BACKGROUND: Use of artificial intelligence (AI) in rare diseases has grown rapidly in recent years. In this review we have outlined the most common machine-learning and deep-learning methods currently being used to classify and analyse large amounts of data, such as standardized images or specific text in electronic health records. To illustrate how these methods have been adapted or developed for use with rare diseases, we have focused on Fabry disease, an X-linked genetic disorder caused by lysosomal α-galactosidase. A deficiency that can result in multiple organ damage. METHODS: We searched PubMed for articles focusing on AI, rare diseases, and Fabry disease published anytime up to 08 January 2025. Further searches, limited to articles published between 01 January 2021 and 31 December 2023, were also performed using double combinations of keywords related to AI and each organ affected in Fabry disease, and AI and rare diseases. RESULTS: In total, 20 articles on AI and Fabry disease were included. In the rare disease field, AI methods may be applied prospectively to large populations to identify specific patients, or retrospectively to large data sets to diagnose a previously overlooked rare disease. Different AI methods may facilitate Fabry disease diagnosis, help monitor progression in affected organs, and potentially contribute to personalized therapy development. The implementation of AI methods in general healthcare and medical imaging centres may help raise awareness of rare diseases and prompt general practitioners to consider these conditions earlier in the diagnostic pathway, while chatbots and telemedicine may accelerate patient referral to rare disease experts. The use of AI technologies in healthcare may generate specific ethical risks, prompting new AI regulatory frameworks aimed at addressing these issues to be established in Europe and the United States. CONCLUSION: AI-based methods will lead to substantial improvements in the diagnosis and management of rare diseases. The need for a human guarantee of AI is a key issue in pursuing innovation while ensuring that human involvement remains at the centre of patient care during this technological revolution.

• Keywords
• Artificial intelligence, Deep learning, Fabry disease, Machine learning, Rare diseases,
• MeSH
• Fabry Disease * diagnosis   MeSH
• Humans MeSH
• Artificial Intelligence * MeSH
• Rare Diseases * diagnosis   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Review MeSH

Fabry disease is an X-linked lysosomal storage disorder that causes accumulation of glycosphingolipids in body tissues and fluids, leading to progressive organ damage and life-threatening complications. It can affect both males and females and can be classified into classic or later-onset phenotypes. The disease severity in females ranges from asymptomatic to the more severe, classic phenotype. Most females are hemizygous and the X-linked inheritance is associated with variable X-activation pattern and residual enzymatic activity. The heterogeneity of clinical presentation in females requires different approaches to diagnosis and management than males. A European group of 7 physicians, experienced in the management of Fabry disease, convened to discuss patient perspectives and published guidelines. The experts discussed the need to focus on psychological treatment in relation to individual coping styles when monitoring targets, and the lack of data supporting the use of plasma globotriaosylsphingosine over enzyme activity in the diagnosis of these patients. It was suggested that the high phenotypic variability in female patients may be related to the dynamic nature of the X-chromosome inactivation process and further understanding of this process could help predict the progression of Fabry disease in females and facilitate timely intervention. Due to the range of disease severity they exhibit, female patients with Fabry disease may require a more individualized treatment approach than males. Despite current recommendations, the experts agreed that early disease-specific treatment initiation in high-risk females could improve clinical outcome.

• Keywords
• Early diagnosis, Enzyme replacement therapy, Fabry disease, Female, Patient-reported outcome measures,
• MeSH
• Fabry Disease * therapy   genetics   diagnosis   MeSH
• Humans MeSH
• Check Tag
• Humans MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Review MeSH

Fabry disease is a progressive, X-linked lysosomal disorder caused by reduced or absent α-galactosidase A activity due to GLA variants. The effects of migalastat were examined in a cohort of 125 Fabry patients with migalastat-amenable GLA variants in the followME Pathfinders registry (EUPAS20599), an ongoing, prospective, patient-focused registry evaluating outcomes for current Fabry disease treatments. We report annualised estimated glomerular filtration rate (eGFR) and Fabry-associated clinical events (FACEs) in a cohort of patients who had received ≥3 years of migalastat treatment in a real-world setting. As of August 2022, 125 patients (60% male) had a mean migalastat exposure of 3.9 years. At enrolment, median age was 58 years (males, 57; females, 60) with a mean eGFR of 83.7 mL/min/1.73 m2 (n = 122; males, 83.7; females, 83.8) and a median left ventricular mass index of 115.1 g/m2 (n = 61; males, 131.2; females, 98.0). Mean (95% confidence interval) eGFR annualised rate of change in the overall cohort (n = 116) was -0.9 (-10.8, 9.9) mL/min/1.73 m2/year with a similar rate of change observed across patients with varying levels of kidney function at enrolment. Despite population age and baseline morbidity, 80% of patients did not experience a FACE during the mean 3.9 years of migalastat exposure. The incidence of renal, cardiac, and cerebrovascular events was 2.0, 83.2, and 4.1 events per 1000 patient-years, respectively. These data support a role of migalastat in preserving renal function and multisystem effectiveness during ≥3 years of migalastat treatment in this real-world Fabry population.

• Keywords
• Fabry disease, migalastat, real world evidence,
• MeSH
• 1-Deoxynojirimycin * analogs & derivatives   therapeutic use   MeSH
• alpha-Galactosidase genetics   MeSH
• Adult MeSH
• Fabry Disease * drug therapy   complications   MeSH
• Glomerular Filtration Rate drug effects   MeSH
• Cohort Studies MeSH
• Kidney drug effects   MeSH
• Middle Aged MeSH
• Humans MeSH
• Prospective Studies MeSH
• Registries MeSH
• Aged MeSH
• Treatment Outcome MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Names of Substances
• 1-Deoxynojirimycin * MeSH
• alpha-Galactosidase MeSH
• migalastat MeSH Browser

Fabry disease, a rare X-linked genetic disorder, results from pathogenic variants in GLA, leading to deficient lysosomal α-galactosidase A enzyme activity and multi-organ manifestations. Since 2001, enzyme replacement therapy (ERT), using agalsidase alfa or agalsidase beta, has been the mainstay treatment, albeit with limitations such as rapid clearance and immunogenicity. Pegunigalsidase alfa, a novel PEGylated recombinant alpha-galactosidase, offers promise as an alternative. Produced in plant cells, pegunigalsidase alfa exhibits enhanced stability, prolonged half-life, and reduced immunogenicity due to pegylation. A phase 1/2 clinical trial demonstrated Gb3 clearance from renal capillary endothelial cells and its 48-month extension study revealed notable outcomes in renal function preservation. Three phase 3 clinical trials (BRIDGE, BRIGHT, and BALANCE) have shown favorable efficacy and safety profile, although caution is warranted in interpreting the results of BRIDGE and BRIGHT which lacked control groups. In BALANCE, the pivotal phase 3 trial comparing pegunigalsidase alfa with agalsidase beta, an intention-to-treat analysis of the eGFR decline over 2 years showed that the intergroup difference [95%confidence interval] in the median slope was -0.36 mL/min/1.73 m2/year [-2.44; 1.73]. The confidence interval had a lower limit above the prespecified value of -3 mL/min/1.73 m2/year and included zero. Despite challenges such as occasional hypersensitivity reactions and immune-complex-mediated glomerulonephritis, pegunigalsidase alfa approval by the European Medicines Agency and the Food and Drug Administration represents a significant addition to Fabry disease therapeutic landscape providing an option for patients in whom enzyme replacement therapy with current formulations is poorly tolerated or poorly effective.

• Keywords
• Fabry disease, PEGylation, agalsidase, non-inferiority trial, renal function,
• Publication type
• Journal Article MeSH
• Review MeSH

AIMS: Fabry disease (FD) is a multisystemic lysosomal storage disorder caused by a defect in the alpha-galactosidase A gene that manifests as a phenocopy of hypertrophic cardiomyopathy. We assessed the echocardiographic 3D left ventricular (LV) strain of patients with FD in relation to heart failure severity using natriuretic peptides, the presence of a cardiovascular magnetic resonance (CMR) late gadolinium enhancement scar, and long-term prognosis. METHODS AND RESULTS: 3D echocardiography was feasible in 75/99 patients with FD [aged 47 ± 14 years, 44% males, LV ejection fraction (EF) 65 ± 6% and 51% with hypertrophy or concentric remodelling of the LV]. Long-term prognosis (death, heart failure decompensation, or cardiovascular hospitalization) was assessed over a median follow-up of 3.1 years. A stronger correlation was observed for N-terminal pro-brain natriuretic peptide levels with 3D LV global longitudinal strain (GLS, r = -0.49, P < 0.0001) than with 3D LV global circumferential strain (GCS, r = -0.38, P < 0.001) or 3D LVEF (r = -0.25, P = 0.036). Individuals with posterolateral scar on CMR had lower posterolateral 3D circumferential strain (CS; P = 0.009). 3D LV-GLS was associated with long-term prognosis [adjusted hazard ratio 0.85 (confidence interval 0.75-0.95), P = 0.004], while 3D LV-GCS and 3D LVEF were not (P = 0.284 and P = 0.324). CONCLUSION: 3D LV-GLS is associated with both heart failure severity measured by natriuretic peptide levels and long-term prognosis. Decreased posterolateral 3D CS reflects typical posterolateral scarring in FD. Where feasible, 3D-strain echocardiography can be used for a comprehensive mechanical assessment of the LV in patients with FD.

• Keywords
• 3D echocardiography, Fabry disease, cardiovascular magnetic resonance, heart failure, myocardial strain,
• MeSH
• Ventricular Dysfunction, Left * diagnostic imaging   etiology   MeSH
• Echocardiography, Three-Dimensional * methods   MeSH
• Echocardiography methods   MeSH
• Fabry Disease * complications   diagnostic imaging   MeSH
• Ventricular Function, Left MeSH
• Gadolinium MeSH
• Cicatrix diagnostic imaging   MeSH
• Contrast Media MeSH
• Humans MeSH
• Prognosis MeSH
• Reproducibility of Results MeSH
• Heart Failure * diagnostic imaging   etiology   MeSH
• Stroke Volume MeSH
• Check Tag
• Humans MeSH
• Male MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Names of Substances
• Gadolinium MeSH
• Contrast Media MeSH

Restrictive cardiomyopathy (RCM) is a heterogeneous group of diseases characterized by restrictive left ventricular pathophysiology, i.e. a rapid rise in ventricular pressure with only small increases in filling volume due to increased myocardial stiffness. More precisely, the defining feature of RCM is the coexistence of persistent restrictive pathophysiology, diastolic dysfunction, non-dilated ventricles, and atrial dilatation, regardless of ventricular wall thickness and systolic function. Beyond this shared haemodynamic hallmark, the phenotypic spectrum of RCM is wide. The disorders manifesting as RCM may be classified according to four main disease mechanisms: (i) interstitial fibrosis and intrinsic myocardial dysfunction, (ii) infiltration of extracellular spaces, (iii) accumulation of storage material within cardiomyocytes, or (iv) endomyocardial fibrosis. Many disorders do not show restrictive pathophysiology throughout their natural history, but only at an initial stage (with an evolution towards a hypokinetic and dilated phenotype) or at a terminal stage (often progressing from a hypertrophic phenotype). Furthermore, elements of both hypertrophic and restrictive phenotypes may coexist in some patients, making the classification challenge. Restrictive pathophysiology can be demonstrated by cardiac catheterization or Doppler echocardiography. The specific conditions may usually be diagnosed based on clinical data, 12-lead electrocardiogram, echocardiography, nuclear medicine, or cardiovascular magnetic resonance, but further investigations may be needed, up to endomyocardial biopsy and genetic evaluation. The spectrum of therapies is also wide and heterogeneous, but disease-modifying treatments are available only for cardiac amyloidosis and, partially, for iron overload cardiomyopathy.

• Keywords
• Amyloidosis, Classification, Myocardial disease, RCM, Restrictive cardiomyopathy,
• MeSH
• Echocardiography, Doppler MeSH
• Ventricular Dysfunction, Left * pathology   MeSH
• Echocardiography MeSH
• Humans MeSH
• Myocardium pathology   MeSH
• Cardiomyopathy, Restrictive * diagnosis   pathology   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

AIMS: Fabry disease (FD) is a rare X-linked genetic disorder caused by α-galactosidase A (AGALA) deficiency. Whereas 'classic' variant has multisystemic manifestation, the more recently described 'later-onset' variant is characterized by predominant cardiac involvement that often mimics hypertrophic cardiomyopathy (HCM). METHODS AND RESULTS: Consecutive unrelated patients with HCM were screened for FD in 16 (out of 17) cardiac centres in the Czech Republic covering specialized cardiology care from June 2017 to December 2018. AGALA activity and globotriaosylsphingosine (lyso-Gb3 ) levels were measured in all subjects using the dry blood spot method. FD was suspected in male patients with AGALA activity <1.2 μmol/h/L and in females with either low AGALA activity or lyso-Gb3 > 3.5 ng/mL. Positive screening results were confirmed by genetic testing. We evaluated 589 patients (390 males, 66%) with HCM (mean maximal myocardial thickness 19.1 ± 4.3 mm). The average age was 58.4 ± 14.7 years. In total, 17 patients (11 males, 6 females) had a positive screening result, and subsequently, six of them (four males and two females) had a genetically confirmed pathogenic GLA mutation (total prevalence of 1.02%). Five of these patients were carrying the p.N215S mutation known to cause a typical later-onset cardiac FD. CONCLUSIONS: We confirmed the prevalence of FD repeatedly reported in previous screening programmes (approximately 1% irrespective of gender) in a non-selected HCM population in Central Europe. Our findings advocate a routine screening for FD in all adult patients with HCM phenotype including both genders. The dry blood spot method used led to identification of clearly pathogenic variants.

• Keywords
• Alpha-galactosidase, Fabry disease, Genetic testing, Hypertrophic cardiomyopathy, Lyso-Gb3, Screening,
• MeSH
• alpha-Galactosidase genetics   MeSH
• Adult MeSH
• Fabry Disease * diagnosis   epidemiology   genetics   MeSH
• Genetic Testing MeSH
• Cardiomyopathy, Hypertrophic * diagnosis   epidemiology   genetics   MeSH
• Middle Aged MeSH
• Humans MeSH
• Aged MeSH
• Check Tag
• Adult MeSH
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Geographicals
• Czech Republic epidemiology   MeSH
• Names of Substances
• alpha-Galactosidase MeSH

BACKGROUND: Fabry disease (FD, OMIM #301500) is a rare, progressive, X-linked, inherited genetic disease caused by a functional deficiency of lysosomal α-galactosidase, leading to the accumulation of glycosphingolipids in virtually all of the body's cell types and fluids. Patients with rare genetic diseases and non-specific symptoms often experience substantial diagnostic delays, which can negatively impact the prompt initiation of treatment. If FD is not treated specifically, end organ damage (such as chronic renal failure, hypertrophic cardiomyopathy with arrhythmia, and strokes) impairs quality of life and reduces life expectancy. PATIENTS AND METHODS: For 83 consecutive patients with FD referred to the Russian reference center for lysosomal storage diseases, family trees were built and genetic testing (cascade genotyping) was offered to family members. RESULTS: The pathogenic GLA variant associated with FD was identified for all 83 probands. Family testing using cascade genotyping enabled the identification of 165 additional cases of FD among the tested 331 at-risk family members. DISCUSSION: This is the first study to have described family screening in a large Russian cohort of patients with FD and chronic kidney disease. Raising awareness of FD among clinicians is important for earlier diagnosis and specific treatment.

• Keywords
• Fabry disease, cascade genotyping, early diagnosis, family screening, rare diseases,
• MeSH
• alpha-Galactosidase genetics   MeSH
• Renal Insufficiency, Chronic * diagnosis   genetics   MeSH
• Fabry Disease * diagnosis   genetics   metabolism   MeSH
• Genetic Testing MeSH
• Glycosphingolipids MeSH
• Quality of Life MeSH
• Humans MeSH
• Mutation MeSH
• Family MeSH
• Rare Diseases genetics   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Names of Substances
• alpha-Galactosidase MeSH
• Glycosphingolipids MeSH

Fabry disease is a rare lysosomal storage disorder caused by mutations in the GLA gene, which, without treatment, can cause significant renal dysfunction. We evaluated the effects of enzyme replacement therapy with agalsidase alfa on renal decline in patients with Fabry disease using data from the Fabry Outcome Survey (FOS) registry. Male patients with Fabry disease aged >16 years at agalsidase alfa start were stratified by low (≤0.5 g/24 h) or high (>0.5 g/24 h) baseline proteinuria and by ‘classic’ or ‘non-classic’ phenotype. Overall, 193 male patients with low (n = 135) or high (n = 58) baseline proteinuria were evaluated. Compared with patients with low baseline proteinuria, those with high baseline proteinuria had a lower mean ± standard deviation baseline eGFR (89.1 ± 26.2 vs. 106.6 ± 21.8 mL/min/1.73 m2) and faster mean ± standard error eGFR decline (−3.62 ± 0.42 vs. −1.61 ± 0.28 mL/min/1.73 m2 per year; p < 0.0001). Patients with classic Fabry disease had similar rates of eGFR decline irrespective of baseline proteinuria; only one patient with non-classic Fabry disease had high baseline proteinuria, preventing meaningful comparisons between groups. In this analysis, baseline proteinuria significantly impacted the rate of eGFR decline in the overall population, suggesting that early treatment with good proteinuria control may be associated with renoprotective effects.

• Keywords
• Fabry disease, enzyme replacement therapy, estimated glomerular filtration rate, proteinuria,
• Publication type
• Journal Article MeSH

Fabry disease (FD) is a rare X-linked disorder of glycosphingolipid metabolism caused by pathogenic variants within the alpha-galactosidase A (GLA) gene, often leading to neurological manifestations including stroke. Multiple screening programs seeking GLA variants among stroke survivors lacked detailed phenotype description, making the interpretation of the detected variant's pathogenicity difficult. Here, we describe detailed clinical characteristics of GLA variant carriers identified by a nationwide stroke screening program in the Czech Republic. A total of 23 individuals with 8 different GLA variants were included in the study. A comprehensive diagnostic workup was performed by a team of FD specialists. The investigation led to the suggestion of phenotype reclassification for the G325S mutation from late-onset to classical. A novel variant R30K was found and was classified as a variant of unknown significance (VUS). The typical manifestation in our FD patients was a stroke occurring in the posterior circulation with an accompanying pathological finding in the cerebrospinal fluid. Moreover, we confirmed that cornea verticillata is typically associated with classical variants. Our findings underline the importance of detailed phenotype description and data sharing in the correct identification of pathogenicity of gene variants detected by high-risk-population screening programs.

• Keywords
• Fabry disease, GLA gene variants, data sharing, phenotype, screening programs, stroke,
• Publication type
• Journal Article MeSH