Mansour-Essgaer/Breast-Cancer-Biological-and-Tumor-Markers-Datset
Domaine:
healthcareType de record:
dataset
Créateur:
Man
Hôte:
The Sebha Breast Cancer Prediction Corpus is a medical dataset collected from the Sebha Oncology Center (SOC) in southern Libya. It focuses on using routine blood test data—specifically biological and tumor markers—to predict breast cancer (BC) in its early stages.
---
# Sebha Breast Cancer Dataset
### Biological & Tumor Marker Dataset for Early Detection
## 📌 Overview
The **Sebha Breast Cancer Prediction Corpus** is a medical dataset collected from the **Sebha Oncology Center (SOC)** in southern Libya. It focuses on using routine blood test data—specifically biological and tumor markers—to predict breast cancer (BC) in its early stages.
This dataset was created to address the lack of breast cancer research in Libya's southern region and to investigate cost-effective alternatives to biopsies for early diagnosis. It serves as a benchmark for evaluating machine learning models, particularly **Classification and Regression Trees (CART)**, in medical diagnostics.
## 📊 Dataset Statistics
| Attribute | Value |
| --- | --- |
| **Total Cases** | **2,435** |
| **Time Period** | 2015 – 2020 |
| **Source** | Sebha Oncology Center (SOC) routine blood tests |
| **Class Distribution** | Benign (55.9%), Malignant (44.1%) |
| **Features** | 23 clinical attributes (Biological & Tumor Markers) |
| **Target Variable** | Diagnosis (0 = Benign, 1 = Malignant) |
---
## 📁 Data Features
The dataset contains **23 features** categorized into patient demographics, biological markers (BM), and tumor markers (TM).
### Key Predictors (Top Correlated Features)
Based on correlation analysis, these features have the strongest relationship with the diagnosis:
* **`CA-15.3`**: Cancer Antigen 15-3 (Strongest positive correlation)
* **`CEA`**: Carcinoembryonic Antigen
* **`LDH`**: Lactate Dehydrogenase
* **`PLT`**: Platelets Count
* **`WBC`**: White Blood Cells Count
* **`ALB`**: Albumin
### Full Feature List
| Category | Features |
| --- | --- |
| **Demographics** | `Age`, `Sex`, `Address` |
| **Tumor Markers** | `CA-15.3`, `CEA` |
| **Blood Counts** | `WBC` (White Blood Cells), `RBC` (Red Blood Cells), `HGB` (Hemoglobin), `PLT` (Platelets) |
| **Kidney Function** | `Urea`, `Creatinine`, `Na+` (Sodium), `K` (Potassium), `CL-` (Chloride) |
| **Live …
Similaires
Mansour-Essgaer/Libyan-ResturantMansour-Essgaer/Libya-Telecom-companies-corpusMansour-Essgaer/Northern-Benghazi-Power-Plant-DatasetMansour-Essgaer/Predicting-High-School-Dropout-Vulnerability-in-South-LibyaMolecular cues on obesity signals, tumor markers and endometrial cancerAdvances in Biological Breast Cancer Research and Cancer Care in Africa