Reducing preventable hospital re-admissions in Sickle Cell Disease (SCD) could potentially improve outcomes and decrease healthcare costs. In a retrospective study of electronic health records, we hypothesized Machine-Learning (ML) algorithms may outperform standard re-admission scoring systems (LACE and HOSPITAL indices). Participants (n = 446) included patients with SCD with at least one unplanned inpatient encounter between January 1, 2013, and November 1, 2018. Patients were randomly partitioned into training and testing groups. Unplanned hospital admissions (n = 3299) were stratified to training and testing samples. Potential predictors (n = 486), measured from the last unplanned inpatient discharge to the current unplanned inpatient visit, were obtained via both data-driven methods and clinical knowledge. Three standard ML algorithms, Logistic Regression (LR), Support-Vector Machine (SVM), and Random Forest (RF) were applied. Prediction performance was assessed using the C-statistic, sensitivity, and specificity. In addition, we reported the most important predictors in our best models. In this dataset, ML algorithms outperformed LACE [C-statistic 0Á6, 95% Confidence Interval (CI) 0Á57-0Á64] and HOSPITAL (C-statistic 0Á69, 95% CI 0Á66-0Á72), with the RF (C-statistic 0Á77, 95% CI 0Á73-0Á79) and LR (C-statistic 0Á77, 95% CI 0Á73-0Á8) performing the best. ML algorithms can be powerful tools in predicting re-admission in high-risk patient groups.
Background: Sickle cell disease (SCD) is the most common inherited hemoglobinopathy worldwide. The pathophysiology of the disease results in end organ damage which leads to morbidity and mortality. In a subset of patients, SCD-related complications have resulted in prolonged hospitalizations and increased frequency of 30-day hospital readmissions. In the era of value-based health care, hospital quality metrics and reimbursements are generated based on strategic health care utilization. Therefore, being able to identify early unplanned hospital readmissions is critical in managing health care expenditure. Objective: To develop machine learning algorithms for predicting the 30-day unplanned readmission risk of SCD patients and to compare the predictive power of machine learning models against standard hospital readmission scoring systems. Methods: We analyzed retrospective real-world electronic health records (EHR) data for patients with SCD at our institution from January 1, 2013- November 1, 2018. The raw data set contained 2824 unique SCD patients from across 5 hospitals within the University of Pittsburgh Medical Center. After preprocessing using our inclusion criteria, our cohort included 3299 admissions comprising of 446 adult SCD patients. Features extracted from the EHR data were reduced and regrouped using both data-driven methods and clinical knowledge, resulting in 486 unique features. Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF) were applied to predict for 30-day unplanned hospital readmissions in SCD. Prediction performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity and specificity. We compared our results against standard hospital readmission prediction tools such as LACE and HOSPITAL indices. Results: We randomly selected the inpatient admissions incurred by 30 percent of the 195 return patients and 251 nonreturn patients to be included in the testing set (n = 134); the training set contained the inpatient admissions incurred by the remaining 211 patients. Thus, our training and testing sets contained similar demographic information, predictors, and outcomes. The average number of admissions was 7.40 (12.90) for the 446 patients, and 14.47 (16.97) for the 195 patients who had 30-day readmissions. Since the number of samples in our study is comparatively small, our results might be sensitive to the training and testing splits. To address this problem, we performed 100 different training and testing splits and averaged the resulting 100 AUCs. Figure 1 summarizes the two performance metrics of each model. The two benchmark prediction tools, LACE and HOSPITAL, have AUCs of 0.56 (95%CI 0.52-0.60) and 0.63 (95%CI 0.59-0.67), respectively. Notably, all three machine learning algorithms outperformed both benchmarks. The RF was the best machine learning model in prediction of hospital readmissions, as reported in similar machine learning studies (Deschepper et al. 2019), with an AUC of 0.73 (95%CI 0.69-0.76). Table 1 summarizes the sensitivity and specificity of our RF model. Conclusion: Machine learning algorithms outperformed the standard hospital readmission risk scoring systems, LACE and HOSPITAL, by a large margin in a real world data set of SCD patients at a single institution. In particular, machine learning algorithms were able to identify important variables that are underrepresented in the traditional risk scoring systems (Figure 2). The use of machine learning algorithms can be a powerful tool in providing valuable insight towards health care expenditure and resource allocation in high risk patient groups. Disclosures No relevant conflicts of interest to declare.
Background: Recent reports have shown that bone marrow-derived stem cell may contribute to islet regeneration. The goal of our study was to evaluate the safety and efficacy of ABMMC transplantation for patients with IDM. Methods: From June 2005 to January 2007, 28 consecutive patients: 8 Type 1 IDM (T1DM) and 20 Type 2 IDM (T2IDM); who were receiving maximal medical therapy including insulin treatment for 5 years before enrollment. Median time of disease for T2IDM patients was 13 years, without pancreatic islet auto-antibodies. After IRB approval and signed informed consent, bone marrow was harvested and ABMMC were isolated and infused directly into the pancreas via splenic artery using endovascular catheters. Glucose, glycosylated HbA1c and C peptide were measure before and after transplantation. HOMA2 Calculator v2.2 was used to calculated IR and % B (*if Glucose: 3.0 to 25.0 mmol/L and C peptide: 0.2 to 3.5 nmol/L). Results: There were no study related complications. At 1 year follow-up, mean daily insulin requirement was the same in group T1DM and significantly reduced in group T2IDM, from 42.5 to 4.5 U/d (t=7.94, p<0.001). Ten of the twenty (50%) T2IDM established complete insulin independence. Data in table 1. Table 1: Median values PRE POST t p T2IDM (n=20) Fasting Glucose (mmol/L) 10.8 6.6 3.98 0.01 Glycosylated HbA1c (%) 9.6 8.1 3.98 0.01 C peptide (nmol/L) 0.5 0.84 5.11 < 0.01 HOMA 2 IR (n=17)* 2.2 2.26 0.94 0.92 HOMA 2 %B (n=17)* 42.4 130.2 4.9 < 0.01 T1DM (n=8) Fasting Glucose (mmol/L) 10.1 11.1 1.382 0.21 Glycosylated HbA1c (%) 8.7 8.7 0.45 0.66 C peptide (nmol/L) 0.17 0.16 1.00 0.35 Conclusions: The use of ABMMC transplantation for T1DM and T2IDM is safe. In this pilot study, only T2IDM patients have significant improvement in pancreatic function demostrated by better glycemic and HbA1c control, and are associated with a significant independence of the insulin. This has formed for a randomized multi-center study which is currently in progress.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.