{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MEK4ZIBW562VOSEVNSGJ6PI3ZB","short_pith_number":"pith:MEK4ZIBW","schema_version":"1.0","canonical_sha256":"6115cca036efb55748956c8c9f3d1bc86e5fa9be66c97bfde61f8b310769bec0","source":{"kind":"arxiv","id":"2405.02664","version":3},"attestation_state":"computed","paper":{"title":"MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Barnali Das, Kshitij Jadhav, Lipika Bhat, Roomani Srivastava, Sarvesh Deshpande, Suraj Prasad","submitted_at":"2024-05-04T13:25:06Z","abstract_excerpt":"Introduction: The labour-intensive nature of data extraction from sources like discharge summaries (DS) poses significant obstacles to the digitisation of medical records particularly for low- and middle-income countries (LMICs). In this paper we present a completely automated method MedPromptExtract to efficiently extract data from DS while maintaining confidentiality. Methods: The source of data was Discharge Summaries (DS) from Kokilaben Dhirubhai Ambani Hospital (KDAH) of patients having Acute Kidney Injury (AKI). A pre-existing tool EIGEN which leverages semi-supervised learning technique"},"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":"2405.02664","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-04T13:25:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"999b789428d4399c5fbe9f54dc4f1e4234ab3eed1fa6653c2dd750b56c78fe95","abstract_canon_sha256":"c43bada04ab1a7271446c08e58ff005d1b9d9a7f9de33903abbd839fc8cd9695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:53.062445Z","signature_b64":"0RwlJlAFSBHJ9sRQzN1bbDnyuQZcFMEk2zqE/es+gfATB9+BDnQmyZX4drDuCX9p0kAyz9RgNwVFB4yum6SZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6115cca036efb55748956c8c9f3d1bc86e5fa9be66c97bfde61f8b310769bec0","last_reissued_at":"2026-07-05T09:03:53.062019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:53.062019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedPromptExtract (Medical Data Extraction Tool): Anonymization and Hi-fidelity Automated data extraction using NLP and prompt engineering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Barnali Das, Kshitij Jadhav, Lipika Bhat, Roomani Srivastava, Sarvesh Deshpande, Suraj Prasad","submitted_at":"2024-05-04T13:25:06Z","abstract_excerpt":"Introduction: The labour-intensive nature of data extraction from sources like discharge summaries (DS) poses significant obstacles to the digitisation of medical records particularly for low- and middle-income countries (LMICs). In this paper we present a completely automated method MedPromptExtract to efficiently extract data from DS while maintaining confidentiality. Methods: The source of data was Discharge Summaries (DS) from Kokilaben Dhirubhai Ambani Hospital (KDAH) of patients having Acute Kidney Injury (AKI). A pre-existing tool EIGEN which leverages semi-supervised learning technique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02664","kind":"arxiv","version":3},"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/2405.02664/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":"2405.02664","created_at":"2026-07-05T09:03:53.062074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02664v3","created_at":"2026-07-05T09:03:53.062074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02664","created_at":"2026-07-05T09:03:53.062074+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEK4ZIBW562V","created_at":"2026-07-05T09:03:53.062074+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEK4ZIBW562VOSEV","created_at":"2026-07-05T09:03:53.062074+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEK4ZIBW","created_at":"2026-07-05T09:03:53.062074+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/MEK4ZIBW562VOSEVNSGJ6PI3ZB","json":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB.json","graph_json":"https://pith.science/api/pith-number/MEK4ZIBW562VOSEVNSGJ6PI3ZB/graph.json","events_json":"https://pith.science/api/pith-number/MEK4ZIBW562VOSEVNSGJ6PI3ZB/events.json","paper":"https://pith.science/paper/MEK4ZIBW"},"agent_actions":{"view_html":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB","download_json":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB.json","view_paper":"https://pith.science/paper/MEK4ZIBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02664&json=true","fetch_graph":"https://pith.science/api/pith-number/MEK4ZIBW562VOSEVNSGJ6PI3ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/MEK4ZIBW562VOSEVNSGJ6PI3ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB/action/storage_attestation","attest_author":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB/action/author_attestation","sign_citation":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB/action/citation_signature","submit_replication":"https://pith.science/pith/MEK4ZIBW562VOSEVNSGJ6PI3ZB/action/replication_record"}},"created_at":"2026-07-05T09:03:53.062074+00:00","updated_at":"2026-07-05T09:03:53.062074+00:00"}