JMIR Publications

ABSTRACT

Background:

Evidence-based clinical intake tools (EBCITs) are structured assessment tools used to gather information about patients and help healthcare providers make more informed decisions. The growing demand for personalized medicine, along with the big data revolution, have rendered EBCITs a promising solution. These tools have the potential to provide comprehensive and individualized assessments of symptoms, enabling accurate and timely diagnosis, while contributing to the grounding of medical care.

Objective:

This work examines whether EBCITs can serve as a reliable tool that covers disorders and symptoms, similar to a physician’s assessment. We also explore the potential of EBCITs to discover and ground real correlations between disorders and symptoms.

Methods:

HelixVM is a virtual healthcare provider in the USA. Between August 1, 2022 and January 15, 2023, patients who used HelixVM’s services were first assessed by the Kahun EBCIT. Kahun platform gathered, documented, and analyzed the information from the sessions and its clinical findings. In this study, we computed the correlations between the symptoms presented by the patients and known medical disorders, based on two sets of data. The first set analyzed correlations between symptoms and disorders, as determined by the Kahun's knowledge engine. The second set analyzed correlations between symptoms and disorders, solely based on the information gathered from HelixVM patients using Kahun. The variance between these two correlations allowed us to verify how well Kahun was able to take in and make use of new data, while integrating existing knowledge. To analyze the comprehensiveness of the Kahun's knowledge engine, we compared how well it covers weighted data for the symptoms and disorders found in the 2019 National Ambulatory Medical Care Survey (NAMCS).

Results:

As part of this work, 2550 patients used the Kahun to complete a full assessment, among them 1714 females and 836 males. Kahun collected 314 different chief complaints and proposed 108,523 suggestions related to symptoms during the intake process. At the end of the intake process, 6496 conditions were presented to the caregiver. Kahun covered 94% (526157569/562150572) of the weighted symptoms and 91% (1582637476/1734783244) of the weighted disorders in NAMCS 2019. Kahun’s engine yielded 519 correlations between disorders and symptoms while the Kahun-HelixVM cohort yielded 599; 156 correlations were unique to the latter and 443 correlations were shared by both databases.

Conclusions:

ECBITs, such as Kahun, encompass extensive amounts of knowledge and could serve as a reliable database for inferring medical insights. Using this credible database, potential correlations between symptoms and disorders were discovered or grounded. This highlights the possible application of ECBITs to improve the understanding of relationships between disorders and symptoms.