) in colorectal cancer (CRC) and develop a machine learning model for accurate prediction. Methods: This study enrolled 680 patients with CRC who underwent curative resection, randomly allocated into a training set (n = 477) and a validation set (n = 203) in a 7:3 ratio. Feature selection was performed using Boruta and Lasso algorithms, identifying nine core prognostic factors through variable intersection. Seven machine learning (ML) models were constructed using the training set, with the optimal predictive model selected based on comprehensive evaluation metrics. An interactive visualization tool was developed to interpret the dynamic impact of key features on individual predictions. The partial dependence plots (PDPs) revealed a potential dose–response relationship between inflammatory–nutritional markers and MLM risk. Results: Among 680 patients with CRC, the cumulative incidence of MLM at 6 months postoperatively was 39.1%. Multimodal feature selection identified nine key predictors, including the N stage, vascular invasion, carcinoembryonic antigen (CEA), systemic immune–inflammation index (SII), albumin–bilirubin index (ALBI), differentiation grade, prognostic nutritional index (PNI), fatty liver, and T stage. The gradient boosting machine (GBM) demonstrated the best overall performance (AUROC: 0.916, sensitivity: 0.772, specificity: 0.871). The generalized additive model (GAM)-fitted SHAP analysis established, for the first time, risk thresholds for four continuous variables (CEA > 8.14 μg/L, PNI < 44.46, SII > 856.36, ALBI > −2.67), confirming their significant association with MLM development. Conclusions: This study developed a GBM model incorporating inflammatory-nutritional biomarkers and clinical features to accurately predict MLM in colorectal cancer. Integrated with dynamic visualization tools, the model enables real-time risk stratification via a freely accessible web calculator, guiding individualized surveillance planning and optimizing clinical decision-making for precision postoperative care. Full article

Protein phosphorylation is one of the most common and important post-translational modifications (PTMs) and is highly involved in various biological processes. Ideal adsorbents with high sensitivity and specificity toward phosphopeptides with large coverage are therefore essential for enrichment and mass spectroscopy-based phosphoproteomics analysis. In this study, a newly designed IMAC adsorbent composite was constructed on the graphene matrix coated with mesoporous silica. The outer functional 3D-network layer was prepared by free radical polymerization of the phosphonate-functionalized vinyl imidazolium salt monomer and subsequent metal immobilization. Due to its unique structural feature and high content of Ti⁴⁺ ions, the resulting phosphonate-immobilized adsorbent composite G@mSiO₂@PPFIL-Ti⁴⁺ exhibits excellent performance in phosphopeptide enrichment with a low detection limit (0.1 fmol, tryptic β-casein digest) and superior selectivity (molar ratio of 1:15,000, digest mixture of β-casein and bovine serum albumin). G@mSiO₂@PPFIL-Ti⁴⁺ displays high tolerance to loading and elution conditions and thus can be reused without a marked decrease in enrichment efficacy. The captured phosphopeptides can be released globally, and mono-/multi-phosphopeptides can be isolated stepwise by gradient elution. When applying this material to enrich phosphopeptides from human lung cell lysates, a total of 3268 unique phosphopeptides were identified, corresponding to 1293 phosphoproteins. Furthermore, 2698 phosphorylated peptides were found to be differentially expressed (p < 0.05) between human lung adenocarcinoma cells (SPC-A1) and human normal epithelial cells (Beas-2B), of which 1592 were upregulated and 1106 were downregulated in the cancer group. These results demonstrate the material’s superior enrichment efficiency in complex biological samples. Full article

Background: Heart failure (HF) ranks among the foremost causes of mortality globally, exhibiting particularly high prevalence and significant impact within intensive care units (ICUs). This study sought to develop, validate, and deploy a time-dependent machine learning model aimed at predicting the one-year all-cause mortality risk in ICU patients diagnosed with HF, thereby facilitating precise prognostic evaluation and risk stratification. Methods: This study encompassed a cohort of 8960 ICU patients with HF sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database (version 3.1). This latest version of the database added data from 2020 to 2022 on the basis of version 2.2 (covering data from 2008 to 2019); therefore, data spanning 2008 to 2019 (n = 5748) were designated for the training set, while data from 2020 to 2022 (n = 3212) were reserved for the test set. The primary endpoint of interest was one-year all-cause mortality. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to select predictive features from an initial pool of 64 candidate variables (including demographic characteristics, vital signs, comorbidities and complications, therapeutic interventions, routine laboratory data, and disease severity scores). Four predictive models were developed and compared: Cox proportional hazards, random survival forest (RSF), Cox proportional hazards deep neural network (DeepSurv), and eXtreme Gradient Boosting (XGBoost). Model performance was assessed using the concordance index (C-index) and Brier score, with model interpretability addressed through SHapley Additive exPlanations (SHAP) and time-dependent Survival SHapley Additive exPlanations (SurvSHAP(t)). Results: This study revealed a one-year mortality rate of 46.1% within the population under investigation. In the training set, LASSO effectively identified 24 features in the model. In the test set, the XGBoost model exhibited superior predictive performance, as evidenced by a C-index of 0.772 and a Brier score of 0.161, outperforming the Cox model (C-index: 0.740, Brier score: 0.175), the RSF model (C-index: 0.747, Brier score: 0.178), and the DeepSur model (C-index: 0.723, Brier score: 0.183). Decision curve analysis validated the clinical utility of the XGBoost model across a broad spectrum of risk thresholds. Feature importance analysis identified the red cell distribution width-to-albumin ratio (RAR), Charlson Comorbidity Index, Simplified Acute Physiology Score II (SAPS II), Acute Physiology Score III (APS III), and the age–bilirubin–INR–creatinine (ABIC) score as the top five predictive factors. Consequently, an online risk prediction tool based on this model has been developed and is publicly accessible. Conclusions: The time-dependent XGBoost model demonstrated robust predictive capability in evaluating the one-year all-cause mortality risk in critically ill HF patients. This model offered a useful tool for early risk identification and supported timely interventions. Full article

Background/Objectives: Sepsis remains a leading cause of mortality worldwide, necessitating the development of effective prognostic markers for early risk stratification. The C-reactive protein–albumin–lymphocyte (CALLY) index is a novel biomarker that integrates inflammatory, nutritional, and immunological parameters. This study aimed to evaluate the association between the CALLY index and 30-day all-cause mortality in sepsis patients. Methods: This retrospective cohort study included adult patients diagnosed with sepsis in the emergency department between 1 January 2022, and 1 January 2025. The CALLY index was calculated as (CRP × absolute lymphocyte count)/albumin. The primary outcome was 30-day all-cause mortality. Five machine learning models—extreme gradient boosting (XGBoost), multilayer perceptron, random forest, support vector machine, and generalized linear model—were developed for mortality prediction. Four feature selection strategies (gain score, SHAP values, Boruta, and LASSO regression) were used to evaluate predictor consistency. The clinical utility of the CALLY index was assessed using decision curve analysis (DCA). Results: A total of 1644 patients were included, of whom 345 (21.0%) died within 30 days. Among the five machine learning models, the XGBoost model achieved the highest performance (AUC: 0.995, R²: 0.867, MAE: 0.063, RMSE: 0.145). In gain-based feature selection, the CALLY index emerged as the top predictor (gain: 0.187), followed by serum lactate (0.185) and white blood cell count (0.117). The CALLY index also ranked second in SHAP analysis (mean value: 0.317) and first in Boruta importance (mean importance: 37.54). DCA showed the highest net clinical benefit of the CALLY index within the 0.10–0.15 risk threshold range. Conclusions: This study demonstrates that the CALLY index is a significant predictor of 30-day mortality in sepsis patients. Machine learning analysis further reinforced the prognostic value of the CALLY index. Full article

Background: Pressure injuries (PIs) are increasing worldwide, and there has been no significant improvement in preventing them. Traditional assessment tools are widely used to identify a patient at risk of developing a PI. This study aims to construct a novel fused multi-channel prediction model of PIs in adult hospitalized patients using machine learning algorithms (MLAs). Methods: A multi-phase quantitative approach involving a case–control experimental design was used. A first-hand dataset was collected retrospectively between March/2022 and August/2023 from the electronic medical records of three hospitals in Palestine. Results: The total number of patients was 49,500. A balanced dataset was utilized with a total number of 1110 patients (80% training and 20% testing). The models that were developed utilized eight MLAs, including linear regression and support vector regression (SVR), logistic regression (LR), random forest (RF), gradient boosting (GB), K-nearest neighbor (KNN), decision tree (DT), and extreme gradient boosting (XG boosting) and validated with five-fold cross-validation techniques. The best model was RF, for which the accuracy was 0.962, precision was 0.942, recall was 0.922, F1 was 0.931, area under curve (AUC) was 0.922, false positive rate (FPR) was 0.155, and true positive rate (TPR) was 0.782. Conclusions: The predictive factors were age, moisture, activity, length of stay (LOS), systolic blood pressure (BP), and albumin. A novel fused multi-channel prediction model of pressure injury was developed from different datasets. Full article

Protein identification in complex biological samples using the shotgun mode of LC-MS/MS is typically enhanced by employing longer LC columns and extended gradient times. However, improved identification rates can also be achieved by optimizing MS acquisition frequencies and employing advanced software, without increasing analysis time, thus maintaining the throughput of the method. To date, we found only one study in the literature examining the influence of MS acquisition frequency on protein identification, specifically using two ion trap mass spectrometer models. This study aims to address the gap by analyzing the impact of MS acquisition tuning of the QTOF instrument on the analysis of complex samples. Our findings indicate that increasing acquisition frequency generally improves protein identification, although the extent of improvement depends on the sample type. For CHO cell lysates, protein identifications increased by over 10%, while E. coli and albumin-depleted plasma samples demonstrated gains of 3.6% and 2.6%, respectively. Higher contributions to protein identification were also achieved with extended LC gradients, resulting in improvements of 21.6% for CHO, 18.2% for E. coli, and 10.3% for plasma. Moreover, enabling PEAKS’ deep learning feature significantly boosted identifications, with increases of 22.9% for CHO, 23.2% for E. coli, and 9.2% for plasma. Full article

Background. Sepsis presents significant diagnostic and prognostic challenges, and traditional scoring systems, such as SOFA and APACHE, show limitations in predictive accuracy. Machine learning (ML)-based predictive survival models can support risk assessment and treatment decision-making in the intensive care unit (ICU) by accounting for the numerous and complex factors that influence the outcome in the septic patient. Methods. A systematic literature review of studies published from 2014 to 2024 was conducted using the PubMed database. Eligible studies investigated the development of ML models incorporating commonly available laboratory and clinical data for predicting survival outcomes in adult ICU patients with sepsis. Study selection followed the PRISMA guidelines and relied on predefined inclusion criteria. All records were independently assessed by two reviewers, with conflicts resolved by a third senior reviewer. Data related to study design, methodology, results, and interpretation of the results were extracted in a predefined grid. Results. Overall, 19 studies were identified, encompassing primarily logistic regression, random forests, and neural networks. Most used datasets were US-based (MIMIC-III, MIMIC-IV, and eICU-CRD). The most common variables used in model development were age, albumin levels, lactate levels, and ventilator. ML models demonstrated superior performance metrics compared to conventional methods and traditional scoring systems. The best-performing model was a gradient boosting decision tree, with an area under curve of 0.992, an accuracy of 0.954, and a sensitivity of 0.917. However, several critical limitations should be carefully considered when interpreting the results, such as population selection bias (i.e., single center studies), small sample sizes, limited external validation, and model interpretability. Conclusions. Through real-time integration of routine laboratory and clinical data, ML-based tools can assist clinical decision-making and enhance the consistency and quality of sepsis management across various healthcare contexts, including ICUs with limited resources. Full article

Background: Acute myocardial infarction (AMI) constitutes a major health problem with high mortality rates worldwide. In patients with ST-segment elevation myocardial infarction (STEMI), no-reflow phenomenon is a condition that adversely affects response to therapy. Previous studies have demonstrated that the CALLY index, calculated using C-reactive protein (CRP), albumin, and lymphocytes, is a reliable indicator of mortality in patients with non-cardiac diseases. The objective of this study is to investigate the potential utility of the CALLY index in detecting no-reflow patients and to determine the predictability of this phenomenon using machine learning (ML) methods. Methods: This study included 1785 STEMI patients admitted to the clinic between January 2020 and June 2024 who underwent percutaneous coronary intervention (PCI). Patients were in no-reflow status, and other clinical data were analyzed. The CALLY index was calculated using data on patients’ inflammatory status. The Extreme Gradient Boosting (XGBoost) ML algorithm was used for no-reflow prediction. Results: No-reflow was detected in a proportion of patients participating in this study. The model obtained with the XGBoost algorithm showed high accuracy rates in predicting no-reflow status. The role of the CALLY index in predicting no-reflow status was clearly demonstrated. Conclusions: The CALLY index has emerged as a valuable tool for predicting no-reflow status in STEMI patients. This study demonstrates how machine learning methods can be effective in clinical applications and paves the way for innovative approaches for the management of no-reflow phenomenon. Future research needs to confirm and extend these findings with larger sample sizes. Full article

Background: Accurate and rapid detection of COVID-19 remains critical for clinical management, especially in resource-limited settings. Current diagnostic methods face challenges in terms of speed and reliability, creating a need for complementary AI-based models that integrate diverse data sources. Objectives: This study aimed to develop and evaluate a multi-modal machine learning model that combines clinical biomarkers and chest X-ray images to enhance diagnostic accuracy and provide interpretable insights. Methods: We used a dataset of 250 patients (180 COVID-19 positive and 70 negative cases) collected from clinical settings. Biomarkers such as CRP, ferritin, NLR, and albumin were included alongside chest X-ray images. Random Forest and Gradient Boosting models were used for biomarkers, and ResNet and VGG CNN architectures were applied to imaging data. A late-fusion strategy integrated predictions from these modalities. Stratified k-fold cross-validation ensured robust evaluation while preventing data leakage. Model performance was assessed using AUC-ROC, F1-score, Specificity, Negative Predictive Value (NPV), and Matthews Correlation Coefficient (MCC), with confidence intervals calculated via bootstrap resampling. Results: The Gradient Boosting + VGG fusion model achieved the highest performance, with an AUC-ROC of 0.94, F1-score of 0.93, Specificity of 93%, NPV of 96%, and MCC of 0.91. SHAP and LIME interpretability analyses identified CRP, ferritin, and specific lung regions as key contributors to predictions. Discussion: The proposed multi-modal approach significantly enhances diagnostic accuracy compared to single-modality models. Its interpretability aligns with clinical understanding, supporting its potential for real-world application. Full article

Background: Liver diseases are a global health concern. Many in vitro liver models utilize cryopreserved primary human hepatocytes (PHHs), which commonly undergo post-thaw processing through colloidal silica gradients to remove debris and enrich for a viable PHH population. Post-thaw processing effects on healthy PHHs are partially understood, but the consequences of applying disease-origin PHHs to post-thaw density gradient separation have not been described. Methods: Using the TruVivo^® system, diseased, type 2 diabetes mellitus (T2DM), and fibrotic PHHs were cultured for 14 days after initially being subjected to either low-density (permissive) or high-density (selective) gradients using Percoll-based thawing medium. Results: Changes in functionality, including albumin and urea secretion and CYP3A4 activity, were measured in diseased, T2DM, and fibrotic PHHs enriched in low Percoll compared to PHHs enriched in high Percoll. Lipogenesis increased in the PHHs enriched in low Percoll. Higher expression of CK18 and TGF-β, two fibrotic markers, and changes in expression of the macrophage markers CD68 and CD163 were also measured. Conclusions: The use of Percoll for the enrichment of PHHs post-thaw results in differences in attachment and functionality, along with changes in diseased phenotypes, in the TruVivo^® system. Full article

Ascites is a common syndrome characterized by an excess of fluid in the peritoneum. While cirrhosis is the most common cause, a wide range of other conditions—such as cancer, right heart failure, and tuberculosis—can also lead to ascites, and multiple etiologies may be present simultaneously. Effective diagnosis and management are essential, primarily relying on clinical examination and paracentesis, guided by specific tests. Full article

Hepatocellular carcinoma (HCC) presents high mortality rates worldwide, with limited evidence on prognostic factors at diagnosis. This study evaluates the utility of common scores incorporating albumin as predictors of mortality at HCC diagnosis using Machine Learning techniques. They are also compared to other scores and variables commonly used. A retrospective cohort study was conducted with 191 patients from Virgen de la Luz Hospital of Cuenca and University Hospital of Guadalajara. Demographic, analytical, and tumor-specific variables were included. Various Machine Learning algorithms were implemented, with eXtreme Gradient Boosting (XGB) as the reference method. In the predictive model developed, the Barcelona Clinic Liver Cancer score was the best predictor of mortality, closely followed by the Platelet-Albumin-Bilirubin and Albumin-Bilirubin scores. Albumin levels alone also showed high relevance. Other scores, such as C-Reactive Protein/albumin and Child-Pugh performed less effectively. XGB proved to be the most accurate method across the metrics analyzed, outperforming other ML algorithms. In conclusion, the Barcelona Clinic Liver Cancer, Platelet-Albumin-Bilirubin and Albumin-Bilirubin scores are highly reliable for assessing survival at HCC diagnosis. The XGB-developed model proved to be the most reliable for this purpose compared to the other proposed methods. Full article

Background: Antibiotic overuse in pediatric patients with upper respiratory tract infections (UR-TIs) raises concerns about antimicrobial resistance. This study examines the impact of antibiotics on hospital stay duration and fever resolution in pediatric patients diagnosed with viral infections via a multiplex polymerase chain reaction (PCR) respiratory panel. Methods: In the pediatric ward of Imam Abdulrahman Bin Faisal Hospital, a retrospective cohort analysis was conducted on pediatric patients with viral infections confirmed by nasopharyngeal aspirates from October 2016 to December 2021. Cohorts receiving antibiotics versus those not receiving them were balanced using the gradient boosting machine (GBM) technique for propensity score matching. Results: Among 238 patients, human rhinovirus/enterovirus (HRV/EV) was most common (44.5%), followed by respiratory syncytial virus (RSV) (18.1%). Co-infections occurred in 8.4% of cases. Antibiotic administration increased hospital length of stay (LOS) by an average of 2.19 days (p-value: 0.00). Diarrhea reduced LOS by 2.26 days, and higher albumin levels reduced LOS by 0.40 days. Fever and CRP levels had no significant effect on LOS. Time to recovery from fever showed no significant difference between antibiotic-free (Abx0) and antibiotic-received (Abx1) groups (p-value: 0.391), with a hazard ratio of 0.84 (CI: 0.57–1.2). Conclusions: Antibiotics did not expedite recovery but were associated with longer hospital stays in pediatric patients with acute viral respiratory infections. Clinicians should exercise caution in prescribing antibiotics to pediatric patients with confirmed viral infections, especially when non-critical. Full article

Clinically significant portal hypertension (CSPH) in patients with compensated advanced chronic liver disease indicates an increased risk of decompensation and death. While invasive methods like hepatic venous–portal gradient measurement is considered the gold standard, non-invasive tests (NITs) have emerged as valuable tools for diagnosing and monitoring CSPH. This review comprehensively explores non-invasive diagnostic modalities for portal hypertension, focusing on NITs in the setting of hepatitis B and hepatitis C virus-related cirrhosis. Biochemical-based NITs can be represented by single serum biomarkers (e.g., platelet count) or by composite scores that combine different serum biomarkers with each other or with demographic characteristics (e.g., FIB-4). On the other hand, liver stiffness measurement and spleen stiffness measurement can be assessed using a variety of elastography techniques, and they can be used alone, in combination with, or as a second step after biochemical-based NITs. The incorporation of liver and spleen stiffness measurements, alone or combined with platelet count, into established and validated criteria, such as Baveno VI or Baveno VII criteria, provides useful tools for the prediction of CSPH and for ruling out high-risk varices, potentially avoiding invasive tests like upper endoscopy. Moreover, they have also been shown to be able to predict liver-related events (e.g., the occurrence of hepatic decompensation). When transient elastography is not available or not feasible, biochemical-based NITs (e.g., RESIST criteria, that are based on the combination of platelet count and albumin levels) are valid alternatives for predicting high-risk varices both in patients with untreated viral aetiology and after sustained virological response. Ongoing research should explore novel biomarkers and novel elastography techniques, but current evidence supports the utility of routine blood tests, LSM, and SSM as effective surrogates in diagnosing and staging portal hypertension and predicting patient outcomes. Full article