Multiple myeloma(MM) is a challenging and incurable type of blood cancer. The global impact of MM was estimated in 2018, with 160,000 recorded deaths worldwide. Accurate risk stratification remains critical for personalized treatment, yet current models such as the International Staging System (ISS) lack sufficient accuracy and the goal is to build models that can stratify the risk of patients better than ISS.

There remains a lack of accurate and reliable risk stratification models for MM. In this thesis, we investigated neural network (NN)-based predictive models to stratify high-risk MM patients from low-risk ones.

We implemented four NN architectures including 1D-CNN, CNN-MLP hybrid, Resnet and Tabnet. The effect of using input features without any selection was compared to two feature selection methods, variance threshold and NetRank. Furthermore, we investigated the effect of represent- ing input data with and without sorting by chromosomal location of genes. The dataset consisted of 241 patients, with 97 categorised as high-risk patients (death within 3 years of diagnosis) and 144 as as low-risk (survived longer than 3 years).

Our results show that Tabnet combined with feature selection via variance thresholding outper- formed all other methods. It achieved an accuracy of 0.72, F1-score of 0.76, recall of 0.92, preci- sion of 0.60 and area under curve (AUC) of 0.58. The performance on accuracy was better than the current clinically used international staging system (ISS), which achieves accuracy of 0.65.