Multimodal AI-based 28-day mortality prediction of pneumonia patients at ED discharge: a multicenter study.

Although 72-hour emergency department (ED) revisits are increasingly used as a hospital metric, there is no known empirical basis for this 72-hour threshold. The objective of this study was to determine the timing of ED revisits for adult patients within 30 days of ED discharge. This was a retrospective cohort study of all nonfederal ED discharges in Florida and Nebraska from April 1, 2010, to March 31, 2011, using data from the Agency for Healthcare Research and Quality (AHRQ) Healthcare Cost and Utilization Project (HCUP). ED discharges were followed forward to identify ED revisits occurring at any hospital within the same state within 30 days. The cumulative hazard of an ED revisit was plotted. Parametric and nonparametric modeling was performed to characterize the rate of ED revisits. There were 4,782,045 ED discharges, with 7.5% (95% confidence interval [CI] = 7.4% to 7.5%) associated with 3-day revisits, and 22.4% (95% CI = 22.3% to 22.4%) associated with 30-day revisits, inclusive of the 3-day revisits. A double-exponential model fit the data best (p < 0.0001), and a single hinge point at 9 days (multivariate adaptive regression splines [MARS] model) yielded the best linear fit to the data, suggesting 9 days as the most reasonable cutoff for identification of acute ED revisits. Multiple stratified and subgroup analyses produced similar results. Future work should focus on identifying primary reasons for potentially avoidable return ED visits instead of on the revisit occurrence itself, thus more directly measuring potential lapses in delivery of high-quality care. Almost one-quarter of ED discharges are linked to 30-day ED revisits, and the current 72-hour ED metric misses close to 70% of these patients. Our findings support 9 days as a more inclusive cutoff for studies of ED revisits.

Analysis of Emergency Department Visits for Palpitations (from the National Hospital Ambulatory Medical Care Survey)

Hepatocellular carcinoma (HCC) exhibits a propensity for early recurrence following liver resection, resulting in a bleak prognosis. At present, majority of the predictive models for the early postoperative recurrence of HCC rely on the linear assumption of the Cox Proportional Hazard (CPH) model. However, the predictive efficacy of this model is constrained by the intricate nature of clinical data. The present study aims to investigate the efficacy of the random survival forest (RSF) model, which is a machine learning algorithm, in predicting the early postoperative recurrence of HCC, and compare its performance with that of the traditional CPH model. This analysis seeks to elucidate the potential advantages of the RSF model over the CPH model in addressing this clinical challenge. The present retrospective cohort study was conducted at a single center. After excluding 41 patients, a total of 541 patients were included in the final model construction and subsequent analysis. The patients were randomly divided into two groups at a 7:3 ratio: training group (n = 378) and validation group (n = 163). The least absolute shrinkage and selection operator (LASSO) regression was used to identify the risk factors in the training group. Then, the identified factors were used to develop the RSF and CPH regression models. The predictive ability of the model was assessed using the concordance index (C-index). The accuracy of the model predictions was evaluated using the receiver operating characteristic curve (ROC) and area under the receiver operating characteristic curve (AUC). The clinical practicality of the model was measured by decision curve analysis (DCA), and the overall performance of the model was evaluated using the Brier score. The RSF model was visually represented using the Shapley additive explanations (SHAP) framework. Then, the RSF, CPH regression, and albumin-bilirubin (ALBI) grade models were compared. The following variables were examined by LASSO regression: alpha fetoprotein (AFP), gamma-glutamyl transpeptidase to platelet ratio (GPR), blood transfusion (BT), microvascular invasion (MVI), large vessel invasion (LVI), Edmondson-Steiner (ES) grade, liver capsule invasion (LCI), satellite nodule (SN), and Barcelona clinic liver cancer (BCLC) grade. Then, a RSF model was developed using 500 trees, and the variable importance (VIMP) ranking was MVI, LCI, SN, BT, BCLC, ESG, AFP, GPR and LVI. After these aforementioned factors were applied, the RSF and CPH regression models were developed and compared using the ALBI grade model. The C-index for the RSF model (0.896 and 0.798, respectively) outperformed that of the CPH regression model (0.803 and 0.772, respectively) and ALBI grade model (0.517 and 0.515, respectively), in both the training and validation groups. Three time points were selected to assess the predictive capabilities of these models: 6, 12 and 18 months. For the training group, the AUC value for the RSF model at 6, 12 and 18 months was 0.971 (95% CI: 0.955-0.988), 0.919 (95% CI: 0.887-0.951) and 0.899 (95% CI: 0.867-0.932), respectively. For the validation cohort, the AUC value for the RSF model at 6, 12 and 18 months was 0.830 (95% CI: 0.728-0.932), 0.856 (95% CI: 0.787-0.924) and 0.832 (95% CI: 0.764-0.901), respectively. The AUC values were higher in the RSF model, when compared to the CPH regression model and ALBI grade model, in both groups. The DCA results revealed that the net clinical benefits associated to the RSF model were superior to those associated to the CPH regression model and ALBI grade model in both groups, suggesting a higher level of clinical utility in the RSF model. The Brier score for the RSF model at 6, 12 and 18 months was 0.062, 0.125 and 0.178, respectively, in the training group, and 0.111, 0.128 and 0.149, respectively, in the validation group. In summary, the RSF model demonstrated superior performance, when compared to the CPH regression model and ALBI grade model. Furthermore, the RSF model demonstrated superior predictive ability, accuracy, clinical practicality, and overall performance, when compared to the CPH regression model and ALBI grade model. In addition, the RSF model was able to successfully stratify patients into three distinct risk groups (low-risk, medium-risk and high-risk) in both groups (p < 0.001). The RSF model demonstrates efficacy in predicting early recurrence following HCC surgery, exhibiting superior performance, when compared to the CPH regression model and ALBI grade model. For patients undergoing HCC surgery, the RSF model can serve as a valuable tool for clinicians to postoperatively stratify patients into distinct risk categories, offering guidance for subsequent follow-up care.

Random survival forests-based survival prediction for spinal chordomas.

BackgroundElderly patients with sepsis have many comorbidities, and the clinical reaction is not obvious. Thus, clinical treatment is difficult. We planned to use the laboratory test results and comorbidities of elderly patients with sepsis from a large-scale public database Medical Information Mart for Intensive Care (MIMIC) IV to build a random survival forest (RSF) model and to evaluate the model’s predictive value for these patients.MethodsClinical information of elderly patients with sepsis in MIMIC IV database was collected retrospectively. Machine learning (RSF) was used to select the top 30 variables in the training cohort to build the final RSF model. The model was compared with the traditional scoring systems SOFA, SAPSII, and APSIII. The performance of the model was evaluated by C index and calibration curve.ResultsA total of 6,503 patients were enrolled in the study. The top 30 important variables screened by RSF were used to construct the final RSF model. The new model provided a better C-index (0.731 in the validation cohort). The calibration curve described the agreement between the predicted probability of RSF model and the observed 30-day survival.ConclusionsWe constructed a prognostic model to predict a 30-day mortality risk in elderly patients with sepsis based on machine learning (RSF algorithm), and it proved superior to the traditional scoring systems. The risk factors affecting the patients were also ranked. In addition to the common risk factors of vasopressors, ventilator use, and urine output. Newly added factors such as RDW, type of ICU unit, malignant cancer, and metastatic solid tumor also significantly influence prognosis.

BackgroundThe present study aimed to explore the application value of random survival forest (RSF) model and Cox model in predicting the progression-free survival (PFS) among patients with locoregionally advanced nasopharyngeal carcinoma (LANPC) after induction chemotherapy plus concurrent chemoradiotherapy (IC + CCRT).MethodsEligible LANPC patients underwent magnetic resonance imaging (MRI) scan before treatment were subjected to radiomics feature extraction. Radiomics and clinical features of patients in the training cohort were subjected to RSF analysis to predict PFS and were tested in the testing cohort. The performance of an RSF model with clinical and radiologic predictors was assessed with the area under the receiver operating characteristic (ROC) curve (AUC) and Delong test and compared with Cox models based on clinical and radiologic parameters. Further, the Kaplan-Meier method was used for risk stratification of patients.ResultsA total of 294 LANPC patients (206 in the training cohort; 88 in the testing cohort) were enrolled and underwent magnetic resonance imaging (MRI) scans before treatment. The AUC value of the clinical Cox model, radiomics Cox model, clinical + radiomics Cox model, and clinical + radiomics RSF model in predicting 3- and 5-year PFS for LANPC patients was [0.545 vs 0.648 vs 0.648 vs 0.899 (training cohort), and 0.566 vs 0.736 vs 0.730 vs 0.861 (testing cohort); 0.556 vs 0.604 vs 0.611 vs 0.897 (training cohort), and 0.591 vs 0.661 vs 0.676 vs 0.847 (testing cohort), respectively]. Delong test showed that the RSF model and the other three Cox models were statistically significant, and the RSF model markedly improved prediction performance (P < 0.001). Additionally, the PFS of the high-risk group was lower than that of the low-risk group in the RSF model (P < 0.001), while comparable in the Cox model (P > 0.05).ConclusionThe RSF model may be a potential tool for prognostic prediction and risk stratification of LANPC patients.

BackgroundWilms tumor (WT) is the most common malignant renal tumor in children. Despite advances in treatment, accurate prediction of the long-term prognosis remains challenging. Various Cox regression-based models have been developed to assess WT survival rates; however, there is a pressing need for more precise tools.MethodsData from the SEER database (2000–2021) and external validation data from Chongqing Medical University Children’s Hospital were utilized. Key prognostic factors for children with WT were identified via last absolute shrinkage and selection operator (LASSO) regression, which was subsequently used to construct the Random Survival Forest(RSF) model for long-term survival prediction. SHAP were applied to enhance the interpretability of the model. The model performance was compared to that of conventional Cox models via calibration curves, the Concordance index (C-index), the net reclassification index (NRI), and the integrated discrimination index (IDI).ResultsWe included 1,629 children with WT from the SEER database and externally validated the model via data from 169 children at Children’s Hospital of Chongqing Medical University(CHCMU). Kaplan‒Meier curves revealed higher mortality rates for Chinese children with WT than for their counterparts in the United States. LASSO regression identified six key variables for the development of the RSF and Cox models. The SHAP method was utilized to rank these variables in descending order of importance: tumor stage, age, lymph node density(LND), tumor metastasis, number of positive lymph nodes, and laterality (unilateral/bilateral). The RSF model demonstrated superior predictive performance and generalizability, as indicated by Brier scores, calibration curves, AUC curves, and risk curves. Moreover, the RSF model significantly outperformed the Cox model in terms of prediction accuracy (C-index: 0.868 vs. 0.759), with substantial improvements in the NRI and IDI (P < 0.01). Decision curve analysis also revealed that the RSF model provided a greater net benefit at 3, 5, and 7 years than did the Cox model, which underscored the greater clinical utility of the RSF model. Sensitivity analysis based on imputed data confirmed the robustness of the model, with consistent predictor selection and comparable performance metrics, further supported the stability and reliability of the RSF framework.ConclusionWe successfully developed a robust machine learning model that accurately assesses key prognostic factors affecting the long-term survival of children with WT. This model offers substantial clinical value for risk stratification and can assist clinicians in making more informed treatment decisions. By applying SHAP analysis, physicians can better understand the critical factors influencing WT prognosis and tailor intervention strategies more precisely.Supplementary InformationThe online version contains supplementary material available at 10.1007/s12672-025-03645-2.

This study aimed to develop and evaluate an artificial intelligence model to predict 28-day mortality of pneumonia patients at the time of disposition from emergency department (ED). A multicenter retrospective study was conducted on data from pneumonia patients who visited the ED of a tertiary academic hospital for 8 months and from the Medical Information Mart for Intensive Care (MIMIC-IV) database. We combined chest X-ray information, clinical data, and CURB-65 score to develop three models with the CURB-65 score as a baseline. A total of 2,874 ED visits were analyzed. The RSF model using CXR, clinical data and CURB-65 achieved a C-index of 0.872 in test set, significantly outperforming the CURB-65 score. This study developed a prediction model in pneumonia patients' prognosis, highlighting the potential for supporting clinical decision making in ED through multi-modal clinical information.

Background and Objectives The purpose of this study was to analyze the survival data of salivary gland cancer (SGCs) patients to construct machine learning and deep learning models that can predict survival and use them to stratify SGC patients according to risk estimate.Subjects and Method We retrospectively analyzed the clinicopathologic data from 460 patients with SGCs from 2006 to 2018.Results In Cox proportional hazard (CPH) model, pM, stage, lymphovascular invasion, lymph node ratio, and age exhibited significant correlation with patient’s survival. In the CPH model, the c-index value for the training set was 0.85, and that for the test set was 0.81. In the Random Survival Forest model, the c-index value for the training set was 0.86, and that for the test set was 0.82. Stage and age exhibited high importance in both the Random Survival Forest and CPH models. In the deep learning-based model, the c-index value was 0.72 for the training set and 0.72 for the test set. Among the three models mentioned above, the Random Survival Forest model exhibited the highest performance in predicting the survival of SGC patients.Conclusion A survival prediction model using machine learning techniques showed acceptable performance in predicting the survival of SGC patients. Although large-scale clinical and multicenter studies should be conducted to establish more powerful predictive model, we expect that individualized treatment can be realized according to risk stratification made by the machine learning model.

Background Adverse drug reactions (ADRs) increase health-care resource utilization, including that for emergency department (ED) visits. However, cost analyses of ADRs resulting in ED visits are scarce. Therefore, we aimed to estimate the direct medical costs before and after ADR occurrence and analyzed the cost-driving factors. Methods The ADR cases were identified by a retrospective review of medical records of patients who visited the ED of three tertiary hospitals in South Korea from July to December 2014. The direct medical cost was estimated by the difference in costs six months before and after the ED visit. A generalized linear model was used to identify the ADR-associated cost-driving factors. Results The mean cost per ADR increased by 26.1% (±SD = 4.3) during the six-month follow-up compared with that during the six months before the ED visit (p < 0.05). Preventable ADRs accounted for approximately 19.9% of the cost increase among all ADR cases. The regression analysis revealed that ‘ADR-related hospitalization’ was a significant (p < 0.05) factor leading to an increase in the direct medical costs. Conclusion Drug-related ED visits increase the burden on health insurance systems and patients’ out-of-pocket costs, mostly due to the hospitalization costs.

e13554 Background: Quantitative 18F-NaF PET/CT imaging metrics have been shown to be prognostic in metastatic prostate cancer (mPC) patients. However, previous studies have shown conflicting results in which metrics could be prognostic. This study investigates if current methods from literature generalize to external datasets and explores which combination of features are necessary to for survival models to generalize across datasets. Methods: Imaging and progression-free survival (PFS) data from 118 patients with mPC from four separate prospective clinical trials were gathered retrospectively. Patients received 18F-NaF PET/CT imaging at baseline and at follow-up, between eight and thirteen weeks. TRAQinform IQ technology (AIQ Solutions) was used to identify, segment, and track individual lesions from baseline to follow-up. Eighty-four imaging features were extracted from each patient and sorted into baseline, follow-up, response, patient-level (no inter-lesion comparison), and intrapatient heterogeneity (comparisons between lesions). The data was split into two training and testing sets, 44 patients from one study and 73 patients from the remaining 3 studies. As they can utilize large number of inputs without overfitting, random survival forest (RSF) models were chosen to evaluate performance of feature sets in predicting PFS. Different combinations of features were used as inputs to RSF models to compare single timepoint features with response features and patient-level features with intrapatient heterogeneity features. The performance of the RSF models, together with other methods identified in literature, were evaluated in each dataset using Kaplan-Meier analysis for categorical variables and the c-index for continuous variables. Results: No patient-level imaging features highlighted by literature displayed significant association to PFS across all four clinical trials (c-index &lt; 0.62 in at least one dataset). Other criteria from literature did not generalize across all datasets (P &gt; 0.05). The RSF model trained with all features had high c-indices in all four datasets (range: 0.66-0.80). RSF models built with response features (min: 0.63) performed better on average than models built with features obtained from single timepoints (min: 0.55). Patient-level features (min: 0.56) were not sufficient in all testing scenarios as compared to intrapatient heterogeneity features (min: 0.63). Conclusions: The candidate imaging biomarkers from previous 18F-NaF PET/CT imaging studies of mPC patients did not generalize across all datasets. Incorporating response and heterogeneity features with single-timepoint and patient-level features resulted in RSF prediction models which were generalizable across all datasets. Use of such models hold promise for improving outcome prediction in mPC patients.

The authors sought to describe the epidemiology of and risk factors for recurrent and high-frequency use of the emergency department (ED) by children. This was a retrospective cohort study using a database of children aged 0 to 17 years, inclusive, presenting to 22 EDs of the Pediatric Emergency Care Applied Research Network (PECARN) during 2007, with 12-month follow-up after each index visit. ED diagnoses for each visit were categorized as trauma, acute medical, or chronic medical conditions. Recurrent visits were defined as any repeat visit; high-frequency use was defined as four or more recurrent visits. Generalized estimating equations (GEEs) were used to measure the strength of associations between patient and visit characteristics and recurrent ED use. A total of 695,188 unique children had at least one ED visit each in 2007, with 455,588 recurrent ED visits in the 12 months following the index visits. Sixty-four percent of patients had no recurrent visits, 20% had one, 8% had two, 4% had three, and 4% had four or more recurrent visits. Acute medical diagnoses accounted for most visits regardless of the number of recurrent visits. As the number of recurrent visits per patient rose, chronic diseases were increasingly represented, with asthma being the most common ED diagnosis. Trauma-related diagnoses were more common among patients without recurrent visits than among those with high-frequency recurrent visits (28% vs. 9%; p<0.001). High-frequency recurrent visits were more often within the highest severity score classifications. In multivariable analysis, recurrent visits were associated with younger age, black or Hispanic race or ethnicity, and public health insurance. Risk factors for recurrent ED use by children include age, race and ethnicity, and insurance status. Although asthma plays an important role in recurrent ED use, acute illnesses account for the majority of recurrent ED visits.

Improving Quality of Asthma Care After Emergency Department Discharge: Evidence Before Action

Many patients are discharged from the emergency department (ED) with an incomplete understanding of the information needed to safely care for themselves at home. Patients have demonstrated particular difficulty in understanding post-ED care instructions (including medications, home care, and follow-up). The objective of this study was to further characterize these deficits and identify gaps in knowledge that may place the patient at risk for complications or poor outcomes. This was a prospective cohort, phone interview-based study of 159 adult English-speaking patients within 24 to 36 hours of ED discharge. Patient knowledge was assessed for five diagnoses (ankle sprain, back pain, head injury, kidney stone, and laceration) across the following five domains: diagnosis, medications, home care, follow-up, and return instructions. Knowledge was determined based on the concordance between direct patient recall and diagnosis-specific discharge instructions combined with chart review. Two authors scored each case independently and discussed discrepancies before providing a final score for each domain (no, minimal, partial, or complete comprehension). Descriptive statistics were used for the analyses. The study population was 50% female with a median age of 41 years (interquartile range [IQR] = 29 to 53 years). Knowledge deficits were demonstrated by the majority of patients in the domain of home care instructions (80%) and return instructions (79%). Less frequent deficits were found for the domains of follow-up (39%), medications (22%), and diagnosis (14%). Minimal or no understanding in at least one domain was demonstrated by greater than two-thirds of patients and was found in 40% of cases for home care and 51% for return instructions. These deficits occurred less frequently for domains of follow-up (18%), diagnosis (3%), and medications (3%). Patients demonstrate the most frequent knowledge deficits for home care and return instructions, raising significant concerns for adherence and outcomes.

There have been no reports about the application of random survival forest (RSF) model to predict disease progression of HIV-associated B-cell lymphoma. A total of 44 patients with HIV-associated B-cell lymphoma who were referred to Nanjing Second Hospital from 2012 to 2019 were included. The RSF model was used to find predictors of survival, and the results of the RSF model were compared with those of the Cox model. The data were analyzed using R software (version 4.1.1). One-, 2-, and 3-year survival rates were 74.5%, 57.7%, and 48.6%, respectively, and the median survival was 59.0 months. The first 3 most important predictors of survival included lactate dehydrogenase (LDH), absolute monocyte count (AMC), and white blood cells (WBCs) count. The median survival of high-risk patients was only 4.0 months. Areas under the curve (AUCs) of the RSF model remained at more than 0.90 at 1, 2, and 3 years. The RSF model displayed a lower prediction error rate (21.9%) than the Cox model (25.4%). Lactate dehydrogenase, AMC, and WBCs count are the most important prognostic predictors for patients with HIV-associated B-cell lymphoma. Much larger prospective and/or multicentre studies are required to validtae this RSF model.