Modelling the progression of Alzheimer's disease using Neutrosophic hidden Markov models

Abstract

Alzheimer's disease is the primary cause of dementia. Due to the sluggish rate of progression of
Alzheimer's disease, individuals have the opportunity to start receiving therapy early through
routine testing. procedures since they are pricy and difficult to find. For many slowly advancing
disorders, such as Alzheimer's disease (AD), the capacity to recognise changes in disease
progression is essential. Machine learning methods with a high degree of modularity were used
throughout the pipeline. We propose the use of Neutrosophic hidden Markov models (NHMMs)
to simulate disease progression in a more thorough manner than the clinical phases of the disease.
Due to the complexity and ambiguity of reality, decision-makers find it challenging to draw
conclusions from precise data. Since they cannot be computed directly, the variables are encoded
using a single interval Neutrosophic set. We showed that the trained HMM can imitate sickness
development more accurately than the commonly acknowledged clinical phases