{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M57FNZA3XKTF7DSQ3ZBFSIJAJC","short_pith_number":"pith:M57FNZA3","schema_version":"1.0","canonical_sha256":"677e56e41bbaa65f8e50de425921204887d456c27650544188713c38f6d43cf9","source":{"kind":"arxiv","id":"2206.01436","version":1},"attestation_state":"computed","paper":{"title":"Modeling electronic health record data using a knowledge-graph-embedded topic model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ahmad Pesaranghader, Aman Verma, David Buckeridge, Yue Li, Yuesong Zou","submitted_at":"2022-06-03T07:58:17Z","abstract_excerpt":"The rapid growth of electronic health record (EHR) datasets opens up promising opportunities to understand human diseases in a systematic way. However, effective extraction of clinical knowledge from the EHR data has been hindered by its sparsity and noisy information. We present KG-ETM, an end-to-end knowledge graph-based multimodal embedded topic model. KG-ETM distills latent disease topics from EHR data by learning the embedding from the medical knowledge graphs. We applied KG-ETM to a large-scale EHR dataset consisting of over 1 million patients. We evaluated its performance based on EHR r"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.01436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T07:58:17Z","cross_cats_sorted":["cs.IR","q-bio.QM"],"title_canon_sha256":"3b0b5c702f0b148c78c0122eb5c2c4f35c65e3ef1a18bd29381faaf20d3484c0","abstract_canon_sha256":"412d2a274449413fff107c1782a123d6cef70521289a3a80d1259c1741885a8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:47.611115Z","signature_b64":"/vfaA2xmILZt1PLs1fyPwISey+5ToBV/Thg7W+yKUujXh0OTmHULaeOvsEtxOmsQ8EmkpQUuJ2qRZkGWooIHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"677e56e41bbaa65f8e50de425921204887d456c27650544188713c38f6d43cf9","last_reissued_at":"2026-07-05T04:28:47.610613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:47.610613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling electronic health record data using a knowledge-graph-embedded topic model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Ahmad Pesaranghader, Aman Verma, David Buckeridge, Yue Li, Yuesong Zou","submitted_at":"2022-06-03T07:58:17Z","abstract_excerpt":"The rapid growth of electronic health record (EHR) datasets opens up promising opportunities to understand human diseases in a systematic way. However, effective extraction of clinical knowledge from the EHR data has been hindered by its sparsity and noisy information. We present KG-ETM, an end-to-end knowledge graph-based multimodal embedded topic model. KG-ETM distills latent disease topics from EHR data by learning the embedding from the medical knowledge graphs. We applied KG-ETM to a large-scale EHR dataset consisting of over 1 million patients. We evaluated its performance based on EHR r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01436","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.01436/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.01436","created_at":"2026-07-05T04:28:47.610672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01436v1","created_at":"2026-07-05T04:28:47.610672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01436","created_at":"2026-07-05T04:28:47.610672+00:00"},{"alias_kind":"pith_short_12","alias_value":"M57FNZA3XKTF","created_at":"2026-07-05T04:28:47.610672+00:00"},{"alias_kind":"pith_short_16","alias_value":"M57FNZA3XKTF7DSQ","created_at":"2026-07-05T04:28:47.610672+00:00"},{"alias_kind":"pith_short_8","alias_value":"M57FNZA3","created_at":"2026-07-05T04:28:47.610672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC","json":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC.json","graph_json":"https://pith.science/api/pith-number/M57FNZA3XKTF7DSQ3ZBFSIJAJC/graph.json","events_json":"https://pith.science/api/pith-number/M57FNZA3XKTF7DSQ3ZBFSIJAJC/events.json","paper":"https://pith.science/paper/M57FNZA3"},"agent_actions":{"view_html":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC","download_json":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC.json","view_paper":"https://pith.science/paper/M57FNZA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01436&json=true","fetch_graph":"https://pith.science/api/pith-number/M57FNZA3XKTF7DSQ3ZBFSIJAJC/graph.json","fetch_events":"https://pith.science/api/pith-number/M57FNZA3XKTF7DSQ3ZBFSIJAJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC/action/storage_attestation","attest_author":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC/action/author_attestation","sign_citation":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC/action/citation_signature","submit_replication":"https://pith.science/pith/M57FNZA3XKTF7DSQ3ZBFSIJAJC/action/replication_record"}},"created_at":"2026-07-05T04:28:47.610672+00:00","updated_at":"2026-07-05T04:28:47.610672+00:00"}