{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BN3AXFRKY2KXH4GC7MGMNEWMT6","short_pith_number":"pith:BN3AXFRK","schema_version":"1.0","canonical_sha256":"0b760b962ac69573f0c2fb0cc692cc9fb5c7eb90baf2bd897c176ee6a27a05d9","source":{"kind":"arxiv","id":"2211.07549","version":2},"attestation_state":"computed","paper":{"title":"Phenotype Detection in Real World Data via Online MixEHR Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Decker, Jacob Oppenheim, Romane Gauriau, Ying Xu","submitted_at":"2022-11-14T17:14:39Z","abstract_excerpt":"Understanding patterns of diagnoses, medications, procedures, and laboratory tests from electronic health records (EHRs) and health insurer claims is important for understanding disease risk and for efficient clinical development, which often require rules-based curation in collaboration with clinicians. We extended an unsupervised phenotyping algorithm, mixEHR, to an online version allowing us to use it on order of magnitude larger datasets including a large, US-based claims dataset and a rich regional EHR dataset. In addition to recapitulating previously observed disease groups, we discovere"},"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":"2211.07549","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T17:14:39Z","cross_cats_sorted":[],"title_canon_sha256":"112113e23c29c8e3dffd2cc167ba182b32199452d1fea6f41e82a8f42de9a7c9","abstract_canon_sha256":"aa11b8921f9f20da817e66a9c12a34c962a1101300630990a52f1ab8ae0dbbcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:04.261708Z","signature_b64":"nu0wqzdX1eHKXwBPw8iYFx3pFzvAoc0Xq4CU0xFAAlxRtgqDg1loIVzDt4miGk8Ih129vSBSX4tEfSOhx0f2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b760b962ac69573f0c2fb0cc692cc9fb5c7eb90baf2bd897c176ee6a27a05d9","last_reissued_at":"2026-07-05T05:16:04.261202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:04.261202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phenotype Detection in Real World Data via Online MixEHR Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anna Decker, Jacob Oppenheim, Romane Gauriau, Ying Xu","submitted_at":"2022-11-14T17:14:39Z","abstract_excerpt":"Understanding patterns of diagnoses, medications, procedures, and laboratory tests from electronic health records (EHRs) and health insurer claims is important for understanding disease risk and for efficient clinical development, which often require rules-based curation in collaboration with clinicians. We extended an unsupervised phenotyping algorithm, mixEHR, to an online version allowing us to use it on order of magnitude larger datasets including a large, US-based claims dataset and a rich regional EHR dataset. In addition to recapitulating previously observed disease groups, we discovere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07549","kind":"arxiv","version":2},"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/2211.07549/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":"2211.07549","created_at":"2026-07-05T05:16:04.261258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07549v2","created_at":"2026-07-05T05:16:04.261258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07549","created_at":"2026-07-05T05:16:04.261258+00:00"},{"alias_kind":"pith_short_12","alias_value":"BN3AXFRKY2KX","created_at":"2026-07-05T05:16:04.261258+00:00"},{"alias_kind":"pith_short_16","alias_value":"BN3AXFRKY2KXH4GC","created_at":"2026-07-05T05:16:04.261258+00:00"},{"alias_kind":"pith_short_8","alias_value":"BN3AXFRK","created_at":"2026-07-05T05:16:04.261258+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/BN3AXFRKY2KXH4GC7MGMNEWMT6","json":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6.json","graph_json":"https://pith.science/api/pith-number/BN3AXFRKY2KXH4GC7MGMNEWMT6/graph.json","events_json":"https://pith.science/api/pith-number/BN3AXFRKY2KXH4GC7MGMNEWMT6/events.json","paper":"https://pith.science/paper/BN3AXFRK"},"agent_actions":{"view_html":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6","download_json":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6.json","view_paper":"https://pith.science/paper/BN3AXFRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07549&json=true","fetch_graph":"https://pith.science/api/pith-number/BN3AXFRKY2KXH4GC7MGMNEWMT6/graph.json","fetch_events":"https://pith.science/api/pith-number/BN3AXFRKY2KXH4GC7MGMNEWMT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6/action/storage_attestation","attest_author":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6/action/author_attestation","sign_citation":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6/action/citation_signature","submit_replication":"https://pith.science/pith/BN3AXFRKY2KXH4GC7MGMNEWMT6/action/replication_record"}},"created_at":"2026-07-05T05:16:04.261258+00:00","updated_at":"2026-07-05T05:16:04.261258+00:00"}