Pneumonia readmission prevention

Abstract

A decision support tool is provided for discharging a patient by predicting the probability of a patient's readmission with pneumonia based on information available prior to discharge. The information used to make the prediction may include labs, vitals, diagnoses, and medications from prior encounters and from the current encounter. At least some of this information may be used to compute one or more severity metrics for the patient, such as a cancer score, an epilepsy or seizure score, a pneumococcal pneumonia score, and an instability score, to be input into one or more prediction models. An ensemble of machine learning models may be applied to the patient information to generate a prediction of that patient being readmitted with pneumonia within a future time interval. Based on the prediction, one or more intervening actions may be initiated to reduce the probability of readmission.

What is claimed is: 
     
         1 . Computer storage media having computer-executable instructions embodied thereon that, when executed, provide a method for implementing a decision support tool for pneumonia patients, the method comprising:
 generating a prediction of a patient being readmitted for pneumonia; and   based on the prediction of whether the patient will be readmitted for pneumonia, initiating one or more intervening actions prior to discharge to reduce a likelihood of readmission, the one or more intervening actions performed by automatically modifying computer code executed in a healthcare software program for treating the patient and/or discharging planning, thereby transforming the program at runtime.   
     
     
         2 . The computer storage media of  claim 1 , further comprising receiving patient information for a patient being treated for pneumonia. 
     
     
         3 . The computer storage media of  claim 2 , further comprising applying an ensemble of models to the patient information to generate the prediction of the patient being readmitted for pneumonia within a future time interval. 
     
     
         4 . The computer storage media of  claim 3 , wherein the patient information used to generate the prediction is available prior to discharge of the patient. 
     
     
         5 . The computer storage media of  claim 1 , further comprising receiving reference information on a reference population. 
     
     
         6 . The computer storage media of  claim 5 , further comprising selecting a plurality of features for predicting pneumonia readmisison, wherein selecting the plurality of features comprises applying sequential modeling using a plurality of feature-selection models to a potential feature pool based on reference information available prior to discharge. 
     
     
         7 . The computer storage media of  claim 6 , further comprising training a plurality of prediction models to predict a likelihood that a patient will be readmitted with pneumonia within a future time interval, each prediction model being trained on a different set of features from the plurality of features. 
     
     
         8 . The computer storage media of  claim 7 , further comprising generating a prediction that a target patient will be readmitted with pneumonia within the future time interval using the plurality of prediction models, wherein each prediction model provides a probability and wherein the probabilities from the plurality of prediction models are combined to generate the prediction, wherein the prediction is generated prior to discharge of the target patient. 
     
     
         9 . The computer storage media of  claim 8 , further comprising:
 dividing the reference information into categorical features and continuous features; and   training a first gradient tree model using the categorical features and a second gradient tree model using the continuous features.   
     
     
         10 . The computer storage media of claim  0 , further comprising:
 identifying potential categorical features from the first gradient tree model and potential continuous features from the second gradient tree model; and   combining the potential categorical features, the potential continuous features, and one or more severity metrics to create the potential feature pool.   
     
     
         11 . The computer storage media of  claim 10 , wherein the plurality of prediction models comprises an ensemble of ten linear regression models and wherein the plurality of feature-selection models comprises an adaptive GLMnet, and further wherein the prediction that the target patient will be readmitted with pneumonia within the future time interval is used to automatically initiate one or more intervening actions to reduce the likelihood of readmission. 
     
     
         12 . A computer system for providing a discharge decision support tool for reducing readmissions due to pneumonia, the system comprising:
 one or more processors;   computer storage media storing computer-useable instructions that, when executed by the one or more processors, implement a method comprising:
 generating a prediction of a patient being readmitted for pneumonia; and 
 based on the prediction of whether the patient will be readmitted for pneumonia, initiating one or more intervening actions prior to discharge to reduce a likelihood of readmission, the one or more intervening actions performed by automatically modifying computer code executed in a healthcare software program for treating the patient and/or discharging planning, thereby transforming the program at runtime. 
   
     
     
         12 . The computer system of  claim 11 , further comprising receiving reference information on a reference population. 
     
     
         13 . The computer system of  claim 12 , further comprising selecting a plurality of features for predicting pneumonia readmisison, wherein selecting the plurality of features comprises applying sequential modeling using a plurality of feature-selection models to a potential feature pool based on reference information available prior to discharge. 
     
     
         14 . The computer system of  claim 13 , further comprising:
 training a plurality of prediction models to predict a likelihood that a patient will be readmitted with pneumonia within a future time interval, each prediction model being trained on a different set of features from the plurality of features; and   generating a prediction that a target patient will be readmitted with pneumonia within the future time interval using the plurality of prediction models, wherein each prediction model provides a probability and wherein the probabilities from the plurality of prediction models are combined to generate the prediction, wherein the prediction is generated prior to discharge of the target patient.   
     
     
         15 . The computer system of  claim 14 , further comprising:
 dividing the reference information into categorical features and continuous features;   training a first gradient tree model using the categorical features and a second gradient tree model using the continuous features;   identifying potential categorical features from the first gradient tree model and potential continuous features from the second gradient tree model; and   combining the potential categorical features, the potential continuous features, and one or more severity metrics to create the potential feature pool.   
     
     
         16 . The computer system of  claim 11 , wherein the plurality of prediction models comprises an ensemble of ten linear regression models and wherein the plurality of feature-selection models comprises an adaptive GLMnet, and further wherein the prediction that the target patient will be readmitted with pneumonia within the future time interval is used to automatically initiate one or more intervening actions to reduce the likelihood of readmission. 
     
     
         17 . A computerized method for providing a discharge decision support tool to reduce pneumonia readmissions, the method comprising:
 generating a prediction of a patient being readmitted for pneumonia; and   based on the prediction of whether the patient will be readmitted for pneumonia, initiating one or more intervening actions prior to discharge to reduce a likelihood of readmission, the one or more intervening actions performed by automatically modifying computer code executed in a healthcare software program for treating the patient and/or discharging planning, thereby transforming the program at runtime.   
     
     
         18 . The computerized method of  claim 17 , further comprising:
 receiving reference information on a reference population;   selecting a plurality of features for predicting pneumonia readmisison, wherein selecting the plurality of features comprises applying sequential modeling using a plurality of feature-selection models to a potential feature pool based on reference information available prior to discharge;   training a plurality of prediction models to predict a likelihood that a patient will be readmitted with pneumonia within a future time interval, each prediction model being trained on a different set of features from the plurality of features; and   generating a prediction that a target patient will be readmitted with pneumonia within the future time interval using the plurality of prediction models, wherein each prediction model provides a probability and wherein the probabilities from the plurality of prediction models are combined to generate the prediction, wherein the prediction is generated prior to discharge of the target patient.   
     
     
         19 . The computerized method of  claim 18 , wherein selecting the plurality of features further comprises determining the potential feature pool by:
 dividing the reference information into categorical features and continuous features;   training a first gradient tree model using the categorical features and a second gradient tree model using the continuous features;   identifying potential categorical features from the first gradient tree model and potential continuous features from the second gradient tree model; and   combining the potential categorical features, the potential continuous features, and one or more severity metrics to create the potential feature pool.   
     
     
         20 . The computerized method of  claim 19 , wherein the plurality of prediction models comprises an ensemble of ten linear regression models and wherein the plurality of feature-selection models comprises an adaptive GLMnet, and further wherein the prediction that the target patient will be readmitted with pneumonia within the future time interval is used to automatically initiate one or more intervening actions to reduce the likelihood of readmission.