Blood Urea Nitrogen and In-Hospital Mortality in Critically Ill Patients with Cardiogenic Shock: Analysis of the MIMIC-III Database

Blood Urea Nitrogen to Left Ventricular Ejection Ratio as a Predictor of Short-Term Outcome in Acute Myocardial Infarction Complicated by Cardiogenic Shock

INTRODUCTION

Cardiogenic shock (CS) is the most critical complication after acute myocardial infarction (AMI) with mortality above 50%. Both blood urea nitrogen and left ventricular ejection fraction were important prognostic indicators. We aimed to evaluate the prognostic value of admission blood urea nitrogen to left ventricular ejection fraction ratio (BUNLVEFr) in patients with AMI complicated by CS (AMI-CS).

METHODS

268 consecutive patients with AMI-CS were divided into two groups according to the admission BUNLVEFr cut-off value determined by Youden index. The primary endpoint was 30-day all-cause mortality and the secondary endpoint was the composite events of major adverse cardiovascular events (MACEs). Cox proportional hazard models were performed to analyze the association of BUNLVEFr with the outcome.

RESULTS

The optimal cut-off value of BUNLVEFr is 16.63. The 30-day all-cause mortality and MACEs in patients with BUNLVEFr≥16.63 was significantly higher than in patients with BUNLVEFr<16.63 (30-day all-cause mortality: 66.2% vs. 17.1%, p < 0.001; 30-day MACEs: 80.0% vs. 48.0%, p < 0.001). After multivariable adjustment, BUNLVEFr≥16.63 remained an independent predictor for higher risk of 30-day all-cause mortality (HR = 3.553, 95% CI: 2.125-5.941, p < 0.001) and MACEs (HR = 2.026, 95% CI: 1.456-2.820, p < 0.001). Subgroup analyses found that the effect of BUNLVEFr was consistent in different subgroups (all p-interaction>0.05).

CONCLUSION

The admission BUNLVEFr provided important prognostic information for AMI-CS patients.

A case-control study on the clinical characteristics of granisetron-related arrhythmias and the development of a predictive nomogram

BACKGROUND

Automatic monitoring and assessment are increasingly employed in drug safety evaluations using hospital information system data. The increasing concern about granisetron-related arrhythmias requires real-world studies to improve our understanding of its safety.

AIM

This study aimed to analyze the incidence, clinical characteristics, and risk factors of granisetron-related arrhythmias in hospitalized patients using real-world data obtained from the Adverse Drug Event Active Surveillance and Assessment System-II (ADE-ASAS-II) and concurrently aimed to develop and validate a nomogram to predict the occurrence of arrhythmias.

METHOD

Retrospective automatic monitoring of inpatients using granisetron was conducted in a Chinese hospital from January 1, 2017, to December 31, 2021, to determine the incidence of arrhythmias using ADE-ASAS- II. Propensity score matching was used to balance confounders and analyze clinical characteristics. Based on risk factors identified through logistic regression analysis, a prediction nomogram was established and internally validated using the Bootstrap method.

RESULTS

Arrhythmias occurred in 178 of 72,508 cases taking granisetron with an incidence of 0.3%. Independent risk factors for granisetron-related arrhythmias included medication duration, comorbid cardiovascular disease, concomitant use of other 5-hydroxytryptamine 3 receptor antagonists, alanine aminotransferase > 40 U/L, and blood urea nitrogen > 7.5 mmol/L. The nomogram demonstrated good differentiation and calibration, with enhanced clinical benefit observed when the risk threshold ranged from 0.10 to 0.82.

CONCLUSION

The nomogram, based on the five identified independent risk factors, may be valuable in predicting the risk of granisetron-related arrhythmias in the administered population, offering significant clinical applications.

The long-term effects of blood urea nitrogen levels on cardiovascular disease and all-cause mortality in diabetes: a prospective cohort study

BACKGROUND

The long-term effects of blood urea nitrogen(BUN) in patients with diabetes remain unknown. Current studies reporting the target BUN level in patients with diabetes are also limited. Hence, this prospective study aimed to explore the relationship of BUN with all-cause and cardiovascular mortalities in patients with diabetes.

METHODS

In total, 10,507 participants with diabetes from the National Health and Nutrition Examination Survey (1999-2018) were enrolled. The causes and numbers of deaths were determined based on the National Death Index mortality data from the date of NHANES interview until follow-up (December 31, 2019). Multivariate Cox proportional hazard regression models were used to calculate the hazard ratios (HRs) and 95% confidence interval (CIs) of mortality.

RESULTS

Of the adult participants with diabetes, 4963 (47.2%) were female. The median (interquartile range) BUN level of participants was 5 (3.93-6.43) mmol/L. After 86,601 person-years of follow-up, 2,441 deaths were documented. After adjusting for variables, the HRs of cardiovascular disease (CVD) and all-cause mortality in the highest BUN level group were 1.52 and 1.35, respectively, compared with those in the lowest BUN level group. With a one-unit increment in BUN levels, the HRs of all-cause and CVD mortality rates were 1.07 and 1.08, respectively. The results remained robust when several sensitivity and stratified analyses were performed. Moreover, BUN showed a nonlinear association with all-cause and CVD mortality. Their curves all showed that the inflection points were close to the BUN level of 5 mmol/L.

CONCLUSION

BUN had a nonlinear association with all-cause and CVD mortality in patients with diabetes. The inflection point was at 5 mmol/L.

Blood urea nitrogen to serum albumin ratio: a novel mortality indicator in intensive care unit patients with coronary heart disease

The blood urea nitrogen to albumin ratio (BAR) has been demonstrated as a prognostic factor in sepsis and respiratory diseases, yet its role in severe coronary heart disease (CHD) remains unexplored. This retrospective study, utilizing data from the Medical Information Mart for Intensive Care-IV database, included 4254 CHD patients, predominantly male (63.54%), with a median age of 74 years (IQR 64-83). Primary outcomes included in-hospital, 28-day and 1-year all-cause mortality after ICU admission. The Kaplan-Meier curves, Cox regression analysis, multivariable restricted cubic spline regression were employed to assess association between BAR index and mortality. In-hospital, within 28-day and 1-year mortality rates were 16.93%, 20.76% and 38.11%, respectively. Multivariable Cox proportional hazards analysis revealed associations between the increased BAR index and higher in-hospital mortality (HR 1.11, 95% CI 1.02-1.21), 28-day mortality (HR 1.17, 95% CI 1.08-1.27) and 1-year mortality (HR 1.23, 95% CI 1.16-1.31). Non-linear relationships were observed for 28-day and 1-year mortality with increasing BAR index (both P for non-linearity < 0.05). Elevated BAR index was a predictor for mortality in ICU patients with CHD, offering potential value for early high-risk patient identification and proactive management by clinicians.

Association between blood urea nitrogen levels and the risk of diabetes mellitus in Chinese adults: secondary analysis based on a multicenter, retrospective cohort study

Background

As one of the recognized indicators of kidney function, blood urea nitrogen (BUN) is a key marker of metabolic diseases and other diseases. Currently, data on the relationship of BUN levels with the risk of diabetes mellitus (DM) in Chinese adults are sparse. This study aimed to investigate the correlation between BUN levels and DM risk in Chinese adults.

Data and methods

This study is a secondary analysis of a multicenter, retrospective cohort study with data from the Chinese health screening program in the DATADRYAD database. From 2010 to 2016, health screening was conducted on 211833 Chinese adults over the age of 20 in 32 locations and 11 cities in China, and there was no DM at baseline. Cox proportional hazards regression analysis assessed an independent correlation between baseline BUN levels and the risk of developing DM. The Generalized Sum Model (GAM) and smoothed curve fitting methods were used to explore the nonlinear relationship. In addition, subgroup analyses were performed to assess the consistency of correlations between different subgroups and further validate the reliability of the results.

Results

After adjusting for potential confounding factors (age, sex, etc.), BUN levels were positively correlated with the occurrence of DM (HR=1.11, 95% CI (1.00~1.23)). BUN level had a nonlinear relationship with DM risk, and its inflection point was 4.2mmol/L. When BUN was greater than 4.2mmol/L, BUN was positively correlated with DM, and the risk of DM increased by 7% for every 1 mmol/L increase in BUN (P<0.05). Subgroup analysis showed that a more significant correlation between BUN levels and DM was observed in terms of sex, BMI, systolic blood pressure (SBP), diastolic blood pressure (DBP), total cholesterol (TC), triglycerides (TG), low-density lipoprotein (LDL), alaninetransaminase (ALT), aspartate transaminase (AST), creatinine (Cr) and smoking status (interaction P<0.05).

Conclusion

High levels of BUN are associated with an increased risk of DM in Chinese adults, suggesting that active control of BUN levels may play an important role in reducing the risk of DM in Chinese adults.

Blood Urea Nitrogen-to-Albumin Ratio May Predict Mortality in Patients with Traumatic Brain Injury from the MIMIC Database: A Retrospective Study

Traumatic brain injury (TBI), a major global health burden, disrupts the neurological system due to accidents and other incidents. While the Glasgow coma scale (GCS) gauges neurological function, it falls short as the sole predictor of overall mortality in TBI patients. This highlights the need for comprehensive outcome prediction, considering not just neurological but also systemic factors. Existing approaches relying on newly developed biomolecules face challenges in clinical implementation. Therefore, we investigated the potential of readily available clinical indicators, like the blood urea nitrogen-to-albumin ratio (BAR), for improved mortality prediction in TBI. In this study, we investigated the significance of the BAR in predicting all-cause mortality in TBI patients. In terms of research methodologies, we gave preference to machine learning methods due to their exceptional performance in clinical support in recent years. Initially, we obtained data on TBI patients from the Medical Information Mart for Intensive Care database. A total of 2602 patients were included, of whom 2260 survived and 342 died in hospital. Subsequently, we performed data cleaning and utilized machine learning techniques to develop prediction models. We employed a ten-fold cross-validation method to obtain models with enhanced accuracy and area under the curve (AUC) (Light Gradient Boost Classifier accuracy, 0.905 ± 0.016, and AUC, 0.888; Extreme Gradient Boost Classifier accuracy, 0.903 ± 0.016, and AUC, 0.895; Gradient Boost Classifier accuracy, 0.898 ± 0.021, and AUC, 0.872). Simultaneously, we derived the importance ranking of the variable BAR among the included variables (in Light Gradient Boost Classifier, the BAR ranked fourth; in Extreme Gradient Boost Classifier, the BAR ranked sixth; in Gradient Boost Classifier, the BAR ranked fifth). To further evaluate the clinical utility of BAR, we divided patients into three groups based on their BAR values: Group 1 (BAR < 4.9 mg/g), Group 2 (BAR ≥ 4.9 and ≤10.5 mg/g), and Group 3 (BAR ≥ 10.5 mg/g). This stratification revealed significant differences in mortality across all time points: in-hospital mortality (7.61% vs. 15.16% vs. 31.63%), as well as one-month (8.51% vs. 17.46% vs. 36.39%), three-month (9.55% vs. 20.14% vs. 41.84%), and one-year mortality (11.57% vs. 23.76% vs. 46.60%). Building on this observation, we employed the Cox proportional hazards regression model to assess the impact of BAR segmentation on survival. Compared to Group 1, Groups 2 and 3 had significantly higher hazard ratios (95% confidence interval (CI)) for one-month mortality: 1.77 (1.37-2.30) and 3.17 (2.17-4.62), respectively. To further underscore the clinical potential of BAR as a standalone measure, we compared its performance to established clinical scores, like sequential organ failure assessment (SOFA), GCS, and acute physiology score III(APS-III), using receiver operator characteristic curve (ROC) analysis. Notably, the AUC values (95%CI) of the BAR were 0.67 (0.64-0.70), 0.68 (0.65-0.70), and 0.68 (0.65-0.70) for one-month mortality, three-month mortality, and one-year mortality. The AUC value of the SOFA did not significantly differ from that of the BAR. In conclusion, the BAR is a highly influential factor in predicting mortality in TBI patients and should be given careful consideration in future TBI prediction research. The blood urea nitrogen-to-albumin ratio may predict mortality in TBI patients.

Development and validation of a nomogram for predicting in-hospital mortality in patients with nonhip femoral fractures

BACKGROUND

The incidence of nonhip femoral fractures is gradually increasing, but few studies have explored the risk factors for in-hospital death in patients with nonhip femoral fractures in the ICU or developed mortality prediction models. Therefore, we chose to study this specific patient group, hoping to help clinicians improve the prognosis of patients.

METHODS

This is a retrospective study based on the data from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. Least absolute shrinkage and selection operator (LASSO) regression was used to screen risk factors. The receiver operating characteristic (ROC) curve was drawn, and the areas under the curve (AUC), net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the discrimination of the model. The consistency between the actual probability and the predicted probability was assessed by the calibration curve and Hosmer-Lemeshow goodness of fit test (HL test). Decision curve analysis (DCA) was performed, and the nomogram was compared with the scoring system commonly used in clinical practice to evaluate the clinical net benefit.

RESULTS

The LASSO regression analysis showed that heart rate, temperature, red blood cell distribution width, blood urea nitrogen, Glasgow Coma Scale (GCS), Simplified Acute Physiology Score II (SAPSII), Charlson comorbidity index and cerebrovascular disease were independent risk factors for in-hospital death in patients with nonhip femoral fractures. The AUC, IDI and NRI of our model in the training set and validation set were better than those of the GCS and SAPSII scoring systems. The calibration curve and HL test results showed that our model prediction results were in good agreement with the actual results (P = 0.833 for the HL test of the training set and P = 0.767 for the HL test of the validation set). DCA showed that our model had a better clinical net benefit than the GCS and SAPSII scoring systems.

CONCLUSION

In this study, the independent risk factors for in-hospital death in patients with nonhip femoral fractures were determined, and a prediction model was constructed. The results of this study may help to improve the clinical prognosis of patients with nonhip femoral fractures.

Blood urea nitrogen concentration is associated with severe abdominal aortic calcification in adults: a cross-sectional investigation

The purpose of this research is to examine the correlation between blood urea nitrogen (BUN) and severe abdominal aortic calcification (AAC) among American adults aged 40 years and older. A total of 2757 participants in the NHANES from 2013 to 2014 were included in the final analysis. BUN was measured by means of the enzymatic conductivity rate method. AAC scores were quantified by the Kauppila scoring system, and severe AAC was defined as an AAC score ≥ 6. Multivariable logistic regression and restricted cubic splines were used in the analyses. In the multivariable logistic regression model, the highest BUN level (log 2-transformed) was associated with an increased risk of severe AAC [odds ratio (OR) = 1.77, 95% CI 1.17, 2.71]. The restricted cubic spline plot displayed a reverse L-shaped association between BUN (log2-transformed) and severe AAC (p for nonlinearity < 0.001). In addition,the interactions of BUN were not discover. In general, there is a positive correlation between BUN and the risk of severe AAC.

Construction and evaluation of prognostic models of ECMO in elderly patients with cardiogenic shock based on BP neural network, random forest, and decision tree

OBJECTIVE

To analyze the predictive effect of a back propagation (BP) neural network, random forest (RF) and decision tree model on the prognosis of elderly patients with cardiogenic shock after extracorporeal membrane oxygenation (ECMO).

METHODS

This is a retrospective analysis of the clinical data of elderly patients with cardiogenic shock (258 cases) who underwent ECMO in People's Hospital of Guangxi Zhuang Autonomous Region from January 2016 to January 2022. All patients were followed up for 6 months after ECMO treatment. The prognosis was evaluated, and the prognostic factors were analyzed. BP neural network, RF and decision tree were used to establish predictive models, and the predictive performance of the models was evaluated.

RESULTS

Among the 258 elderly patients with cardiogenic shock, 52 (20.16%) died 6 months after the ECMO treatment. Based on BP neural network, RF, and decision tree, predictive models for the prognosis and death of elderly patients with cardiogenic shock were constructed. A test set was used to predict the performance of the three models. The results showed that the predictive performances of the three models were all more than 80.00%. The accuracy, sensitivity, and specificity of the RF model were 0.987, 1.000, and 0.929 respectively, which were higher than those of the decision tree model. The area under the receiver operating characteristic curve (AUC) of the RF model was 1.000, which was higher than 0.916 for the decision tree model. DeLong test showed that there was a significant difference in the AUC of the RF model compared to the decision tree test set (D=-2.063, P=0.042 < 0.05).

CONCLUSION

The predictive performance is good in all the three models, which have a high application value for prognosis of ECMO in elderly patients with cardiogenic shock. In clinical practice, predictive models should be selected according to the actual situation, so clinicians and patients can make decisions.

Effect of sex on the association between arterial partial pressure of oxygen and in-hospital mortality in ICU patients with cardiogenic shock: a retrospective cohort study

Background

Maintaining tissue perfusion and oxygen supply are essential for cardiogenic shock (CS) treatment. Sex has been reported to be associated with mortality and oxygen use in patients with CS. Males and females respond differently to hypoxia. We designed this cohort study to evaluate the effects of sex on the association between the arterial partial pressure of oxygen (PaO₂) and in-hospital mortality.

Methods

We used the Medical Information Mart for Intensive Care (MIMIC) IV database for this cohort study. The outcome was in-hospital mortality. The relationship between the PaO₂ and in-hospital mortality was compared with sex (via an interaction test) using multivariable Cox regression models. Presence of interaction between PaO₂ and sex was tested by using inter interaction terms.

Results

A total of 1,772 patients with CS were enrolled in this study. The association between PaO₂ and in-hospital mortality appeared to differ between males and females [hazard ratio (HR): 0.997, 95% confidence interval (CI): 0.995-0.999 vs. HR: 1.002, 95% CI: 0.999-1.003, P for interaction =0.002]. We repeated the analyses, based on different PaO₂ category (PaO₂ <60 mmHg; PaO₂ 60-100 mmHg; PaO₂ >100 mmHg) and the results remained stable, P for interaction =0.008.

Conclusions

Sex affects the relationship between PaO₂ and in-hospital mortality in CS patients. Our findings may lead to the development of individualized therapies that focus on the use of different target oxygen partial pressures in different sexes to treat patients with CS.

Relationship between the Blood Urea Nitrogen to Creatinine Ratio and In-Hospital Mortality in Non-Traumatic Subarachnoid Hemorrhage Patients: Based on Propensity Score Matching Method

(1) Background: To explore the correlation between the blood urea nitrogen to creatinine ratio (UCR) and in-hospital mortality in non-traumatic subarachnoid hemorrhage patients. (2) Methods: Specific clinical information was collected from the Medical Information Mart for Intensive Ⅳ (MIMIC-Ⅳ) database. The optimal cut-off value of the UCR was calculated with ROC curve analysis conducted using the maximum Youden index for the prediction of survival status. Univariable and multivariable logistic regression analyses were also carried out to assess the prognostic significance of UCR, and the Kaplan−Meier (K−M) analysis was conducted to draw the survival curves. Then, the 1:1 propensity score matching (PSM) method was applied to improve the reliability of the research results while balancing the unintended influence of underlying confounders. (3) Results: This retrospective cohort study included 961 patients. The optimal cut-off value of the UCR for in-hospital mortality was 27.208. The PSM was performed to identify 92 pairs of score-matched patients, with balanced differences exhibited for nearly all variables. According to the K−M analysis, those patients with a UCR of more than 27.208 showed a significantly higher level of in-hospital mortality compared to the patients with a UCR of less than 27.208 (p < 0.05). After the adjustment for possible confounders, those patients whose UCR was more than 27.208 still had a significantly higher level of in-hospital mortality than the patients whose UCR was less than 27.208, as revealed by the multivariable logistic regression analysis (OR = 3.783, 95% CI: 1.959~7.305, p < 0.001). Similarly, the in-hospital mortality remained substantially higher for those patients in the higher UCR group than for the patients in the lower UCR group after PSM. (4) Conclusion: A higher level of the UCR was evidently associated with an increased risk of in-hospital mortality, which made the ratio useful as a prognostic predictor of clinical outcomes for those patients with non-traumatic subarachnoid hemorrhage.

Comparison of Prognostic Value of 10 Biochemical Indices at Admission for Prediction Postoperative Myocardial Injury and Hospital Mortality in Patients with Osteoporotic Hip Fracture

Aim: To evaluate the prognostic impact at admission of 10 biochemical indices for prediction postoperative myocardial injury (PMI) and/or hospital death in hip fracture (HF) patients. Methods: In 1273 consecutive patients with HF (mean age 82.9 ± 8.7 years, 73.5% women), clinical and laboratory parameters were collected prospectively, and outcomes were recorded. Multiple logistic regression and receiver-operating characteristic analyses (the area under the curve, AUC) were preformed, the number needed to predict (NNP) outcome was calculated. Results: Age ≥ 80 years and IHD were the most prominent clinical factors associated with both PMI (with cardiac troponin I rise) and in-hospital death. PMI occurred in 555 (43.6%) patients and contributed to 80.3% (49/61) of all deaths (mortality rate 8.8% vs. 1.9% in non-PMI patients). The most accurate biochemical predictive markers were parathyroid hormone > 6.8 pmol/L, urea > 7.5 mmol/L, 25(OH)vitamin D < 25 nmol/L, albumin < 33 g/L, and ratios gamma-glutamyl transferase (GGT) to alanine aminotransferase > 2.5, urea/albumin ≥ 2.0 and GGT/albumin ≥ 7.0; the AUC for developing PMI ranged between 0.782 and 0.742 (NNP: 1.84−2.13), the AUC for fatal outcome ranged from 0.803 to 0.722, (NNP: 3.77−9.52). Conclusions: In HF patients, easily accessible biochemical indices at admission substantially improve prediction of hospital outcomes, especially in the aged >80 years with IHD.

Association Between Pre-operative BUN and Post-operative 30-Day Mortality in Patients Undergoing Craniotomy for Tumors: Data From the ACS NSQIP Database

Objective

There is limited evidence to clarify the specific relationship between pre-operative blood urea nitrogen (BUN) and post-operative 30-day mortality in patients undergoing craniotomy for tumors. Therefore, we aimed to investigate this relationship in detail.

Methods

Electronic medical records of 18,642 patients undergoing craniotomy for tumors in the ACS NSQIP from 2012 to 2015 were subjected to secondary retrospective analysis. The principal exposure was pre-operative BUN. Outcome measures were post-operative 30-day mortality. We used binary logistic regression modeling to evaluate the association between them and conducted a generalized additive model and smooth curve fitting (penalized spline method) to explore the potential relationship and its explicit curve shape. We also conducted sensitivity analyses to ensure the robustness of the results and performed subgroup analyses.

Results

A total of 16,876 patients were included in this analysis. Of these, 47.48% of patients were men. The post-operative 30-day mortality of the included cases was 2.49% (420/16,876), and the mean BUN was 16.874 ± 6.648 mg/dl. After adjusting covariates, the results showed that pre-operative BUN was positively associated with post-operative 30-day mortality (OR = 1.020, 95% CI: 1.004, 1.036). There was also a non-linear relationship between BUN and post-operative 30-day mortality, and the inflection point of the BUN was 9.804. For patients with BUN < 9.804 mg/dl, a 1 unit decrease in BUN was related to a 16.8% increase in the risk of post-operative 30-day mortality (OR = 0.832, 95% CI: 0.737, 0.941); for patients with BUN > 9.804 mg/dl, a 1 unit increase in BUN was related to a 2.8% increase in the risk of post-operative 30-day mortality (OR = 1.028, 95% CI: 1.011, 1.045). The sensitivity analysis proved that the results were robust. The subgroup analysis revealed that all listed subgroups did not affect the relationship between pre-operative BUN and post-operative 30-day mortality (P > 0.05).

Conclusion

Our study demonstrated that pre-operative BUN (mg/dl) has specific linear and non-linear relationships with post-operative 30-day mortality in patients over 18 years of age who underwent craniotomy for tumors. Proper pre-operative management of BUN and maintenance of BUN near the inflection point (9.804 mg/dl) could reduce the risk of post-operative 30-day mortality in these cases.

Predicting ICU Mortality in Rheumatic Heart Disease: Comparison of XGBoost and Logistic Regression

BACKGROUND

Rheumatic heart disease (RHD) accounts for a large proportion of Intensive Care Unit (ICU) deaths. Early prediction of RHD can help with timely and appropriate treatment to improve survival outcomes, and the XGBoost machine learning technology can be used to identify predictive factors; however, its use has been limited in the past. We compared the performance of logistic regression and XGBoost in predicting hospital mortality among patients with RHD from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.

METHODS

The patients with RHD in the MIMIC-IV database were divided into two groups retrospectively according to the availability of data and its clinical significance based on whether they survived or died. Backward stepwise regression was used to analyze the independent factors influencing patients with RHD, and to compare the differences between the two groups. The XGBoost algorithm and logistic regression were used to establish two prediction models, and the areas under the receiver operating characteristic curves (AUCs) and decision-curve analysis (DCA) were used to test and compare the models. Finally, DCA and the clinical impact curve (CIC) were used to validate the model.

RESULTS

Data on 1,634 patients with RHD were analyzed, comprising 207 who died during hospitalization and 1,427 survived. According to estimated results for the two models using AUCs [0.838 (95% confidence interval = 0.786-0.891) and 0.815 (95% confidence interval = 0.765-0.865)] and DCA, the logistic regression model performed better. DCA and CIC verified that the logistic regression model had convincing predictive value.

CONCLUSIONS

We used logistic regression analysis to establish a more meaningful prediction model for the final outcome of patients with RHD. This model might be clinically useful for patients with RHD and help clinicians to provide detailed treatments and precise management.

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients' length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.