Opis: Different studies have demonstrated the importance of comorbidities to better understand the origin and evolution of medical complications. This study focuses on improvement of the predictive model interpretability based on simple logical features representing comorbidities. We use group lasso based feature interaction discovery followed by a post-processing step, where simple logic terms are added. In the final step, we reduce the feature set by applying lasso logistic regression to obtain a compact set of non-zero coefficients that represent a more comprehensible predictive model. The effectiveness of the proposed approach was demonstrated on a pediatric hospital discharge dataset that was used to build a readmission risk estimation model. The evaluation of the proposed method demonstrates a reduction of the initial set of features in a regression model by 72%, with a slight improvement in the Area Under the ROC Curve metric from 0.763 (95% CI: 0.755%0.771) to 0.769 (95% CI: 0.761%0.777). Additionally, our results show improvement in comprehensibility of the final predictive model using simple comorbidity based terms for logistic regression.Ključne besede: predictive models, logistic regression, readmission classification, comorbiditiesObjavljeno: 19.06.2017; Ogledov: 95; Prenosov: 6 Celotno besedilo (1,13 MB)
Opis: The increasing availability of electronic health care records has provided remarkable progress in the field of population health. In particular the identification of disease risk factors has flourished under the surge of available data. Researchers can now access patient data across a broad range of demographics and geographic locations. Utilizing this Big healthcare data researchers have been able to empirically identify specific high-risk conditions found within differing populations. However to date the majority of studies approached the issue from the top down, focusing on the prevalence of specific diseases within a population. Through our work we demonstrate the power of addressing this issue bottom-up by identifying specifically which diseases are higher-risk for a specific population. In this work we demonstrate that network-based analysis can present a foundation to identify pairs of diagnoses that differentiate across population segments. We provide a case study highlighting differences between high and low income individuals in the United States. This work is particularly valuable when addressing population health management within resource-constrained environments such as community health programs where it can be used to provide insight and resource planning into targeted care for the population served.Ključne besede: population screening, risk factors, network analysisObjavljeno: 23.06.2017; Ogledov: 83; Prenosov: 2 Celotno besedilo (743,53 KB)
Opis: Background: Reduction of readmissions after discharge represents an important challenge for many hospitals and has attracted the interest of many researchers in the past few years. Most of the studies in this field focus on building cross-sectional predictive models that aim to predict the occurrence of readmission within 30-days based on information from the current hospitalization. The aim of this study is demonstration of predictive performance gain obtained by inclusion of information from historical hospitalization records among morbidly obese patients.
Methods: The California Statewide inpatient database was used to build regularized logistic regression models for prediction of readmission in morbidly obese patients (n = 18,881). Temporal features were extracted from historical patient hospitalization records in a one-year timeframe. Five different datasets of patients were prepared based on the number of available hospitalizations per patient. Sample size of the five datasets ranged from 4,787 patients with more than five hospitalizations to 20,521 patients with at least two hospitalization records in one year. A 10-fold cross validation was repeted 100 times to assess the variability of the results. Additionally, random forest and extreme gradient boosting were used to confirm the results.
Results: Area under the ROC curve increased significantly when including information from up to three historical records on all datasets. The inclusion of more than three historical records was not efficient. Similar results can be observed for Brier score and PPV value. The number of selected predictors corresponded to the complexity of the dataset ranging from an average of 29.50 selected features on the smallest dataset to 184.96 on the largest dataset based on 100 repetitions of 10-fold cross-validation.
Discussion: The results show positive influence of adding information from historical hospitalization records on predictive performance using all predictive modeling techniques used in this study. We can conclude that it is advantageous to build separate readmission prediction models in subgroups of patients with more hospital admissions by aggregating information from up to three previous hospitalizations.Ključne besede: readmission prediction, predictive modelling, temporal dataObjavljeno: 02.08.2017; Ogledov: 107; Prenosov: 5 Celotno besedilo (1,10 MB)