Esophageal Cancer Dataset

Comprehensive Esophageal Cancer Dataset for AI-Driven Early Detection & Research

@kaggle.abhinaba1biswas_esophageal_cancer_dataset

Table List

1 table(286.77 KB)

Esophageal Dataset

@kaggle.abhinaba1biswas_esophageal_cancer_dataset.esophageal_dataset

286.77 KB
3985 rows
85 columns

unnamed_0 Unnamed: 0	patient_barcode Patient Barcode	tissue_source_site Tissue Source Site	patient_id Patient Id	bcr_patient_uuid Bcr Patient Uuid	informed_consent_verified Informed Consent Verified	icd_o_3_site Icd O 3 Site	icd_o_3_histology Icd O 3 Histology	icd_10 Icd 10	tissue_prospective_collection_indicator Tissue Prospective Collection Indicator	tissue_retrospective_collection_indicator Tissue Retrospective Collection Indicator	days_to_birth Days To Birth	country_of_birth Country Of Birth	gender Gender	height Height	weight Weight	country_of_procurement Country Of Procurement	state_province_of_procurement State Province Of Procurement	city_of_procurement City Of Procurement	race_list Race List	ethnicity Ethnicity	other_dx Other Dx	history_of_neoadjuvant_treatment History Of Neoadjuvant Treatment	person_neoplasm_cancer_status Person Neoplasm Cancer Status	vital_status Vital Status	days_to_death Days To Death	alcohol_history_documented Alcohol History Documented	reflux_history Reflux History	antireflux_treatment_types Antireflux Treatment Types	h_pylori_infection H Pylori Infection	initial_diagnosis_by Initial Diagnosis By	barretts_esophagus Barretts Esophagus	goblet_cells_present Goblet Cells Present	history_of_esophageal_cancer History Of Esophageal Cancer	has_new_tumor_events_information Has New Tumor Events Information	day_of_form_completion Day Of Form Completion	month_of_form_completion Month Of Form Completion	year_of_form_completion Year Of Form Completion	has_follow_ups_information Has Follow Ups Information	has_drugs_information Has Drugs Information	has_radiations_information Has Radiations Information	project Project	stage_event_system_version Stage Event System Version	stage_event_clinical_stage Stage Event Clinical Stage	stage_event_pathologic_stage Stage Event Pathologic Stage	stage_event_tnm_categories Stage Event Tnm Categories	primary_pathology_tumor_tissue_site Primary Pathology Tumor Tissue Site	primary_pathology_esophageal_tumor_cental_location Primary Pathology Esophageal Tumor Cental Location	primary_pathology_esophageal_tumor_involvement_sites Primary Pathology Esophageal Tumor Involvement Sites	primary_pathology_histological_type Primary Pathology Histological Type	primary_pathology_columnar_metaplasia_present Primary Pathology Columnar Metaplasia Present	primary_pathology_columnar_mucosa_goblet_cell_present Primary Pathology Columnar Mucosa Goblet Cell Present	primary_pathology_columnar_mucosa_dysplasia Primary Pathology Columnar Mucosa Dysplasia	primary_pathology_neoplasm_histologic_grade Primary Pathology Neoplasm Histologic Grade	primary_pathology_age_at_initial_pathologic_diagnosis Primary Pathology Age At Initial Pathologic Diagnosis	primary_pathology_year_of_initial_pathologic_diagnosis Primary Pathology Year Of Initial Pathologic Diagnosis	primary_pathology_initial_pathologic_diagnosis_method Primary Pathology Initial Pathologic Diagnosis Method	primary_pathology_init_pathology_dx_method_other Primary Pathology Init Pathology Dx Method Other	primary_pathology_lymph_node_metastasis_radiographic_evidence Primary Pathology Lymph Node Metastasis Radiographic Evidence	primary_pathology_primary_lymph_node_presentation_assessment Primary Pathology Primary Lymph Node Presentation Assessment	primary_pathology_lymph_node_examined_count Primary Pathology Lymph Node Examined Count	primary_pathology_number_of_lymphnodes_positive_by_he Primary Pathology Number Of Lymphnodes Positive By He	primary_pathology_planned_surgery_status Primary Pathology Planned Surgery Status	primary_pathology_treatment_prior_to_surgery Primary Pathology Treatment Prior To Surgery	primary_pathology_residual_tumor Primary Pathology Residual Tumor	primary_pathology_radiation_therapy Primary Pathology Radiation Therapy	primary_pathology_postoperative_rx_tx Primary Pathology Postoperative Rx Tx
	TCGA-2H-A9GF	2H	A9GF	0500F1A6-A528-43F3-B035-12D3B7C99C0F	YES	C15.5	8140/3	C15.5	NO	YES	-24487	nan	MALE	183	95	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	784	NO	nan	nan	nan	Symptomatic	No	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	NO	NO	Negative/no dysplasia	G3	67	2001	Other method, specify:	surgical resection	YES	YES	8	7	nan	nan	R1	NO	NO
1	TCGA-2H-A9GG	2H	A9GG	70084008-697D-442D-8F74-C12F8F598570	YES	C15.5	8140/3	C15.5	NO	YES	-24328	nan	MALE	178	74	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	610	NO	nan	nan	nan	Symptomatic	Yes-UK	NO	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	NO	Low grade dysplasia	G2	66	1999	Other method, specify:	surgical resection	NO	YES	19	4	nan	nan	R1	NO	NO
2	TCGA-2H-A9GH	2H	A9GH	606DC5B8-7625-42A6-A936-504EF25623A4	YES	C15.5	8140/3	C15.5	NO	YES	-16197	nan	MALE	183	91	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	951	NO	NO	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage IIB	T1N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	nan	G2	44	1998	Other method, specify:	surgical resection	NO	YES	30	1	nan	nan	R0	NO	NO
3	TCGA-2H-A9GI	2H	A9GI	CEAF98F8-517E-457A-BF29-ACFE22893D49	YES	C15.5	8140/3	C15.5	NO	YES	-25097	nan	MALE	188	100	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	435	NO	nan	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	nan	G2	68	1999	Other method, specify:	surgical resection	NO	YES	8	4	nan	nan	R0	NO	NO
4	TCGA-2H-A9GJ	2H	A9GJ	EE47CD59-C8D8-4B1E-96DB-91C679E4106F	YES	C15.5	8140/3	C15.5	NO	YES	-21180	nan	MALE	189	70	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	1781	NO	YES	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage I	T1N0M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	High grade dysplasia	G2	57	2000	Other method, specify:	surgical resection	NO	YES	19		nan	nan	R0	NO	NO
5	TCGA-2H-A9GK	2H	A9GK	61DF8A4B-95F8-40AB-A252-D00C4300C290	YES	C15.5	8140/3	C15.5	NO	YES	-16067	nan	MALE	180	80	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	232	NO	YES	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	High grade dysplasia	G3	43	2000	Other method, specify:	surgical resection	YES	YES	5	3	nan	nan	R0	NO	NO
6	TCGA-2H-A9GL	2H	A9GL	AB2755D2-5BD9-4E2F-B255-E813AFC8D268	YES	C15.5	8140/3	C15.5	NO	YES	-27115	nan	MALE	173	85	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	180	NO	NO	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	nan	G3	74	2000	Other method, specify:	surgical resection	NO	YES	7	2	nan	nan	R1	NO	NO
7	TCGA-2H-A9GM	2H	A9GM	6584FA8F-B4F4-4844-A71E-3BFB731AD445	YES	C15.5	8140/3	C15.5	NO	YES	-19484	nan	MALE	179	77	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	424	NO	nan	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage IIB	T1N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	nan	G2	53	2000	Other method, specify:	surgical resection	NO	YES	13	1	nan	nan	R0	NO	NO
8	TCGA-2H-A9GN	2H	A9GN	078DC5F1-D2DC-4408-B785-27703C7813F1	YES	C15.5	8140/3	C15.5	NO	YES	-25664	nan	MALE	185	82	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	272	NO	nan	nan	nan	Symptomatic	No	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage III	T3N1M0	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	NO	NO	Negative/no dysplasia	G3	70	2000	Other method, specify:	surgical resection	NO	YES	22	5	nan	nan	R0	NO	NO
9	TCGA-2H-A9GO	2H	A9GO	CA400EA1-3E4E-437E-A54C-446431B741DA	YES	C15.5	8140/3	C15.5	NO	YES	-21486	nan	MALE	170	83	Netherlands	ZH	Rotterdam	nan	nan	No	No	WITH TUMOR	Dead	494	NO	nan	nan	nan	Symptomatic	Yes-UK	nan	nan	YES	25	2	2014	NO	NO	NO	TCGA-ESCA	5th	nan	Stage IVA	T3N1M1a	Esophagus	Distal	Distal	Esophagus Adenocarcinoma, NOS	YES	nan	nan	G3	58	2000	Other method, specify:	surgical resection	NO	YES	13	9	nan	nan	R1	NO	NO


CREATE TABLE esophageal_dataset (
  "unnamed_0" BIGINT,
  "patient_barcode" VARCHAR,
  "tissue_source_site" VARCHAR,
  "patient_id" VARCHAR,
  "bcr_patient_uuid" VARCHAR,
  "informed_consent_verified" VARCHAR,
  "icd_o_3_site" VARCHAR,
  "icd_o_3_histology" VARCHAR,
  "icd_10" VARCHAR,
  "tissue_prospective_collection_indicator" VARCHAR,
  "tissue_retrospective_collection_indicator" VARCHAR,
  "days_to_birth" BIGINT,
  "country_of_birth" VARCHAR,
  "gender" VARCHAR,
  "height" DOUBLE,
  "weight" DOUBLE,
  "country_of_procurement" VARCHAR,
  "state_province_of_procurement" VARCHAR,
  "city_of_procurement" VARCHAR,
  "race_list" VARCHAR,
  "ethnicity" VARCHAR,
  "other_dx" VARCHAR,
  "history_of_neoadjuvant_treatment" VARCHAR,
  "person_neoplasm_cancer_status" VARCHAR,
  "vital_status" VARCHAR,
  "days_to_last_followup" DOUBLE,
  "days_to_death" DOUBLE,
  "tobacco_smoking_history" DOUBLE,
  "age_began_smoking_in_years" DOUBLE,
  "stopped_smoking_year" DOUBLE,
  "number_pack_years_smoked" DOUBLE,
  "alcohol_history_documented" VARCHAR,
  "frequency_of_alcohol_consumption" DOUBLE,
  "amount_of_alcohol_consumption_per_day" DOUBLE,
  "reflux_history" VARCHAR,
  "antireflux_treatment_types" VARCHAR,
  "h_pylori_infection" VARCHAR,
  "initial_diagnosis_by" VARCHAR,
  "barretts_esophagus" VARCHAR,
  "goblet_cells_present" VARCHAR,
  "history_of_esophageal_cancer" VARCHAR,
  "number_of_relatives_diagnosed" DOUBLE,
  "has_new_tumor_events_information" VARCHAR,
  "day_of_form_completion" BIGINT,
  "month_of_form_completion" BIGINT,
  "year_of_form_completion" BIGINT,
  "has_follow_ups_information" VARCHAR,
  "has_drugs_information" VARCHAR,
  "has_radiations_information" VARCHAR,
  "project" VARCHAR,
  "stage_event_system_version" VARCHAR,
  "stage_event_clinical_stage" VARCHAR,
  "stage_event_pathologic_stage" VARCHAR,
  "stage_event_tnm_categories" VARCHAR,
  "stage_event_psa" VARCHAR,
  "stage_event_gleason_grading" VARCHAR,
  "stage_event_ann_arbor" VARCHAR,
  "stage_event_serum_markers" VARCHAR,
  "stage_event_igcccg_stage" VARCHAR,
  "stage_event_masaoka_stage" VARCHAR,
  "primary_pathology_tumor_tissue_site" VARCHAR,
  "primary_pathology_esophageal_tumor_cental_location" VARCHAR,
  "primary_pathology_esophageal_tumor_involvement_sites" VARCHAR,
  "primary_pathology_histological_type" VARCHAR,
  "primary_pathology_columnar_metaplasia_present" VARCHAR,
  "primary_pathology_columnar_mucosa_goblet_cell_present" VARCHAR,
  "primary_pathology_columnar_mucosa_dysplasia" VARCHAR,
  "primary_pathology_neoplasm_histologic_grade" VARCHAR,
  "primary_pathology_days_to_initial_pathologic_diagnosis" BIGINT,
  "primary_pathology_age_at_initial_pathologic_diagnosis" BIGINT,
  "primary_pathology_year_of_initial_pathologic_diagnosis" DOUBLE,
  "primary_pathology_initial_pathologic_diagnosis_method" VARCHAR,
  "primary_pathology_init_pathology_dx_method_other" VARCHAR,
  "primary_pathology_lymph_node_metastasis_radiographic_evidence" VARCHAR,
  "primary_pathology_primary_lymph_node_presentation_assessment" VARCHAR,
  "primary_pathology_lymph_node_examined_count" DOUBLE,
  "primary_pathology_number_of_lymphnodes_positive_by_he" DOUBLE,
  "primary_pathology_number_of_lymphnodes_positive_by_ihc" DOUBLE,
  "primary_pathology_planned_surgery_status" VARCHAR,
  "primary_pathology_treatment_prior_to_surgery" VARCHAR,
  "primary_pathology_residual_tumor" VARCHAR,
  "primary_pathology_karnofsky_performance_score" DOUBLE,
  "primary_pathology_eastern_cancer_oncology_group" DOUBLE,
  "primary_pathology_radiation_therapy" VARCHAR,
  "primary_pathology_postoperative_rx_tx" VARCHAR
);