Processing documents in content repositories to generate personalized treatment guidelines
A computer system processes documents in a content repository. Each document of a plurality of documents is classified into one of a functional category and a clinical category. Each document is annotated using one or more corpora to generate document annotations. Documents satisfying one or more query terms are identified by comparing each query term to the document annotations. The identified documents are ranked based on a determined relevance. Guidelines are produced based on the ranking of the identified documents. Embodiments of the present invention further include a method and program product for processing documents in a content repository in substantially the same manner described above.
1. A computer-implemented method of processing documents in a content repository, the method comprising:
classifying each document of a plurality of documents into one of a functional category and a clinical category;
annotating each document using one or more corpora to generate document annotations, wherein a first corpus is used to annotate documents in the functional category, and a second corpus is used to annotate documents in the clinical category;
identifying documents satisfying one or more query terms by comparing each query term to the document annotations;
ranking the identified documents based on a determined relevance, wherein the determined relevance of each document is determined using neural network-based machine learning; and
producing guidelines based on the ranking of the identified documents.
2. The computer-implemented method of claim 1 , wherein the query terms include one or more of a gene term, a gene variant term, a drug term, a resistance mutation term, and a disease term.
3. The computer-implemented method of claim 1 , wherein ranking the identified documents comprises:
calculating a priority score for each document, wherein the priority score is calculated according to a presence of one or more query terms in a document, and wherein each query term is weighted according to a section of the document in which the query term is located; and
ranking the documents according to the priority score of each document.
4. The computer-implemented method of claim 1 , wherein document annotations indicate a location and a frequency of a word or phrase in each document that matches a word or phrase in the one or more corpora.
5. The computer-implemented method of claim 1 , wherein the guidelines comprise one or more disease types and corresponding data relating to precision medicine.
6. A computer system for processing documents in a content repository, the computer system comprising:
one or more computer processors;
one or more computer readable storage media;
program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising instructions to:
classify each document of a plurality of documents into one of a functional category and a clinical category;
annotate each document using one or more corpora to generate document annotations, wherein a first corpus is used to annotate documents in the functional category, and a second corpus is used to annotate documents in the clinical category;
identify documents satisfying one or more query terms by comparing each query term to the document annotations;
rank the identified documents based on a determined relevance, wherein the determined relevance of each document is determined using neural network-based machine learning; and
produce guidelines based on the ranking of the identified documents.
7. The computer system of claim 6 , wherein the query terms include one or more of a gene term, a gene variant term, a drug term, a resistance mutation term, and a disease term.
8. The computer system of claim 6 , wherein the instructions to rank the identified documents comprise instructions to:
calculate a priority score for each document, wherein the priority score is calculated according to a presence of one or more query terms in a document, and wherein each query term is weighted according to a section of the document in which the query term is located; and
rank the documents according to the priority score of each document.
9. The computer system of claim 6 , wherein document annotations indicate a location and a frequency of a word or phrase in each document that matches a word or phrase in the one or more corpora.
10. The computer system of claim 6 , wherein the guidelines comprise one or more disease types and corresponding data relating to precision medicine.
11. A computer program product for processing documents in a content repository, the computer program product comprising one or more computer readable storage media collectively having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:
classify each document of a plurality of documents into one of a functional category and a clinical category;
annotate each document using one or more corpora to generate document annotations, wherein a first corpus is used to annotate documents in the functional category, and a second corpus is used to annotate documents in the clinical category;
identify documents satisfying one or more query terms by comparing each query term to the document annotations;
rank the identified documents based on a determined relevance, wherein the determined relevance of each document is determined using neural network-based machine learning; and
produce guidelines based on the ranking of the identified documents.
12. The computer program product of claim 11 , wherein the query terms include one or more of a gene term, a gene variant term, a drug term, a resistance mutation term, and a disease term.
13. The computer program product of claim 11 , wherein the instructions to rank the identified documents comprise instructions to:
calculate a priority score for each document, wherein the priority score is calculated according to a presence of one or more query terms in a document, and wherein each query term is weighted according to a section of the document in which the query term is located; and
rank the documents according to the priority score of each document.
14. The computer program product of claim 11 , wherein document annotations indicate a location and a frequency of a word or phrase in each document that matches a word or phrase in the one or more corpora.
15. The computer program product of claim 11 , wherein the guidelines comprise one or more disease types and corresponding data relating to precision medicine.