Hi Ghandi, Parsing the xml file as you outline should work. Depending upon your end goal there may be other ways to report discovered disease/disorders to users.
> Also, we are planning to implement auto learning to eliminate the disease > terms we don't want. Is this fine? This is great! Are you talking about having user interaction to approve/disapprove of a discovered term? Storing that feedback and using it in future output? If so, do you have any plans to make that type of information available? It may help people who are tackling the word sense disambiguation that I mentioned earlier. >@Sean, regarding custom dictionary creation for MedDRA, do we have to add >every terms manually or do we have a DB script (as in case of Snowmed CT & >RxNORM) to load the terms as in our case we are using MySQL DB? You should be able to create a new hsqldb custom dictionary using the dictionary creator gui. In the custom dictionary you can include any source type in the umls, such as snomed, rxnorm and meddra. You do not need to select terms individually, it is mostly a "bulk import". You can use the same db script that you created to convert the hsql to mysql. Sean -----Original Message----- From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com] Sent: Monday, September 11, 2017 10:51 AM To: dev@ctakes.apache.org Subject: RE: Filtering disease term precisely from EventMention and loading MedDRA library for cTAKES [EXTERNAL] A big thanks to Sean and Arron for taking time out and responding. Currently we are planning to make use of the XML generated by temporal demo application and parse the same to look for " textsem:DiseaseDisorderMention" tag and get the " ontologyConceptArr" attribute value of it, then match the attribute value to "refsem:UmlsConcept" tag's " xmi:id" attribute to get the preferred texts (disease terms). Eg: <textsem:DiseaseDisorderMentionxmi:id="2923"sofa="1"begin="45"end="59"id="0"ontologyConceptArr="2910"typeID="2"discoveryTechnique="1"confidence="0.0"polarity="1"uncertainty="0"conditional="false"generic="false"historyOf="0"event="12574"/> <refsem:UmlsConceptxmi:id="2910"codingScheme="SNOMEDCT_US"code="55822004"score="0.0"disambiguated="false"cui="C0020473"tui="T047"preferredText="Hyperlipidemia"/> Is this approach feasible for now or any better solutions on this from expert's standpoint? Also, we are planning to implement auto learning to eliminate the disease terms we don't want. Is this fine? @Sean, regarding custom dictionary creation for MedDRA, do we have to add every terms manually or do we have a DB script (as in case of Snowmed CT & RxNORM) to load the terms as in our case we are using MySQL DB? Regards, Gandhi -----Original Message----- From: Finan, Sean [mailto:sean.fi...@childrens.harvard.edu] Sent: Monday, September 11, 2017 7:16 PM To: dev@ctakes.apache.org Subject: RE: Filtering disease term precisely from EventMention and loading MedDRA library for cTAKES [EXTERNAL] Hi Ghandi, "plan" is a synonym for C0270724: Infantile Neuroaxonal Dystrophy. One outcome of using generic dictionaries that can be used across multiple fields of interest is that a valid term in one field can be misapplied to text from another. Unwanted terms can be addressed per item by creating a more pointed dictionary without them, adding them to a blacklist that causes ctakes to discard them, or removing them with some kind of discriminating annotator. The last includes application of word sense disambiguation, a hot topic on this forum as well as others. If you create a custom dictionary you can add medDRA terms. https://urldefense.proofpoint.com/v2/url?u=https-3A__cwiki.apache.org_confluence_display_CTAKES_Dictionary-2BCreator-2BGUI&d=DwIFAg&c=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU&r=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao&m=UZRAjFzzLG1OrO6zYRkXw6YLhpDw9ZzLPdaEYsDWMaE&s=np5H0rdvlMLyeOmFBmx5O8JKDaGGrIaap8T6kJsAoqA&e= Sean -----Original Message----- From: Gandhi Rajan Natarajan [mailto:gandhi.natara...@arisglobal.com] Sent: Saturday, September 09, 2017 2:22 PM To: dev@ctakes.apache.org Subject: Filtering disease term precisely from EventMention and loading MedDRA library for cTAKES [EXTERNAL] HI All, we have deployed temporal demo application available under https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_healthnlp_examples_tree_master_ctakes-2Dtemporal-2Ddemo&d=DwIFAg&c=qS4goWBT7poplM69zy_3xhKwEW14JZMSdioCoppxeFU&r=fs67GvlGZstTpyIisCYNYmQCP6r0bcpKGd4f7d4gTao&m=Gl0bP7oHY9HLCgAy9GMSpAb9x-phGTB1-nYh2G7SrWY&s=bKUnUuurg3wWfzmjUKWhFIHzaVGylX_kIaj6f83c4m4&e= locally and referring to dictionaries(RxNORM,SnoMED) loaded in MySQL DB. We are trying to extract out disease terms using this application. When we tried out the text mentioned in user installation guide, " Dr. Nutritious Medical Nutrition Therapy for Hyperlipidemia Referral from: Julie Tester, RD, LD, CNSD Phone contact: (555) 555-1212 Height: 144 cm Current Weight: 45 kg Date of current weight: 02-29-2001 Admit Weight: 53 kg BMI: 18 kg/m2 Diet: General Daily Calorie needs (kcals): 1500 calories, assessed as HB + 20% for activity. Daily Protein needs: 40 grams, assessed as 1.0 g/kg. Pt has been on a 3-day calorie count and has had an average intake of 1100 calories. She was instructed to drink 2-3 cans of liquid supplement to help promote weight gain. She agrees with the plan and has my number for further assessment. May want a Resting Metabolic Rate as well. She takes an aspirin a day for knee pain", it extracted out 'Hyperlipidemia' and 'plan' as DiseaseDisorderMention. But we expected only disease terms to be extracted out(Hyperlipidemia) but "plan" is not what we expected. How do we avoid this or filter out only disease terms like fever, red eye, nausea etc. from the given text. Any help on this is greatly appreciated. Also please let us know is there a provision to load MedDRA dictionaries and lookup the same in cTAKES? If yes, please let us know how to achieve it? Thanks in advance Regards, Gandhi This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you are not the named addressee you should not disseminate, distribute or copy this e-mail. Please notify the sender or system manager by email immediately if you have received this e-mail by mistake and delete this e-mail from your system. If you are not the intended recipient you are notified that disclosing, copying, distributing or taking any action in reliance on the contents of this information is strictly prohibited and against the law. This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you are not the named addressee you should not disseminate, distribute or copy this e-mail. Please notify the sender or system manager by email immediately if you have received this e-mail by mistake and delete this e-mail from your system. If you are not the intended recipient you are notified that disclosing, copying, distributing or taking any action in reliance on the contents of this information is strictly prohibited and against the law.
