Target Projection Feature Matching Based Deep ANN with LSTM for Lung Cancer Prediction

Prediction of lung cancer at early stages is essential for diagnosing and prescribing the correct treatment. With the continuous development of medical data in healthcare services, Lung cancer prediction is the most concerning area of interest. Therefore, early prediction of cancer helps in reducing the mortality rate of humans. The existing techniques are time-consuming and have very low accuracy. The proposed work introduces a novel technique called Target Projection Feature Matched Deep Artificial Neural Network with LSTM (TPFMDANNLSTM) for accurate lung cancer prediction with minimum time consumption. The proposed deep learning model consists of multiple layers to learn the given input patient data. Different processes are carried out at each layer to predict lung cancer at an earlier stage. The input layer of the deep neural network receives the data and associated features and sends them to the hidden layer. The first hidden layer performs the feature selection process using Target Projection matching to identify the relevant features for accurate disease prediction with minimum time consumption. Hidden layer 2 performs the patient Data Classification based on Czekanowski's dice similarity coefficient with the selected relevant features from the previous layer to predict lung cancer. The factors considered for performance evaluation of the proposed technique with the existing state of the art approaches include prediction accuracy, false-positive rate and prediction time. Lunar 16 Lung Cancer dataset consisting of patient data is used for evaluation. The obtained results show that the proposed TPFMDANN-LSTM technique achieves higher prediction accuracy with minimum time consumption and less false positive rate than the state-of-the-art methods. The experimental results reveal that the TPFMDANN-LSTM technique performs better with a 6% improvement in prediction accuracy, 36% reduction of false positives, and 16% faster prediction time for lung cancer detection compared to existing works.