A diagnostic support system based on pain drawings: binary and k-disease classification of EDS, GBS, FSHD, PROMM, and a control group with Pain2D.

BACKGROUND AND OBJECTIVE: The diagnosis of rare diseases (RDs) is often challenging due to their rarity, variability and the high number of individual RDs, resulting in a delay in diagnosis with adverse effects for patients and healthcare systems. The development of computer assisted diagnostic decision support systems could help to improve these problems by supporting differential diagnosis and by prompting physicians to initiate the right diagnostic tests. Towards this end, we developed, trained and tested a machine learning model implemented as part of the software called Pain2D to classify four rare diseases (EDS, GBS, FSHD and PROMM), as well as a control group of unspecific chronic pain, from pen-and-paper pain drawings filled in by patients. METHODS: Pain drawings (PDs) were collected from patients suffering from one of the four RDs, or from unspecific chronic pain. The latter PDs were used as an outgroup in order to test how Pain2D handles more common pain causes. A total of 262 (59 EDS, 29 GBS, 35 FSHD, 89 PROMM, 50 unspecific chronic pain) PDs were collected and used to generate disease specific pain profiles. PDs were then classified by Pain2D in a leave-one-out-cross-validation approach. RESULTS: Pain2D was able to classify the four rare diseases with an accuracy of 61-77% with its binary classifier. EDS, GBS and FSHD were classified correctly by the Pain2D k-disease classifier with sensitivities between 63 and 86% and specificities between 81 and 89%. For PROMM, the k-disease classifier achieved a sensitivity of 51% and specificity of 90%. CONCLUSIONS: Pain2D is a scalable, open-source tool that could potentially be trained for all diseases presenting with pain.

Next-generation phenotyping contributing to the identification of a 4.7 kb deletion in KANSL1 causing Koolen-de Vries syndrome.

Next-generation phenotyping (NGP) is an application of advanced methods of computer vision on medical imaging data such as portrait photos of individuals with rare disorders. NGP on portraits results in gestalt scores that can be used for the selection of appropriate genetic tests, and for the interpretation of the molecular data. Here, we report on an exceptional case of a young girl that was presented at the age of 8 and 15 and enrolled in NGP diagnostics on the latter occasion. The girl had clinical features associated with Koolen-de Vries syndrome (KdVS) and a suggestive facial gestalt. However, chromosomal microarray (CMA), Sanger sequencing, multiplex ligation-dependent probe analysis (MLPA), and trio exome sequencing remained inconclusive. Based on the highly indicative gestalt score for KdVS, the decision was made to perform genome sequencing to also evaluate noncoding variants. This analysis revealed a 4.7 kb de novo deletion partially affecting intron 6 and exon 7 of the KANSL1 gene. This is the smallest reported structural variant to date for this phenotype. The case illustrates how NGP can be integrated into the iterative diagnostic process of test selection and interpretation of sequencing results.

GestaltMatcher facilitates rare disease matching using facial phenotype descriptors.

Many monogenic disorders cause a characteristic facial morphology. Artificial intelligence can support physicians in recognizing these patterns by associating facial phenotypes with the underlying syndrome through training on thousands of patient photographs. However, this 'supervised' approach means that diagnoses are only possible if the disorder was part of the training set. To improve recognition of ultra-rare disorders, we developed GestaltMatcher, an encoder for portraits that is based on a deep convolutional neural network. Photographs of 17,560 patients with 1,115 rare disorders were used to define a Clinical Face Phenotype Space, in which distances between cases define syndromic similarity. Here we show that patients can be matched to others with the same molecular diagnosis even when the disorder was not included in the training set. Together with mutation data, GestaltMatcher could not only accelerate the clinical diagnosis of patients with ultra-rare disorders and facial dysmorphism but also enable the delineation of new phenotypes.

The combined prevalence of classified rare rheumatic diseases is almost double that of ankylosing spondylitis.

BACKGROUND: Rare diseases (RDs) affect less than 5/10,000 people in Europe and fewer than 200,000 individuals in the United States. In rheumatology, RDs are heterogeneous and lack systemic classification. Clinical courses involve a variety of diverse symptoms, and patients may be misdiagnosed and not receive appropriate treatment. The objective of this study was to identify and classify some of the most important RDs in rheumatology. We also attempted to determine their combined prevalence to more precisely define this area of rheumatology and increase awareness of RDs in healthcare systems. We conducted a comprehensive literature search and analyzed each disease for the specified criteria, such as clinical symptoms, treatment regimens, prognoses, and point prevalences. If no epidemiological data were available, we estimated the prevalence as 1/1,000,000. The total point prevalence for all RDs in rheumatology was estimated as the sum of the individually determined prevalences. RESULTS: A total of 76 syndromes and diseases were identified, including vasculitis/vasculopathy (n = 15), arthritis/arthropathy (n = 11), autoinflammatory syndromes (n = 11), myositis (n = 9), bone disorders (n = 11), connective tissue diseases (n = 8), overgrowth syndromes (n = 3), and others (n = 8). Out of the 76 diseases, 61 (80%) are classified as chronic, with a remitting-relapsing course in 27 cases (35%) upon adequate treatment. Another 34 (45%) diseases were predominantly progressive and difficult to control. Corticosteroids are a therapeutic option in 49 (64%) syndromes. Mortality is variable and could not be determined precisely. Epidemiological studies and prevalence data were available for 33 syndromes and diseases. For an additional eight diseases, only incidence data were accessible. The summed prevalence of all RDs was 28.8/10,000. CONCLUSIONS: RDs in rheumatology are frequently chronic, progressive, and present variable symptoms. Treatment options are often restricted to corticosteroids, presumably because of the scarcity of randomized controlled trials. The estimated combined prevalence is significant and almost double that of ankylosing spondylitis (18/10,000). Thus, healthcare systems should assign RDs similar importance as any other common disease in rheumatology.

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

BACKGROUND: The diagnosis of rare diseases poses a particular challenge to clinicians. This study analyzes whether patients' pain drawings (PDs) help in the differentiation of two pain-associated rare diseases, Ehlers-Danlos Syndrome (EDS) and Guillain-Barré Syndrome (GBS). METHOD: The study was designed as a prospective, observational, single-center study. The sample comprised 60 patients with EDS (3 male, 52 female, 5 without gender information; 39.2 ± 11.4 years) and 32 patients with GBS (10 male, 20 female, 2 without gender information; 50.5 ± 13.7 years). Patients marked areas afflicted by pain on a sketch of a human body with anterior, posterior, and lateral views. PDs were electronically scanned and processed. Each PD was classified based on the Ruzicka similarity to the EDS and the GBS averaged image (pain profile) in a leave-one-out cross validation approach. A receiver operating characteristic (ROC) curve was plotted. RESULTS: 60-80% of EDS patients marked the vertebral column with the neck and the tailbone and the knee joints as pain areas, 40-50% the shoulder-region, the elbows and the thumb saddle joint. 60-70% of GBS patients marked the dorsal and plantar side of the feet as pain areas, 40-50% the palmar side of the fingertips, the dorsal side of the left palm and the tailbone. 86% of the EDS patients and 96% of the GBS patients were correctly identified by computing the Ruzicka similarity. The ROC curve yielded an excellent area under the curve value of 0.95. CONCLUSION: PDs are a useful and economic tool to differentiate between GBS and EDS. Further studies should investigate its usefulness in the diagnosis of other pain-associated rare diseases. This study was registered in the German Clinical Trials Register, No. DRKS00014777 (Deutsches Register klinischer Studien, DRKS), on 01.06.2018.

Therapeutic options for patients with rare rheumatic diseases: a systematic review and meta-analysis.

BACKGROUND: Rare diseases (RDs) in rheumatology as a group have a high prevalence, but randomized controlled trials are hampered by their heterogeneity and low individual prevalence. To survey the current evidence of pharmacotherapies for rare rheumatic diseases, we conducted a systematic review and meta-analysis. Randomized controlled trials (RCTs) of RDs in rheumatology for different pharmaco-interventions were included into this meta-analysis if there were two or more trials investigating the same RD and using the same assessment tools or outcome parameters. The Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, and PUBMED were searched up to April 2nd 2020. The overall objective of this study was to identify RCTs of RDs in rheumatology, evaluate the overall quality of these studies, outline the evidence of pharmacotherapy, and summarize recommended therapeutic regimens. RESULTS: We screened 187 publications, and 50 RCTs met our inclusion criteria. In total, we analyzed data of 13 different RDs. We identified several sources of potential bias, such as a lack of description of blinding methods and allocation concealment, as well as small size of the study population. Meta-analysis was possible for 26 studies covering six RDs: Hunter disease, Behçet's disease, giant cell arteritis, ANCA-associated vasculitis, reactive arthritis, and systemic sclerosis. The pharmacotherapies tested in these studies consisted of immunosuppressants, such as corticosteroids, methotrexate and azathioprine, or biologicals. We found solid evidence for idursulfase as a treatment for Hunter syndrome. In Behçet's disease, apremilast and IF-α showed promising results with regard to total and partial remission, and Tocilizumab with regard to relapse-free remission in giant cell arteritis. Rituximab, cyclophosphamide, and azathioprine were equally effective in ANCA-associated vasculitis, while mepolizumab improved the efficacy of glucocorticoids. The combination of rifampicin and azithromycin showed promising results in reactive arthritis, while there was no convincing evidence for the efficacy of pharmacotherapy in systemic sclerosis. CONCLUSION: For some diseases such as systemic sclerosis, ANCA-associated vasculitis, or Behcet's disease, higher quality trials were available. These RCTs showed satisfactory efficacies for immunosuppressants or biological drugs, except for systemic sclerosis. More high quality RCTs are urgently warranted for a wide spectrum of RDs in rheumatology.