Classification on back pain data
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. Here, it is focused on classifying subjects according to the type of back pain they are experiencing. For that we have a collection of 380 subjects and 32 clinical indicators (12 numerical, 11 ordinal and 19 categorical). So, here each subject is classified as nociceptive (pain that’s likely to be caused by the body being harmed which includes mechanical or physical damage to non-neural tissue) or neuropathic (Pain initiated or caused by a primary lesion or dysfunction in the nervous system). To get best accurate classification we are using range of algorithms like Logistic Regression, Classification Trees, Support Vector Machine etc. The methods like bootstrapping, bagging and boosting will also be done to increase the efficiency of the classifier. The merits and demerits of each algorithm will be discussed along with the results after running these algorithms on our dataset. The model with higher accuracy for most of the cases will be selected as the best model and will be used to classify the type of lower back pain they experience.