Early Prediction of Neurodegenerative Disease Progression using Quantum Twin Learning for Multimodal Patient Digital Twins: A Survey

Rapidly rising neurodegenerative diseases around the globe are caused by the ageing population including Amyotrophic lateral Sclerosis (ALS), Parkinson's Disease (PD), Huntingdon's Disease (HD) and Alzheimer's Disease (AD). The bimodal clinical manifestations and multimodal medical information, coupled with the lack of certainty in long-term courses still pose significant challenges of early forecast of disease progression. Artificial Intelligence (AI), Digital Twin and Quantum Machine Learning (QML) have brought about significant transformation in healthcare.Artificial Intelligence (AI), Digital Twin, and Quantum Machine Learning (QML) represent game-changers within the healthcare sector, having had a profound impact on the field in recent years. To this end, this survey provides a comprehensive introduction to the concept of a multimodal patient digital twin and hybrid multiclass/multilabel quantum–classical learning methods for prediction of neurodegenerative diseases. This paper will discuss an overview of the existing AI diagnostic envelopes, multimodal data integration, Quantum Computing applications, and Digital Twin architectures for the healthcare sector. In addition, existing challenges, datasets, applications, and research directions into the future are discussed. The survey highlights the advantages of QTL for improved predictions, and the potential to model more complex temporal patterns and precision medicine for neurodegenerative diseases.