Medical decision making and machine learning application in medicine considers hospital readmission rate as one of the most important hospital quality indicators. The main reason is that unplanned hospital readmissions have high human and financial consequences. This motivated a number of applications to propose models that are trying to predict readmission as a single label, binary problem (patient will be readmitted or not). However, such models do not answer the question extit{“why is a patient at risk for readmission”}. Our objective is to develop interpretable predictive models that can explain why patient is likely to be readmitted (with which diagnoses). which will help making the shift from predictive to prescriptive exploitation of machine learning models application in real medical practice.We address this problem utilizing Predictive Clustering Trees for multiā€“label and hierarchical multi-label classification. Both decision tree-like (multi-label and hierarchical multi-label) models enable not only prediction of readmission risk, but also prediction of the causes for potential readmission. In this case, we predict diagnoses and symptoms that are likely to appear on readmitting for specific patient. For the hierarchical multi-label classificationtask we inspect the influence of data-driven and expert driven hierarchies on predictive performance. Experiments are conducted on pediatric population of patients from state of California.The results are thoroughly evaluated by example-based, label-based and ranking-based performance measures. Additionally, results are interpreted and discussed by medical doctors. Usage of structure improved accuracy from 21.9\% to 65.2\%. Drastic improvement in performance is visible in other measures such as precision, recall, ranking loss etc. It is shown that integration of structure (both data and knowledge driven) increases predictive performance compared to flat models and that multi-label classification models based on Predictive Clustering Trees allow building of accurate and highly interpretable solutions.

x

Hi!
I'm Erica!

Would you like to get a custom essay? How about receiving a customized one?

Check it out