{"prediction": {"id": "7f2a5fc2-3595-556a-8504-670fceb2fd83", "work_id": "1b267e8f-17af-5e77-bfcb-acff0eb361fb", "study_id": "25afb31c-0594-5e90-b4a0-b1f4bab71153", "kind": "Model evaluation", "pages": [9], "version": "Version of record", "source_work_id": "1b267e8f-17af-5e77-bfcb-acff0eb361fb", "title": "Integration of machine learning to develop a disulfidptosis model for predicting glioma prognosis, immunotherapy response, and drug.", "doi": "10.1016/j.isci.2026.115657", "pdf_sha256": "540fc5c59875d0be06a4b1f86038c6baabb2a64c3e5fc5942039f2b8ab84ccb6", "physical_page_count": 27}, "fields": {"comparator": {"value": "alternative_model_or_method", "source_basis": "verified_profile", "pages": [9]}, "endpoint": {"value": "concordance_index", "source_basis": "verified_profile", "pages": [9]}, "family": {"value": "clinical_discrimination", "source_basis": "verified_profile", "pages": [9]}, "measurement_role": {"value": "prediction_performance", "source_basis": "original_pdf_review", "pages": [9]}, "metric": {"value": "concordance_index", "source_basis": "original_pdf_review", "pages": [9]}, "reference_type": {"value": "alternative_computational_methods", "source_basis": "verified_profile", "pages": [9]}, "result_operation": {"value": "survival_ranking", "source_basis": "original_pdf_review", "pages": [9]}, "role": {"value": "model_performance", "source_basis": "verified_profile", "pages": [9]}, "unit": {"value": "dimensionless", "source_basis": "verified_profile", "pages": [9]}}, "endpoints": [{"term": "discrimination_index", "label": "C-index and time-dependent AUC"}], "validations": [{"id": "65f809fc-f9e7-52cb-85d7-a1805c74b83b", "claim_id": "7f2a5fc2-3595-556a-8504-670fceb2fd83", "coverage": "direct_comparison", "support": "supports", "source": "unknown", "overlap": "overlap", "comparability": "matched", "statistics": "not_applicable", "anchors": [{"work_id": "1b267e8f-17af-5e77-bfcb-acff0eb361fb", "version": "Version of record", "pages": [26]}]}], "model_resources": {"total": 1, "page": 1, "limit": 50, "rows": [{"id": 497, "work_id": "1b267e8f-17af-5e77-bfcb-acff0eb361fb", "claim_id": "7f2a5fc2-3595-556a-8504-670fceb2fd83", "kind": "model", "label": "Glioma prognostic model training and validation script", "repository": "Author GitHub", "identifier": "Machine learning model.R", "source_page": 21, "availability": "author_reported_public", "url": "https://github.com/clarozhong/Rdata/blob/main/Machine%20learning%20model.R", "scope": "related_reference", "resource_version": null, "version_basis": null, "repository_commit": null, "repository_member": null, "source_file_sha256": null, "source_basis": "legacy_curated_resource", "priority": 2, "doi": "10.1016/j.isci.2026.115657", "title": "Integration of machine learning to develop a disulfidptosis model for predicting glioma prognosis, immunotherapy response, and drug.", "version": "Version of record", "pdf_sha256": "540fc5c59875d0be06a4b1f86038c6baabb2a64c3e5fc5942039f2b8ab84ccb6", "association_scope": "prediction", "resource_relation": "related_reference", "source_review": {"indexed": true, "source_basis": "legacy_curated_resource"}}], "review_status": "indexed_source"}}