Methods and apparatus for extracting facts from a medical text

Abstract

Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.

What is claimed is: 
     
         1 . A method of extracting a plurality of facts from a medical text, the method comprising:
 A) applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact, wherein the at least one first medical fact is linked to at least first text in the at least a portion of the medical text; and   B) applying a second model to the first text, wherein the second model extracts at least one second fact that is an attribute of the at least one first medical fact, wherein the first and second models are applied using at least one computer processor.   
     
     
         2 . The method of  claim 1 , further comprising:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the at least one first medical fact.   
     
     
         3 . The method of  claim 1 , further comprising:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the first text and/or information identifying a location of the first text in the medical text.   
     
     
         4 . The method of  claim 1 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact selected from the group consisting of a problem, medication, procedure and an allergy. 
     
     
         5 . The method of  claim 4 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a medication. 
     
     
         6 . The method of  claim 5 , wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a dosage and/or frequency of administration of the medication. 
     
     
         7 . The method of  claim 4 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a problem, and wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a laterality of the problem. 
     
     
         8 . The method of  claim 1 , wherein applying the second model to the first text comprises applying the second model to extract at least one second fact regarding a negation of one or more of the at least one first medical fact. 
     
     
         9 . At least one computer-readable storage medium encoded with computer-executable instructions that, when executed, perform a method comprising:
 A) applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact, wherein the at least one first medical fact is linked to at least first text in the at least a portion of the medical text; and   B) applying a second model to the first text, wherein the second model extracts at least one second fact that is an attribute of the at least one first medical fact.   
     
     
         10 . The at least one computer-readable storage medium of  claim 9 , wherein the method further comprises:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the at least one first medical fact.   
     
     
         11 . The at least one computer-readable storage medium of  claim 9 , wherein the method further comprises:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the first text and/or information identifying a location of the first text in the medical text.   
     
     
         12 . The at least one computer-readable storage medium of  claim 9 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact selected from the group consisting of a problem, medication, procedure and an allergy. 
     
     
         13 . The at least one computer-readable storage medium of  claim 12 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a medication. 
     
     
         14 . The at least one computer-readable storage medium of  claim 13 , wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a dosage and/or frequency of administration of the medication. 
     
     
         15 . The at least one computer-readable storage medium of  claim 12 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a problem, and wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a laterality of the problem. 
     
     
         16 . The at least one computer-readable storage medium of  claim 9 , wherein applying the second model to the first text comprises applying the second model to extract at least one second fact regarding a negation of one or more of the at least one first medical fact. 
     
     
         17 . An apparatus comprising:
 at least one processor; and   at least one memory storing processor-executable instructions that, when executed by the at least one processor, perform a method comprising:
 A) applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact, wherein the at least one first medical fact is linked to at least first text in the at least a portion of the medical text; and 
 B) applying a second model to the first text, wherein the second model extracts at least one second fact that is an attribute of the at least one first medical fact. 
   
     
     
         18 . The apparatus of  claim 17 , wherein the method further comprises:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the at least one first medical fact.   
     
     
         19 . The apparatus of  claim 17 , wherein the method further comprises:
 C) prior to the act B, passing, from the first model to the second model, and as a feature of the second model, the first text and/or information identifying a location of the first text in the medical text.   
     
     
         20 . The apparatus of  claim 17 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact selected from the group consisting of a problem, medication, procedure and an allergy. 
     
     
         21 . The apparatus of  claim 20 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a medication. 
     
     
         22 . The apparatus of  claim 21 , wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a dosage and/or frequency of administration of the medication. 
     
     
         23 . The apparatus of  claim 20 , wherein applying, to at least a portion of the medical text, a first model that extracts at least one first medical fact comprises applying the first model to extract at least one first medical fact regarding a problem, and wherein applying a second model to the first text comprises applying the second model to extract at least one second fact regarding a laterality of the problem. 
     
     
         24 . The apparatus of  claim 17 , wherein applying the second model to the first text comprises applying the second model to extract at least one second fact regarding a negation of one or more of the at least one first medical fact.