Development of a prediction model for the risk of 30-day unplanned readmission in older patients with heart failure: A multicenter retrospective study.

BACKGROUND AND AIM: Heart failure (HF) imposes significant global health costs due to its high incidence, readmission, and mortality rate. Accurate assessment of readmission risk and precise interventions have become important measures to improve health for patients with HF. Therefore, this study aimed to develop a machine learning (ML) model to predict 30-day unplanned readmissions in older patients with HF. METHODS AND RESULTS: This study collected data on hospitalized older patients with HF from the medical data platform of Chongqing Medical University from January 1, 2012, to December 31, 2021. A total of 5 candidate algorithms were selected from 15 ML algorithms with excellent performance, which was evaluated by area under the operating characteristic curve (AUC) and accuracy. Then, the 5 candidate algorithms were hyperparameter tuned by 5-fold cross-validation grid search, and performance was evaluated by AUC, accuracy, sensitivity, specificity, and recall. Finally, an optimal ML model was constructed, and the predictive results were explained using the SHapley Additive exPlanations (SHAP) framework. A total of 14,843 older patients with HF were consecutively enrolled. CatBoost model was selected as the best prediction model, and AUC was 0.732, with 0.712 accuracy, 0.619 sensitivity, and 0.722 specificity. NT.proBNP, length of stay (LOS), triglycerides, blood phosphorus, blood potassium, and lactate dehydrogenase had the greatest effect on 30-day unplanned readmission in older patients with HF, according to SHAP results. CONCLUSIONS: The study developed a CatBoost model to predict the risk of unplanned 30-day special-cause readmission in older patients with HF, which showed more significant performance compared with the traditional logistic regression model.

Ammonia oxidizing archaea and bacteria respond to different manure application rates during organic vegetable cultivation in Northwest China.

Ammonia oxidization is a critical process in nitrogen cycling that involves ammonia oxidizing archaea (AOA) and bacteria (AOB). However, the effects of different manure amounts on ammonia-oxidizing microorganisms (AOMs) over the course of organic vegetables production remains unclear. We used the amoA gene to evaluated AOMs abundance and community structure in organic vegetable fields. Quantitative PCR revealed that AOB were more abundant than AOA. Among them, the amoA copy number of AOB treated with 900 kgN ha-1 was 21.3 times that of AOA. The potential nitrification rate was significantly correlated with AOB abundance (P < 0.0001) but not with AOA, suggesting that AOB might contribute more to nitrification than AOA. AOB sequences were classified into Nitrosomonas and Nitrosospira, and AOA into Nitrosopumilus and Nitrososphaera. Nitrosomonas and Nitrosopumilus were predominant in treatments that received manure nitrogen at ≥ 900 kg ha-1 (52.7-56.5%) and when manure was added (72.7-99.8%), respectively, whereas Nitrosospira and Nitrososphaera occupied more than a half percentage in those that received ≤ 600 kg ha-1 (58.4-84.9%) and no manure (59.6%). A similar manure rate resulted in more identical AOMs' community structures than greater difference manure rate. The bacterial amoA gene abundances and ratios of AOB and AOA showed significantly positive correlations with soil electrical conductivity, total carbon and nitrogen, nitrate, phosphorus, potassium, and organic carbon, indicating that these were potential key factors influencing AOMs. This study explored the AOMs' variation in organic vegetable fields in Northwest China and provided a theoretical basis and reference for the subsequent formulation of proper manure management.

Development and assessment of scoring model for ICU stay and mortality prediction after emergency admissions in ischemic heart disease: a retrospective study of MIMIC-IV databases.

Ischemic heart disease (IHD) is the leading cause of death and emergency department (ED) admission. We aimed to develop more accurate and straightforward scoring models to optimize the triaging of IHD patients in ED. This was a retrospective study based on the MIMIC-IV database. Scoring models were established by AutoScore formwork based on machine learning algorithm. The predictive power was measured by the area under the curve in the receiver operating characteristic analysis, with the prediction of intensive care unit (ICU) stay, 3d-death, 7d-death, and 30d-death after emergency admission. A total of 8381 IHD patients were included (median patient age, 71 years, 95% CI 62-81; 3035 [36%] female), in which 5867 episodes were randomly assigned to the training set, 838 to validation set, and 1676 to testing set. In total cohort, there were 2551 (30%) patients transferred into ICU; the mortality rates were 1% at 3 days, 3% at 7 days, and 7% at 30 days. In the testing cohort, the areas under the curve of scoring models for shorter and longer term outcomes prediction were 0.7551 (95% CI 0.7297-0.7805) for ICU stay, 0.7856 (95% CI 0.7166-0.8545) for 3d-death, 0.7371 (95% CI 0.6665-0.8077) for 7d-death, and 0.7407 (95% CI 0.6972-0.7842) for 30d-death. This newly accurate and parsimonious scoring models present good discriminative performance for predicting the possibility of transferring to ICU, 3d-death, 7d-death, and 30d-death in IHD patients visiting ED.

Predicting diabetic kidney disease for type 2 diabetes mellitus by machine learning in the real world: a multicenter retrospective study.

Objective: Diabetic kidney disease (DKD) has been reported as a main microvascular complication of diabetes mellitus. Although renal biopsy is capable of distinguishing DKD from Non Diabetic kidney disease(NDKD), no gold standard has been validated to assess the development of DKD.This study aimed to build an auxiliary diagnosis model for type 2 Diabetic kidney disease (T2DKD) based on machine learning algorithms. Methods: Clinical data on 3624 individuals with type 2 diabetes (T2DM) was gathered from January 1, 2019 to December 31, 2019 using a multi-center retrospective database. The data fell into a training set and a validation set at random at a ratio of 8:2. To identify critical clinical variables, the absolute shrinkage and selection operator with the lowest number was employed. Fifteen machine learning models were built to support the diagnosis of T2DKD, and the optimal model was selected in accordance with the area under the receiver operating characteristic curve (AUC) and accuracy. The model was improved with the use of Bayesian Optimization methods. The Shapley Additive explanations (SHAP) approach was used to illustrate prediction findings. Results: DKD was diagnosed in 1856 (51.2 percent) of the 3624 individuals within the final cohort. As revealed by the SHAP findings, the Categorical Boosting (CatBoost) model achieved the optimal performance 1in the prediction of the risk of T2DKD, with an AUC of 0.86 based on the top 38 characteristics. The SHAP findings suggested that a simplified CatBoost model with an AUC of 0.84 was built in accordance with the top 12 characteristics. The more basic model features consisted of systolic blood pressure (SBP), creatinine (CREA), length of stay (LOS), thrombin time (TT), Age, prothrombin time (PT), platelet large cell ratio (P-LCR), albumin (ALB), glucose (GLU), fibrinogen (FIB-C), red blood cell distribution width-standard deviation (RDW-SD), as well as hemoglobin A1C(HbA1C). Conclusion: A machine learning-based model for the prediction of the risk of developing T2DKD was built, and its effectiveness was verified. The CatBoost model can contribute to the diagnosis of T2DKD. Clinicians could gain more insights into the outcomes if the ML model is made interpretable.

A novel web-based calculator to predict 30-day all-cause in-hospital mortality for 7,202 elderly patients with heart failure in ICUs: a multicenter retrospective cohort study in the United States.

Background and aims: Heart failure (HF) is a significant cause of in-hospital mortality, especially for the elderly admitted to intensive care units (ICUs). This study aimed to develop a web-based calculator to predict 30-day in-hospital mortality for elderly patients with HF in the ICU and found a relationship between risk factors and the predicted probability of death. Methods and results: Data (N = 4450) from the MIMIC-III/IV database were used for model training and internal testing. Data (N = 2,752) from the eICU-CRD database were used for external validation. The Brier score and area under the curve (AUC) were employed for the assessment of the proposed nomogram. Restrictive cubic splines (RCSs) found the cutoff values of variables. The smooth curve showed the relationship between the variables and the predicted probability of death. A total of 7,202 elderly patients with HF were included in the study, of which 1,212 died. Multivariate logistic regression analysis showed that 30-day mortality of HF patients in ICU was significantly associated with heart rate (HR), 24-h urine output (24h UOP), serum calcium, blood urea nitrogen (BUN), NT-proBNP, SpO2, systolic blood pressure (SBP), and temperature (P < 0.01). The AUC and Brier score of the nomogram were 0.71 (0.67, 0.75) and 0.12 (0.11, 0.15) in the testing set and 0.73 (0.70, 0.75), 0.13 (0.12, 0.15), 0.65 (0.62, 0.68), and 0.13 (0.12, 0.13) in the external validation set, respectively. The RCS plot showed that the cutoff values of variables were HR of 96 bmp, 24h UOP of 1.2 L, serum calcium of 8.7 mg/dL, BUN of 30 mg/dL, NT-pro-BNP of 5121 pg/mL, SpO2 of 93%, SBP of 137 mmHg, and a temperature of 36.4°C. Conclusion: Decreased temperature, decreased SpO2, decreased 24h UOP, increased NT-proBNP, increased serum BUN, increased or decreased SBP, fast HR, and increased or decreased serum calcium increase the predicted probability of death. The web-based nomogram developed in this study showed good performance in predicting 30-day in-hospital mortality for elderly HF patients in the ICU.

Interpretable machine learning for predicting 28-day all-cause in-hospital mortality for hypertensive ischemic or hemorrhagic stroke patients in the ICU: a multi-center retrospective cohort study with internal and external cross-validation.

Background: Timely and accurate outcome prediction plays a critical role in guiding clinical decisions for hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. However, interpreting and translating the predictive models into clinical applications are as important as the prediction itself. This study aimed to develop an interpretable machine learning (IML) model that accurately predicts 28-day all-cause mortality in hypertensive ischemic or hemorrhagic stroke patients. Methods: A total of 4,274 hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU in the USA from multicenter cohorts were included in this study to develop and validate the IML model. Five machine learning (ML) models were developed, including artificial neural network (ANN), gradient boosting machine (GBM), eXtreme Gradient Boosting (XGBoost), logistic regression (LR), and support vector machine (SVM), to predict mortality using the MIMIC-IV and eICU-CRD database in the USA. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Model performance was evaluated based on the area under the curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV). The ML model with the best predictive performance was selected for interpretability analysis. Finally, the SHapley Additive exPlanations (SHAP) method was employed to evaluate the risk of all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. Results: The XGBoost model demonstrated the best predictive performance, with the AUC values of 0.822, 0.739, and 0.700 in the training, test, and external cohorts, respectively. The analysis of feature importance revealed that age, ethnicity, white blood cell (WBC), hyperlipidemia, mean corpuscular volume (MCV), glucose, pulse oximeter oxygen saturation (SpO2), serum calcium, red blood cell distribution width (RDW), blood urea nitrogen (BUN), and bicarbonate were the 11 most important features. The SHAP plots were employed to interpret the XGBoost model. Conclusions: The XGBoost model accurately predicted 28-day all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. The SHAP method can provide explicit explanations of personalized risk prediction, which can aid physicians in understanding the model.

Local tumor destruction and liver resection increase overall survival in intermediate/advanced hepatocellular carcinoma patients: evidence from a population-based study.

Background: Liver resection (LR) and local tumor destruction (LTD) are effective treatments, but not commonly recommended for patients with intermediate/advanced hepatocellular carcinoma (HCC). This study aimed to explore whether LR/LTD could improve overall survival (OS) of these patients, and to identify the patients who will most likely benefit from LR/LTD. Methods: Data of patients with intermediate/advanced HCC between 2001 and 2018 were extracted from Surveillance, Epidemiology, and End Results database. OS was compared between HCC patients who received LR/LTD and those who did not. A nomogram was constructed for predicting OS, and it was then validated. Results: A total of 535 eligible patients were included, among which 128 received LR/LTD while 407 did not. Significantly higher OS in patients who received LR/LTD was observed (P<0.001). Based on independent prognostic factors obtained from univariate and multivariate analyses, a nomogram was constructed. The C-indices of nomogram were higher than those of the TNM staging system (training cohort: 0.74 vs. 0.59; validation cohort: 0.78 vs. 0.61). Similarly, areas under receiver operating characteristic curves and calibration curves indicated good accuracy of the nomogram. Decision curve analysis curves revealed good clinical practicability of the nomogram. Furthermore, low-risk patients (nomogram score: 0-221.9) had higher OS compared with high-risk patients (nomogram score: higher than 221.9) (P<0.001). Conclusion: LR/LTD significantly improves OS in patients with intermediate/advanced HCC. The nomogram developed in the present study shows high predicating value for OS in patients with intermediate/advanced HCC, which might be useful in selecting patients who are most suitable for LR/LTD.

Effect of surgical treatment on patients with stage T3 or T4 triple-negative breast cancer: a SEER-based retrospective observational study.

Background: The use of surgery is controversial in patients with stage T3 or T4 triple-negative breast cancer (TNBC). We aimed to explore the effect of surgical treatment on overall survival (OS) of these patients. Methods: A total of 2,041 patients were selected and divided into the surgical and non-surgical groups based on the Surveillance, Epidemiology, and End Results database from 2010 to 2018. Propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) were applied to balance covariates between different groups. The OS of the two groups were assessed by Kaplan-Meier survival curves and Cox proportional hazards regression models. Results: A total of 2,041 patients were included in the study. After PSM and IPTW, baseline characteristics of the matched variables were fully balanced. Kaplan-Meier survival curves showed that the median survival time and OS of TNBC patients with stage T3 or T4 in the surgical group were significantly improved compared with those in the non-surgical group. Multivariate Cox proportional hazards regression analysis showed that surgery was a protective factor for prognosis. Conclusion: Our study found that surgery prolonged the median survival and improved OS compared with the non-surgical group of TNBC patients with stage T3 or T4.

Explainable machine learning models for predicting 30-day readmission in pediatric pulmonary hypertension: A multicenter, retrospective study.

Background: Short-term readmission for pediatric pulmonary hypertension (PH) is associated with a substantial social and personal burden. However, tools to predict individualized readmission risk are lacking. This study aimed to develop machine learning models to predict 30-day unplanned readmission in children with PH. Methods: This study collected data on pediatric inpatients with PH from the Chongqing Medical University Medical Data Platform from January 2012 to January 2019. Key clinical variables were selected by the least absolute shrinkage and the selection operator. Prediction models were selected from 15 machine learning algorithms with excellent performance, which was evaluated by area under the operating characteristic curve (AUC). The outcome of the predictive model was interpreted by SHapley Additive exPlanations (SHAP). Results: A total of 5,913 pediatric patients with PH were included in the final cohort. The CatBoost model was selected as the predictive model with the greatest AUC for 0.81 (95% CI: 0.77-0.86), high accuracy for 0.74 (95% CI: 0.72-0.76), sensitivity 0.78 (95% CI: 0.69-0.87), and specificity 0.74 (95% CI: 0.72-0.76). Age, length of stay (LOS), congenital heart surgery, and nonmedical order discharge showed the greatest impact on 30-day readmission in pediatric PH, according to SHAP results. Conclusions: This study developed a CatBoost model to predict the risk of unplanned 30-day readmission in pediatric patients with PH, which showed more significant performance compared with traditional logistic regression. We found that age, LOS, congenital heart surgery, and nonmedical order discharge were important factors for 30-day readmission in pediatric PH.

Risk Stratification Model for Predicting the Overall Survival of Elderly Triple-Negative Breast Cancer Patients: A Population-Based Study.

Background: The objective of this study was to evaluate the prognostic value of clinical characteristics in elderly patients with triple-negative breast cancer (TNBC). Methods: The cohort was selected from the Surveillance, Epidemiology, and End Results (SEER) program dating from 2010 to 2015. Univariate and multivariate analyses were performed using a Cox proportional risk regression model, and a nomogram was constructed to predict the 1-, 3-, and 5-year prognoses of elderly patients with TNBC. A concordance index (C-index), calibration curve, and decision curve analysis (DCA) were used to verify the nomogram. Results: The results of the study identified a total of 5,677 patients who were randomly divided 6:4 into a training set (n = 3,422) and a validation set (n = 2,255). The multivariate analysis showed that age, race, grade, TN stage, chemotherapy status, radiotherapy status, and tumor size at diagnosis were independent factors affecting the prognosis of elderly patients with TNBC. Together, the 1 -, 3 -, and 5-year nomograms were made up of 8 variables. For the verification of these results, the C-index of the training set and validation set were 0.757 (95% CI 0.743-0.772) and 0.750 (95% CI 0.742-0.768), respectively. The calibration curve also showed that the actual observation of overall survival (OS) was in good agreement with the prediction of the nomograms. Additionally, the DCA showed that the nomogram had good clinical application value. According to the score of each patient, the risk stratification system of elderly patients with TNBC was further established by perfectly dividing these patients into three groups, namely, low risk, medium risk, and high risk, in all queues. In addition, the results showed that radiotherapy could improve prognosis in the low-risk group (P = 0.00056), but had no significant effect in the medium-risk (P < 0.4) and high-risk groups (P < 0.71). An online web app was built based on the proposed nomogram for convenient clinical use. Conclusion: This study was the first to construct a nomogram and risk stratification system for elderly patients with TNBC. The well-established nomogram and the important findings from our study could guide follow-up management strategies for elderly patients with TNBC and help clinicians improve individual treatment.

Soil moisture and nitrate-nitrogen dynamics and economic yield in the greenhouse cultivation of tomato and cucumber under negative pressure irrigation in the North China Plain.

A field experiment was carried out for two years to investigate the benefits of negative pressure water supply on surface soil water content, nitrate-nitrogen (NO3--N) distribution in the soil profile, economic yield and water and fertilizer use efficiency of tomato and cucumber under greenhouse cultivation in the North China Plain. The experiment included two irrigation treatments: drip irrigation with nutrient solution (DIN) and negative pressure irrigation with nutrient solution (NIN). The results showed that the NIN treatment had a relatively stable soil moisture (about 87% of field capacity), and the fluctuation of soil water content in the 0-20 cm soil layer was 20.6%-25.0% during the experiment period in 2014-2015, which was less than the range of 19.2%-28.1% in the DIN treatment. In both the DIN and NIN treatments, the NO3--N at the end of the four growing seasons was mainly distributed in the 0-40 cm soil layer and showed a gradually increasing trend as the number of cultivation years increased. Compared with the DIN treatment, the NO3--N content in the 0-60 cm layer of the NIN treatment was significantly decreased by 19.7%-28.0% after the fourth growing season. The NIN treatment produced the highest economic yield with lower water and nutrient input than the DIN treatment, however, no significant difference was observed in tomato and cucumber yield in the two years. Average irrigation water use efficiency (WUEi) and partial factor productivity of fertilizer (PFPf) over the study period were all significantly improved under the NIN treatment relative to the DIN treatment, with increases of 26.2% and 25.7% (P < 0.05), respectively. Negative pressure water supply not only maintained a high fruit yield, but significantly increased WUEi and PFPf, indicating a great advantage in water and fertilizer saving compared with drip irrigation.