Ingest Local Clinical Documents and Link Them to Patients | Patient Journey Intelligence

John Snow Labs is a healthcare AI company and the industry leader in medical language models, with 150M+ downloads of its open-source libraries and models, 500+ enterprise customers, and 30+ peer-reviewed papers. Its software runs inside your own environment, on-premises or in your private cloud, with no data movement and no external API calls. Patient Journey Intelligence is the John Snow Labs platform for secondary use of clinical data. It ingests multimodal patient data (clinical notes, PDFs, FHIR, CDA, DICOM, and structured EHR records), extracts 400+ medical entities from unstructured text, harmonizes everything to the OMOP Common Data Model, and de-identifies PHI with 99%+ accuracy. Every extracted fact carries a confidence score and a link back to the source document it came from. Learn more about Patient Journey Intelligence: https://www.johnsnowlabs.com/patient-journey-intelligence/ IN THIS VIDEO Upload clinical documents straight from your machine and run them through a controlled ingestion workflow: choose which uploaded files actually get processed, pick the pipeline that processes them, map the incoming records to the right patient, visit, provider, care site, and location, then watch the job run and check what came out of each document. Uploading and ingesting are two separate steps. Files land on the server first and stay browsable, so you review the collection and select the subset you want in this job. The rest remain available for a later run. WHY THIS WORKFLOW MATTERS A document ingested without patient and OMOP context is a document your timeline cannot place. The facts inside it are still extracted, but they sit in isolation instead of joining the patient's longitudinal record, and a query that should return them comes back empty. That is why the linkage step happens before execution rather than after. You review the metadata travelling with the incoming records and decide how it maps to persons, providers, care sites, locations, and visits already in the system. Getting those relationships right up front is cheaper than repairing orphaned records once downstream cohorts have been built on them. The same applies to the pipeline choice. It decides what information extraction, normalization, and transformation the documents receive, and rerunning a batch through a different pipeline costs more than picking the right one at the start. WHAT THE VIDEO SHOWS - Starting an ingestion job and selecting Local Upload as the source - Uploading single files, multiple files, or a ZIP archive of a larger collection - Browsing the uploaded documents on the server and selecting the subset to ingest - Choosing a pre-configured pipeline, or configuring a custom one for the document type - Reviewing the metadata on the incoming records - Mapping records to persons, providers, care sites, locations, and visits in OMOP - Reviewing the full ingestion configuration before anything runs - Following the job through live execution logs - Opening a processed document to see everything extracted from it - Reviewing the consolidated results across the whole job WHO THIS IS FOR Clinical data engineers, integration teams, and platform administrators who own the document pipeline, plus the data curators and analysts who need a batch of files in and linked without waiting on a scheduled source. QUESTIONS THIS VIDEO ANSWERS - How do I upload clinical documents from my own machine into Patient Journey Intelligence? - How do I link ingested documents to the right patient, visit, and provider in OMOP? - Can I upload files now and choose which ones to ingest later? - How do I monitor an ingestion job and check what was extracted from each document? LINKS Ingestion Jobs documentation: https://www.johnsnowlabs.com/pji/data_integration/data_ingestions All tutorials: https://www.johnsnowlabs.com/pji/tutorials/overview Patient Journey Intelligence: https://www.johnsnowlabs.com/patient-journey-intelligence/ All patient data shown is synthetically generated for illustration. #HealthcareData #DataIngestion #ClinicalNLP