Login New user?  
Applied Mathematics & Information Sciences
An International Journal
               
 
 
 
 
 
 
 
 
 
 
 
 
 

Content
 

Volumes > Volume 17 > No. 5

 
   

Revolutionizing Human Disease Detection: Advancements and Insights from Machine Learning Algorithms

PP: 948-959
doi:10.18576/amis/170548
Author(s)
Vanaja K, M Ashok Kumar, Jaya Sharma, Neha Ahlawat, D Franklin Vinod,
Abstract
The breakthrough developments in Machine Learning (ML) algorithms have dramatically changed the field of human disease diagnosis in recent years. DTs, RFs, and Naive Bayes have the potential to revolutionise the diagnosis of human diseases. This work intends to explore this potential and offer insightful information about how it might be used. The study starts off by giving a summary of ML algorithms and how they apply to the diagnosis of diseases. In addition to identifying each algorithm's distinctive qualities and applicability for various illness detection scenarios, the research looks at the strengths and weaknesses of each one. Additionally, it examines the effects of several elements, like dataset size, feature selection, and model optimisation methods, on the effectiveness of these algorithms. Furthermore, DTs, RFs, and Naive Bayes have all been used in recent research and practical applications for detecting human diseases. The successful application of these algorithms in several medical fields, including cardiology, oncology, and neurology, is demonstrated through case studies. The results show that while RF delivers resilience and enhanced accuracy through ensemble learning, DTs excel in creating models that are transparent and understandable. While handling huge datasets, Naive Bayes exhibits efficiency and scalability. For clinical practise, patient care, and healthcare systems, the effects of these developments in ML algorithms are examined. The report also emphasises the difficulties and potential paths for future research in applying these algorithms, such as addressing data privacy issues, managing unbalanced datasets, and incorporating them into current healthcare infrastructure. In conclusion, this study highlights the crucial contributions of various ML algorithms to the field of human illness detection. This work contributes to ongoing initiatives to improve disease diagnosis and prognosis and, ultimately, patient outcomes by putting light on their developments and offering insights into their implementation

  Home   About us   News   Journals   Conferences Contact us