Neural Networks for Medical Applications Dr Ana C. Calderon * and Dr Simon Thorne + { * acalderon, + sthorne}@cardiffmet.ac.uk Department of Computing, Cardiff Metropolitan University, Cardiff, U.K. With increases in data size and richness of available data, machine learning (henceforth ML) has seen a resurrection of interest in recent years. In a nutshell ML is a field that studies mechanisms in which computers carry out tasks without being explicitly programmed. It essentially uses large data sets to answers questions, by producing reliable results, as well as providing researchers with mechanisms for uncovering hidden results. As more research is accomplished, and its underlying algorithms become more powerful, we will increasingly witness machine learning’s ubiquity in automated processes of benefit to all areas of society. ML’s usages can be as varied as sorting through produce, self-driving cars, or speech recognition. In this article we will focus on a particular usage, how machine learning can benefit medical diagnostics and data analysis. The basic components of machine learning consists of: • model creation, • data collection and data preparation, • training, • evaluation. Because of the complexity of the domain this article focuses on, we will firstly explain machine learning via a simple example, before moving on to explicating its benefits for medical purposes. Typically researchers will have a model they wish to train, and will therefore need to collect some data with which to train it; an important aspect is ensuring biases are, as much as possible, eliminated from the data. Importantly the stage at which the model is considered ‘good enough’ during training is pre-determined by researchers, depending on what question the model was created to answer. By ‘good enough’ we mean when the model is considered to have learnt enough. Machine learning, by its very nature, cannot guarantee the performance of its algorithms, and it is thus necessary for researchers to stipulate probabilistic bounds on the performance. For instance, for a very simple example suppose you wish to create a model that can distinguish between wine, juice, and beer. Your data might consist of say sugar content, colour (maybe measured through a spectrometer), and alcohol content. The quality and quantity of data is directly correlated to how well your model will perform after training, so if more data was gathered about juice than the other categories, then there is clearly an imbalance here, and the model would typically guess ‘juice’ more often as it would have a greater chance of being right. Once the model has been trained, the next step is evaluating it, which must be done on different data, as otherwise it would just guess the answer. Within the field ML, lies Neural Networks (NN), the first neural network ever made was in 1943 by neurophysiologist Warren McCulloch and mathematician Walter Pitts, based on a paper that sought to describe how neurons in the brain work. They created an approximate model using electrical circuits to explain how neurons might work in the brain. The first computer based neural network came in 1959, it was a system called ADALANE from Stanford university that detected and cancelled echo on telecommunications lines using adaptive filters which is still in use today. Whilst