From b0c975b53fb5e78718427d804ec53f15b75023ae Mon Sep 17 00:00:00 2001 From: Chris Date: Tue, 11 Jun 2024 17:11:21 -0500 Subject: [PATCH] merged clinical nodes --- gdcdictionary/schemas/condition.yaml | 480 +++++++++++++++++- gdcdictionary/schemas/measurement.yaml | 451 ++++++++++++++++ gdcdictionary/schemas/observation.yaml | 209 +++++++- .../blood_pressure_test.yaml | 2 + .../{schemas => unused}/cardiac_mri.yaml | 0 .../{schemas => unused}/comorbidity.yaml | 0 .../{schemas => unused}/diagnosis.yaml | 0 .../{schemas => unused}/diagnostic_test.yaml | 2 + .../electrocardiogram_test.yaml | 0 .../{schemas => unused}/exposure.yaml | 0 .../{schemas => unused}/family_history.yaml | 0 .../{schemas => unused}/followup.yaml | 0 .../{schemas => unused}/lab_result.yaml | 0 .../lifestyle_risk_factor.yaml | 0 .../{schemas => unused}/medical_history.yaml | 0 15 files changed, 1132 insertions(+), 12 deletions(-) rename gdcdictionary/{schemas => unused}/blood_pressure_test.yaml (98%) rename gdcdictionary/{schemas => unused}/cardiac_mri.yaml (100%) rename gdcdictionary/{schemas => unused}/comorbidity.yaml (100%) rename gdcdictionary/{schemas => unused}/diagnosis.yaml (100%) rename gdcdictionary/{schemas => unused}/diagnostic_test.yaml (98%) rename gdcdictionary/{schemas => unused}/electrocardiogram_test.yaml (100%) rename gdcdictionary/{schemas => unused}/exposure.yaml (100%) rename gdcdictionary/{schemas => unused}/family_history.yaml (100%) rename gdcdictionary/{schemas => unused}/followup.yaml (100%) rename gdcdictionary/{schemas => unused}/lab_result.yaml (100%) rename gdcdictionary/{schemas => unused}/lifestyle_risk_factor.yaml (100%) rename gdcdictionary/{schemas => unused}/medical_history.yaml (100%) diff --git a/gdcdictionary/schemas/condition.yaml b/gdcdictionary/schemas/condition.yaml index dd3aba5..3cc45a8 100644 --- a/gdcdictionary/schemas/condition.yaml +++ b/gdcdictionary/schemas/condition.yaml @@ -42,20 +42,20 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" condition_code: - description: The code for a specific codition, assigned by the code system. - type: string + description: The code for a specific codition, assigned by the code system. + type: string -condition_concept_id: - description: The CONDITION_CONCEPT_ID field is recommended for primary use in analyses, and must be used for network studies. This is the standard concept mapped from the source value which represents a condition The CONCEPT_ID that the CONDITION_SOURCE_VALUE maps to. Only records whose source values map to concepts with a domain of “Condition” should go in this table. Accepted Concepts. - type: string + condition_concept_id: + description: The CONDITION_CONCEPT_ID field is recommended for primary use in analyses, and must be used for network studies. This is the standard concept mapped from the source value which represents a condition The CONCEPT_ID that the CONDITION_SOURCE_VALUE maps to. Only records whose source values map to concepts with a domain of “Condition” should go in this table. Accepted Concepts. + type: string -condition_source_concept_id: - description: This is the concept representing the condition source value and may not necessarily be standard. This field is discouraged from use in analysis because it is not required to contain Standard Concepts that are used across the OHDSI community, and should only be used when Standard Concepts do not adequately represent the source detail for the Condition necessary for a given analytic use case. Consider using CONDITION_CONCEPT_ID instead to enable standardized analytics that can be consistent across the network. If the CONDITION_SOURCE_VALUE is coded in the source data using an OMOP supported vocabulary put the concept id representing the source value here. - type: string + condition_source_concept_id: + description: This is the concept representing the condition source value and may not necessarily be standard. This field is discouraged from use in analysis because it is not required to contain Standard Concepts that are used across the OHDSI community, and should only be used when Standard Concepts do not adequately represent the source detail for the Condition necessary for a given analytic use case. Consider using CONDITION_CONCEPT_ID instead to enable standardized analytics that can be consistent across the network. If the CONDITION_SOURCE_VALUE is coded in the source data using an OMOP supported vocabulary put the concept id representing the source value here. + type: string -condition_source_value: - description: This field houses the verbatim value from the source data representing the condition that occurred. For example, this could be an ICD10 or Read code. This code is mapped to a Standard Condition Concept in the Standardized Vocabularies and the original code is stored here for reference. - type: string + condition_source_value: + description: This field houses the verbatim value from the source data representing the condition that occurred. For example, this could be an ICD10 or Read code. This code is mapped to a Standard Condition Concept in the Standardized Vocabularies and the original code is stored here for reference. + type: string condition_code_system: description: The system that assigned the code for a specific condition. @@ -104,3 +104,461 @@ condition_source_value: subjects: description: The submitter_id or id of the case this condition describes, i.e., a link to a record in the parent node. $ref: "_definitions.yaml#/to_one" + + ## From BloodPAC "comorbidity" node + comorbidity: ## From BloodPAC "comorbidity" node + description: > + Text term to identify a coexistent disease or condition in a person. + + + ### From BloodPAC "diagnosis" node + age_at_diagnosis: + term: + $ref: "_terms.yaml#/age_at_diagnosis" + type: integer + maximum: 89 + minimum: 0 + + age_at_diagnosis_gt89: + term: + $ref: "_terms.yaml#/age_at_diagnosis" + enum: + - "Yes" + - "No" + + ajcc_clinical_m: + term: + $ref: "_terms.yaml#/ajcc_clinical_m" + type: string + + ajcc_clinical_n: + term: + $ref: "_terms.yaml#/ajcc_clinical_n" + type: string + + ajcc_clinical_stage: + term: + $ref: "_terms.yaml#/ajcc_clinical_stage" + type: string + + ajcc_clinical_t: + term: + $ref: "_terms.yaml#/ajcc_clinical_t" + type: string + + ajcc_pathologic_m: + term: + $ref: "_terms.yaml#/ajcc_pathologic_m" + type: string + + ajcc_pathologic_n: + term: + $ref: "_terms.yaml#/ajcc_pathologic_n" + type: string + + ajcc_pathologic_stage: + term: + $ref: "_terms.yaml#/ajcc_pathologic_stage" + type: string + + ajcc_pathologic_t: + term: + $ref: "_terms.yaml#/ajcc_pathologic_t" + type: string + + best_overall_response: + description: "The best improvement achieved throughout the entire course of protocol treatment." + type: string + + classification_of_tumor: + term: + $ref: "_terms.yaml#/classification_of_tumor" + type: string + + # days_to_best_overall_response: + # description: "Number of days between the date used for index and the date of the patient's best overall response." + # type: integer + + # days_to_diagnosis: + # description: "Number of days between the date used for index and the date of the patient's diagnosis." + # type: integer + + method_of_diagnosis: + term: + $ref: "_terms.yaml#/method_of_diagnosis" + type: string + + morphology: + term: + $ref: "_terms.yaml#/morphology" + type: string + + overall_survival: + description: "Number of days between the date used for index and the patient's date of death or the date the patient was last known to be alive." + type: integer + + primary_diagnosis: + term: + $ref: "_terms.yaml#/primary_diagnosis" + type: string + + prior_malignancy: + term: + $ref: "_terms.yaml#/prior_malignancy" + type: string + + prior_treatment: + term: + $ref: "_terms.yaml#/prior_treatment" + type: string + + progression_free_survival: + description: "Number of days between the date used for index and the first date the patient is known to be free of disease progression." + type: integer + + progression_free_survival_event: + description: "The event used to define the patient's disease progression." + type: string + + residual_disease: + term: + $ref: "_terms.yaml#/residual_disease" + type: string + + tissue_or_organ_of_origin: + term: + $ref: "_terms.yaml#/tissue_or_organ_of_origin" + type: string + + tumor_grade: + term: + $ref: "_terms.yaml#/tumor_grade" + type: string + + +### From BioData Catalyst "medical_history" node + age_at_cac_volume: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of cac_volume (years) (HARMONIZED) + type: number + + age_at_cac_score: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of cac_score (years) (HARMONIZED) + type: number + + age_at_carotid_plaque: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of carotid_plaque (years) (HARMONIZED) + type: number + + age_at_carotid_stenosis: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of carotid_stenosis (years) (HARMONIZED) + type: number + + age_at_cimt_2: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of cimt_2 (years) (HARMONIZED) + type: number + + age_at_cimt_1: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of cimt_1 (years) (HARMONIZED) + type: number + + age_at_vte_case_status: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of vte_case_status (HARMONIZED) + type: number + + age_at_vte_prior_history: ### From BioData Catalyst "medical_history" node + description: > + age at measurement of vte_prior_history (years) (HARMONIZED) + type: number + + asthma: ### From BioData Catalyst "medical_history" node + description: > + Reported Asthma condition in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + atrial_fibrillation: ### From BioData Catalyst "medical_history" node + description: > + Reported atrial fibrillation condition in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + cabg_presence: ### From BioData Catalyst "medical_history" node + description: > + Reported presence of coronary artery bypass graft (CABG) in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + cac_score: ### From BioData Catalyst "medical_history" node + description: > + Coronary artery calcification (CAC) score using Agatston scoring of CT scan(s) of coronary arteries decimal (HARMONIZED) + type: number + + cac_volume: ### From BioData Catalyst "medical_history" node + description: > + Coronary artery calcium volume using CT scan(s) of coronary arteries (HARMONIZED) + type: number + + carotid_plaque: + description: > + Presence or absence of carotid plaque. (HARMONIZED) + enum: + - "Plaque not present" + - "Plaque present" + + carotid_stenosis: ### From BioData Catalyst "medical_history" node + description: > + Extent of narrowing of the carotid artery. (HARMONIZED) + type: string + + cerebrovascular_disease: ### From BioData Catalyst "medical_history" node + description: > + Reported Cerebrovascular disease in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + chronic_bronchitis: ### From BioData Catalyst "medical_history" node + description: > + Reported chronic bronchitis condition in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + cimt_1: ### From BioData Catalyst "medical_history" node + description: > + Common carotid intima-media thickness, calculated as the mean of two values: mean of multiple thickness estimates from the left far wall and from the right far wall. (HARMONIZED) + type: number + + cimt_2: ### From BioData Catalyst "medical_history" node + description: > + Common carotid intima-media thickness, calculated as the mean of four values: maximum of multiple thickness estimates from the left far wall, left near wall, right far wall, and right near wall. (mm) (HARMONIZED) + type: number + + copd: ### From BioData Catalyst "medical_history" node + description: > + Reported Chronic Obstructive Pulmonary Disease (COPD) in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + covid_hospital_admission: ### From BioData Catalyst "medical_history" node + description: > + Did COVID-19 contribute to need for hospital admission? + enum: + - "Yes" + - "No" + - Not Reported + + covid_hospital_admission_age: ### From BioData Catalyst "medical_history" node + description: > + Age on hospital admit (years, age ≥1 year) + type: integer + + covid_icu: ### From BioData Catalyst "medical_history" node + description: > + Was patient admitted to ICU during hospitalization? + enum: + - "Yes" + - "No" + - Not Reported + + covid_icu_stay_length: ### From BioData Catalyst "medical_history" node + description: > + Total ICU length of stay (from hospital admit) + type: integer + + covid_pos_ever_yn: ### From BioData Catalyst "medical_history" node + description: > + Any positive COVID-19 test? + enum: + - "Yes" + - "No" + - Not Reported + + diabetes: ### From BioData Catalyst "medical_history" node + description: > + Reported Diabetes in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + emphysema: ### From BioData Catalyst "medical_history" node + description: > + Reported Emphysema in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + chronic_respiratory_disease: ### From BioData Catalyst "medical_history" node + description: > + Reported Chronic Respiratory disease in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + coronary_artery_disease: ### From BioData Catalyst "medical_history" node + description: > + Reported Coronary Artery disease in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + heart_failure: ### From BioData Catalyst "medical_history" node + description: > + Reported Heart failure in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + hyperlipidemia: ### From BioData Catalyst "medical_history" node + description: > + Reported Hyperlipidemia condition in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + hypertension: ### From BioData Catalyst "medical_history" node + description: > + Reported Hypertension condition in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + myocardial_infarction: ### From BioData Catalyst "medical_history" node + description: > + Reported Myocardial Infarction in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + stroke: ### From BioData Catalyst "medical_history" node + description: > + Reported Stroke in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + + type1_diabetes: ### From BioData Catalyst "medical_history" node + description: > + Reported Type-1 Diabetes in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + type2_diabetes: ### From BioData Catalyst "medical_history" node + description: > + Reported Type-2 Diabetes in the participant (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + vte_case_status: + description: > + An indicator of whether a subject experienced a venous thromboembolismevent (VTE) that was verified by adjudication or by medical professionals. (HARMONIZED) + enum: + - "Yes" + - "No" + - "Not reported" + - "Unknown" + + vte_followup_start_age: ### From BioData Catalyst "medical_history" node + description: > + Age of subject at the start of the follow up period during which venousthromboembolism (VTE) events were reviewed and adjudicated. (years) (HARMONIZED) + type: number + + vte_prior_history: ### From BioData Catalyst "medical_history" node + description: > + An indicator of whether a subject had a venous thromboembolism (VTE)event prior to the start of the medical review process (includingself-reported events). (HARMONIZED) + type: boolean + + + unit_vte_followup_start_age: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for vte_followup_start_age (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_vte_prior_history: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for vte_prior_history (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_vte_case_status: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for vte_case_status (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + + unit_cac_volume: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for cac_volume (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_cac_score: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for cac_score (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_carotid_stenosis: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for carotid_stenosis (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_cimt_1: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for cimt_1 (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_cimt_2: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for cimt_2 (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_carotid_plaque: ### From BioData Catalyst "medical_history" node + description: > + harmonization unit for carotid_plaque (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string diff --git a/gdcdictionary/schemas/measurement.yaml b/gdcdictionary/schemas/measurement.yaml index db78335..fec4a56 100644 --- a/gdcdictionary/schemas/measurement.yaml +++ b/gdcdictionary/schemas/measurement.yaml @@ -40,6 +40,7 @@ properties: $ref: "_definitions.yaml#/ubiquitous_properties" +## OMOP properties days_to_measurement: description: The difference in days between the subject's index_date and the date of the measurement. Used to de-identify the measurement date. type: integer @@ -108,4 +109,454 @@ properties: description: The submitter_id or id of the subject this measurement describes, i.e., a link to a record in the parent node. $ref: "_definitions.yaml#/to_one" + ####### Non OMOP properties + bp_diastolic: # from BDC "blood_pressure_test" node + description: > + Resting diastolic blood pressure from the upper arm in a clinical setting. (mmHg) + type: number + + bp_systolic: # from BDC "blood_pressure_test" node + description: > + Resting systolic blood pressure from the upper arm in a clinical setting. (mmHg) + type: number + + age_at_bp_systolic: # from BDC "blood_pressure_test" node + description: > + age at measurement of bp_systolic (years) + type: number + + unit_bp_systolic: # from BDC "blood_pressure_test" node + description: > + harmonization unit for bp_systolic (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) + type: string + + age_at_bp_diastolic: # from BDC "blood_pressure_test" node + description: > + age at measurement of bp_diastolic (years) + type: number + + unit_bp_diastolic: # from BDC "blood_pressure_test" node + description: > + harmonization unit for bp_diastolic (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) + type: string + + cardiac_output: # from BDC "cardiac_mri" node + description: > + RV Cardiac output (l/min) + type: number + + pr_duration: # from BDC "cardiac_mri" and "electrocardiogram_test" nodes + description: > + PR interval (msec) (HARMONIZED) + type: number + + qrs_duration: # from BDC "cardiac_mri" and "electrocardiogram_test" nodes + description: > + QRS interval (msec) (HARMONIZED) + type: number + + qt_duration: # from BDC "cardiac_mri" and "electrocardiogram_test" nodes + description: > + QT interval (msec) (HARMONIZED) + type: number + + gtc_duration: # from BDC "cardiac_mri" and "electrocardiogram_test" nodes + description: > + QTC interval (msec) (HARMONIZED) + type: number + + + + + + + +### From BDC "lab_result" node; most or all of these should be harmonized to OMOP + + age_at_basophil_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of basophil_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_eosinophil_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of eosinophil_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_hdl: ### From BDC "lab_result" node + description: > + age at measurement of hdl (years) (HARMONIZED) + type: number + + age_at_hemoglobin_mcnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of hemoglobin_mcnc_bld. (years) (HARMONIZED) + type: number + + age_at_hematocrit_vfr_bld: ### From BDC "lab_result" node + description: > + Measurement of hematocrit, the fraction of volume (vfr) of blood (bld) that is composed of red blood cells. (years) (HARMONIZED) + type: number + + age_at_ldl: ### From BDC "lab_result" node + description: > + age at measurement of ldl (years) (HARMONIZED) + type: number + + age_at_lymphocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of lymphocyte_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_mch_entmass_rbc: ### From BDC "lab_result" node + description: > + age at measurement of mch_entmass_rbc (years) (HARMONIZED) + type: number + + age_at_mchc_mcnc_rbc: ### From BDC "lab_result" node + description: > + age at measurement of mchc_mcnc_rbc (years) (HARMONIZED) + type: number + + age_at_mcv_entvol_rbc: ### From BDC "lab_result" node + description: > + age at measurement of mcv_entvol_rbc (years) (HARMONIZED) + type: number + + age_at_monocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of monocyte_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_neutrophil_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of neutrophil_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_platelet_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of platelet_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_pmv_entvol_bld: ### From BDC "lab_result" node + description: > + age at measurement of pmv_entvol_bld (years) (HARMONIZED) + type: number + + age_at_rbc_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of rbc_ncnc_bld (years) (HARMONIZED) + type: number + + age_at_rdw_ratio_rbc: ### From BDC "lab_result" node + description: > + age at measurement of rdw_ratio_rbc (years) (HARMONIZED) + type: number + + age_at_total_cholesterol: ### From BDC "lab_result" node + description: > + age at measurement of total_cholesterol (years) (HARMONIZED) + type: number + + age_at_triglycerides: ### From BDC "lab_result" node + description: > + age at measurement of triglycerides (HARMONIZED) + type: number + + age_at_wbc_ncnc_bld: ### From BDC "lab_result" node + description: > + age at measurement of wbc_ncnc_bld (years) (HARMONIZED) + type: number + + basophil_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of basophils in the blood (bld). (thousands / microliter) (HARMONIZED) + type: number + + eosinophil_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of eosinophils in the blood (bld). (thousands / microliter) (HARMONIZED) + type: number + + hdl: ### From BDC "lab_result" node + description: > + Hdl cholesterol (mg/dl) (HARMONIZED) + type: number + + hematocrit_vfr_bld: ### From BDC "lab_result" node + description: > + Measurement of hematocrit, the fraction of volume (vfr) of blood (bld) that is composed of red blood cells. (percentage) (HARMONIZED) + type: number + + hemoglobin_mcnc_bld: ### From BDC "lab_result" node + description: > + Measurement of mass per volume, or mass concentration (mcnc), of hemoglobin in the blood (bld). (g / dL = grams per deciliter) (HARMONIZED) + type: number + + ldl: ### From BDC "lab_result" node + description: > + Ldl cholesterol (mg/dl) (HARMONIZED) + type: number + + lymphocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of lymphocytes in the blood (bld). (thousands / microliter) (HARMONIZED) + type: number + + mch_entmass_rbc: ### From BDC "lab_result" node + description: > + Measurement of the average mass (entmass) of hemoglobin per red blood cell(rbc), known as mean corpuscular hemoglobin (MCH). (pg = picogram) (HARMONIZED) + type: number + + mchc_mcnc_rbc: ### From BDC "lab_result" node + description: > + Measurement of the mass concentration (mcnc) of hemoglobin in a given volume of packed red blood cells (rbc), known as mean corpuscular hemoglobin concentration (MCHC). (g /dL = grams per deciliter) (HARMONIZED) + type: number + + mcv_entvol_rbc: ### From BDC "lab_result" node + description: > + Measurement of the mass concentration (mcnc) of hemoglobin in a given volume of packed red blood cells (rbc), known as mean corpuscular hemoglobin concentration (MCHC). (g /dL = grams per deciliter) (HARMONIZED) + type: number + + monocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of monocytes in the blood (bld). (HARMONIZED) + type: number + + neutrophil_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of neutrophils in the blood (bld). (HARMONIZED) + type: number + + platelet_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of platelets in the blood (bld). (thousands / microliter) (HARMONIZED) + type: number + + pmv_entvol_bld: ### From BDC "lab_result" node + description: > + Measurement of the mean volume (entvol) of platelets in the blood (bld), known as mean platelet volume (MPV or PMV). (fL = femtoliter) (HARMONIZED) + type: number + + rbc_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of red blood cells in the blood (bld). (millions / microliter) (HARMONIZED) + type: number + + rdw_ratio_rbc: ### From BDC "lab_result" node + description: > + Measurement of the ratio of variation in width to the mean width of the red blood cell (rbc) volume distribution curve taken at +/- 1 CV, known as red cell distribution width (RDW). (percentage) (HARMONIZED) + type: number + + total_cholesterol: ### From BDC "lab_result" node + description: > + Total cholesterol (mg/dl) (HARMONIZED) + type: number + + triglycerides: ### From BDC "lab_result" node + description: > + Triglycerides (mg/dl) (HARMONIZED) + type: number + + unit_basophil_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for basophil_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_eosinophil_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for eosinophil_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_hdl: ### From BDC "lab_result" node + description: > + harmonization unit for hdl (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_hematocrit_vfr_bld: ### From BDC "lab_result" node + description: > + harmonization unit for hematocrit_vfr_bld. (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_hemoglobin_mcnc_bld: ### From BDC "lab_result" node + description: > + Measurement of hematocrit, the fraction of volume (vfr) of blood (bld) that is composed of red blood cells. (percentage) (HARMONIZED) + type: string + + unit_ldl: ### From BDC "lab_result" node + description: > + harmonization unit for ldl (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_lymphocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for lymphocyte_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_mch_entmass_rbc: ### From BDC "lab_result" node + description: > + harmonization unit for mch_entmass_rbc (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_mchc_mcnc_rbc: ### From BDC "lab_result" node + description: > + harmonization unit for mchc_mcnc_rbc (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_mcv_entvol_rbc: ### From BDC "lab_result" node + description: > + harmonization unit for mcv_entvol_rbc (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_monocyte_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for monocyte_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_neutrophil_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for neutrophil_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_platelet_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for platelet_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_pmv_entvol_bld: ### From BDC "lab_result" node + description: > + harmonization unit for pmv_entvol_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_rbc_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for rbc_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_rdw_ratio_rbc: ### From BDC "lab_result" node + description: > + harmonization unit for rdw_ratio_rbc (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_total_cholesterol: ### From BDC "lab_result" node + description: > + harmonization unit for total_cholesterol (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_triglycerides: ### From BDC "lab_result" node + description: > + harmonization unit for triglycerides (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + unit_wbc_ncnc_bld: ### From BDC "lab_result" node + description: > + harmonization unit for wbc_ncnc_bld (A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed.) (HARMONIZED) + type: string + + wbc_ncnc_bld: ### From BDC "lab_result" node + description: > + Count by volume, or number concentration (ncnc), of white blood cells in the blood (bld). (thousands / microliter) (HARMONIZED) + type: number + + + ### From MIDRC "measurement" node: + test_name: # from MIDRC measurement + description: The name of the test for which this measurement was the result. + type: string + # enum: + # - COVID-19 + + test_result_text: # from MIDRC measurement + description: The measured result of the test described using a list of enumerations. + type: string + # enum: + # - Indeterminate + # - Negative + # - Positive + # - Not Reported + + test_method: # from MIDRC measurement + description: The test method used to confirm a condition or produce a measurement. + type: string + # enum: + # - RT-PCR + # - Rapid antigen test + # - Not Reported + + ### BloodPAC properties + analyte_name: ### From BloodPAC "diagnostic_test" node + description: > + The name of analyte or biomarker tested in the case that the test is a quantitative assay. + type: string + + assay_kit_name: ### From BloodPAC "diagnostic_test" node + term: + $ref: "_terms.yaml#/assay_kit_name" + type: string + + assay_kit_vendor: ### From BloodPAC "diagnostic_test" node + term: + $ref: "_terms.yaml#/assay_kit_vendor" + type: string + + assay_kit_version: ### From BloodPAC "diagnostic_test" node + term: + $ref: "_terms.yaml#/assay_kit_version" + type: string + + # days_to_test: # replaced with days_to_measurement ### From BloodPAC "diagnostic_test" node + # description: > + # Number of days between the date used for index and the date the patient was diagnosed with a comorbidity. + # type: integer + + equipment_manufacturer: ### From BloodPAC "diagnostic_test" node + term: + $ref: "_terms.yaml#/equipment_manufacturer" + type: string + + equipment_model: ### From BloodPAC "diagnostic_test" node + term: + $ref: "_terms.yaml#/equipment_model" + type: string + + test_anatomic_site: ### From BloodPAC "diagnostic_test" node + description: > + Indicate the anatomic site of the biopsy, image or other diagnostic test + type: string + +# test_name: ### From BloodPAC "diagnostic_test" node +# description: > +# The name the laboratory test. +# type: string + +# test_result: ### From BloodPAC "diagnostic_test" node +# description: > +# The categorical result of the laboratory test. +# type: string + +# test_result_concept_id: ### From BloodPAC "diagnostic_test" node +# description: > +# The concept ID of the test. +# type: string + + test_sample_composition: ### From BloodPAC "diagnostic_test" node + description: > + Indicate the composition or type of biological sample used for the test (e.g., blood, urine, solid tissue, saliva, etc.) + type: string + + test_type: ### From BloodPAC "diagnostic_test" node + description: > + The general type or category of the laboratory or diagnostic test. + type: string + + test_units: ### From BloodPAC "diagnostic_test" node + description: > + The units corresponding to a test_value for a test_analyte_type + type: string + + test_result_number: ### From BloodPAC "diagnostic_test" node + description: > + The numerical value representing the laboratory or diagnostic test measurement of the 'analyte_name'; also indicate the 'test_units'. + type: number + diff --git a/gdcdictionary/schemas/observation.yaml b/gdcdictionary/schemas/observation.yaml index 9977f0a..221958e 100644 --- a/gdcdictionary/schemas/observation.yaml +++ b/gdcdictionary/schemas/observation.yaml @@ -53,7 +53,7 @@ properties: type: string observation_name: - description: The short of the observation about the subject obtained in the context of examination, questioning or a during procedure. + description: The short name of the observation about the subject obtained in the context of examination, questioning or a during procedure. type: string observation_source_concept_id: @@ -111,3 +111,210 @@ properties: subjects: $ref: "_definitions.yaml#/to_one" + + ## From BloodPAC / BioData Catalyst "exposure" nodes; smoking/tobacco status questions + age_at_current_smoker_baseline: ## From BDC "exposure" node + description: Age in years at measurement of current_smoker_baseline. + type: number + + age_at_ever_smoker_baseline: ## From BDC "exposure" node + description: Age in years at measurement of ever_smoker_baseline. + type: number + + alcohol_history: ## From BloodPAC "exposure" node + term: + $ref: "_terms.yaml#/alcohol_history" + type: string + + alcohol_intensity: ## From BloodPAC "exposure" node + term: + $ref: "_terms.yaml#/alcohol_intensity" + type: string + + cigarettes_per_day: ## From BloodPAC "exposure" node + term: + $ref: "_terms.yaml#/cigarettes_per_day" + type: number + + current_smoker_baseline: ## From BDC "exposure" node + description: Indicates whether subject currently smokes cigarettes. + type: string + + ever_smoker_baseline: ## From BDC "exposure" node + description: Indicates whether subject ever regularly smoked cigarettes. + type: string + + tobacco_smoking_status: ## From BDC/BloodPAC "exposure" node + description: Subject's tobacco smoking status. + type: string + # enum: + # - "Never" + # - "Former" + # - "Current" + + unit_current_smoker_baseline: ## From BDC "exposure" node + description: Harmonization unit for current_smoker_baseline. A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed. + type: string + + unit_ever_smoker_baseline: ## From BDC "exposure" node + description: Harmonization unit for ever_smoker_baseline. A "harmonization unit" is a defined group of subjects whose phenotypes can be similarly processed. + type: string + + years_smoked: ## From BDC/BloodPAC "exposure" node + term: + $ref: "_terms.yaml#/years_smoked" + type: + - number + maximum: 89 + minimum: 0 + + years_smoked_gt89: ## From BDC "exposure" node + description: Indicator of whether the number of years smoked is greater than 89 years. + enum: + - "Yes" + - "No" + + ## From BloodPAC "family_history" node + relative_with_cancer_history: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/relative_with_cancer_history" + enum: + - "Yes" + - "No" + - Unknown + - Not Reported + + relationship_type: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/relationship_type" + type: string + + relationship_gender: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/gender" + enum: + - Female + - Male + - Unknown + - Unspecified + - Not Reported + + relationship_age_at_diagnosis: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/relationship_age_at_diagnosis" + type: integer + maximum: 89 + minimum: 0 + + relationship_age_at_diagnosis_gt89: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/relationship_age_at_diagnosis" + enum: + - "Yes" + - "No" + + relationship_primary_diagnosis: ## From BloodPAC "family_history" node + term: + $ref: "_terms.yaml#/primary_diagnosis" + type: string + + +### From BloodPAC "followup" node + adverse_event: ### From BloodPAC "followup" node + description: "Text that represents the Common Terminology Criteria for Adverse Events low level term name for an adverse event." + type: string + + bmi: ### From BloodPAC "followup" node + description: "The body mass divided by the square of the body height expressed in units of kg/m^2." + type: number + + cause_of_response: ### From BloodPAC "followup" node + description: > + A specific regimen or line of therapy responsible for the patient's observed improvement + achived at a certain point in time during a patient's treatment protocol. + type: string + + # days_to_adverse_event: ### From BloodPAC "followup" node + # description: "Number of days between the date used for index and the date the patient had an adverse event." + # type: integer + + # days_to_followup: ### From BloodPAC "followup" node + # description: "Number of days between the date used for index and the date the patient was seen or contacted at follow-up." + # type: integer + + # days_to_progression: ### From BloodPAC "followup" node + # description: "Number of days between the date used for index and the date the patient was diagnosed with progression of disease." + # type: integer + + # days_to_recurrence: ### From BloodPAC "followup" node + # description: "Number of days between the date used for index and the date the patient was diagnosed with a recurrent malignancy." + # type: integer + + disease_response: ### From BloodPAC "followup" node + description: "The observed improvement achieved at a certain point in time during a patient's treatment protocol." + type: string + + ecog_performance_status: ### From BloodPAC "followup" node + description: "The ECOG functional performance status of the patient/participant." + enum: + - "0" + - "1" + - "2" + - "3" + - "4" + - "5" + + height: ### From BloodPAC "followup" node + description: "The height of the patient in centimeters." + type: number + + progression_or_recurrence: ### From BloodPAC "followup" node + description: "Indicator to identify whether a patient has had a recurrent or relapsed malignancy or a progression of disease." + enum: + - "Yes" + - "No" + - Unknown + + time_from_alcohol: ### From BloodPAC "followup" node + description: > + Hours since the patient last consumed alcohol. + type: number + + time_from_exercise: ### From BloodPAC "followup" node + description: > + Hours since the patient last exercised. + type: number + + time_from_food: ### From BloodPAC "followup" node + description: > + Hours since the patient last consumed food. + type: number + + time_from_physical_trauma: ### From BloodPAC "followup" node + description: > + Hours since the patient last experienced physical trauma. + type: number + + time_from_biopsy: ### From BloodPAC "followup" node + description: > + Hours since the patient last underwent a biopsy; please record the biopsy information in the 'diagnostic_test' node and link that record to this followup record. + type: number + + time_from_recreational_drugs: ### From BloodPAC "followup" node + description: > + Hours since the patient last used recreational drugs. + type: number + + time_from_tobacco: ### From BloodPAC "followup" node + description: > + Hours since the patient last used tobacco. + type: number + + time_from_treatment: ### From BloodPAC "followup" node + description: > + Hours since the patient received a treatment, including surgical procedures or medications; please record the treatment information in the 'treatment' node and link that record to this followup record. + type: number + + weight: ### From BloodPAC "followup" node + description: "The weight of the patient measured in kilograms." + type: number diff --git a/gdcdictionary/schemas/blood_pressure_test.yaml b/gdcdictionary/unused/blood_pressure_test.yaml similarity index 98% rename from gdcdictionary/schemas/blood_pressure_test.yaml rename to gdcdictionary/unused/blood_pressure_test.yaml index 7309ed5..ae83a02 100644 --- a/gdcdictionary/schemas/blood_pressure_test.yaml +++ b/gdcdictionary/unused/blood_pressure_test.yaml @@ -1,3 +1,5 @@ +# merged into Measurement node +# from BDC $schema: "http://json-schema.org/draft-04/schema#" id: "blood_pressure_test" diff --git a/gdcdictionary/schemas/cardiac_mri.yaml b/gdcdictionary/unused/cardiac_mri.yaml similarity index 100% rename from gdcdictionary/schemas/cardiac_mri.yaml rename to gdcdictionary/unused/cardiac_mri.yaml diff --git a/gdcdictionary/schemas/comorbidity.yaml b/gdcdictionary/unused/comorbidity.yaml similarity index 100% rename from gdcdictionary/schemas/comorbidity.yaml rename to gdcdictionary/unused/comorbidity.yaml diff --git a/gdcdictionary/schemas/diagnosis.yaml b/gdcdictionary/unused/diagnosis.yaml similarity index 100% rename from gdcdictionary/schemas/diagnosis.yaml rename to gdcdictionary/unused/diagnosis.yaml diff --git a/gdcdictionary/schemas/diagnostic_test.yaml b/gdcdictionary/unused/diagnostic_test.yaml similarity index 98% rename from gdcdictionary/schemas/diagnostic_test.yaml rename to gdcdictionary/unused/diagnostic_test.yaml index 1fc848a..1390041 100644 --- a/gdcdictionary/schemas/diagnostic_test.yaml +++ b/gdcdictionary/unused/diagnostic_test.yaml @@ -1,3 +1,4 @@ +## From BloodPAC/MIDRC; merged into Measurement node schema: "http://json-schema.org/draft-04/schema#" id: "diagnostic_test" @@ -57,6 +58,7 @@ properties: description: The name of the test for which this measurement was the result. enum: - COVID-19 + test_result_text: # from MIDRC measurement description: The measured result of the test described using a list of enumerations. enum: diff --git a/gdcdictionary/schemas/electrocardiogram_test.yaml b/gdcdictionary/unused/electrocardiogram_test.yaml similarity index 100% rename from gdcdictionary/schemas/electrocardiogram_test.yaml rename to gdcdictionary/unused/electrocardiogram_test.yaml diff --git a/gdcdictionary/schemas/exposure.yaml b/gdcdictionary/unused/exposure.yaml similarity index 100% rename from gdcdictionary/schemas/exposure.yaml rename to gdcdictionary/unused/exposure.yaml diff --git a/gdcdictionary/schemas/family_history.yaml b/gdcdictionary/unused/family_history.yaml similarity index 100% rename from gdcdictionary/schemas/family_history.yaml rename to gdcdictionary/unused/family_history.yaml diff --git a/gdcdictionary/schemas/followup.yaml b/gdcdictionary/unused/followup.yaml similarity index 100% rename from gdcdictionary/schemas/followup.yaml rename to gdcdictionary/unused/followup.yaml diff --git a/gdcdictionary/schemas/lab_result.yaml b/gdcdictionary/unused/lab_result.yaml similarity index 100% rename from gdcdictionary/schemas/lab_result.yaml rename to gdcdictionary/unused/lab_result.yaml diff --git a/gdcdictionary/schemas/lifestyle_risk_factor.yaml b/gdcdictionary/unused/lifestyle_risk_factor.yaml similarity index 100% rename from gdcdictionary/schemas/lifestyle_risk_factor.yaml rename to gdcdictionary/unused/lifestyle_risk_factor.yaml diff --git a/gdcdictionary/schemas/medical_history.yaml b/gdcdictionary/unused/medical_history.yaml similarity index 100% rename from gdcdictionary/schemas/medical_history.yaml rename to gdcdictionary/unused/medical_history.yaml