Loading [MathJax]/extensions/MathMenu.js
Toward Symptom Assessment Guided Symptom Investigation and Disease Diagnosis | IEEE Journals & Magazine | IEEE Xplore

Toward Symptom Assessment Guided Symptom Investigation and Disease Diagnosis


Impact Statement:In the past five years, dozens of surveys and reports indicate an unbalanced doctor-to-population ratio. These reports firmly suggest that the alarming figures need to be...Show More

Abstract:

Automatic disease diagnosis has gained immense popularity and demand over the past few years, and it is emerging as an effective diagnostic assistant to doctors. Diagnosi...Show More
Impact Statement:
In the past five years, dozens of surveys and reports indicate an unbalanced doctor-to-population ratio. These reports firmly suggest that the alarming figures need to be improved by increasing the number of healthcare professionals and better utilizing their time. With the motivation to assist doctors and ease early diagnosis, the proposed automatic disease diagnosis assistant (diagnosis chatbot) conducts a thorough symptom investigation and prepares a diagnosis report for doctors in the real world. The work is the first attempt that scrutinizes the role of symptom investigation in disease diagnosis and builds a novel symptom assessment guided symptom investigation and diagnosis assistant. The rigorous experiments, along with human analysis across various algorithms and datasets, reveal a significant role of symptom importance in both symptom investigation and disease inference. Furthermore, the proposed diagnosis method not only improves diagnosis accuracy but also greatly enhances e...

Abstract:

Automatic disease diagnosis has gained immense popularity and demand over the past few years, and it is emerging as an effective diagnostic assistant to doctors. Diagnosis assistants assist clinicians in conducting a thorough symptom investigation and identifying possible diseases. Doctors correctly diagnose patients by observing only a few symptoms in most cases, even though the diagnosed disease has numerous symptoms. Also, some common symptoms, such as fever and headache, usually emerge due to other symptoms, which do not play a major role in identifying suffering diseases. In this work, we investigate the role of symptom importance in disease diagnosis through several feature engineering techniques and propose a novel symptom assessment guided symptom investigation and disease diagnosis (SA-SIDD) assistant using hierarchical reinforcement learning (HRL). The proposed SA-SIDD assistant first collects an adequate set of symptoms/sign information through conversing with users and then...
Published in: IEEE Transactions on Artificial Intelligence ( Volume: 4, Issue: 6, December 2023)
Page(s): 1752 - 1766
Date of Publication: 13 January 2023
Electronic ISSN: 2691-4581

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.