Paper Title
Early Prediction Model for KOA with Idyllic Measurements using Big-Data Analytics
Abstract
Osteoarthritis is the most common form of arthritis, affecting 528 million people worldwide. In India more than
10 million cases occur each year. The prevalence of this disease increases with age, and women are generally more affected
than men. With the help of different classifiers, we developed a machine learning model that bridges major risk factors for
OA, such as rural population with heavy physical labour, obesity, poor posture, other medical conditions, lack of activity,
joint laxity, muscle weakness, stress, and cultural differences in Indians like cross-legged sitting, certain occupations, family
histories, squat toilets, and walking without proper footwear as baseline markers for predicting knee OA risk. There are more
than a few challenges associated with each step of coping with massive information which can solely be surpassed through
using high-end computing solutions for big statistics analysis. We proposed a model based on no pharmacological treatment
of Osteoarthritis to determine the risk of Osteoarthritis based on risk factors of OA. A machine learning model was built to
predict OA years before it occurs and predict the percentage of OA likely to occur in advance.Such a framework will allow
the adjustment of the treatment plan and therapeutic approaches that can lead to improved long-term patient outcomes and
hopefully delay the time to or stop the need for surgery.The main problems of this research area to early prediction chances
of Osteoarthritis in human knee using Machine learning classifier's from Risk factors to prevent OA (osteoarthritis) of the
knee and replacement surgery just before KOA happens. We can create a model of the highest accuracy using the risk factor
dataset of GUJARAT STATE physiotherapy clinics to predict the chances of KOA on an early basis. Often, clinical
decisions are based more on doctors' insights and experiences than on knowledge-rich data hidden in the dataset. This
practice leads to unwanted biases, errors, and excessive medical costs which affect the quality of service provided to
patients. The proposed system will integrate clinical decision support with computer-based patient records. As a result,
medical errors will be reduced, patient safety will be enhanced, unwanted practice variations will be reduced, and patient
outcomes will also be improved. This suggestion is promising as data modeling and analysis tools, e.g., data mining, have
the potential to generate a knowledge-rich environment that can help to significantly improve the quality of clinical
decisions. There are a lot of records in the medical data domain, and it has become necessary to use data mining techniques
to aid in decision support and prediction in healthcare. The use of medical data mining contributes to business intelligence,
which is useful in diagnosing disease.
Keywords - Osteoarthritis, KOA, Big-Data, Gujarat, Data- Collection, Data-Preprocessing, Machine Learning