Medical scan natural language analysis system, methods and articles

Abstract

A medical report natural language model includes an artificial neural network implemented via the processor and is trained based a plurality of medical reports wherein each of the medical reports is mapped to at least one medical code of a plurality of medical codes and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes. A system operates by determining a first medical code of the plurality of medical codes utilizing the medical report natural language model on the first medical report by: recognizing, via the artificial neural network of the medical report natural language model, a first medical condition term of the plurality of medical condition terms in the first medical report; and determining the first medical code of the plurality of medical codes, based on the plurality of alias mapping pairs, wherein the determining the first medical code includes identifying a first alias mapping pair of the plurality of alias mapping pairs that pairs the first medical condition term deterministically to the first medical code; and mapping the first medical code of the plurality of medical codes and the first medical condition term of the plurality of medical condition terms to a first medical scan corresponding to the first medical report.

What is claimed is: 
     
         1 . A medical scan natural language analysis system, comprising:
 a medical scan database that includes a plurality of medical scans and a corresponding plurality of medical reports, wherein each of the plurality of medical reports includes natural language text data describing a corresponding one of the plurality of medical scans and wherein each of the medical reports is mapped to at least one medical code of a plurality of medical codes;   a processing system that includes a processor; and   a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising:
 generating a medical report natural language model that includes an artificial neural network implemented via the processor and is trained based a plurality of medical reports of a medical scan database wherein each of the plurality of medical reports includes natural language text data describing a corresponding one of a plurality of medical scans and wherein each of the medical reports is mapped to at least one medical code of a plurality of medical codes and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes; 
 accessing a first medical report that is not included in the medical scan database; 
 determining a first medical code of the plurality of medical codes utilizing the medical report natural language model on the first medical report by:
 recognizing, via the artificial neural network of the medical report natural language model, a first medical condition term of the plurality of medical condition terms in the first medical report; and 
 determining the first medical code of the plurality of medical codes, based on the plurality of alias mapping pairs, wherein the determining the first medical code includes identifying a first alias mapping pair of the plurality of alias mapping pairs that pairs the first medical condition term deterministically to the first medical code; and 
 
 mapping the first medical code of the plurality of medical codes and the first medical condition term of the plurality of medical condition terms to a first medical scan corresponding to the first medical report; and 
 facilitating display by a display device of the first medical condition term and the first medical code in conjunction with the first medical scan. 
   
     
     
         2 . The medical scan natural language analysis system of  claim 1 , wherein the operations further comprise:
 receiving a new alias mapping pair that is not included in the plurality of alias mapping pairs; and generating an updated medical report natural model based on the new alias mapping pair.   
     
     
         3 . The medical scan natural language analysis system of  claim 1 , wherein generating the medical report natural language model includes generating the plurality of alias mapping pairs. 
     
     
         4 . The medical scan natural language analysis system of  claim 3 , wherein the operations further comprise:
 receiving a second medical report that is not included in the selected set via the network; and   identifying a second medical condition term in the second medical report.   
     
     
         5 . The medical scan natural language analysis system of  claim 4 , wherein the operations further comprise:
 identifying a second alias mapping pair of the plurality of alias mapping pairs by determining a second medical condition term of the plurality of medical condition terms that corresponds to the second alias mapping pair compares favorably to the second medical condition term; and   mapping a second medical code of the plurality of medical codes to a second medical scan corresponding to the second medical report, wherein the second medical code corresponds to the second alias mapping pair.   
     
     
         6 . The medical scan natural language analysis system of  claim 1 , wherein the first medical code is one of: a SNOMED code, a Current Procedure Technology (CPT) code, an ICD-9 code, or an ICD-10 code. 
     
     
         7 . The medical scan natural language analysis system of  claim 1 , wherein generating the medical report natural language model includes utilizing a forward propagation algorithm on the plurality of medical reports to generate a preliminary set of neural network parameters of the artificial neural network, and by utilizing a back propagation algorithm to generate an updated set of neural network parameters of the artificial neural network based on a calculated set of parameter errors and the preliminary set of neural network parameters, and wherein determining a first medical code includes utilizing the forward propagation algorithm on the first medical report based on the updated set of neural network parameters. 
     
     
         8 . The medical scan natural language analysis system of  claim 1 , wherein the operations further comprise:
 receiving a second plurality of medical reports that are not included in the selected set via a network; and   determining at least one second medical code for each of the second plurality of medical reports by utilizing the medical report natural language model on the second plurality of medical reports.   
     
     
         9 . The medical scan natural language analysis system of  claim 8 , wherein the operations further comprise:
 generating a training set that includes a second plurality of medical scans corresponding to the second plurality of medical reports; and   generating a medical scan image analysis model based on the training set and the at least one second medical code corresponding to each of the second plurality of medical reports by applying computer vision techniques to the second plurality of medical scans.   
     
     
         10 . The medical scan natural language analysis system of  claim 9 , wherein the operations further comprise:
 receiving a third medical scan via the network;   determining a third medical code of the plurality of medical codes by utilizing the medical scan image analysis model on the third medical scan; and   mapping the third medical code of the plurality of medical codes to the third medical scan.   
     
     
         11 . A method for execution by a medical scan natural language analysis system that includes a processor, the method comprising:
 generating a medical report natural language model that includes an artificial neural network implemented via the processor and is trained based on a selected set of medical reports of a plurality of medical reports including at least one medical code of a plurality of medical codes mapped to each of the selected set of medical reports and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes;   accessing a first medical report that is not included in the selected set;   determining a first medical code of the plurality of medical codes utilizing the medical report natural language model on the first medical report by:
 recognizing, via the artificial neural network of the medical report natural language model, a first medical condition term of the plurality of medical condition terms in the first medical report; and 
 determining the first medical code of the plurality of medical codes, based on the plurality of alias mapping pairs, wherein the determining the first medical code includes identifying a first alias mapping pair of the plurality of alias mapping pairs that pairs the first medical condition term deterministically to the first medical code; and 
   mapping the first medical code of the plurality of medical codes and the first medical condition term of the plurality of medical condition terms to a first medical scan corresponding to the first medical report; and   facilitating display by a display device of the first medical condition term and the first medical code in conjunction with the first medical scan.   
     
     
         12 . The method of  claim 11 , further comprising:
 receiving a new alias mapping pair that is not included in the plurality of alias mapping pairs; and   generating an updated medical report natural model based on the new alias mapping pair.   
     
     
         13 . The method of  claim 11 , wherein generating the medical report natural language model includes generating the plurality of alias mapping pairs. 
     
     
         14 . The method of  claim 13 , further comprising:
 receiving a second medical report that is not included in the selected set via the network; and   identifying a second medical condition term in the second medical report.   
     
     
         15 . The method of  claim 14 , further comprising:
 identifying a second alias mapping pair of the plurality of alias mapping pairs by determining a second medical condition term of the plurality of medical condition terms that corresponds to the second alias mapping pair compares favorably to the second medical condition term; and   mapping a second medical code of the plurality of medical codes to a second medical scan corresponding to the second medical report, wherein the second medical code corresponds to the second alias mapping pair.   
     
     
         16 . The method of  claim 11 , wherein the first medical code is one of: a SNOMED code, a Current Procedure Technology (CPT) code, an ICD-9 code, or an ICD-10 code. 
     
     
         17 . The method of  claim 11 , wherein generating the medical report natural language model includes utilizing a forward propagation algorithm on the plurality of medical reports to generate a preliminary set of neural network parameters of the artificial neural network, and by utilizing a back propagation algorithm to generate an updated set of neural network parameters of the artificial neural network based on a calculated set of parameter errors and the preliminary set of neural network parameters, and wherein determining a first medical code includes utilizing the forward propagation algorithm on the first medical report based on the updated set of neural network parameters. 
     
     
         18 . An article of manufacture that includes a tangible storage medium that stores operational instructions, that when executed by a processor, causes the processor to:
 generate a medical report natural language model that includes an artificial neural network implemented via the processor and is trained based on a selected set of medical reports of a plurality of medical reports including at least one medical code of a plurality of medical codes mapped to each of the selected set of medical reports and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes;   access a first medical report that is not included in the selected set via a network;   determine a first medical code of the plurality of medical codes utilizing the medical report natural language model on the first medical report by:
 recognize, via the artificial neural network of the medical report natural language model, a first medical condition term of the plurality of medical condition terms in the first medical report; and 
 determine the first medical code of the plurality of medical codes, based on the plurality of alias mapping pairs, wherein the determining the first medical code includes identifying a first alias mapping pair of the plurality of alias mapping pairs that pairs the first medical condition term deterministically to the first medical code; and 
   map the first medical code of the plurality of medical codes and the first medical condition term of the plurality of medical condition terms to a first medical scan corresponding to the first medical report; and   facilitate display by a display device of the first medical condition term and the first medical code in conjunction with the first medical scan.   
     
     
         19 . The article of manufacture of  claim 18 , wherein the operational instructions, when executed by a processor, further cause the processor to:
 receive a new alias mapping pair that is not included in the plurality of alias mapping pairs; and   generate an updated medical report natural model based on the new alias mapping pair.   
     
     
         20 . The article of manufacture of  claim 18 , wherein generating the medical report natural language model includes generating the plurality of alias mapping pairs.