Symptoms are known by their companies: towards association guided disease diagnosis assistant

Abstract

Over the last few years, dozens of healthcare surveys have shown a shortage of doctors and an alarming doctor-population ratio. With the motivation of assisting doctors and utilizing their time efficiently, automatic disease diagnosis using artificial intelligence is experiencing an ever-growing demand and popularity. Humans are known by the company they keep; similarly, symptoms also exhibit the association property, i.e., one symptom may strongly suggest another symptom’s existence/non-existence, and their association provides crucial information about the suffering condition. The work investigates the role of symptom association in symptom investigation and disease diagnosis process. We propose and build a virtual assistant called Association guided Symptom Investigation and Diagnosis Assistant (A-SIDA) using hierarchical reinforcement learning. The proposed A-SIDDA converses with patients and extracts signs and symptoms as per patients’ chief complaints and ongoing dialogue context. We infused association-based recommendations and critic into the assistant, which reinforces the assistant for conducting context-aware, symptom-association guided symptom investigation. Following the symptom investigation, the assistant diagnoses a disease based on the extracted signs and symptoms. The assistant then diagnoses a disease based on the extracted signs and symptoms. In addition to diagnosis accuracy, the relevance of inspected symptoms is critical to the usefulness of a diagnosis framework. We also propose a novel evaluation metric called Investigation Relevance Score (IReS), which measures the relevance of symptoms inspected during symptom investigation. The obtained improvements (Diagnosis success rate-5.36%, Dialogue length-1.16, Match rate-2.19%, Disease classifier-6.36%, IReS-0.3501, and Human score-0.66) over state-of-the-art methods firmly establish the crucial role of symptom association that gets uncovered by the virtual agent. Furthermore, we found that the association guided symptom investigation greatly increases human satisfaction, owing to its seamless topic (symptom) transition.

Lupus RGMX: Social and Clinical Characteristics and their Contribution to Quality of Life in a Mexican Cohort with SLE

“…Lupus RGMX future efforts will focus on establishing collaborations with clinicians to evaluate the participants, and to provide a clinically valid indicator of their manifestations, such as the SLEDAI or the SLICC index, to compare with the observations established by the self-reported survey. The validation of the relevance and potential applications of self-reported clinical surveys will provide a tool not only for the prevention of SLE associated complications, but also an easier and more reachable approach to follow up the response to treatments (Tiwari et al, 2022).…”

Can you Summarize my learnings? Towards Perspective-based Educational Dialogue Summarization

“…In the context of the Social Good theme, there have been an upsurge of research in the latest time focused on understanding dialogues. For example works in mental health conversations (Saha et al, 2022a(Saha et al, ,b,c, 2021, disease diagnosis assistant (Tiwari et al, 2022;Saha et al, 2023), education (Jain et al, 2022 etc. A broad spectrum of research has been done on dialogue summarization spanning different domains.…”