Diagnosis support systems for rare diseases: a scoping review

Abstract

Introduction: Rare diseases affect approximately 350 million people worldwide. Delayed diagnosis is frequent due to lack of knowledge of most clinicians and a small number of expert centers. Consequently, computerized diagnosis support systems have been developed to address these issues, with many relying on rare disease expertise and taking advantage of the increasing volume of generated and accessible health-related data. Our objective is to perform a review of all initiatives aiming to support the diagnosis of rare diseases. Methods: A scoping review was conducted based on methods proposed by Arksey and O'Malley. A charting form for relevant study analysis was developed and used to categorize data. Results: Sixty-eight studies were retained at the end of the charting process. Diagnosis targets varied from 1 rare disease to all rare diseases. Material used for diagnosis support consisted mostly of phenotype concepts, images or fluids. Fifty-seven percent of the studies used expert knowledge. Two-thirds of the studies relied on machine learning algorithms, and one-third used simple similarities. Manual algorithms were encountered as well. Most of the studies presented satisfying performance of evaluation by comparison with references or with external validation. Fourteen studies provided online tools, most of which aimed to support the diagnosis of all rare diseases by considering queries based on phenotype concepts. Conclusion: Numerous solutions relying on different materials and use of various methodologies are emerging with satisfying preliminary results. However, the variability of approaches and evaluation processes complicates the comparison of results. Efforts should be made to adequately validate these tools and guarantee reproducibility and explicability.

Pain drawings as a diagnostic tool for the differentiation between two pain-associated rare diseases (Ehlers-Danlos-Syndrome, Guillain-Barré-Syndrome)

“…Comparison of our results with other computer aided diagnostic tools is difficult due to the differences in approaches, as is pointed out by the authors of a recent scoping review summarizing current developments in the field of rare disease diagnosis support [ 38 ]. They identified 72 studies published between 2009 and 2019, with roughly half of those published after 2016, highlighting the very recent progress made towards this end.…”

“…From a practical perspective in a clinical setting, Pain2D [ 18 ] in its final form is supposed to narrow down the possibilities of diagnosis to accelerate the diagnostic process. Like most computer aided diagnosis support tools, it is not meant to be a one-and-done approach, but to make diagnosis of rare diseases easier by concentrating on a few possible candidates [ 38 ]. The final diagnosis will always have to be done by other clinical methods, but the advantage of the diagnostic aid tool is that it is quick, easy, non-interventional, and can be applied in any setting where PDs can be generated.…”

“…Recently, Grigull et al developed a questionnaire-based diagnostic support tool for several rare neuromuscular diseases by combining patient-oriented questions and data mining algorithms [ 39 ], a study that is also included in the recent review by Faviez et al [ 38 ]. It is conceivable that a combination of PD analysis with this advancement in taking medical history will take diagnostic procedures of rare diseases to a new level of improvement.…”

Description and clinical validation of a real-time AI diagnostic companion for fetal ultrasound examination

“…Faviez et al recently reviewed the performance of diagnostic DSSs for rare diseases (6). The systems presented in this review rely on post-hoc postnatal phenotyping and do not provide real-time assistance.…”

“…The impact of the suspicion of a fetal anomaly is known to undermine the attachment of the pregnant woman to her pregnancy with a significant and prolonged impact even when reaching a favorable prognosis (4). Given the growing complexity of medical knowledge and the increasing availability of data sources, decision support systems (DSS) have been developed to assist clinicians in their decision-making, particularly for rare diseases diagnosis (5,6). However, to our knowledge, such systems have not been developed for the specific needs of fetal ultrasound.…”