Clinical Lung Cancer Outcomes

Columns

• Patient_ID: A unique identifier for each patient.
• Age: The patient's age, ranging from 30 to 79 years, with an average of 54.4 years.
• Gender: The patient's gender, equally distributed between Male and Female (50% each).
• Smoking_History: Details of the patient's smoking history, with Former Smoker and Current Smoker categories each representing approximately one-third of the data.
• Tumor_Size_mm: The size of the tumour in millimetres, ranging from 10 to 100 mm, with a mean of 55.4 mm.
• Tumor_Location: The anatomical location of the tumour, with Upper Lobe and Middle Lobe each making up around one-third of instances.
• Stage: The cancer stage, including Stage IV and Stage III each at 25%, and other stages making up the remaining 50%.
• Treatment: The type of treatment received, such as Radiation Therapy and Surgery, each accounting for 25% of the data.
• Survival_Months: The patient's survival time in months, spanning from 1 to 119 months, with an average of 59.9 months.
• Ethnicity: The patient's ethnicity, with Caucasian and Hispanic each at 20%, and other ethnicities making up 60%.
• Insurance_Type: The type of insurance held by the patient, including Medicare and Medicaid each at 25%.
• Family_History: A boolean indicator for whether the patient has a family history of cancer (49% true, 51% false).
• Comorbidity_Diabetes: A boolean indicator for the presence of diabetes as a comorbidity (50% true, 50% false).
• Comorbidity_Hypertension: A boolean indicator for the presence of hypertension as a comorbidity (50% true, 50% false).
• Comorbidity_Heart_Disease: A boolean indicator for the presence of heart disease as a comorbidity (50% true, 50% false).
• Comorbidity_Chronic_Lung_Disease: A boolean indicator for the presence of chronic lung disease as a comorbidity (50% true, 50% false).
• Comorbidity_Kidney_Disease: A boolean indicator for the presence of kidney disease as a comorbidity (50% true, 50% false).
• Comorbidity_Autoimmune_Disease: A boolean indicator for the presence of autoimmune disease as a comorbidity (50% true, 50% false).
• Comorbidity_Other: A boolean indicator for the presence of other comorbidities (50% true, 50% false).
• Performance_Status: The patient's performance status, ranging from 0 to 4, with a mean of 2.
• Blood_Pressure_Systolic: Systolic blood pressure readings, ranging from 90 to 179, with an average of 134.
• Blood_Pressure_Diastolic: Diastolic blood pressure readings, ranging from 60 to 109, with an average of 84.5.
• Blood_Pressure_Pulse: Pulse rate, ranging from 60 to 99, with an average of 79.6.
• Hemoglobin_Level: Hemoglobin levels, ranging from 10 to 18, with a mean of 14.
• White_Blood_Cell_Count: White blood cell count, ranging from 3.5 to 10, with an average of 6.74.
• Platelet_Count: Platelet count, ranging from 150 to 450, with a mean of 300.
• Albumin_Level: Albumin levels, ranging from 3 to 5, with an average of 4.
• Alkaline_Phosphatase_Level: Alkaline phosphatase levels, ranging from 30 to 120, with a mean of 75.
• Alanine_Aminotransferase_Level: Alanine aminotransferase levels, ranging from 5 to 40, with an average of 22.5.
• Aspartate_Aminotransferase_Level: Aspartate aminotransferase levels, ranging from 10 to 50, with an average of 30.1.
• Creatinine_Level: Creatinine levels, ranging from 0.5 to 1.5, with a mean of 1.
• LDH_Level: LDH levels, ranging from 100 to 250, with an average of 175.
• Calcium_Level: Calcium levels, ranging from 8 to 10.5, with a mean of 9.26.
• Phosphorus_Level: Phosphorus levels, ranging from 2.5 to 5, with an average of 3.74.
• Glucose_Level: Glucose levels, ranging from 70 to 150, with a mean of 110.
• Potassium_Level: Potassium levels, ranging from 3.5 to 5, with an average of 4.25.
• Sodium_Level: Sodium levels, ranging from 135 to 145, with a mean of 140.
• Smoking_Pack_Years: Smoking pack-years, ranging from 0.02 to 100, with an average of 49.9.

Distribution

Usage

• Developing predictive models for lung cancer prognosis.
• Assessing patient prognosis based on various clinical and demographic factors.
• Analysing the effectiveness of different lung cancer treatments.
• Conducting research into factors influencing lung cancer outcomes.

Coverage

License

Who Can Use It

• Researchers: To explore correlations and develop new insights into lung cancer.
• Data Scientists: For building and validating machine learning models for prediction and analysis.
• Medical Professionals and Academics: To understand patient characteristics and treatment outcomes in a simulated clinical environment.
• Students: As a valuable resource for learning and practicing data analysis in healthcare.

Dataset Name Suggestions

• Lung Cancer Prognosis Dataset
• Synthetic Lung Cancer Patient Data
• Clinical Lung Cancer Outcomes
• Lung Cancer Prediction Data

Attributes