Lung Cancer Prediction

A comprehensive dataset for predictive modeling of lung cancer prognosis.

@kaggle.rashadrmammadov_lung_cancer_prediction

Table List

1 table(3.91 MB)

Lung Cancer Data

@kaggle.rashadrmammadov_lung_cancer_prediction.lung_cancer_data

3.91 MB
23658 rows
38 columns

patient_id Patient ID	age Age	gender Gender	smoking_history Smoking History	tumor_size_mm Tumor Size Mm	tumor_location Tumor Location	stage Stage	treatment Treatment	survival_months Survival Months	ethnicity Ethnicity	insurance_type Insurance Type	family_history Family History	comorbidity_diabetes Comorbidity Diabetes	comorbidity_hypertension Comorbidity Hypertension	comorbidity_heart_disease Comorbidity Heart Disease	comorbidity_chronic_lung_disease Comorbidity Chronic Lung Disease	comorbidity_kidney_disease Comorbidity Kidney Disease	comorbidity_autoimmune_disease Comorbidity Autoimmune Disease	comorbidity_other Comorbidity Other	performance_status Performance Status	blood_pressure_systolic Blood Pressure Systolic	blood_pressure_diastolic Blood Pressure Diastolic	blood_pressure_pulse Blood Pressure Pulse	hemoglobin_level Hemoglobin Level	white_blood_cell_count White Blood Cell Count	platelet_count Platelet Count	albumin_level Albumin Level	alkaline_phosphatase_level Alkaline Phosphatase Level	alanine_aminotransferase_level Alanine Aminotransferase Level	aspartate_aminotransferase_level Aspartate Aminotransferase Level	creatinine_level Creatinine Level	ldh_level LDH Level	calcium_level Calcium Level	phosphorus_level Phosphorus Level	glucose_level Glucose Level	potassium_level Potassium Level	sodium_level Sodium Level	smoking_pack_years Smoking Pack Years
Patient0000	68	Male	Current Smoker	81.67867747756685	Lower Lobe	Stage III	Surgery	44	Hispanic	Medicare	No	Yes	Yes	Yes	No	Yes	Yes	Yes	3	161	99	92	13.5379998633062	9.800707283777747	321.735265899458	3.568383173574926	49.310048081727466	27.98557074949406	46.8012136915355	1.2458486726480742	239.2402553447476	10.36630749700868	3.547734301889561	113.91924253800109	4.968163296458876	139.82286127557495	17.006956111026494
Patient0001	58	Male	Never Smoked	78.44827194239302	Lower Lobe	Stage I	Radiation Therapy	101	Caucasian	Private	Yes	Yes	Yes	No	No	Yes	Yes	No	4	101	91	93	16.800312038086574	4.378427902136247	251.5815383873528	3.6993565701964513	111.42163211736928	30.12095635790461	39.71153145943822	1.4632310298788858	233.5152370171749	10.08173118964734	2.9450198927233777	101.32157805655784	3.896794578388724	135.44936131433727	93.27089292439568
Patient0002	44	Male	Former Smoker	67.71430467925421	Lower Lobe	Stage I	Chemotherapy	69	African American	Other	Yes	No	No	No	Yes	Yes	No	No		109	74	81	14.473492785109077	6.157791530165437	393.45653224054007	4.708385124714766	76.64800593598139	5.882418451499677	32.64060170870275	0.6301090575275732	169.03745956809786	8.660892100741602	4.637399497433549	78.21417677160993	4.369050355351924	143.3771551945199	70.3483762961798
Patient0003	72	Male	Current Smoker	70.80600837963757	Lower Lobe	Stage III	Chemotherapy	95	African American	Medicare	Yes	Yes	No	Yes	No	Yes	Yes	No	1	103	85	68	17.442062880199174	6.259383054768449	275.1778982828902	4.727672192051879	81.95248643573177	38.90815443693127	44.31939271999705	0.5943416106583191	213.96759011172344	8.832668791450816	3.617098166594064	127.89536077939006	4.348474077210295	138.58600528043175	19.82812752042046
Patient0004	37	Female	Never Smoked	87.2724327432066	Lower Lobe	Stage IV	Radiation Therapy	105	Asian	Medicaid	No	Yes	Yes	Yes	No	Yes	No	No		165	69	99	13.54517055258052	5.203515891066979	381.7055721407794	4.605604018896203	107.51342331410716	26.34487688935821	15.746905887054648	1.478239027082041	118.1875433250214	9.247608723647453	4.773254868358881	148.8011850535362	3.671975834333574	141.2307242821763	81.04745606131432
Patient0005	50	Male	Never Smoked	72.1486560839287	Lower Lobe	Stage I	Surgery	49	Hispanic	Other	Yes	No	Yes	No	Yes	No	Yes	Yes	4	109	103	68	15.93371798343157	4.764999299816994	175.7956143129846	3.051211922162908	47.4520133474508	34.81386853753784	29.76965549143069	0.825544006698517	218.20461402865183	8.71192402542881	2.6610528218789358	142.78261909035513	4.606624509454229	135.49794434650542	18.058524678606503
Patient0006	68	Female	Current Smoker	19.122174980343733	Middle Lobe	Stage I	Radiation Therapy	63	African American	Other	No	Yes	No	Yes	Yes	Yes	No	Yes	3	137	93	89	16.705865260008313	6.572108623069942	190.84991462207944	4.34065260751277	68.49174146332655	31.016446010942158	39.87895320826876	0.7995927921017624	181.55072776883495	8.08988530886587	4.5918857577716805	75.37709376216404	4.800979942364532	138.3734129022012	86.48233924788725
Patient0007	48	Male	Current Smoker	68.09505652070685	Lower Lobe	Stage IV	Chemotherapy	101	African American	Medicare	No	Yes	No	Yes	Yes	No	No	Yes	3	90	101	95	12.015746587687492	5.261679595465527	378.2855744618188	4.860352810042039	103.52569637220034	12.208267304633562	23.90810712512025	1.4364531541299097	119.05709723579524	9.367765752942784	4.909358938944225	99.51188084924698	4.061255316555459	136.34715867747045	68.23992040517143
Patient0008	52	Female	Former Smoker	25.29943999554186	Lower Lobe	Stage I	Targeted Therapy	35	Caucasian	Other	No	No	No	Yes	No	No	No	No	4	157	87	67	16.240749005318236	8.161061959857904	248.1479522272848	4.683562103220213	63.91831282760667	36.88835753351768	35.82295255685182	1.0891689830166689	197.7917569704557	10.188012959616234	3.326972618633935	145.65715391772818	4.767092005123215	141.11350253458968	96.80888873695108
Patient0009	40	Male	Current Smoker	11.282766617549546	Lower Lobe	Stage I	Surgery	19	Other	Medicaid	Yes	No	No	Yes	No	Yes	Yes	Yes	1	161	95	71	15.027361908001904	6.330154812646519	186.85725108680347	4.731632301032728	92.96150398498852	33.83607395215947	44.23024013118724	1.0787938515579505	227.04842956010276	8.248717873901262	3.1734707621667324	109.75547768471203	4.075269200733317	139.17485507619472	68.5958747306421


CREATE TABLE lung_cancer_data (
  "patient_id" VARCHAR,
  "age" BIGINT,
  "gender" VARCHAR,
  "smoking_history" VARCHAR,
  "tumor_size_mm" DOUBLE,
  "tumor_location" VARCHAR,
  "stage" VARCHAR,
  "treatment" VARCHAR,
  "survival_months" BIGINT,
  "ethnicity" VARCHAR,
  "insurance_type" VARCHAR,
  "family_history" VARCHAR,
  "comorbidity_diabetes" VARCHAR,
  "comorbidity_hypertension" VARCHAR,
  "comorbidity_heart_disease" VARCHAR,
  "comorbidity_chronic_lung_disease" VARCHAR,
  "comorbidity_kidney_disease" VARCHAR,
  "comorbidity_autoimmune_disease" VARCHAR,
  "comorbidity_other" VARCHAR,
  "performance_status" BIGINT,
  "blood_pressure_systolic" BIGINT,
  "blood_pressure_diastolic" BIGINT,
  "blood_pressure_pulse" BIGINT,
  "hemoglobin_level" DOUBLE,
  "white_blood_cell_count" DOUBLE,
  "platelet_count" DOUBLE,
  "albumin_level" DOUBLE,
  "alkaline_phosphatase_level" DOUBLE,
  "alanine_aminotransferase_level" DOUBLE,
  "aspartate_aminotransferase_level" DOUBLE,
  "creatinine_level" DOUBLE,
  "ldh_level" DOUBLE,
  "calcium_level" DOUBLE,
  "phosphorus_level" DOUBLE,
  "glucose_level" DOUBLE,
  "potassium_level" DOUBLE,
  "sodium_level" DOUBLE,
  "smoking_pack_years" DOUBLE
);