Explore the vast range of titles available.

Purpose To improve the outcome of the acute respiratory distress syndrome (ARDS), one needs to identify potentially modifiable factors associated with mortality. Methods The large observational study to understand the global impact of severe acute respiratory failure (LUNG SAFE) was an international, multicenter, prospective cohort study of patients with severe respiratory failure, conducted in the winter of 2014 in a convenience sample of 459 ICUs from 50 countries across five continents. A pre-specified secondary aim was to examine the factors associated with outcome. Analyses were restricted to patients (93.1 %) fulfilling ARDS criteria on day 1–2 who received invasive mechanical ventilation. Results 2377 patients were included in the analysis. Potentially modifiable factors associated with increased hospital mortality in multivariable analyses include lower PEEP, higher peak inspiratory, plateau, and driving pressures, and increased respiratory rate. The impact of tidal volume on outcome was unclear. Having fewer ICU beds was also associated with higher hospital mortality. Non-modifiable factors associated with worsened outcome from ARDS included older age, active neoplasm, hematologic neoplasm, and chronic liver failure. Severity of illness indices including lower pH, lower PaO 2 /FiO 2 ratio, and higher non-pulmonary SOFA score were associated with poorer outcome. Of the 578 (24.3 %) patients with a limitation of life-sustaining therapies or measures decision, 498 (86.0 %) died in hospital. Factors associated with increased likelihood of limitation of life-sustaining therapies or measures decision included older age, immunosuppression, neoplasia, lower pH and increased non-pulmonary SOFA scores. Conclusions Higher PEEP, lower peak, plateau, and driving pressures, and lower respiratory rate are associated with improved survival from ARDS. Trial Registration: ClinicalTrials.gov NCT02010073.

The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Variables were screened using the Recursive Feature Elimination method. Five machine learning algorithms were used to build predictive models. Models were evaluated through nested cross-validation to select the best one. The model was interpreted using Shapley Additive Explanations. We selected the optimal model to generate the web calculator. A total of 23 predictive features were selected. The Light Gradient Boosting Machine (LightGBM) model had an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CI: 0.757–0.927), with an external 5-fold cross-validation average AUC of 0.842 ± 0.038, which was superior to the other models. External validation results also demonstrated good performance by the LightGBM model with an AUC of 0.856 (95% CI: 0.792–0.921). Based on this, we generated a web calculator by combining five high importance predictive factors. The LightGBM model was confirmed to be efficient and stable in predicting the mortality risk of patients with SCAP admitted to the ICU. The web calculator based on the LightGBM model can provide clinicians with a prognostic evaluation tool.

This is the first population-level study to examine inequalities in COVID-19 mortality according to working-age individuals' occupations and the indirect occupational effects on COVID-19 mortality of older individuals who live with them. We used early-release data for the entire population of Sweden of all recorded COVID-19 deaths from 12 March 2020 to 23 February 2021, which we linked to administrative registers and occupational measures. Cox proportional hazard models assessed relative risks of COVID-19 mortality for the working-aged population registered in an occupation in December 2018 and the older population who lived with them. Among working aged-adults, taxi/bus drivers had the highest relative risk of COVID-19 mortality: over four times that of skilled workers in IT, economics, or administration when adjusted only for basic demographic characteristics. After adjusting for socioeconomic factors (education, income and country of birth), there are no occupational groups with clearly elevated (statistically significant) COVID-19 mortality. Neither a measure of exposure within occupations nor the share that generally can work from home were related to working-aged adults' risk of COVID-19 mortality. Instead of occupational factors, traditional socioeconomic risk factors best explained variation in COVID-19 mortality. Elderly individuals, however, faced higher COVID-19 mortality risk both when living with a delivery or postal worker or worker(s) in occupations that generally work from home less, even when their socioeconomic factors are taken into account. Inequalities in COVID-19 mortality of working-aged adults were mostly based on traditional risk factors and not on occupational divisions or characteristics in Sweden. However, older individuals living with those who likely cannot work from home or work in delivery or postal services were a vulnerable group.

This study aims to develop and validate a machine learning-based mortality risk prediction model for V-A ECMO patients to improve the precision of clinical decision-making. This multicenter retrospective cohort study included 280 patients receiving V-A ECMO from the Second Affiliated Hospital of Guangxi Medical University, Yulin First People’s Hospital, and the MIMIC-IV database. The data from the Second Affiliated Hospital of Guangxi Medical University and the MIMIC-IV database were merged and randomly divided in a 7:3 ratio into a training set and an internal validation set, respectively. The dataset from Yulin First People’s Hospital was reserved as an external validation cohort. The primary study outcome was defined as in-hospital mortality.Feature selection was conducted using Lasso regression, followed by the development of six machine learning models: Logistic Regression, Random Forest (RF), Deep Neural Network (DNN), Support Vector Machine (SVM), LightGBM, and CatBoost. Model performance was assessed using the Area Under the Curve (AUC), accuracy, sensitivity, specificity, and F1 score. Model validation was performed through calibration and decision curve analysis. Feature importance was evaluated using SHAP, and subgroup analysis was conducted to assess the model’s applicability across different clinical scenarios. In internal validation, the Logistic Regression model performed the best, with an AUC of 0.86 (95% CI: 0.77–0.93), accuracy of 0.76, sensitivity of 0.73, specificity of 0.79, and an F1 score of 0.73. It outperformed other models (RF: AUC = 0.79, DNN: AUC = 0.78, SVM: AUC = 0.76, LightGBM: AUC = 0.71, CatBoost: AUC = 0.77). External validation yielded consistent results, with the Logistic Regression model’s AUC at 0.75 (95% CI: 0.56–0.92), accuracy of 0.69, sensitivity of 0.64, specificity of 0.73, and an F1 score of 0.66. Calibration curve analysis revealed that the Logistic Regression model had the lowest Brier score (0.1496), indicating the most reliable predicted probabilities. Decision curve analysis demonstrated that the model provided the highest net benefit across most decision thresholds. SHAP analysis identified lactate, age, and albumin as key predictors of mortality, with lactate and age positively correlated, and albumin negatively correlated. Subgroup analysis revealed better performance in the cardiac arrest group (AUC = 0.81), non-sepsis group (AUC = 0.75), and non-diabetes group (AUC = 0.78). The Logistic Regression-based mortality risk prediction model for V-A ECMO patients demonstrated comparable or even favorable performance to more complex machine learning models, with the advantage of higher interpretability.By explicitly incorporating lactate, age, and albumin as the principal predictors, this model facilitates precise risk stratification and provides practical support for clinical decision-making in ECMO management.

At present, there is insufficient evidence to evaluate the prognosis of patients with sepsis. This study anazed the clinical data of 822 sepsis patients in the ICU of a tertiary Grade A hospital to construct and validate a nomogram model for predicting the 28-day mortality risk in sepsis patients. The model was constructed using multivariate logistic regression analysis to screen for independent risk factors affecting prognosis, and a mortality risk prediction model was built based on these independent risk factors. The performance of the model was evaluated using the Hosmer–Lemeshow test, receiver operating characteristic curve (ROC), calibration plot, and decision curve analysis (DCA). Multivariate logistic regression identified five independent risk factors for 28-day mortality in sepsis patients: Age, SOFA score, CRP, Mechanical ventilation, and the use of Vasoactive drugs. The odds ratios ( OR) and 95% confidence intervals (95% CI ) for these factors were 1.037 (1.024–1.050), 1.093 (1.044–1.145), 1.034 (1.026–1.042), 1.967 (1.176–3.328), and 2.515 (1.611–3.941), respectively, with all P -values < 0.05. Based on these five independent risk factors, a nomogram model was constructed, with the area under the ROC curve (AUC) in the training set and external validation set being 0.849 (95% CI 0.818–0.880) and 0.837 (95% CI 0.887–0.886), respectively. Both the DCA curve and calibration plot confirmed that the model has good clinical efficacy. The nomogram prediction model established in this study has excellent predictive ability, which can help clinicians identify high-risk patients early and provide guidance for clinical decision-making.

Background Accurate precision approaches have far not been developed for modeling mortality risk in intensive care unit (ICU) patients. Conventional mortality risk prediction methods can hardly extract the information in longitudinal electronic medical records (EHRs) effectively, since they simply aggregate the heterogeneous variables in EHRs, ignoring the complex relationship and interactions between variables and the time dependence in longitudinal records. Recently deep learning approaches have been widely used in modeling longitudinal EHR data. However, most existing deep learning-based risk prediction approaches only use the information of a single disease, neglecting the interactions between multiple diseases and different conditions. Results In this paper, we address this unmet need by leveraging disease and treatment information in EHRs to develop a mortality risk prediction model based on deep learning (DeepMPM). DeepMPM utilizes a two-level attention mechanism, i.e. visit-level and variable-level attention, to derive the representation of patient risk status from patient’s multiple longitudinal medical records. Benefiting from using EHR of patients with multiple diseases and different conditions, DeepMPM can achieve state-of-the-art performances in mortality risk prediction. Conclusions Experiment results on MIMIC III database demonstrates that with the disease and treatment information DeepMPM can achieve a good performance in terms of Area Under ROC Curve (0.85). Moreover, DeepMPM can successfully model the complex interactions between diseases to achieve better representation learning of disease and treatment than other deep learning approaches, so as to improve the accuracy of mortality prediction. A case study also shows that DeepMPM offers the potential to provide users with insights into feature correlation in data as well as model behavior for each prediction.

Neonatal mortality poses a critical challenge in global health, particularly in low- and middle-income countries. Leveraging advancements in technology, such as machine learning (ML) algorithms, offers the potential to improve neonatal care by enabling precise prediction and prevention of mortality risks. This study utilized the Maternal and Neonatal Health Registry (MNHR) dataset from the National Institutes of Health (NIH), encompassing multicentric neonatal data across various countries, to evaluate the effectiveness of ML in predicting neonatal mortality risk. We compared three training approaches: a generalized model applicable across all countries, country-specific models tailored to local healthcare characteristics, and a model derived from the largest single-country dataset. Utilizing data from 2010 to 2016 for training and validation from 2017 to 2019, our analysis included 575,664 pregnancies and assessed five ML algorithms based on key neonatal health indicators recommended by the World Health Organization. Notably, the generalized model demonstrated the highest predictive performance, achieving an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.816, highlighting the benefits of leveraging a diverse dataset. Our findings advocate for the integration of generalized ML models into healthcare strategies to improve neonatal health outcomes and emphasize the importance of data diversity in reducing neonatal mortality rates.

The estimates used to value mortality risk reductions are a major determinant of the benefits of many public health and environmental policies. These estimates (typically expressed as the value per statistical life, VSL) describe the willingness of those affected by a policy to exchange their own income for the risk reductions they experience. While these values are relatively well studied in high-income countries, less is known about the values held by lower-income populations. We identify 26 studies conducted in the 172 countries considered low- or middle-income in any of the past 20 years; several have significant limitations. Thus there are few or no direct estimates of VSL for most such countries. Instead, analysts typically extrapolate values from wealthier countries, adjusting only for income differences. This extrapolation requires selecting a base value and an income elasticity that summarizes the rate at which VSL changes with income. Because any such approach depends on assumptions of uncertain validity, we recommend that analysts conduct a standardized sensitivity analysis to assess the extent to which their conclusions change depending on these estimates. In the longer term, more research on the value of mortality risk reductions in low- and middle-income countries is essential.

Veno-arterial extracorporeal membrane oxygenation (VA-ECMO) is a critical life support technology for severely ill patients. Despite its benefits, patients face high costs and significant mortality risks. To improve clinical decision-making, this study aims to develop a non-invasive, efficient artificial intelligence (AI)-enabled model to predict the risk of mortality within 28 days post-weaning from VA-ECMO. A multicenter, retrospective cohort study was conducted across five hospitals in China, including all the patients who received VA-ECMO support between January 2020 and January 2024. Based on the innovatively selected 25 easily obtainable patient examination features as potentially relevant, this study involved developing ten predictive models using both classical and advanced machine learning techniques. The model’s performance is evaluated using various statistical metrics and the optimal predictive model are identified. Feature correlations are analyzed using Pearson correlation coefficients, and SHapley Additive exPlanations (SHAP) are employed to interpret feature importance. Decision curve analysis is used to evaluate the clinical utility of the predictive models. The study included 225 patients, with 66 patients from one hospital forming the training cohort. Three validation cohorts were used: internal validation with 16 patients from the training hospital and external validation with 30 and 60 patients from the other 4 hospitals. The random forest model emerged as the best predictor of 28-day mortality, achieving an AUROC of 1.00 in the training cohort and 1.00, 0.97, and 0.93 in the three validation cohorts, respectively. Despite the limited training data, the developed model, eCMoML, demonstrated high accuracy, generalizability and reliability. The model will be available online for immediate use by clinicians. The eCMoML model, validated in a multicenter cohort study, offers a rapid, stable, and accurate tool for predicting 28-day mortality post-VA-ECMO weaning. It has the potential to significantly enhance clinical decision-making, helping doctors better assess patient prognosis, optimize treatment plans, and improve survival rates.

Hip fractures among the elderly population continue to present significant risks and high mortality rates despite advancements in surgical procedures. In this study, we developed machine learning (ML) algorithms to estimate 30-day mortality risk post-hip fracture surgery in the elderly using data from the National Surgical Quality Improvement Program (NSQIP 2012–2017, n = 62,492 patients). Our approach involves two models: one estimating the patients’ 30-day mortality risk based on pre-operative conditions, and another considering both pre-operative and post-operative factors. We performed comprehensive data cleaning and preprocessing, then applied tenfold cross-validation with randomized search to the training set to identify optimal hyperparameters for various machine learning models. We used logistic regression, Naive Bayes, random forest, AdaBoost, XGBoost, CatBoost, Gradient Boosting, and LightGBM. The models’ performances were evaluated on the test set using the Area Under the Receiver Operating Characteristic Curve (AUC). The best pre-operative model was AdaBoost, achieving an AUC of 0.792 with 29 features (predictors), and the best post-operative model was CatBoost, achieving an AUC of 0.885 with 45 features. After modeling, we derived feature importance for each of the two models and decreased the number of features to reach a parsimonious highly performing model. The pre-operative model achieves an AUC of 0.725 with the eight most important features and the post-operative model achieves an AUC of 0.8529 with the six most important features. To ensure the models’ decision-making is compatible with clinical decisions and common practices, we applied explainability techniques such as SHAP to reveal the patterns learned by the models. These patterns were found to be clinically plausible. In summary, our approach involving data preprocessing, model tuning, feature selection, and explainability achieved state-of-the-art performance in predicting 30-day mortality rates following hip fractures surgery using a limited set of features, making it highly applicable in clinical settings.