{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A3BP5RVGXWMLPLVPOZUDIPBG7U","short_pith_number":"pith:A3BP5RVG","schema_version":"1.0","canonical_sha256":"06c2fec6a6bd98b7aeaf7668343c26fd15752385a855f2d3365e816ef8915034","source":{"kind":"arxiv","id":"1810.13348","version":4},"attestation_state":"computed","paper":{"title":"Multimodal Machine Learning for Automated ICD Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashish K. Khanna, Charlotte Band, Eric Xing, Frank Papay, Jacek B. Cywinski, Jingzhi Pang, Kamal Maheshwari, Keyang Xu, Mike Lam, Pengtao Xie, Piyush Mathur, Xin Gao","submitted_at":"2018-10-31T15:39:32Z","abstract_excerpt":"This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modalities, including unstructured text, semi-structured text and structured tabular data. We further employed an ensemble method to integrate all modality-specific models to generate ICD-10 codes. Key evidence was also extracted to make our prediction more convincing and explainable. We used the Medical Information Mart for Intensive Care III (MIMIC -III) dataset to validate our approach. For ICD code prediction, our best"},"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":"1810.13348","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-31T15:39:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"582fe89f903cc398ab9f309fa1817d2774be75c8709951b6c555d74835aa0672","abstract_canon_sha256":"72016a510d1b6efdade6db310ed8d6eedb51eaab5eb41ff2392891502cf018fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:38.023586Z","signature_b64":"PKhZJ90yeElhfJ/qrFl09+ya2Tf++0E9RwYvuiTiHF5JOp6OaOpET4fnTwXokCmyCz2u2BiH5T84Ud1zAy1RDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06c2fec6a6bd98b7aeaf7668343c26fd15752385a855f2d3365e816ef8915034","last_reissued_at":"2026-07-05T04:53:38.023100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:38.023100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multimodal Machine Learning for Automated ICD Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashish K. Khanna, Charlotte Band, Eric Xing, Frank Papay, Jacek B. Cywinski, Jingzhi Pang, Kamal Maheshwari, Keyang Xu, Mike Lam, Pengtao Xie, Piyush Mathur, Xin Gao","submitted_at":"2018-10-31T15:39:32Z","abstract_excerpt":"This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modalities, including unstructured text, semi-structured text and structured tabular data. We further employed an ensemble method to integrate all modality-specific models to generate ICD-10 codes. Key evidence was also extracted to make our prediction more convincing and explainable. We used the Medical Information Mart for Intensive Care III (MIMIC -III) dataset to validate our approach. For ICD code prediction, our best"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13348","kind":"arxiv","version":4},"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/1810.13348/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":"1810.13348","created_at":"2026-07-05T04:53:38.023158+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.13348v4","created_at":"2026-07-05T04:53:38.023158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13348","created_at":"2026-07-05T04:53:38.023158+00:00"},{"alias_kind":"pith_short_12","alias_value":"A3BP5RVGXWML","created_at":"2026-07-05T04:53:38.023158+00:00"},{"alias_kind":"pith_short_16","alias_value":"A3BP5RVGXWMLPLVP","created_at":"2026-07-05T04:53:38.023158+00:00"},{"alias_kind":"pith_short_8","alias_value":"A3BP5RVG","created_at":"2026-07-05T04:53:38.023158+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/A3BP5RVGXWMLPLVPOZUDIPBG7U","json":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U.json","graph_json":"https://pith.science/api/pith-number/A3BP5RVGXWMLPLVPOZUDIPBG7U/graph.json","events_json":"https://pith.science/api/pith-number/A3BP5RVGXWMLPLVPOZUDIPBG7U/events.json","paper":"https://pith.science/paper/A3BP5RVG"},"agent_actions":{"view_html":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U","download_json":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U.json","view_paper":"https://pith.science/paper/A3BP5RVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.13348&json=true","fetch_graph":"https://pith.science/api/pith-number/A3BP5RVGXWMLPLVPOZUDIPBG7U/graph.json","fetch_events":"https://pith.science/api/pith-number/A3BP5RVGXWMLPLVPOZUDIPBG7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U/action/storage_attestation","attest_author":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U/action/author_attestation","sign_citation":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U/action/citation_signature","submit_replication":"https://pith.science/pith/A3BP5RVGXWMLPLVPOZUDIPBG7U/action/replication_record"}},"created_at":"2026-07-05T04:53:38.023158+00:00","updated_at":"2026-07-05T04:53:38.023158+00:00"}