A hospital wide predictive model for unplanned readmission using hierarchical ICD data

BACKGROUND AND OBJECTIVE

Hospitals already acquire a large amount of data, mainly for administrative, billing and registration purposes. Tapping on these already available data for additional purposes, aiming at improving care, without significant incremental effort and cost. This potential of secondary patient data is explored through modeling administrative and billing data, as well as the hierarchical structure of pathology codes of the International Classification of Diseases (ICD) in the prediction of unplanned readmissions, as a clinically relevant outcome parameter that can be impacted on in a quality improvement program.

METHODS

In this single-center, hospital-wide observational cohort study, we included all adult patients discharged in 2016 after applying an exclusion protocol (n = 29,702). In addition to administrative variables, such as age and length of stay, structured pathology data were taken into account in predictive models. As a first research question, we compared logistic regression against penalized logistic regression, gradient boosting and Random Forests to predict unplanned readmission. As a second research goal, we investigated the level of hierarchy within the pathology data needed to achieve the best accuracy. Finally, we investigated which prediction variables play a prominent role in predicting hospital readmission. The performance of all models was evaluated using the Area Under the ROC Curve (AUC) measure.

RESULTS

All models have the best predictive results using Random Forests. An added value of 7% is observed compared to a baseline method such as logistic regression. The best model, based on Random Forests, achieved an AUC of 0.77, using the diagnosis category and procedure code as lowest level of the hierarchical pathology data.

CONCLUSIONS

The most accurate model to predict hospital wide unplanned readmission is based on Random Forests and includes the ICD hierarchy, especially diagnosis category. Such an approach lowers the number of predictor variables and yields a higher interpretability than a model based on a detailed diagnosis. The performance of the model proved high enough to be used as a decision support tool.

Survival and function of mesenchymal stem cells (MSCs) depend on glucose to overcome exposure to long-term, severe and continuous hypoxia

Use of mesenchymal stem cells (MSCs) has emerged as a potential new treatment for various diseases but has generated marginally successful results. A consistent finding of most studies is massive death of transplanted cells. The present study examined the respective roles of glucose and continuous severe hypoxia on MSC viability and function with respect to bone tissue engineering. We hereby demonstrate for the first time that MSCs survive exposure to long-term (12 days), severe (pO₂ < 1.5 mmHg) hypoxia, provided glucose is available. To this end, an in vitro model that mimics the hypoxic environment and cell-driven metabolic changes encountered by grafted sheep cells was established. In this model, the hallmarks of hypoxia (low pO₂, hypoxia inducible factor-1α expression and anaerobic metabolism) were present. When conditions switched from hypoxic (low pO₂) to ischemic (low pO₂ and glucose depletion), MSCs exhibited shrinking, decreased cell viability and ATP content due to complete exhaustion of glucose at day 6; these results provided evidence that ischemia led to the observed massive cell death. Moreover, MSCs exposed to severe, continuous hypoxia, but without any glucose shortage, remained viable and maintained both their in vitro proliferative ability after simulation with blood reperfusion at day 12 and their in vivo osteogenic ability. These findings challenge the traditional view according to which severe hypoxia per se is responsible for the massive MSC death observed upon transplantation of these cells and provide evidence that MSCs are able to withstand exposure to severe, continuous hypoxia provided that a glucose supply is available.