In this chapter, the authors propose a novel recommendation algorithm for patient-centric healthcare that utilizes learning applications. The algorithm aims to predict and recommend suitable learning applications to patients based on their individual needs and preferences. By leveraging machine learning techniques and patient data, the algorithm analyzes various factors such as medical history, demographics, and personal interests to generate personalized recommendations. This patient-centric approach enhances the healthcare experience by empowering patients to actively engage in their own health management and education. The algorithm's effectiveness is evaluated through experiments and comparisons with existing recommendation methods, demonstrating its potential to improve patient outcomes and overall healthcare quality.
Top2. Literature Review
It is observed that biomedical images are extensively used for many purposes in these existing medical cases. In medical science, these images play a vital role. The use case like MRI- Magnetic Resonance Imaging captures the information on the internal structure of the human brain and is also used to picture other parts of the body. MRI data are analyzed manually by medical experts in brain tumor and it is a difficult and cumbersome process. The edge detection idea is used here, to generate the high-definition images. Here, we mainly review the existing systems, identify the problems in it and assist it in proceeding the further research effectively to design an effective approach for brain tumor segmentation and classification using MRI with novel machine learning schemes.
P. Gokila Brindha et. al. (2021), proposed assures to be highly efficient and precise for brain tumor detection, classification, and segmentation. To achieve this precise automatic or semiautomatic methods are needed. The research proposes an automatic segmentation method that relies upon CNN (Convolution Neural Networks), determining small 3 x 3 kernels. By incorporating this single technique, segmentation and classification is accomplished [1].
Lotlikar V. S. et. al. (2021), presented an exhaustive study of techniques such as preprocessing, machine learning, and deep learning that have been adopted in the last 15 years and based on it to present a detailed comparative analysis. The challenges encountered by researchers in the past for tumor detection have been discussed along with the future scopes that can be taken by the researchers as the future work. Clinical challenges that are encountered have also been discussed, which are missing in existing review articles [2].
S. Grampurohit, V et. al. (2020) Proposed Deep learning models like the convolutional
neural network (CNN) model and VGG-16 architecture (built from scratch) to detect the tumor region in the scanned brain images. Considered Brain MRI images of 253 patients, out of which 155 MRI images are tumorous and 98 of them are non-tumorous. The study presents a comparative study of the outcomes of CNN model and VGG-16 architecture used [3].
Amin, J. et. al. (2021), presented the study of all important aspects and the latest work done so far with their limitations and challenges. It will be helpful for the researchers to develop an understanding of doing new research in a short time and correct direction. The deep learning methods have contributed significantly but still require a generic technique. These methods provided better results when training and testing are performed on similar acquisition characteristics (intensity range and resolution); however, a slight variation in the training and testing images directly affects the robustness of the methods. In research can be conducted to detect brain tumors more accurately, using real patient data from any medium (different image acquisition (scanners) [4].
Subhashis Banerjee et. al. (2019), proposed novel ConvNet models, which are trained from scratch, on MRI patches, slices, and multi-planar volumetric slices. The suitability of transfer learning for the task is next studied by applying two existing ConvNets models (VGGNet and ResNet) trained on the ImageNet dataset, through fine-tuning of the last few layers. Leave-one-patient-out (LOPO) testing and testing on the holdout dataset are used to evaluate the performance of the ConvNets. Results demonstrate that the proposed ConvNets achieve better accuracy in all cases where the model is trained on the multi- planar volumetric dataset. Unlike conventional models, it obtains a testing accuracy of 95% for the low/high-grade glioma classification problem. A score of 97% is generated for classification of LGG with/without 1p/19q codeletion, without any additional effort towards extraction and selection of features [5].