IRC log of hcls on 2024-01-18
Timestamps are in UTC.
- 16:02:24 [RRSAgent]
- RRSAgent has joined #hcls
- 16:02:28 [RRSAgent]
- logging to https://www.w3.org/2024/01/18-hcls-irc
- 16:02:28 [dbooth]
- rrsagent, make logs public
- 16:02:32 [dbooth]
- Meeting: FHIR RDF
- 16:02:38 [dbooth]
- Chair: David Booth
- 16:05:15 [dbooth]
- Topic: Introductions
- 16:09:20 [dbooth]
- Darrell Woelk: involved in semantic world, going back to MCC. Then worked on Carno, using Cyc. The started Info Sloop, Made a company in 1995, then got into healthcare, building a soft dev platform in healthcare Started w FHIR in 2015. Green Room Tech is our latest. I do FHIR consulting, both tech and business. When Chat GTP cam out, I started working on AI again. Ivolved w U Texax Information, doing lectures on FHIR, then last hyear on gene
- 16:09:20 [dbooth]
- rative AI. Had 4 gra dstudents working on gen AI, and want to do more this year.
- 16:09:50 [dbooth]
- Topic: Darrell's ideas on student involvement.
- 16:10:01 [dbooth]
- darrell: Working w Dr Ding.
- 16:10:07 [dbooth]
- ... KG and LLM.
- 16:11:14 [dbooth]
- .. Spoke w Juan Sequeda in Data.world. They did soft dev and pub an article about KG and LLM bencharks.
- 16:11:30 [dbooth]
- ... It can gen SQL, using SQL DL.
- 16:12:10 [dbooth]
- ... Doing the same thing w an ont and SPARQL
- 16:12:22 [dbooth]
- ... Juan did a mapping into DB
- 16:12:35 [dbooth]
- ... They had a claims ont.
- 16:12:51 [dbooth]
- ... data.world executes the SPARQL queries.
- 16:13:06 [dbooth]
- ... They turn those SPARQL queries into SQL and return answers.
- 16:14:00 [dbooth]
- ... They did a benchmark, comparing SQL-only-based vs ont-informed. It was 50% better, and they showed why.
- 16:14:17 [dbooth]
- .. They used zero-shot prompt.
- 16:14:35 [dbooth]
- ... They made this available for others to try.
- 16:15:07 [dbooth]
- ... Proposing to do this in the healthcare domain. On the left side, that meansw we don't have to tell chatGPT what the FHIR resources are, becuase it already knows that.
- 16:15:19 [dbooth]
- ... Use a FHIR API earch instead of SQL.
- 16:16:39 [dbooth]
- .. On the RHS want to do something similar to what they did w insurance claim, but w phenotype ont.
- 16:17:09 [dbooth]
- ... Then using FHIR RDF data.
- 16:17:36 [dbooth]
- ... Or could export all my FHIR RDF data into the triplestore.
- 16:18:12 [dbooth]
- eric: Sounds fun. There might be some code that you could reuse, that does part of that.
- 16:18:56 [dbooth]
- ... SPARQL query gets dismantled to match hierarchies agains a library of FHIR path. Rule head would be FHIR Path, body would be SPARQL.
- 16:19:30 [dbooth]
- .. Divide up resources and test it against know FHIR paths. Launch , get results back, bind appropriate resources.
- 16:21:06 [dbooth]
- (Eric explains the code more)
- 16:21:26 [dbooth]
- eric: That's in typescript right now, Claude Nanjo and I worked on it.
- 16:22:33 [dbooth]
- eric: There's a shex schema for FHIR.
- 16:22:41 [dbooth]
- dbooth: And a FHIR ont.
- 16:23:32 [dbooth]
- darrell: Phenopackets include a lot of data. Vulcan project trying to come up w FHIR rep of phenopacket.
- 16:23:45 [dbooth]
- ... Met w them yuesterday.
- 16:25:18 [dbooth]
- jim: HPO folks have a transformation to FHIR ont.
- 16:25:33 [dbooth]
- ... They're at least workin on it.
- 16:25:48 [dbooth]
- ... Someone who works for Chris Chute working on it.
- 16:26:48 [dbooth]
- darrell: These are grad students. Class is AI and health. Want a group of 2-3 students. How to intro FHIR RDF?
- 16:27:42 [dbooth]
- https://yosemiteproject.org/tutorial-fhir-rdf-as-a-bridge-to-the-semantic-web-in-healthcare/
- 16:28:38 [dbooth]
- dbooth: That hasn't been updated to R5 yet.
- 16:30:26 [dbooth]
- eric: Did the HPI queries assume that the closures implied by the ont were already instantiated in the SQL data?
- 16:30:30 [dbooth]
- darrell: IDK.
- 16:31:12 [dbooth]
- eric: could either assume no inference, or could add subsumptions in tables, and join those also.
- 16:31:35 [dbooth]
- ... Or you could transform the query to add the subsumptions.
- 16:32:14 [dbooth]
- darrell: They product is a catalog. Guessing that they're not pushing on inference, but I'm interested in it.
- 16:32:29 [dbooth]
- ... This would be a first step toward building a test system.
- 16:32:46 [dbooth]
- jim: I think the work by Joe Flack on ontology-to-FHIR has been folded into OAK python (Ontology Access Kit): https://incatools.github.io/ontology-access-kit/howtos/fhir-conversions.html
- 16:33:08 [dbooth]
- eric: Queries were supposed to go over their info mdel.
- 16:33:31 [dbooth]
- ... You could infer the structure from the DDL, or maybe from an ont.
- 16:33:43 [dbooth]
- ... But sounds like they used both. How did they use the ont?
- 16:34:20 [dbooth]
- darrell: Their product maps from KG to individual DBs.
- 16:36:11 [dbooth]
- eric: Could ask a FHIR query, either 1. "I'm looking for sombody w a procedure performed on the kidney", and that's turned into a query for procedure performed on a kidney, or on kidney lining, etc., using the closure over the subclasses to expand the query.
- 16:36:39 [dbooth]
- ... 2. Issue the original SPARQL query, but have the infra on the FHIR side, HAPI FhIR server goes to the term server to do that closure.
- 16:36:50 [dbooth]
- darrell: And HPO work is doing that?
- 16:37:45 [dbooth]
- jim: Joe Flack is the developer working on that at HPO. He works for Chris Chute at Johns Hopkins, but also working on Monarch initiative.
- 16:38:11 [dbooth]
- ... The OAK python toolkit does lots of things w ont. IDK if they're hosting the HPO ont someplace as FHIR.
- 16:42:40 [dbooth]
- eric: Wonder if you could use shex to steer GPT4.
- 16:43:43 [dbooth]
- gaurav: You could also give it a shex schema and tell GPT4 to "using this schema, give me ... "
- 16:44:24 [dbooth]
- eric: But a well-informed person still needs to read the GPT4 responses to tell it to correct them.. Maybe use shex for that.
- 16:45:16 [dbooth]
- eric: Will be hard to make it guess a good query.
- 16:45:39 [dbooth]
- darrell: Benchmarks that data.world did are not perfect, an dthey discuss them.
- 16:45:54 [dbooth]
- ... How to prompt it to correct the mistakes?
- 16:46:38 [dbooth]
- eric: What's "included" in the FHIR queries?
- 16:47:05 [dbooth]
- darrell: it joins other info to your results.
- 16:50:18 [dbooth]
- Topic: Concept IRIs
- 16:50:36 [dbooth]
- gaurav: The submission part of jira is down right now. Cannot edit it right now.
- 16:51:07 [dbooth]
- ... But I'll keep an eye on it.
- 16:51:33 [dbooth]
- Present: Jim Balhoff, Gaurav Vaidya, David Booth, EricP, Darrell Woelk
- 16:51:39 [dbooth]
- ADJOURNED
- 16:51:43 [dbooth]
- rrsagent, draft minutes
- 16:51:45 [RRSAgent]
- I have made the request to generate https://www.w3.org/2024/01/18-hcls-minutes.html dbooth
- 16:56:51 [dbooth]
- i/Working w Dr Ding/Darrell's slides: https://lists.w3.org/Archives/Public/www-archive/2024Jan/att-0001/Human_Phenotype_Ontology_and_FHIR.pdf
- 16:56:54 [dbooth]
- rrsagent, draft minutes
- 16:56:55 [RRSAgent]
- I have made the request to generate https://www.w3.org/2024/01/18-hcls-minutes.html dbooth