The Occurrence of 275 Rare Diseases and 47 Rare Disease Groups in Italy. Results from the National Registry of Rare Diseases

A multi-center distributed learning approach for Parkinson's disease classification using the traveling model paradigm

Distributed learning is a promising alternative to central learning for machine learning (ML) model training, overcoming data-sharing problems in healthcare. Previous studies exploring federated learning (FL) or the traveling model (TM) setup for medical image-based disease classification often relied on large databases with a limited number of centers or simulated artificial centers, raising doubts about real-world applicability. This study develops and evaluates a convolution neural network (CNN) for Parkinson's disease classification using data acquired by 83 diverse real centers around the world, mostly contributing small training samples. Our approach specifically makes use of the TM setup, which has proven effective in scenarios with limited data availability but has never been used for image-based disease classification. Our findings reveal that TM is effective for training CNN models, even in complex real-world scenarios with variable data distributions. After sufficient training cycles, the TM-trained CNN matches or slightly surpasses the performance of the centrally trained counterpart (AUROC of 83% vs. 80%). Our study highlights, for the first time, the effectiveness of TM in 3D medical image classification, especially in scenarios with limited training samples and heterogeneous distributed data. These insights are relevant for situations where ML models are supposed to be trained using data from small or remote medical centers, and rare diseases with sparse cases. The simplicity of this approach enables a broad application to many deep learning tasks, enhancing its clinical utility across various contexts and medical facilities.

Facilitating the Molecular Diagnosis of Rare Genetic Disorders Through Facial Phenotypic Scores

With recent advances in computer vision, many applications based on artificial intelligence have been developed to facilitate the diagnosis of rare genetic disorders through the analysis of patients' two-dimensional frontal images. Some of these have been implemented on online platforms with user-friendly interfaces and provide facial analysis services, such as Face2Gene. However, users cannot run the facial analysis processes in house because the training data and the trained models are unavailable. This article therefore provides an introduction, designed for users with programming backgrounds, to the use of the open-source GestaltMatcher approach to run facial analysis in their local environment. The Basic Protocol provides detailed instructions for applying for access to the trained models and then performing facial analysis to obtain a prediction score for each of the 595 genes in the GestaltMatcher Database. The prediction results can then be used to narrow down the search space of disease-causing mutations or further connect with a variant-prioritization pipeline. © 2023 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol: Using the open-source GestaltMatcher approach to perform facial analysis.

Digital health solution for monitoring and surveillance of Amyotrophic Lateral Sclerosis in Brazil

Amyotrophic Lateral Sclerosis (ALS) is a complex and rare neurodegenerative disease given its heterogeneity. Despite being known for many years, few countries have accurate information about the characteristics of people diagnosed with ALS, such as data regarding diagnosis and clinical features of the disease. In Brazil, the lack of information about ALS limits data for the research progress and public policy development that benefits people affected by this health condition. In this context, this article aims to show a digital health solution development and application for research, intervention, and strengthening of the response to ALS in the Brazilian Health System. The proposed solution is composed of two platforms: the Brazilian National ALS Registry, responsible for the data collection in a structured way from ALS patients all over Brazil; and the Brazilian National ALS Observatory, responsible for processing the data collected in the National Registry and for providing a monitoring room with indicators on people diagnosed with ALS in Brazil. The development of this solution was supported by the Brazilian Ministry of Health (MoH) and was carried out by a multidisciplinary team with expertise in ALS. This solution represents a tool with great potential for strengthening public policies and stands out for being the only public database on the disease, besides containing innovations that allow data collection by health professionals and/or patients. By using both platforms, it is believed that it will be possible to understand the demographic and epidemiological data of ALS in Brazil, since the data will be able to be analyzed by care teams and also by public health managers, both in the individual and collective monitoring of people living with ALS in Brazil.

Frequency-based rare diagnoses as a novel and accessible approach for studying rare diseases in large datasets: a cross-sectional study

BACKGROUND

Up to 8% of the general population have a rare disease, however, for lack of ICD-10 codes for many rare diseases, this population cannot be generically identified in large medical datasets. We aimed to explore frequency-based rare diagnoses (FB-RDx) as a novel method exploring rare diseases by comparing characteristics and outcomes of inpatient populations with FB-RDx to those with rare diseases based on a previously published reference list.

METHODS

Retrospective, cross-sectional, nationwide, multicenter study including 830,114 adult inpatients. We used the national inpatient cohort dataset of the year 2018 provided by the Swiss Federal Statistical Office, which routinely collects data from all inpatients treated in any Swiss hospital. Exposure: FB-RDx, according to 10% of inpatients with the least frequent diagnoses (i.e.1.decile) vs. those with more frequent diagnoses (deciles 2-10). Results were compared to patients having 1 of 628 ICD-10 coded rare diseases.

PRIMARY OUTCOME

In-hospital death.

SECONDARY OUTCOMES

30-day readmission, admission to intensive care unit (ICU), length of stay, and ICU length of stay. Multivariable regression analyzed associations of FB-RDx and rare diseases with these outcomes.

RESULTS

464,968 (56%) of patients were female, median age was 59 years (IQR: 40-74). Compared with patients in deciles 2-10, patients in the 1. were at increased risk of in-hospital death (OR 1.44; 95% CI: 1.38, 1.50), 30-day readmission (OR 1.29; 95% CI 1.25, 1.34), ICU admission (OR 1.50; 95% CI 1.46, 1.54), increased length of stay (Exp(B) 1.03; 95% CI 1.03, 1.04) and ICU length of stay (1.15; 95% CI 1.12, 1.18). ICD-10 based rare diseases groups showed similar results: in-hospital death (OR 1.82; 95% CI 1.75, 1.89), 30-day readmission (OR 1.37; 95% CI 1.32, 1.42), ICU admission (OR 1.40; 95% CI 1.36, 1.44) and increased length of stay (OR 1.07; 95% CI 1.07, 1.08) and ICU length of stay (OR 1.19; 95% CI 1.16, 1.22).

CONCLUSION(S)

This study suggests that FB-RDx may not only act as a surrogate for rare diseases but may also help to identify patients with rare disease more comprehensively. FB-RDx associate with in-hospital death, 30-day readmission, intensive care unit admission, and increased length of stay and intensive care unit length of stay, as has been reported for rare diseases.

An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction

OBJECTIVE

Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

MATERIALS AND METHODS

2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).

RESULTS

Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9 ± 0.13 years, while the TM achieved a MAE of 6.21 ± 0.50 years, comparable to central learning (MAE = 5.99 years).

DISCUSSION

Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.

CONCLUSION

The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.

10 years of CEMARA database in the AnDDI-Rares network: a unique resource facilitating research and epidemiology in developmental disorders in France

BACKGROUND

In France, the Ministry of Health has implemented a comprehensive program for rare diseases (RD) that includes an epidemiological program as well as the establishment of expert centers for the clinical care of patients with RD. Since 2007, most of these centers have entered the data for patients with developmental disorders into the CEMARA population-based registry, a national online data repository for all rare diseases. Through the CEMARA web portal, descriptive demographic data, clinical data, and the chronology of medical follow-up can be obtained for each center. We address the interest and ongoing challenges of this national data collection system 10 years after its implementation.

METHODS

Since 2007, clinicians and researchers have reported the "minimum dataset (MDS)" for each patient presenting to their expert center. We retrospectively analyzed administrative data, demographic data, care organization and diagnoses.

RESULTS

Over 10 years, 228,243 RD patients (including healthy carriers and family members for whom experts denied any suspicion of RD) have visited an expert center. Among them, 167,361 were patients affected by a RD (median age 11 years, 54% children, 46% adults, with a balanced sex ratio), and 60,882 were unaffected relatives (median age 37 years). The majority of patients (87%) were seen no more than once a year, and 52% of visits were for a diagnostic procedure. Among the 2,869 recorded rare disorders, 1,907 (66.5%) were recorded in less than 10 patients, 802 (28%) in 10 to 100 patients, 149 (5.2%) in 100 to 1,000 patients, and 11 (0.4%) in > 1,000 patients. Overall, 45.6% of individuals had no diagnosis and 6.7% had an uncertain diagnosis. Children were mainly referred by their pediatrician (46%; n = 55,755 among the 121,136 total children referrals) and adults by a medical specialist (34%; n = 14,053 among the 41,564 total adult referrals). Given the geographical coverage of the centers, the median distance from the patient's home was 25.1 km (IQR = 6.3 km-64.2 km).

CONCLUSIONS

CEMARA provides unprecedented support for epidemiological, clinical and therapeutic studies in the field of RD. Researchers can benefit from the national scope of CEMARA data, but also focus on specific diseases or patient subgroups. While this endeavor has been a major collective effort among French RD experts to gather large-scale data into a single database, it provides tremendous potential to improve patient care.

Privacy preserving distributed learning classifiers - Sequential learning with small sets of data

BACKGROUND

Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database.

METHODS

We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC).

FINDINGS

The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset.

INTERPRETATION

Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

Multifactorial Rare Diseases: Can Uncertainty Analysis Bring Added Value to the Search for Risk Factors and Etiopathogenesis?

Uncertainty analysis is the process of identifying limitations in knowledge and evaluating their implications for scientific conclusions. Uncertainty analysis is a stable component of risk assessment and is increasingly used in decision making on complex health issues. Uncertainties should be identified in a structured way and prioritized according to their likely impact on the outcome of scientific conclusions. Uncertainty is inherent to the rare diseases (RD) area, where research and healthcare have to cope with knowledge gaps due to the rarity of the conditions; yet a systematic approach toward uncertainties is not usually undertaken. The uncertainty issue is particularly relevant to multifactorial RD, whose etiopathogenesis involves environmental factors and genetic predisposition. Three case studies are presented: the newly recognized acute multisystem inflammatory syndrome in children and adolescents associated with SARS-CoV-2 infection; the assessment of risk factors for neural tube defects; and the genotype-phenotype correlation in familial Mediterranean fever. Each case study proposes the initial identification of the main epistemic and sampling uncertainties and their impacts. Uncertainty analysis in RD may present aspects similar to those encountered when conducting risk assessment in data-poor scenarios; therefore, approaches such as expert knowledge elicitation may be considered. The RD community has a main strength in managing uncertainty, as it proactively develops stakeholder involvement, data sharing and open science. The open science approaches can be profitably integrated by structured uncertainty analysis, especially when dealing with multifactorial RD involving environmental and genetic risk factors.

Awareness of rare and genetic neurological diseases among italian neurologist. A national survey

Rare neurological diseases (RNDs) are a heterogeneous group of disorders mainly affecting the central and peripheral nervous systems, representing almost 50% of all rare diseases; this explains why neurologists are very often involved in their diagnosis, treatment and research. The purpose of this study was to quantitatively describe the awareness of RNDs among the neurological community of the Italian Society of Neurology (SIN). A survey of the Italian Neurogenetics and Rare diseases group of the SIN, similar to what was submitted to the members of the EAN Task Force on Rare Neurologic Diseases and to EAN Panels Scientific Committee Management Groups, was launched in January 2019 in order to verify the specific Italian situations and possibly the regional differences. Answers were collected online. We observed that Italian Members of the SIN Neurogenetics and Rare Neurologic Diseases Scientific Group are well aware of the burden posed by RNDs but at the national and regional level, the relative awareness is sketchy and disparate. Although many national initiatives have been undertaken to facilitate the diagnosis and management in Italy, our survey reveals that much works has to be done in supporting RNDs patients, including a deeper collaboration between politics, universities and all stakeholders in the field.

Primary Sclerosing Cholangitis: Burden of Disease and Mortality Using Data from the National Rare Diseases Registry in Italy

Introduction: Studies on the epidemiology of primary sclerosing cholangitis (PSC) are mainly based on tertiary referral centers; and are retrospective case series susceptible to selection bias. The aim of this study was to estimate incidence; survival and cause of mortality of PSC in Italy; using population-based data. Methods: Data collected from the National Rare Diseases Registry (RNMR) and the National Mortality Database (NMD) were integrated and analyzed. Results: We identified 502 PSC incident cases. The crude incidence rate between 2012 and 2014 was 0.10 per 100,000 individuals. Sixty percent were male; mean age at disease onset and at diagnosis were 33 and 37 years; respectively; highlighting a mean diagnostic delay of 4 years. The rate of interregional mobility was 12%. Ten-year survival was 92%. In 32% of cases the cause of death was biliary-related; 12% died of biliary or gallbladder cancer. Conclusions: For rare diseases such as PSC; population-based cohort’s studies are of paramount importance. Incidence rates of PSC in Italy are markedly lower and survival much longer than the ones reported from tertiary; single-centre series. Moreover; the diagnostic delay and the patient interregional mobility highlights the need for increasing awareness on the disease and for resource reallocation among Italian regions within the National Health Service

Prevalence of Huntington Disease in Italy: a systematic review and meta-analysis

Worldwide prevalence of Huntington’s disease (HD) is quite heterogenous. As Italy is characterized by significant genetic heterogeneity, with presumptive differences between Italian regions, this review was undertaken to define available data of HD prevalence in Italy, to assess geographic heterogeneity, and reconcile possible variation in HD prevalence rates with the availability of genetic testing.

Value of the Rare Disease Registry of the Italian Region Friuli Venezia Giulia

BACKGROUND

The lack of epidemiological and clinical data is a major obstacle in health service planning for rare diseases. Patient registries are examples of real-world data that may fill the information gap.

OBJECTIVE

We describe the Rare Disease Registry of the Friuli Venezia Giulia region of Italy and its potential for research and health planning.

METHODS

The Rare Disease Registry data were linked with information on mortality, hospital discharges, ambulatory care, and drug prescriptions contained in administrative databases. All information is anonymous, and data linkage was based on a stochastic key univocal for each patient. Average annual costs owing to hospitalizations, outpatient care, and medications were estimated.

RESULTS

Implementation of the Registry started in 2010, and 4250 participants were registered up to 2017. A total of 2696 patients were living in the region as of January 1, 2017. The overall raw prevalence of rare diseases was 22 per 10,000 inhabitants, with higher prevalence in the pediatric population. The most common disease groups were congenital malformations, chromosomal and genetic syndromes, and circulatory and nervous diseases. In 2017, 30 patients died, 648 were hospitalized, and 2355 received some type of ambulatory care. The total annual estimated cost was approximately €6.5 million, with great variability in the average patient cost across diseases.

CONCLUSIONS

The possibility of following the detailed real-world care experience of patients with each specific rare disease and assessing the costs related to each step in their care path represents a unique opportunity to identify inefficiencies, optimize care, and reduce waste of resources.

Red Flags for early referral of people with symptoms suggestive of narcolepsy: a report from a national multidisciplinary panel

OBJECTIVE

Narcolepsy is a lifelong disease, manifesting with excessive daytime sleepiness and cataplexy, arising between childhood and young adulthood. The diagnosis is typically made after a long delay that burdens the disease severity. The aim of the project, promoted by the "Associazione Italiana Narcolettici e Ipersonni" is to develop Red Flags to detect symptoms for early referral, targeting non-sleep medicine specialists, general practitioners, and pediatricians.

MATERIALS AND METHODS

A multidisciplinary panel, including patients, public institutions, and representatives of national scientific societies of specialties possibly involved in the diagnostic process of suspected narcolepsy, was convened. The project was accomplished in three phases. Phase 1: Sleep experts shaped clinical pictures of narcolepsy in pediatric and adult patients. On the basis of these pictures, Red Flags were drafted. Phase 2: Representatives of the scientific societies and patients filled in a form to identify barriers to the diagnosis of narcolepsy. Phase 3: The panel produced suggestions for the implementation of Red Flags.

RESULTS

Red Flags were produced representing three clinical pictures of narcolepsy in pediatric patients ((1) usual sleep symptoms, (2) unusual sleep symptoms, (3) endocrinological signs) and two in adult patients ((1) usual sleep symptoms, (2) unusual sleep symptoms). Inadequate knowledge of symptoms at onset by medical doctors turned out to be the main reported barrier to diagnosis.

CONCLUSIONS

This report will hopefully enhance knowledge and awareness of narcolepsy among non-specialists in sleep medicine in order to reduce the diagnostic delay that burdens patients in Italy. Similar initiatives could be promoted across Europe.