Non-small cell lung carcinoma (NSCLC) is a prevalent and aggressive form of lung cancer, with a poor prognosis for metastatic disease. Immunotherapy, particularly immune checkpoint inhibitors (ICIs), has revolutionized the management of NSCLC, but response rates are highly variable. Identifying reliable predictive biomarkers is crucial to optimize patient selection and treatment outcomes. This systematic review aimed to evaluate the current state of artificial intelligence (AI) and machine learning (ML) applications in predicting the response to immunotherapy in NSCLC. A comprehensive literature search identified 19 studies that met the inclusion criteria. The studies employed diverse AI/ML techniques, including deep learning, artificial neural networks, support vector machines, and gradient boosting methods, applied to various data modalities such as medical imaging, genomic data, clinical variables, and immunohistochemical markers. Several studies demonstrated the ability of AI/ML models to accurately predict immunotherapy response, progression-free survival, and overall survival in NSCLC patients. However, challenges remain in data availability, quality, and interpretability of these models. Efforts have been made to develop interpretable AI/ML techniques, but further research is needed to improve transparency and explainability. Additionally, translating AI/ML models from research settings to clinical practice poses challenges related to regulatory approval, data privacy, and integration into existing healthcare systems. Nonetheless, the successful implementation of AI/ML models could enable personalized treatment strategies, improve treatment outcomes, and reduce unnecessary toxicities and healthcare costs associated with ineffective treatments.

UNASSIGNED: Our recently developed Coronary Artery Tree description and Lesion EvaluaTion (CatLet) angiographic scoring system is unique in its description of the variability in the coronary anatomy, the degree of stenosis of a diseased coronary artery, and its subtended myocardial territory, and can be utilized to predict clinical outcomes for patients with acute myocardial infarction (AMI) presenting ≤12 h after symptom onset. The current study aimed to assess whether the Clinical CatLet score (CCS), as compared with CatLet score (CS), better predicted clinical outcomes for AMI patients presenting >12 h after symptom onset.
UNASSIGNED: CS was calculated in 1018 consecutive AMI patients enrolled in a retrospective registry. CCS was calculated by multiplying CS by the ACEF I score (age, creatinine, and left ventricular ejection fraction). Primary endpoint was major adverse cardiac events (MACEs) at 4-year-follow-up, a composite of cardiac death, myocardial infarction, and ischemia-driven revascularization.
UNASSIGNED: Over a 4-year follow-up period, both scores were independent predictors of clinical outcomes after adjustment for a broad spectrum of risk factors. Areas-under-the-curve (AUCs) for CS and CCS were 0.72(0.68-0.75) and 0.75(0.71-0.78) for MACEs; 0.68(0.63-0.73) and 0.78(0.74-0.83) for all-cause death; 0.73(0.68-0.79) and 0.83(0.79-0.88) for cardiac death; and 0.69(0.64-0.73) and 0.75(0.7-0.79) for myocardial infarction; and 0.66(0.61-0.7) and 0.63(0.58-0.68) for revascularization, respectively. CCS performed better than CS in terms of the above-mentioned outcome predictions, as confirmed by the net reclassification and integrated discrimination indices.
UNASSIGNED: CCS was better than CS to be able to risk-stratify long-term outcomes in AMI patients presenting >12 h after symptom onset. These findings have indicated that both anatomic and clinical variables should be considered in decision-making on management of patients with AMI presenting later.

COVID-19 induced acute respiratory distress syndrome (ARDS) could have two different phenotypes, which was reported to have different response and outcome to the typical ARDS positive end-expiration pressure (PEEP) treatment. The identification of the different phenotypes in terms of the recruitability can help improve the patient outcome. In this contribution we conducted alveolar overdistention and collapse analysis with the long term electrical impedance tomography monitoring data on two severe COVID-19 pneumonia patients. The result showed different patient reactions to the PEEP trial, revealed the progressive change in the patient status, and indicted a possible phenotype transition in one patient. It might suggest that EIT can be a practical tool to identify phenotypes and to provide progressive information of COVID-19 pneumonia.

Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL). A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models. After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83-0.89), 0.81 (0.76-0.85), 0.82 (0.78-0.85), and 0.77 (0.73-0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors. Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.

BACKGROUND: Addressing suicide requires an understanding of regional patterns of epidemiology, with health variables being central. However, the clinical profile of people who commit suicide has received little attention. The objectives of this study were to analyze the sociodemographic, clinical, and forensic characteristics of persons who committed suicide in Galicia between 2013 and 2016, analyze suicide mortality rates, and identify trajectories of hospitalizations and associated variables.
METHODS: A population study was carried out on the 1354 people who died by suicide in Galicia.
RESULTS: The most common profile was a retired man, 57.9 years old (SD=18.5), from an urban and inner area. 43.6% had been previously hospitalized, 41.6% had been diagnosed with physical disorders, and 26.8% with mental disorders. 48.2% had been prescribed psychiatric medications and 29.6% had received outpatient psychiatric care. The highest prevalence of death by suicide (27.5%) was in 2014, with the predominant method being hanging (59.1%). The average raw rate was 12.3/100,000. Three trajectories of hospitalizations emerged: 94.83% had experienced few hospitalizations; 2.95% an increasing pattern; and 2.22% a decreasing pattern. These trajectories were associated with number of psychiatric appointments, prescription of psychiatric medications, and diagnoses of physical and mental disorders.
CONCLUSIONS: These findings are crucial for detection and prevention.

Background: The present retrospective observational study aims to identify differences in clinical features and peripheral biomarkers among patients affected by substance-induced psychotic disorder (SIPD) according to the primary substance of abuse. Methods: A sample of 218 patients was divided into three groups according to the type of consumed substance: alcohol, cannabis, and psychostimulants. The three groups were compared using one-way analyses of variance (ANOVAs) for continuous variables and χ2 tests for qualitative variables. After excluding the alcohol-induced psychotic disorder group, the same analyses were repeated. The statistically significant variables from these subsequent analyses were included in a binary logistic regression model to confirm their reliability as predictors of cannabis- or psychostimulant-induced psychotic disorder. Results: Psychotic cannabis abusers were younger (p < 0.01), with illness onset at an earlier age (p < 0.01). Alcohol consumers presented a longer duration of illness (p < 0.01), more frequent previous hospitalizations (p = 0.04) and medical comorbidities (p < 0.01), and higher mean Modified Sad Persons Scale scores (p < 0.01). Finally, psychostimulant abusers had a higher frequency of lifetime history of poly-substance use disorders (p < 0.01). A binary logistic regression analysis revealed that higher mean Brief Psychiatric Rating Scale scores (p < 0.01) and higher sodium (p = 0.012) and hemoglobin (p = 0.040) plasma levels were predictors of cannabis misuse in SIPD patients. Conclusions: Different clinical factors and biochemical parameters con be associated with SIPD according to the main substance of abuse, thus requiring specific management by clinicians.

Growing antibiotic resistance complicates H. pylori eradication, posing a public health challenge. Inconclusive research on sociodemographic and clinical factors emphasizes the necessity for further investigations. Hence, this study aims to evaluate the correlation between demographic and clinical factors and the success rates of H. pylori eradication. A group of 162 H. pylori-positive patients were allocated randomly to receive either a ten-day moxifloxacin-based triple therapy or a levofloxacin-based sequential therapy. Eradication success was determined through the stool antigen test. Logistic regression analysis was utilized to figure out potential factors that contribute to H. pylori eradication success. Significantly higher H. pylori eradication rates were observed in the middle age group (COR: 3.671, p = 0.007), among females (p = 0.035), those with BMI ≥ 25 (COR: 2.011, p = 0.045), and non-smokers (COR: 2.718, p = 0.018). In multivariate analysis, age and smoking emerged as significant predictors (p < 0.05). Patients with comorbidities, excluding diabetes and hypertension (COR: 4.432, p = 0.019), dyspepsia (COR: 0.178, p < 0.001), and moxifloxacin triple therapy (COR: 0.194, p = 0.000), exhibited higher chances of eradication (p < 0.05). Further research is vital for tailored approaches to enhance eradication success.

UNASSIGNED: Vascular calcification (VC) commonly occurs and seriously increases the risk of cardiovascular events and mortality in patients with hemodialysis. For optimizing individual management, we will develop a diagnostic multivariable prediction model for evaluating the probability of VC.
UNASSIGNED: The study was conducted in four steps. First, identification of miRNAs regulating osteogenic differentiation of vascular smooth muscle cells (VSMCs) in calcified condition. Second, observing the role of miR-129-3p on VC in vitro and the association between circulating miR-129-3p and VC in hemodialysis patients. Third, collecting all indicators related to VC as candidate variables, screening predictors from the candidate variables by Lasso regression, developing the prediction model by logistic regression and showing it as a nomogram in training cohort. Last, verifying predictive performance of the model in validation cohort.
UNASSIGNED: In cell experiments, miR-129-3p was found to attenuate vascular calcification, and in human, serum miR-129-3p exhibited a negative correlation with vascular calcification, suggesting that miR-129-3p could be one of the candidate predictor variables. Regression analysis demonstrated that miR-129-3p, age, dialysis duration and smoking were valid factors to establish the prediction model and nomogram for VC. The area under receiver operating characteristic curve of the model was 0.8698. The calibration curve showed that predicted probability of the model was in good agreement with actual probability and decision curve analysis indicated better net benefit of the model. Furthermore, internal validation through bootstrap process and external validation by another independent cohort confirmed the stability of the model.
UNASSIGNED: We build a diagnostic prediction model and present it as an intuitive tool based on miR-129-3p and clinical indicators to evaluate the probability of VC in hemodialysis patients, facilitating risk stratification and effective decision, which may be of great importance for reducing the risk of serious cardiovascular events.

BACKGROUND: In 2017, the French public health authority HAS published new guidelines for the management of newborns at risk of early bacterial neonatal infection. These guidelines were based on ante- and intrapartum risk factors and clinical monitoring. In January 2021, we implemented a new protocol based on these guidelines in our tertiary maternity unit.
OBJECTIVE: To assess the impact of the protocol implemented on neonates\' antibiotic prescriptions.
METHODS: An \"old protocol\" group comprising newborns hospitalized between July 1, 2020 and December 31, 2020, was compared to a \"new protocol\" group formed between January 14, 2021 and July 13, 2021. Data were collected on infectious risk factors, antibiotic prescriptions, and emergency room visits within 2 weeks for an infection or suspected infection.
RESULTS: The \"old protocol\" population comprised 1565 children and the \"new protocol\" population 1513. Antibiotic therapy was prescribed for 29 newborns (1.85 %) in the old protocol group versus 15 (0.99 %) in the new one (p = 0.05). The median duration was 5 days and 2 days respectively (p = 0.08). With the new protocol, newborns in category B were about 20 times more likely (p = 0.01), and those in category C about 54 times more likely (p = 0.005) to have an infection than those classified in categories N or A.
CONCLUSIONS: This study demonstrates that clinical monitoring criteria enable reduced use and duration of antibiotic therapy and are reliable.

OBJECTIVE: To examine the ability of serum proteins in predicting future heart failure (HF) events, including HF with reduced or preserved ejection fraction (HFrEF or HFpEF), in relation to event time, and with or without considering established HF-associated clinical variables.
RESULTS: In the prospective population-based Age, Gene/Environment Susceptibility Reykjavik Study (AGES-RS), 440 individuals developed HF after their first visit with a median follow-up of 5.45 years. Among them, 167 were diagnosed with HFrEF and 188 with HFpEF. A least absolute shrinkage and selection operator regression model with non-parametric bootstrap were used to select predictors from an analysis of 4782 serum proteins, and several pre-established clinical parameters linked to HF. A subset of 8-10 distinct or overlapping serum proteins predicted different future HF outcomes, and C-statistics were used to assess discrimination, revealing proteins combined with a C-index of 0.80 for all incident HF, 0.78 and 0.80 for incident HFpEF or HFrEF, respectively. In the AGES-RS, protein panels alone encompassed the risk contained in the clinical information and improved the performance characteristics of prediction models based on N-terminal pro-B-type natriuretic peptide and clinical risk factors. Finally, the protein predictors performed particularly well close to the time of an HF event, an outcome that was replicated in the Cardiovascular Health Study.
CONCLUSIONS: A small number of circulating proteins accurately predicted future HF in the AGES-RS cohort of older adults, and they alone encompass the risk information found in a collection of clinical data. Incident HF events were predicted up to 8 years, with predictor performance significantly improving for events occurring less than 1 year ahead, a finding replicated in an external cohort study.