JMIR Publications

ABSTRACT

Background:

Diagnostic delay in rare disease (RD) is common, occasionally lasting up to seven years. In attempting to reduce it, diagnostic support tools have been studied extensively. However, social platforms have not yet been used for systematic diagnostic support. This paper illustrates the development and application of a social network using scientifically developed questions to match individuals without a diagnosis. The aim of this study is to outline, create, and evaluate a website-based prototype (RarePairs) in assisting patients with possible rare diseases, in order to find individuals with similar symptoms. The prototype of RarePairs might be a low-threshold patient platform, proved suitable to match different individuals with comparable symptoms.

Objective:

The study aimed to outline, create and evaluate a prototype tool (a social network platform named ‘Rare Pairs’), helping patients with undiagnosed rare diseases to find individuals with similar symptoms. The prototype includes a matching-algorithm, bringing together individuals with similar disease burden in the lead-up to diagnosis.

Methods:

We divided our project into four phases. In phase one, we used known data and findings in literature to understand and specify the context of use. In phase two, we specified the user requirements. Thirdly, we designed a prototype based on the results of phase one and two, as well as incorporating a state-of-the-art questionnaire for recognizing a RD. Lastly, we evaluated this prototype with a data set of 973 questionnaires from individuals suffering from different RD using 24 distance calculating methods.

Results:

Based on a step-by-step construction process, the digital patient platform prototype, RarePairs, was developed. In order to match individuals with similar experiences, it uses answer patterns generated by diagnostic questionnaires. 973 questionnaires answered by patients with RDs were used to construct and test an Artificial Intelligence (AI) algorithm like the k-nearest-neighbor search. With this, we found matches for every single one of the 973 records. The cross-validation of those matches showed that the algorithm outperforms random matching in all reviewed categories significantly. Statistically, for every data set the algorithm found at least one other record (=match) with the exact same diagnosis.

Conclusions:

Diagnostic delay is tormentous for patients without a diagnosis. Shortening the delay is important for both doctors and patients. Diagnostic support using AI can be promoted differently. The prototype of a social media platform RarePairs might be a low-threshold patient platform, proved suitable to match different individuals with comparable symptoms, in order to foster experience exchange. This exchange in RarePairs might be used to speed up the diagnostic process. Further studies need to evaluate the impact in prospective settings.