Readmission risk assessment

Abstract

A readmission risk prediction model is generated and used for identifying patients having elevated risk of readmission and determining inpatient treatment and outpatient activities based on readmission risk. Readmission risk prediction models may be generated for a variety of different clinical conditions using logistic regression techniques. When a patient is admitted to a hospital, the patient's condition is identified and a corresponding readmission risk prediction model is employed to identify the patient's risk of readmission. The readmission risk may be presented to a clinician and employed to recommend interventions intended to treat the patient and reduce the probability of readmission for the patient. The patient's readmission risk may also be calculated after the patient has been discharged and used for planning outpatient activities for the patient.

What is claimed is: 
     
         1 . One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising:
 computing a readmission risk score for a patient previously discharged from a clinical facility;   determining an outpatient treatment recommendation based on the readmission risk score; and   providing the outpatient treatment recommendation for presentation to a clinician.   
     
     
         2 . The one or more computer storage media of  claim 1 , wherein determining the outpatient treatment recommendation based on the readmission risk score comprises comparing the readmission risk score against one or more predetermined thresholds and determining the outpatient treatment recommendation based on the comparison. 
     
     
         3 . The one or more computer storage media of  claim 1 , wherein determining the outpatient treatment recommendation based on the readmission risk score comprises determining to readmit the patient based on the readmission risk score exceeding a predetermined threshold. 
     
     
         4 . The one or more computer storage media of  claim 1 , wherein the outpatient treatment recommendation comprises at least one selected from the following:
 performing outpatient monitoring, scheduling outpatient appointments for the patient, providing in-home healthcare, and educating the patient on healthcare issues related to the patient's condition.   
     
     
         5 . The one or more computer storage media of  claim 1 , wherein determining the outpatient treatment recommendation based on the readmission risk score and providing the outpatient treatment recommendation for presentation to the clinician comprises determining that the patient has a high risk for readmission based on the readmission risk score and placing or maintaining the patient on a call list for high risk patients. 
     
     
         6 . The one or more computer storage media of  claim 1 , wherein the readmission risk score is computed using a readmission risk prediction model selected based on a patient condition for the patient. 
     
     
         7 . The one or more computer storage media of  claim 6 , wherein multiple patient conditions are identified for the patient, and wherein the readmission risk prediction model corresponds with the multiple patient conditions. 
     
     
         8 . The one or more computer storage media of  claim 6 , wherein the method further comprises:
 identifying a second patient condition for the patient; and   selecting a second readmission risk prediction model based on the second patient condition;   wherein the readmission risk score is computed using the readmission risk prediction model and the second readmission risk prediction model.   
     
     
         9 . The one or more computer storage media of  claim 1 , wherein the patient is identified as a high readmission risk based on the readmission risk score. 
     
     
         10 . The one or more computer storage media of  claim 1 , wherein the operations further comprise re-computing the readmission risk score and determining new outpatient treatment recommendations based on the recomputed readmission risk score. 
     
     
         11 . One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising:
 receiving clinically relevant data associated with a given clinical condition from a plurality of patient cases;   building a logistic regression model using the clinically relevant data; and   developing a readmission risk prediction model using the logistic regression model, the readmission risk prediction model being capable of calculating a readmission risk score for patients based on patient data, wherein a readmission risk score for a patient represents a probability of readmission for the patient.   
     
     
         12 . The one or more computer storage media of  claim 11 , wherein the operations further comprise testing the logistic regression model for model fit by performing a receiver-operating characteristic (ROC) area-under-the curve analysis. 
     
     
         13 . The one or more computer storage media of  claim 11 , wherein the operations further comprise repeating building a logistic regression model until the ROC area-under-the curve analysis satisfies a predetermined threshold. 
     
     
         14 . A computerized system comprising:
 one or more processors; and   one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to:   compute a readmission risk score for a patient previously discharged from a clinical facility;   determine an outpatient treatment recommendation based on the readmission risk score; and   provide the outpatient treatment recommendation for presentation to a clinician.   
     
     
         15 . The system of  claim 14 , wherein the outpatient treatment recommendation is determined based on the readmission risk score by comparing the readmission risk score against one or more predetermined thresholds and determining the outpatient treatment recommendation based on the comparison. 
     
     
         16 . The system of  claim 14 , wherein the outpatient treatment recommendation includes determining to readmit the patient based on the readmission risk score exceeding a predetermined threshold. 
     
     
         17 . The system of  claim 14 , wherein the outpatient treatment recommendation comprises at least one selected from the following: performing outpatient monitoring, scheduling outpatient appointments for the patient, providing in-home healthcare, and educating the patient on healthcare issues related to the patient's condition. 
     
     
         18 . The system of  claim 14 , wherein the outpatient treatment recommendation is determined based on the readmission risk score by determining that the patient has a high risk for readmission based on the readmission risk score, and the outpatient treatment recommendation is provided for presentation to the clinician by placing or maintaining the patient on a call list for high risk patients. 
     
     
         19 . The system of  claim 14 , wherein the readmission risk score is computed using a readmission risk prediction model selected based on a patient condition for the patient. 
     
     
         20 . The system of  claim 19 , wherein multiple patient conditions are identified for the patient, and wherein the readmission risk prediction model corresponds with the multiple patient conditions.