{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E36BKXSITPQWNY7BNTAMAPLE3Y","short_pith_number":"pith:E36BKXSI","schema_version":"1.0","canonical_sha256":"26fc155e489be166e3e16cc0c03d64de00b94874450f7e376beac099ffdd6890","source":{"kind":"arxiv","id":"2105.01238","version":1},"attestation_state":"computed","paper":{"title":"Supervised multi-specialist topic model with applications on large-scale electronic health record data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Aihua Liu, Aman Verma, Ariane Marelli, David Buckeridge, Guido Powell, Liming Guo, Xavier Sumba Toral, Yixin Xu, Yue Li, Ziyang Song","submitted_at":"2021-05-04T01:27:11Z","abstract_excerpt":"Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a"},"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":"2105.01238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-04T01:27:11Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"23ffed4200d0870b3de842ead040bef7aaf60bcf392e817e984f226dbf3f9b07","abstract_canon_sha256":"c9192ce52071801cc9033621fd89f20fe0651e04c6e65e539972e6170a52eed9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:15.062742Z","signature_b64":"4WflMAillEx2m34BDdBd6oTQ3H6ois8UovqupOF9RZ63q+0D3zGvmF6qjtpfV9DafIdrHHl6O/EaSABJmUqRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fc155e489be166e3e16cc0c03d64de00b94874450f7e376beac099ffdd6890","last_reissued_at":"2026-07-05T02:37:15.062304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:15.062304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised multi-specialist topic model with applications on large-scale electronic health record data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Aihua Liu, Aman Verma, Ariane Marelli, David Buckeridge, Guido Powell, Liming Guo, Xavier Sumba Toral, Yixin Xu, Yue Li, Ziyang Song","submitted_at":"2021-05-04T01:27:11Z","abstract_excerpt":"Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.01238","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/2105.01238/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":"2105.01238","created_at":"2026-07-05T02:37:15.062379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.01238v1","created_at":"2026-07-05T02:37:15.062379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.01238","created_at":"2026-07-05T02:37:15.062379+00:00"},{"alias_kind":"pith_short_12","alias_value":"E36BKXSITPQW","created_at":"2026-07-05T02:37:15.062379+00:00"},{"alias_kind":"pith_short_16","alias_value":"E36BKXSITPQWNY7B","created_at":"2026-07-05T02:37:15.062379+00:00"},{"alias_kind":"pith_short_8","alias_value":"E36BKXSI","created_at":"2026-07-05T02:37:15.062379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14583","citing_title":"Synthetic Data Augmentation for Table Detection: Re-evaluating TableNet's Performance with Automatically Generated Document Images","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y","json":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y.json","graph_json":"https://pith.science/api/pith-number/E36BKXSITPQWNY7BNTAMAPLE3Y/graph.json","events_json":"https://pith.science/api/pith-number/E36BKXSITPQWNY7BNTAMAPLE3Y/events.json","paper":"https://pith.science/paper/E36BKXSI"},"agent_actions":{"view_html":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y","download_json":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y.json","view_paper":"https://pith.science/paper/E36BKXSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.01238&json=true","fetch_graph":"https://pith.science/api/pith-number/E36BKXSITPQWNY7BNTAMAPLE3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/E36BKXSITPQWNY7BNTAMAPLE3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y/action/storage_attestation","attest_author":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y/action/author_attestation","sign_citation":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y/action/citation_signature","submit_replication":"https://pith.science/pith/E36BKXSITPQWNY7BNTAMAPLE3Y/action/replication_record"}},"created_at":"2026-07-05T02:37:15.062379+00:00","updated_at":"2026-07-05T02:37:15.062379+00:00"}