Physician attribution for inpatient care

Abstract

A system and method for performing physician attribution is presented. In one aspect, the system can comprise instructions comprising querying a first database; extracting a plurality of data from the first database, said extracted data comprising at least a physician, a note type, a note text and a patient; storing the extracted data in a second database; computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data; storing the attribution scores in the second database; and attributing the physician with a highest score to the patient.

What is claimed is: 
     
         1 . A system for performing physician attribution, comprising:
 a memory; and   a processor connected to the memory, the processor performing instructions stored in the memory, the instructions comprising:   querying a first database;   extracting a plurality of data from the first database, said extracted data comprising at least a physician, a note type, a note text and a patient;   storing the extracted data in a second database;   computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data;   storing the attribution scores in the second database;   attributing the physician with a highest score to the patient.   
     
     
         2 . The system according to  claim 1 , further comprising:
 a display device, wherein the display device displays the patient and the physician attributed to the patient.   
     
     
         3 . The system according to  claim 1 , the processor further performing instructions of:
 sampling and validating the attribution scores; and   correcting the predetermined weights based on the sampling and validating.   
     
     
         4 . The system according to  claim 1 , further comprising a web interface, wherein the processor further performs instructions of obtaining modified data using the web interface. 
     
     
         5 . The system according to  claim 1 , wherein the processor learns the predetermined weights based on a machine learning algorithm. 
     
     
         6 . The system according to  claim 5 , wherein the computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data is performed automatically based on the machine learning algorithm. 
     
     
         7 . A method for performing physician attribution, comprising:
 querying a first database;   extracting a plurality of data from the first database, said extracted data comprising at least a physician, a note type, a note text and a patient;   storing the extracted data in a second database;   computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data;   storing the attribution scores in the second database;   attributing the physician with a highest score to the patient.   
     
     
         8 . The method according to  claim 7 , further comprising displaying on a display device the patient and the physician attributed to the patient. 
     
     
         9 . The method according to  claim 7 , further comprising:
 sampling and validating the attribution scores; and   correcting the predetermined weights based on the sampling and validating.   
     
     
         10 . The method according to  claim 1 , further comprising performing instructions of obtaining modified data via a web interface. 
     
     
         11 . The method according to  claim 1 , further comprising learning the predetermined weights by the processor based on a machine learning algorithm. 
     
     
         12 . The method according to  claim 11 , wherein the computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data is performed automatically based on the machine learning algorithm. 
     
     
         13 . A computer readable storage device storing a program of instructions executable by a machine to perform a method of performing physician attribution, the method comprising:
 extracting a plurality of data from the first database, said extracted data comprising at least a physician, a note type, a note text and a patient;   storing the extracted data in a second database;   computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data;   storing the attribution scores in the second database;   attributing the physician with a highest score to the patient.   
     
     
         14 . The computer readable storage device according to  claim 13 , further comprising displaying on a display device the patient and the physician attributed to the patient. 
     
     
         15 . The computer readable storage device according to  claim 13 , further comprising:
 sampling and validating the attribution scores; and   correcting the predetermined weights based on the sampling and validating.   
     
     
         16 . The computer readable storage device according to  claim 13 , further comprising performing instructions of obtaining modified data via a web interface. 
     
     
         17 . The computer readable storage device according to  claim 13 , further comprising learning the predetermined weights by the processor based on a machine learning algorithm. 
     
     
         18 . The computer readable storage device according to  claim 17 , wherein the computing attribution scores using predetermined weights for the note types and the plurality of notes in the extracted data is performed automatically based on the machine learning algorithm.