{"prediction": {"id": "61f7ff5a-c492-5c0d-8acd-c4e008ce6ded", "work_id": "1a3ebd2e-7092-511f-8c46-85f73e06190b", "study_id": "0fbfbc1b-59ac-5a72-8cd0-c3145b5e42b4", "kind": "Clinical cohort holdout validation", "pages": [10], "version": "Version of record", "source_work_id": "1a3ebd2e-7092-511f-8c46-85f73e06190b", "title": "Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad.", "doi": "10.2196/29455", "pdf_sha256": "df428a6cd2f7a0b452519cdd293eb911f5298c2a74ead46768166e8cbf8ad966", "physical_page_count": 21}, "fields": {"endpoint": {"value": "classification_accuracy", "source_basis": "verified_profile", "pages": [10]}, "evaluation_scope": {"value": "internal_holdout", "source_basis": "verified_profile", "pages": [1, 10]}, "family": {"value": "classification_performance", "source_basis": "verified_profile", "pages": [10]}, "measurement_role": {"value": "classification_performance", "source_basis": "original_pdf_review", "pages": [10]}, "metric": {"value": "classification_accuracy", "source_basis": "original_pdf_review", "pages": [10]}, "population": {"value": "human_observations", "source_basis": "verified_profile", "pages": [1, 10]}, "prediction_target_type": {"value": "future_clinical_outcome", "source_basis": "original_pdf_review", "pages": [1]}, "role": {"value": "model_performance", "source_basis": "verified_profile", "pages": [10]}, "scenario": {"value": "internal_holdout", "source_basis": "original_pdf_review", "pages": [1, 10]}, "unit": {"value": "dimensionless", "source_basis": "verified_profile", "pages": [10]}}, "endpoints": [{"term": "classification_performance", "label": "Classification performance"}], "validations": [{"id": "573dc9ad-ccb1-575e-a485-b54bc587b527", "claim_id": "61f7ff5a-c492-5c0d-8acd-c4e008ce6ded", "coverage": "direct_comparison", "support": "supports", "source": "same_source", "overlap": "disjoint", "comparability": "matched", "statistics": "not_applicable", "anchors": [{"work_id": "1a3ebd2e-7092-511f-8c46-85f73e06190b", "version": "Version of record", "pages": [1, 10]}]}], "model_resources": {"total": 2, "page": 1, "limit": 50, "rows": [{"id": 70, "work_id": "1a3ebd2e-7092-511f-8c46-85f73e06190b", "claim_id": "61f7ff5a-c492-5c0d-8acd-c4e008ce6ded", "kind": "model", "label": "SVC_models.py", "repository": "GitHub", "identifier": "SVC_models.py", "source_page": 19, "availability": "author_reported_public", "url": "https://github.com/ElisaTardini/HNC-Digital-Twin/blob/main/SVC_models.py", "scope": "claim_specific", "resource_version": null, "version_basis": null, "repository_commit": null, "repository_member": null, "source_file_sha256": "4f3c1c709a932095ce16a406b54433bf7c99b8a292919f8893bbbbe73c77ab1b", "source_basis": "ai_reviewed_primary_file", "priority": 0, "doi": "10.2196/29455", "title": "Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad.", "version": "Version of record", "pdf_sha256": "df428a6cd2f7a0b452519cdd293eb911f5298c2a74ead46768166e8cbf8ad966", "association_scope": "prediction", "resource_relation": "indexed_resource", "source_review": {"indexed": true, "source_basis": "ai_reviewed_primary_file"}}, {"id": 502, "work_id": "1a3ebd2e-7092-511f-8c46-85f73e06190b", "claim_id": "61f7ff5a-c492-5c0d-8acd-c4e008ce6ded", "kind": "model", "label": "Head and neck cancer treatment-decision digital twin", "repository": "GitHub", "identifier": "ElisaTardini/HNC-Digital-Twin", "source_page": 9, "availability": "author_reported_available", "url": "https://github.com/ElisaTardini/HNC-Digital-Twin", "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": "10.2196/29455", "title": "Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad.", "version": "Version of record", "pdf_sha256": "df428a6cd2f7a0b452519cdd293eb911f5298c2a74ead46768166e8cbf8ad966", "association_scope": "prediction", "resource_relation": "related_reference", "source_review": {"indexed": true, "source_basis": "legacy_curated_resource"}}], "review_status": "indexed_source"}}