{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MICDDZUN5OVLZFNPD3GHUYZKSY","short_pith_number":"pith:MICDDZUN","schema_version":"1.0","canonical_sha256":"620431e68debaabc95af1ecc7a632a96222bbbf99c5b62a1c539298b5e215c3d","source":{"kind":"arxiv","id":"2211.09781","version":2},"attestation_state":"computed","paper":{"title":"Monitoring machine learning (ML)-based risk prediction algorithms in the presence of confounding medical interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexej Gossmann, Berkman Sahiner, Gene Pennello, Jean Feng, Nicholas Petrick, Romain Pirracchio","submitted_at":"2022-11-17T18:54:34Z","abstract_excerpt":"Performance monitoring of machine learning (ML)-based risk prediction models in healthcare is complicated by the issue of confounding medical interventions (CMI): when an algorithm predicts a patient to be at high risk for an adverse event, clinicians are more likely to administer prophylactic treatment and alter the very target that the algorithm aims to predict. A simple approach is to ignore CMI and monitor only the untreated patients, whose outcomes remain unaltered. In general, ignoring CMI may inflate Type I error because (i) untreated patients disproportionally represent those with low "},"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":"2211.09781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-11-17T18:54:34Z","cross_cats_sorted":["cs.CY","cs.LG"],"title_canon_sha256":"224588e96955aa06cd8176c967cda577833e4c8f145dd08eed2b66b925df44ec","abstract_canon_sha256":"a547a8eb2799bf8bfd4c33737cadee419a7023cc213c4f81d226ba2fc0b955cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:58.007901Z","signature_b64":"4qjmusxwfPltxwvuwVZXM5l9VSbFDwlBArM7HATESW0UtxNK0ixedRpRvhX1NlpCh6z/r57g2D8eHvTCNRktCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620431e68debaabc95af1ecc7a632a96222bbbf99c5b62a1c539298b5e215c3d","last_reissued_at":"2026-07-05T06:00:58.007512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:58.007512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monitoring machine learning (ML)-based risk prediction algorithms in the presence of confounding medical interventions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexej Gossmann, Berkman Sahiner, Gene Pennello, Jean Feng, Nicholas Petrick, Romain Pirracchio","submitted_at":"2022-11-17T18:54:34Z","abstract_excerpt":"Performance monitoring of machine learning (ML)-based risk prediction models in healthcare is complicated by the issue of confounding medical interventions (CMI): when an algorithm predicts a patient to be at high risk for an adverse event, clinicians are more likely to administer prophylactic treatment and alter the very target that the algorithm aims to predict. A simple approach is to ignore CMI and monitor only the untreated patients, whose outcomes remain unaltered. In general, ignoring CMI may inflate Type I error because (i) untreated patients disproportionally represent those with low "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09781","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/2211.09781/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":"2211.09781","created_at":"2026-07-05T06:00:58.007577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09781v2","created_at":"2026-07-05T06:00:58.007577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09781","created_at":"2026-07-05T06:00:58.007577+00:00"},{"alias_kind":"pith_short_12","alias_value":"MICDDZUN5OVL","created_at":"2026-07-05T06:00:58.007577+00:00"},{"alias_kind":"pith_short_16","alias_value":"MICDDZUN5OVLZFNP","created_at":"2026-07-05T06:00:58.007577+00:00"},{"alias_kind":"pith_short_8","alias_value":"MICDDZUN","created_at":"2026-07-05T06:00:58.007577+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/MICDDZUN5OVLZFNPD3GHUYZKSY","json":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY.json","graph_json":"https://pith.science/api/pith-number/MICDDZUN5OVLZFNPD3GHUYZKSY/graph.json","events_json":"https://pith.science/api/pith-number/MICDDZUN5OVLZFNPD3GHUYZKSY/events.json","paper":"https://pith.science/paper/MICDDZUN"},"agent_actions":{"view_html":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY","download_json":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY.json","view_paper":"https://pith.science/paper/MICDDZUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/MICDDZUN5OVLZFNPD3GHUYZKSY/graph.json","fetch_events":"https://pith.science/api/pith-number/MICDDZUN5OVLZFNPD3GHUYZKSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY/action/storage_attestation","attest_author":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY/action/author_attestation","sign_citation":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY/action/citation_signature","submit_replication":"https://pith.science/pith/MICDDZUN5OVLZFNPD3GHUYZKSY/action/replication_record"}},"created_at":"2026-07-05T06:00:58.007577+00:00","updated_at":"2026-07-05T06:00:58.007577+00:00"}