Hybrid K-Mir Algorithm to Predict Type of Lung Cancer Among Stoicism
Venkata Ramana N1, Chandra Sekhar Kolli2, Ravi Kumar T3, P Nagesh4
1Venkata Ramana N, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (Andhra Pradesh), India.
2Chandra Sekhar Kolli, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (Andhra Pradesh), India.
3Ravi Kumar T, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (Andhra Pradesh), India.
4P.Nagesh, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (Andhra Pradesh), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 13 February 2019 | Manuscript published on 28 February 2019 | PP: 283-287 | Volume-8 Issue-4, February 2019 | Retrieval Number: D2750028419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Health care is the maintenance of health via the prevention, diagnosis, and treatment of disease. The disease that persists over a long period of time is known as Chronic Disease. Chronic diseases may create additional activity restrictions. Common chronic conditions include lung disease, heart stroke, cancer, obesity, and diabetes. Chronic diseases usually show no symptoms and hence not diagnosed in advance. Hence it is necessary to predict the patient-specific chronic diseases in early stage for effective prevention. Machine learning being the vital component of Data Analytics that facilitates the medical domain for malignancy predictions. Patients suffering from misdiagnosed and undiagnosed chronic diseases can be easily recognized with the help of these hospital systems. These systems enable the doctors to take precautionary measures and thereby minimizing the chances of a patient being affected. A new hybrid K-MLR framework using K-means and Multiple Linear Regression has been proposed for diagnosing the type of lung cancer among the patients. As most of the real datasets are high-dimensional, this hybrid framework uses K-Means clustering algorithm that eliminates the noise from the image based dataset at the initial stage. Afterward to reduce the dimensionality it detects the features of nodules in 3D lung CT scans and partitions the data to form the clusters. Finally it reads the new patient data with malignant nodules to predict the type of associated cancer based on the intensity of the nodule features extracted from each CT scan report using Multiple Linear Regression Analysis. Clustering prior to classification makes the hybrid approach beneficial
Keyword: Lung Cancer, Pulmonary Nodules, CT Scan, Prediction, K-Means, And Regression.
Scope of the Article: Predictive Analysis