Personalized Therapy Using Deep Learning Advances

Summary

Personalized therapy is the process of providing personalizing medical care to particular patients based on various features including genetics, inheritance, and lifestyle. The core principle of personalized therapy is to provide the right treatment to the right patient at the right time. The concept of personalized therapy dates back to Hippocrates’ period. Recent developments in diagnostic medical imaging and molecular medicine are gradually improving healthcare systems by providing knowledge and diagnostic data that allow for individualized patient management. Identifying the best approach to personalize and population medicine requires the ability to interpret detailed patient data together with broader aspects in order to track and differentiate between sick and relatively healthy individuals, leading to a greater understanding of biological markers that can signify health changes. Artificial intelligence (AI) developments in the form of new and emerging technology appear poised to help bring objectivity and precision to various traditionally qualitative analytical techniques. One form of AI in particular, known as deep learning, is achieving expert‐level disease classifications in many areas of personalized medicine, relying on algorithms. These algorithms use raw data from an enormous, annotated data set, such as a collection of images or genomes, and then accurately analyze the data and recommend the best possible treatments for patients. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), and autoencoders are deep learning algorithms. Personalized therapy has a promising future in terms of improving treatment, which is based on patients’ specific diagnostic data. This chapter will give an overview of the most common uses of deep learning approaches in personalized therapy, with a focus on data analysis and precision medicine.