Played around with this in my soon-to-be previous health-tech job and its great.<p>Actually the entire hl7-fhir ( <a href="https://www.hl7.org/fhir/" rel="nofollow">https://www.hl7.org/fhir/</a> ) standard seems to me quite solid.
It would be wonderful if a new cohort of start-ups would leverage it to drastically improve the digital UX of healthcare generally.
Does anyone know if there is an equivalent for generating "random" viable products[1] in a PDM/ERP system?<p>I'm demoing some systems in this field for outside interests, but I can't use any "real" data due to ITAR and data restrictions like TC, NC, etc. Wait, what about the ERP? The ERP I'm developing against has "sample" data that's basically useless. Not much better than <i>lorem ipsum</i> pasted across ten thousand cells. Actually, it's worse than that, because . . ah hell, this is HN, I won't waste your time. People here know what the ERP ecosystem is like. I also don't want to build out from a bespoke, brittle ERP - that's how we got into this mess in the first place.<p>[1] Like a multi-level BOM that makes sense, or a Service BOM / Logistics Database that's meaningful. Anything for making pseudo-random PLs that follow MIL-STD-100, which is still considered frickin' Holy Ground by these people.
Synthea is great! We use it a ton at Medplum - and the sample data that conforms to USCDI is especially useful we recommend for those who are getting started. <a href="https://www.medplum.com/docs/tutorials/importing-sample-data">https://www.medplum.com/docs/tutorials/importing-sample-data</a>
I actually had this idea when I worked for a local HIE. I just lacked the technical competency to make it real. I think this would be incredibly useful for the adoption of FHIR and also learning more about HL7. For security-minded folks this information could be a good tool for tuning DLP and other tools without using real patient data.
I recommend the OMOP schema as a goto standard for EHR data. There's an ETL pipeline for converting Synthea output into OMOP.<p><a href="https://github.com/OHDSI/ETL-Synthea">https://github.com/OHDSI/ETL-Synthea</a>
Neat! We made a synthetic patient generation prototype a few years ago: <a href="https://pau.treenotation.org/synth/" rel="nofollow">https://pau.treenotation.org/synth/</a><p>The challenge at the time was generating realistic correlations between the columns. How do you approach this?<p>I noticed LLMs are a huge breakthrough here with the downside that they currently rely on massive online models. I wonder if someone could train a tiny model that could fit on a local machine specifically to solve the synthetic data problem.
I’ve used Synthea for a whole assortment of small and large projects and it’s been boring in the best possible way: reliable and easy to use.<p>I’ve also had the pleasure of working directly with the team at MITRE that owns it on a consulting engagement (we needed some improvements to it) and they are a delight to work with.
I’ve worked at the intersection of AI & healthcare for years and this has been an excellent tool I’ve leveraged in the past; synthetic data is particularly helpful in the context of healthcare!