The goal of this repository is to use the Lower Back Pain Symptoms Dataset to build a Machine Learning Model using Logistic Regression to predict lower back pain in a given individual.
Logistic Regression application in the prediction of Lower Back Pain
In this Kaggle Notebook we would try to answer the following question: given a set of data in several health factors, is it possible to predict lower back pain?
We would make use of Normalization, Decision Tree Classifier to evaluate feature importance, and Logistic Regression to first build our prediction model. Later, we would find out the coefficients of the independent variables, check accuracy metrics and visualize true/false positives and true/false negatives.
- Visualization
- Matplotlib
- Seaborn
- Data Processing
- Numpy
- Pandas
- Regression
- Sklearn
310 Observations, 13 Attributes (12 Numeric Predictors, 1 Binary Class Attribute - No Demographics)
Lower back pain can be caused by a variety of problems with any parts of the complex, interconnected network of spinal muscles, nerves, bones, discs or tendons in the lumbar spine. Typical sources of low back pain include:
- The large nerve roots in the low back that go to the legs may be irritated
- The smaller nerves that supply the low back may be irritated
- The large paired lower back muscles (erector spinae) may be strained
- The bones, ligaments or joints may be damaged
- An intervertebral disc may be degenerating
An irritation or problem with any of these structures can cause lower back pain and/or pain that radiates or is referred to other parts of the body. Many lower back problems also cause back muscle spasms, which don't sound like much but can cause severe pain and disability.
While lower back pain is extremely common, the symptoms and severity of lower back pain vary greatly. A simple lower back muscle strain might be excruciating enough to necessitate an emergency room visit, while a degenerating disc might cause only mild, intermittent discomfort.
This data set is about to identify a person is abnormal or normal using collected physical spine details/data.