Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

Navigating the uncommon: challenges in applying evidence-based medicine to rare diseases and the prospects of artificial intelligence solutions

The study of rare diseases has long been an area of challenge for medical researchers, with agonizingly slow movement towards improved understanding of pathophysiology and treatments compared with more common illnesses. The push towards evidence-based medicine (EBM), which prioritizes certain types of evidence over others, poses a particular issue when mapped onto rare diseases, which may not be feasibly investigated using the methodologies endorsed by EBM, due to a number of constraints. While other trial designs have been suggested to overcome these limitations (with varying success), perhaps the most recent and enthusiastically adopted is the application of artificial intelligence to rare disease data. This paper critically examines the pitfalls of EBM (and its trial design offshoots) as it pertains to rare diseases, exploring the current landscape of AI as a potential solution to these challenges. This discussion is also taken a step further, providing philosophical commentary on the weaknesses and dangers of AI algorithms applied to rare disease research. While not proposing a singular solution, this article does provide a thoughtful reminder that no 'one-size-fits-all' approach exists in the complex world of rare diseases. We must balance cautious optimism with critical evaluation of new research paradigms and technology, while at the same time not neglecting the ever-important aspect of patient values and preferences, which may be challenging to incorporate into computer-driven models.

The impact and future of artificial intelligence in medical genetics and molecular medicine: an ongoing revolution

Artificial intelligence (AI) platforms have emerged as pivotal tools in genetics and molecular medicine, as in many other fields. The growth in patient data, identification of new diseases and phenotypes, discovery of new intracellular pathways, availability of greater sets of omics data, and the need to continuously analyse them have led to the development of new AI platforms. AI continues to weave its way into the fabric of genetics with the potential to unlock new discoveries and enhance patient care. This technology is setting the stage for breakthroughs across various domains, including dysmorphology, rare hereditary diseases, cancers, clinical microbiomics, the investigation of zoonotic diseases, omics studies in all medical disciplines. AI's role in facilitating a deeper understanding of these areas heralds a new era of personalised medicine, where treatments and diagnoses are tailored to the individual's molecular features, offering a more precise approach to combating genetic or acquired disorders. The significance of these AI platforms is growing as they assist healthcare professionals in the diagnostic and treatment processes, marking a pivotal shift towards more informed, efficient, and effective medical practice. In this review, we will explore the range of AI tools available and show how they have become vital in various sectors of genomic research supporting clinical decisions.

Artificial intelligence in drug repurposing for rare diseases: a mini-review

Drug repurposing, the process of identifying new uses for existing drugs beyond their original indications, offers significant advantages in terms of reduced development time and costs, particularly in addressing unmet medical needs in rare diseases. Artificial intelligence (AI) has emerged as a transformative force in healthcare, and by leveraging AI technologies, researchers aim to overcome some of the challenges associated with rare diseases. This review presents concrete case studies, as well as pre-existing platforms, initiatives, and companies that demonstrate the application of AI for drug repurposing in rare diseases. Despite representing a modest part of the literature compared to other diseases such as COVID-19 or cancer, the growing interest, and investment in AI for drug repurposing in rare diseases underscore its potential to accelerate treatment availability for patients with unmet medical needs.

Automatic Classification and Visualization of Text Data on Rare Diseases

More than 7000 rare diseases affect over 400 million people, posing significant challenges for medical research and healthcare. The integration of precision medicine with artificial intelligence offers promising solutions. This work introduces a classifier developed to discern whether research and news articles pertain to rare or non-rare diseases. Our methodology involves extracting 709 rare disease MeSH terms from Mondo and MeSH to improve rare disease categorization. We evaluate our classifier on abstracts from PubMed/MEDLINE and an expert-annotated news dataset, which includes news articles on four selected rare neurodevelopmental disorders (NDDs)-considered the largest category of rare diseases-from a total of 16 analyzed. We achieved F1 scores of 85% for abstracts and 71% for news articles, demonstrating robustness across both datasets and highlighting the potential of integrating artificial intelligence and ontologies to improve disease classification. Although the results are promising, they also indicate the need for further refinement in managing data heterogeneity. Our classifier improves the identification and categorization of medical information, essential for advancing research, enhancing information access, influencing policy, and supporting personalized treatments. Future work will focus on expanding disease classification to distinguish between attributes such as infectious and hereditary diseases, addressing data heterogeneity, and incorporating multilingual capabilities.

Are Current Educational and Therapeutic Programs, Directed at Rare Disease Transplant Candidates and Recipients, Sufficient to Support Them on the Path From Diagnosis to Life After Allogenic Transplantation?-Recommendations for Member State Policymakers

For many rare disease (RD) patients, allogenic transplantation represents an effective therapy, improving overall survival rates and quality of life (QoL). Globally, ∼1% of liver transplants are performed for RDs and rare indications. However, patients and carers report unmet needs on their pathway toward treatment-in education and therapeutic measures, oftentimes shouldering expertise-building responsibility themselves. These issues are exacerbated in child patients. Estimates indicate that 6% to 8% of Poland's population (2.3-3 million persons) are burdened by RDs and potentially face such issues. This work aims to identify shortcomings of Polish policy in the field of educational and therapeutic measures for RD transplant candidates and recipients. Based on solutions introduced by pioneers, recommendations are formulated regarding priority actions. An analysis of national, transnational, and individual-center programs, directed at patients during their path from diagnosis to life post-transplant, was conducted. The investigation uncovered measure gaps not addressed by the National Plan for Rare Diseases-in fields of patient and stakeholder education (pre- and post-transplant), psychological care provision, specialized center creation, integration of data scattered among registries with the national insurer's database, and artificial intelligence (AI) tool implementation to support both early diagnostic efforts and tailoring of patient treatment. Programs directed at RD transplant candidates and recipients must aim to ensure that a satisfactory psychosomatic condition of the patient is maintained before and following the procedure, therefore lending credence to success. This necessitates early diagnosis schemes, and personalized medicine, multidisciplinary approaches to the individual, achievable only through big data system creation and AI introduction.

GPAD: a natural language processing-based application to extract the gene-disease association discovery information from OMIM

BACKGROUND

Thousands of genes have been associated with different Mendelian conditions. One of the valuable sources to track these gene-disease associations (GDAs) is the Online Mendelian Inheritance in Man (OMIM) database. However, most of the information in OMIM is textual, and heterogeneous (e.g. summarized by different experts), which complicates automated reading and understanding of the data. Here, we used Natural Language Processing (NLP) to make a tool (Gene-Phenotype Association Discovery (GPAD)) that could syntactically process OMIM text and extract the data of interest.

RESULTS

GPAD applies a series of language-based techniques to the text obtained from OMIM API to extract GDA discovery-related information. GPAD can inform when a particular gene was associated with a specific phenotype, as well as the type of validation-whether through model organisms or cohort-based patient-matching approaches-for such an association. GPAD extracted data was validated with published reports and was compared with large language model. Utilizing GPAD's extracted data, we analysed trends in GDA discoveries, noting a significant increase in their rate after the introduction of exome sequencing, rising from an average of about 150-250 discoveries each year. Contrary to hopes of resolving most GDAs for Mendelian disorders by now, our data indicate a substantial decline in discovery rates over the past five years (2017-2022). This decline appears to be linked to the increasing necessity for larger cohorts to substantiate GDAs. The rising use of zebrafish and Drosophila as model organisms in providing evidential support for GDAs is also observed.

CONCLUSIONS

GPAD's real-time analyzing capacity offers an up-to-date view of GDA discovery and could help in planning and managing the research strategies. In future, this solution can be extended or modified to capture other information in OMIM and scientific literature.

Knowledge, Perceptions and Attitude of Researchers Towards Using ChatGPT in Research

INTRODUCTION

ChatGPT, a recently released chatbot from OpenAI, has found applications in various aspects of life, including academic research. This study investigated the knowledge, perceptions, and attitudes of researchers towards using ChatGPT and other chatbots in academic research.

METHODS

A pre-designed, self-administered survey using Google Forms was employed to conduct the study. The questionnaire assessed participants' knowledge of ChatGPT and other chatbots, their awareness of current chatbot and artificial intelligence (AI) applications, and their attitudes towards ChatGPT and its potential research uses.

RESULTS

Two hundred researchers participated in the survey. A majority were female (57.5%), and over two-thirds belonged to the medical field (68%). While 67% had heard of ChatGPT, only 11.5% had employed it in their research, primarily for rephrasing paragraphs and finding references. Interestingly, over one-third supported the notion of listing ChatGPT as an author in scientific publications. Concerns emerged regarding AI's potential to automate researcher tasks, particularly in language editing, statistics, and data analysis. Additionally, roughly half expressed ethical concerns about using AI applications in scientific research.

CONCLUSION

The increasing use of chatbots in academic research necessitates thoughtful regulation that balances potential benefits with inherent limitations and potential risks. Chatbots should not be considered authors of scientific publications but rather assistants to researchers during manuscript preparation and review. Researchers should be equipped with proper training to utilize chatbots and other AI tools effectively and ethically.

Natural history of rare diseases using natural language processing of narrative unstructured electronic health records: The example of Dravet syndrome

OBJECTIVE

The increasing implementation of electronic health records allows the use of advanced text-mining methods for establishing new patient phenotypes and stratification, and for revealing outcome correlations. In this study, we aimed to explore the electronic narrative clinical reports of a cohort of patients with Dravet syndrome (DS) longitudinally followed at our center, to identify the capacity of this methodology to retrace natural history of DS during the early years.

METHODS

We used a document-based clinical data warehouse employing natural language processing to recognize the phenotype concepts in the narrative medical reports. We included patients with DS who have a medical report produced before the age of 2 years and a follow-up after the age of 3 years ("DS cohort," 56 individuals). We selected two control populations, a "general control cohort" (275 individuals) and a "neurological control cohort" (281 individuals), with similar characteristics in terms of gender, number of reports, and age at last report. To find concepts specifically associated with DS, we performed a phenome-wide association study using Cox regression, comparing the reports of the three cohorts. We then performed a qualitative analysis of the surviving concepts based on their median age at first appearance.

RESULTS

A total of 76 concepts were prevalent in the reports of children with DS. Concepts appearing during the first 2 years were mostly related with the epilepsy features at the onset of DS (convulsive and prolonged seizures triggered by fever, often requiring in-hospital care). Subsequently, concepts related to new types of seizures and to drug resistance appeared. A series of non-seizure-related concepts emerged after the age of 2-3 years, referring to the nonseizure comorbidities classically associated with DS.

SIGNIFICANCE

The extraction of clinical terms by narrative reports of children with DS allows outlining the known natural history of this rare disease in early childhood. This original model of "longitudinal phenotyping" could be applied to other rare and very rare conditions with poor natural history description.

Is the diagnostic model based on convolutional neural network superior to pediatric radiologists in the ultrasonic diagnosis of biliary atresia?

Background

Many screening and diagnostic methods are currently available for biliary atresia (BA), but the early and accurate diagnosis of BA remains a challenge with existing methods. This study aimed to use deep learning algorithms to intelligently analyze the ultrasound image data, build a BA ultrasound intelligent diagnostic model based on the convolutional neural network, and realize an intelligent diagnosis of BA.

Methods

A total of 4,887 gallbladder ultrasound images of infants with BA, non-BA hyperbilirubinemia, and healthy infants were collected. Two mask region convolutional neural network (Mask R-CNN) models based on different backbone feature extraction networks were constructed. The diagnostic performance between the two models was compared through good-quality images at the image level and the patient level. The diagnostic performance between the two models was compared through poor-quality images. The diagnostic performance of BA between the model and four pediatric radiologists was compared at the image level and the patient level.

Results

The classification performance of BA in model 2 was slightly higher than that in model 1 in the test set, both at the image level and at the patient level, with a significant difference of p = 0.0365 and p = 0.0459, respectively. The classification accuracy of model 2 was slightly higher than that of model 1 in poor-quality images (88.3% vs. 86.4%), and the difference was not statistically significant (p = 0.560). The diagnostic performance of model 2 was similar to that of the two radiology experts at the image level, and the differences were not statistically significant. The diagnostic performance of model 2 in the test set was higher than that of the two radiology experts at the patient level (all p < 0.05).

Conclusion

The performance of model 2 based on Mask R-CNN in the diagnosis of BA reached or even exceeded the level of pediatric radiology experts.

Artificial intelligence in rare disease diagnosis and treatment

Artificial intelligence (AI) utilization in health care has grown over the past few years. It also has demonstrated potential in improving the efficiency of diagnosis and treatment. Some types of AI, such as machine learning, allow for the efficient analysis of vast datasets, identifying patterns, and generating key insights. Predictions can then be made for medical diagnosis and personalized treatment recommendations. The use of AI can bypass some conventional limitations associated with rare diseases. Namely, it can optimize traditional randomized control trials, and may eventually reduce costs for drug research and development. Recent advancements have enabled researchers to train models based on large datasets and then fine-tune these models on smaller datasets typically associated with rare diseases. In this mini-review, we discuss recent advancements in AI and how AI can be applied to streamline rare disease diagnosis and optimize treatment.

RDDL: A systematic ensemble pipeline tool that streamlines balancing training schemes to reduce the effects of data imbalance in rare-disease-related deep-learning applications

Identifying lowly prevalent diseases, or rare diseases, in their early stages is key to disease treatment in the medical field. Deep learning techniques now provide promising tools for this purpose. Nevertheless, the low prevalence of rare diseases entangles the proper application of deep networks for disease identification due to the severe class-imbalance issue. In the past decades, some balancing methods have been studied to handle the data-imbalance issue. The bad news is that it is verified that none of these methods guarantees superior performance to others. This performance variation causes the need to formulate a systematic pipeline with a comprehensive software tool for enhancing deep-learning applications in rare disease identification. We reviewed the existing balancing schemes and summarized a systematic deep ensemble pipeline with a constructed tool called RDDL for handling the data imbalance issue. Through two real case studies, we showed that rare disease identification could be boosted with this systematic RDDL pipeline tool by lessening the data imbalance problem during model training. The RDDL pipeline tool is available at https://github.com/cobisLab/RDDL/.

The Impact of Artificial Intelligence on Optimizing Diagnosis and Treatment Plans for Rare Genetic Disorders

Rare genetic disorders (RDs), characterized by their low prevalence and diagnostic complexities, present significant challenges to healthcare systems. This article explores the transformative impact of artificial intelligence (AI) and machine learning (ML) in addressing these challenges. It emphasizes the need for accurate and early diagnosis of RDs, often hindered by genetic and clinical heterogeneity. This article discusses how AI and ML are reshaping healthcare, providing examples of their effectiveness in disease diagnosis, prognosis, image analysis, and drug repurposing. It highlights AI's ability to efficiently analyze extensive datasets and expedite diagnosis, showcasing case studies like Face2Gene. Furthermore, the article explores how AI tailors treatment plans for RDs, leveraging ML and deep learning (DL) to create personalized therapeutic regimens. It emphasizes AI's role in drug discovery, including the identification of potential candidates for rare disease treatments. Challenges and limitations related to AI in healthcare, including ethical, legal, technical, and human aspects, are addressed. This article underscores the importance of data ethics, privacy, and algorithmic fairness, as well as the need for standardized evaluation techniques and transparency in AI research. It highlights second-generation AI systems that prioritize patient-centric care, efficient patient recruitment for clinical trials, and the significance of high-quality data. The integration of AI with telemedicine, the growth of health databases, and the potential for personalized therapeutic recommendations are identified as promising directions for the field. In summary, this article provides a comprehensive exploration of how AI and ML are revolutionizing the diagnosis and treatment of RDs, addressing challenges while considering ethical implications in this rapidly evolving healthcare landscape.

Clinicians' Views on Using Artificial Intelligence in Healthcare: Opportunities, Challenges, and Beyond

INTRODUCTION

The healthcare industry has made significant progress in information technology, which has improved healthcare procedures and brought about advancements in clinical care services. This includes gathering crucial clinical data and implementing intelligent health information management. Artificial Intelligence (AI) has the potential to bolster further existing health information systems, notably electronic health records (EHRs). With AI, EHRs can offer more customized and adaptable roles for patients. This study aims to delve into the current and potential uses of AI and examine the obstacles that come with it.

METHOD

In this study, we employed a qualitative methodology and purposive sampling to select participants. We sought out clinicians who were eager to share their professional insights. Our research involved conducting three focus group interviews, each lasting an hour. The moderator began each session by introducing the study's goals and assuring participants of confidentiality to foster a collaborative environment. The facilitator asked open-ended questions about EHR, including its applications, challenges, and AI-assisted features.

RESULTS

The research conducted by 26 participants has identified five crucial areas of using AI in healthcare delivery. These areas include predictive analysis, clinical decision support systems, data visualization, natural language processing (NLP), patient monitoring, mobile technology, and future and emerging trends. However, the hype surrounding AI and the fact that the technology is still in its early stages pose significant challenges. Technical limitations related to language processing and context-specific reasoning must be addressed. Furthermore, medico-legal challenges arise when AI supports or autonomously delivers healthcare services. Governments must develop strategies to ensure AI's responsible and transparent application in healthcare delivery.

CONCLUSION

AI technology has the potential to revolutionize healthcare through its integration with EHRs and other existing technologies. However, several challenges must be addressed before this potential can be fully realized. The development and testing of complex EHR systems that utilize AI must be approached with care to ensure their accuracy and trustworthiness in decision-making about patient treatment. Additionally, there is a need to navigate medico-legal obligations and ensure that benefits are equitably distributed.

The Role of Virtual Triage in Improving Clinician Experience and Satisfaction: A Narrative Review

Objective

This review examines the literature on improving clinician satisfaction with a focus on what has been most effective in improving experience from the perspective of clinicians, and the potential role that virtual triage (VT) technology can play in delivering positive clinician experiences that improve clinical care, and bring value to health care delivery organizations (HDOs).

Methods

Review and synthesis of evidence on clinician satisfaction indicating a potential for VT to favorably impact clinician experience, sense of effectiveness, efficiency, and reduction of administrative task burden. Analysis considers how to conceptualize and the value of improving clinician experience, leading clinician dissatisfiers, and the potential role of VT in improving clinician experience/satisfaction.

Results

Contributors to poor clinician experience/satisfaction where VT could have a beneficial impact include better managing resource limitations, administrative workload, lack of care coordination, information overload, and payer interactions. VT can improve clinician experience through the technology's ability to leverage real-time actionable data clinicians can use, streamlining patient-clinician communications, personalizing care delivery, optimizing care coordination, and better aligning digital/virtual services with clinical practice. From an organizational perspective, improvements in clinician experience and satisfaction derive from establishing an effective digital back door, increasing the clinical impact of and satisfaction derived from telemedicine and virtual care, and enhancing clinician centricity.

Conclusions

By embracing digital transformation and implementing solutions such as VT that focus on improving patient and clinician experience, HDOs can address barriers to delivery of high-quality, efficient, and cost-effective care. VT is a digital health tool that can create a more streamlined and satisfying experience for clinicians and the patients they care for. VT is a technology solution that can help clinicians make faster more informed decisions, reduces avoidable care, improves communication with patients and within care teams, and lowers their administrative burden so they have more quality time to care for patients.

Successes and challenges of artificial intelligence in cardiology

In the past decades there has been a substantial evolution in data management and data processing techniques. New data architectures made analysis of big data feasible, healthcare is orienting towards personalized medicine with digital health initiatives, and artificial intelligence (AI) is becoming of increasing importance. Despite being a trendy research topic, only very few applications reach the stage where they are implemented in clinical practice. This review provides an overview of current methodologies and identifies clinical and organizational challenges for AI in healthcare.

A systematic review on machine learning approaches in the diagnosis and prognosis of rare genetic diseases

BACKGROUND

The diagnosis of rare genetic diseases is often challenging due to the complexity of the genetic underpinnings of these conditions and the limited availability of diagnostic tools. Machine learning (ML) algorithms have the potential to improve the accuracy and speed of diagnosis by analyzing large amounts of genomic data and identifying complex multiallelic patterns that may be associated with specific diseases. In this systematic review, we aimed to identify the methodological trends and the ML application areas in rare genetic diseases.

METHODS

We performed a systematic review of the literature following the PRISMA guidelines to search studies that used ML approaches to enhance the diagnosis of rare genetic diseases. Studies that used DNA-based sequencing data and a variety of ML algorithms were included, summarized, and analyzed using bibliometric methods, visualization tools, and a feature co-occurrence analysis.

FINDINGS

Our search identified 22 studies that met the inclusion criteria. We found that exome sequencing was the most frequently used sequencing technology (59%), and rare neoplastic diseases were the most prevalent disease scenario (59%). In rare neoplasms, the most frequent applications of ML models were the differential diagnosis or stratification of patients (38.5%) and the identification of somatic mutations (30.8%). In other rare diseases, the most frequent goals were the prioritization of rare variants or genes (55.5%) and the identification of biallelic or digenic inheritance (33.3%). The most employed method was the random forest algorithm (54.5%). In addition, the features of the datasets needed for training these algorithms were distinctive depending on the goal pursued, including the mutational load in each gene for the differential diagnosis of patients, or the combination of genotype features and sequence-derived features (such as GC-content) for the identification of somatic mutations.

CONCLUSIONS

ML algorithms based on sequencing data are mainly used for the diagnosis of rare neoplastic diseases, with random forest being the most common approach. We identified key features in the datasets used for training these ML models according to the objective pursued. These features can support the development of future ML models in the diagnosis of rare genetic diseases.

Development of an integrated and comprehensive clinical trial process management system

BACKGROUND

The process of initiating and completing clinical drug trials in hospital settings is highly complex, with numerous institutional, technical, and record-keeping barriers. In this study, we independently developed an integrated clinical trial management system (CTMS) designed to comprehensively optimize the process management of clinical trials. The CTMS includes system development methods, efficient integration with external business systems, terminology, and standardization protocols, as well as data security and privacy protection.

METHODS

The development process proceeded through four stages, including demand analysis and problem collection, system design, system development and testing, system trial operation, and training the whole hospital to operate the system. The integrated CTMS comprises three modules: project approval and review management, clinical trial operations management, and background management modules. These are divided into seven subsystems and 59 internal processes, realizing all the functions necessary to comprehensively perform the process management of clinical trials. Efficient data integration is realized through extract-transform-load, message queue, and remote procedure call services with external systems such as the hospital information system (HIS), laboratory information system (LIS), electronic medical record (EMR), and clinical data repository (CDR). Data security is ensured by adopting corresponding policies for data storage and data access. Privacy protection complies with laws and regulations and de-identifies sensitive patient information.

RESULTS

The integrated CTMS was successfully developed in September 2015 and updated to version 4.2.5 in March 2021. During this period, 1388 study projects were accepted, 43,051 electronic data stored, and 12,144 subjects recruited in the First Affiliated Hospital, Zhejiang University School of Medicine.

CONCLUSION

The developed integrated CTMS realizes the data management of the entire clinical trials process, providing basic conditions for the efficient, high-quality, and standardized operation of clinical trials.

A Community-Based Participatory Framework to Co-Develop Patient Education Materials (PEMs) for Rare Diseases: A Model Transferable across Diseases

At least 50% of chronic disease patients don't follow their care plans, leading to lower health outcomes and higher medical costs. Providing Patient Education Materials (PEMs) to individuals living with a disease can help to overcome these problems. PEMs are especially beneficial for people suffering from multisystemic and underrecognized diseases, such as rare diseases. Congenital disorders of glycosylation (CDG) are ultra-rare diseases, where a need was identified for PEMs in plain language that can clearly explain complex information. Community involvement in the design of PEMs is extremely important for diseases whose needs are underserved, such as rare diseases; however, attempts to involve lay and professional stakeholders are lacking. This paper presents a community-based participatory framework to co-create PEMs for CDG, that is transferable to other diseases. A literature review and questionnaire were performed, and only four articles describing the development of PEMS for rare diseases have been found, which demonstrates a lack of standardized approaches. The framework and PEMs were co-developed with CDG families and will be crucial in increasing health literacy and empowering families. We will close a gap in the creation of PEMs for CDG by delivering these resources in lay language in several languages.

Integration of artificial intelligence and multi-omics in kidney diseases

Kidney disease is a leading cause of death worldwide. Currently, the diagnosis of kidney diseases and the grading of their severity are mainly based on clinical features, which do not reveal the underlying molecular pathways. More recent surge of ∼omics studies has greatly catalyzed disease research. The advent of artificial intelligence (AI) has opened the avenue for the efficient integration and interpretation of big datasets for discovering clinically actionable knowledge. This review discusses how AI and multi-omics can be applied and integrated, to offer opportunities to develop novel diagnostic and therapeutic means in kidney diseases. The combination of new technology and novel analysis pipelines can lead to breakthroughs in expanding our understanding of disease pathogenesis, shedding new light on biomarkers and disease classification, as well as providing possibilities of precise treatment.

Systematic Review: Drug Repositioning for Congenital Disorders of Glycosylation (CDG)

Advances in research have boosted therapy development for congenital disorders of glycosylation (CDG), a group of rare genetic disorders affecting protein and lipid glycosylation and glycosylphosphatidylinositol anchor biosynthesis. The (re)use of known drugs for novel medical purposes, known as drug repositioning, is growing for both common and rare disorders. The latest innovation concerns the rational search for repositioned molecules which also benefits from artificial intelligence (AI). Compared to traditional methods, drug repositioning accelerates the overall drug discovery process while saving costs. This is particularly valuable for rare diseases. AI tools have proven their worth in diagnosis, in disease classification and characterization, and ultimately in therapy discovery in rare diseases. The availability of biomarkers and reliable disease models is critical for research and development of new drugs, especially for rare and heterogeneous diseases such as CDG. This work reviews the literature related to repositioned drugs for CDG, discovered by serendipity or through a systemic approach. Recent advances in biomarkers and disease models are also outlined as well as stakeholders’ views on AI for therapy discovery in CDG.

Scoping review and classification of deep learning in medical genetics

Deep learning (DL) is applied in many biomedical areas. We performed a scoping review on DL in medical genetics. We first assessed 14,002 articles, of which 133 involved DL in medical genetics. DL in medical genetics increased rapidly during the studied period. In medical genetics, DL has largely been applied to small data sets of affected individuals (mean = 95, median = 29) with genetic conditions (71 different genetic conditions were studied; 24 articles studied multiple conditions). A variety of data types have been used in medical genetics, including radiologic (20%), ophthalmologic (14%), microscopy (8%), and text-based data (4%); the most common data type was patient facial photographs (46%). DL authors and research subjects overrepresent certain geographic areas (United States, Asia, and Europe). Convolutional neural networks (89%) were the most common method. Results were compared with human performance in 31% of studies. In total, 51% of articles provided data access; 16% released source code. To further explore DL in genomics, we conducted an additional analysis, the results of which highlight future opportunities for DL in medical genetics. Finally, we expect DL applications to increase in the future. To aid data curation, we evaluated a DL, random forest, and rule-based classifier at categorizing article abstracts.

Stakeholders' views on drug development: the congenital disorders of glycosylation community perspective

BACKGROUND

Congenital disorders of glycosylation (CDG) are a large family of rare genetic diseases for which therapies are virtually nonexistent. However, CDG therapeutic research has been expanding, thanks to the continuous efforts of the CDG medical/scientific and patient communities. Hence, CDG drug development is a popular research topic. The main aim of this study was to understand current and steer future CDG drug development and approval by collecting and analysing the views and experiences of the CDG community, encompassing professionals and families. An electronic (e-)survey was developed and distributed to achieve this goal.

RESULTS

A total of 128 respondents (46 CDG professionals and 82 family members), mainly from Europe and the USA, participated in this study. Most professionals (95.0%) were relatively familiar with drug development and approval processes, while CDG families revealed low familiarity levels, with 8.5% admitting to never having heard about drug development. However, both stakeholder groups agreed that patients and families make significant contributions to drug development and approval. Regarding their perceptions of and experiences with specific drug development and approval tools, namely biobanks, disease models, patient registries, natural history studies (NHS) and clinical trials (CT), the CDG community stakeholders described low use and participation, as well as variable familiarity. Additionally, CDG professionals and families shared conflicting views about CT patient engagement and related information sharing. Families reported lower levels of involvement in CT design (25.0% declared ever being involved) and information (60.0% stated having been informed) compared to professionals (60.0% and 85.7%, respectively). These contrasting perceptions were further extended to their insights and experiences with patient-centric research. Finally, the CDG community (67.4% of professionals and 54.0% of families) reported a positive vision of artificial intelligence (AI) as a drug development tool. Nevertheless, despite the high AI awareness among CDG families (76.8%), professionals described limited AI use in their research (23.9%).

CONCLUSIONS

This community-centric study sheds new light on CDG drug development and approval. It identifies educational, communication and research gaps and opportunities for CDG professionals and families that could improve and accelerate CDG therapy development.

New Developments and Possibilities in Reanalysis and Reinterpretation of Whole Exome Sequencing Datasets for Unsolved Rare Diseases Using Machine Learning Approaches

Rare diseases impact the lives of 300 million people in the world. Rapid advances in bioinformatics and genomic technologies have enabled the discovery of causes of 20–30% of rare diseases. However, most rare diseases have remained as unsolved enigmas to date. Newer tools and availability of high throughput sequencing data have enabled the reanalysis of previously undiagnosed patients. In this review, we have systematically compiled the latest developments in the discovery of the genetic causes of rare diseases using machine learning methods. Importantly, we have detailed methods available to reanalyze existing whole exome sequencing data of unsolved rare diseases. We have identified different reanalysis methodologies to solve problems associated with sequence alterations/mutations, variation re-annotation, protein stability, splice isoform malfunctions and oligogenic analysis. In addition, we give an overview of new developments in the field of rare disease research using whole genome sequencing data and other omics.

Convergence of patient- and physician-reported outcomes in the French National Registry of Facioscapulohumeral Dystrophy

Background

Facioscapulohumeral muscular dystrophy (FSHD) is among the most prevalent muscular dystrophies and currently has no treatment. Clinical and genetic heterogeneity are the main challenges to a full comprehension of the physiopathological mechanism. Improving our knowledge of FSHD is crucial to the development of future therapeutic trials and standards of care. National FSHD registries have been set up to this end. The French National Registry of FSHD combines a clinical evaluation form (CEF) and a self-report questionnaire (SRQ), filled out by a physician with expertise in neuromuscular dystrophies and by the patient, respectively. Aside from favoring recruitment, our strategy was devised to improve data quality. Indeed, the pairwise comparison of data from 281 patients for 39 items allowed for evaluating data accuracy. Kappa or intra-class coefficient (ICC) values were calculated to determine the correlation between answers provided in both the CEF and SRQ.

Results

Patients and physicians agreed on a majority of questions common to the SRQ and CEF (24 out of 39). Demographic, diagnosis- and care-related questions were generally answered consistently by the patient and the medical practitioner (kappa or ICC values of most items in these groups were greater than 0.8). Muscle function-related items, i.e. FSHD-specific signs, showed an overall medium to poor correlation between data provided in the two forms; the distribution of agreements in this section was markedly spread out and ranged from poor to good. In particular, there was very little agreement regarding the assessment of facial motricity and the presence of a winged scapula. However, patients and physicians agreed very well on the Vignos and Brooke scores. The report of symptoms not specific to FSHD showed general poor consistency.

Conclusions

Patient and physician answers are largely concordant when addressing quantitative and objective items. Consequently, we updated collection forms by relying more on patient-reported data where appropriate. We hope the revised forms will reduce data collection time while ensuring the same quality standard. With the advent of artificial intelligence and automated decision-making, high-quality and reliable data are critical to develop top-performing algorithms to improve diagnosis, care, and evaluate the efficiency of upcoming treatments.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13023-021-01793-6.

Potential and role of artificial intelligence in current medical healthcare

Artificial intelligence (AI) is defined as the digital computer or computer-controlled robot's ability to mimic intelligent conduct and crucial thinking commonly associated with intelligent beings. The application of AI technology and machine learning in medicine have allowed medical practitioners to provide patients with better quality of services; and current advancements have led to a dramatic change in the healthcare system. However, many efficient applications are still in their initial stages, which need further evaluations to improve and develop these applications. Clinicians must recognize and acclimate themselves with the developments in AI technology to improve their delivery of healthcare services; but for this to be possible, a significant revision of medical education is needed to provide future leaders with the required competencies. This article reviews the potential and limitations of AI in healthcare, as well as the current medical application trends including healthcare administration, clinical decision assistance, patient health monitoring, healthcare resource allocation, medical research, and public health policy development. Also, future possibilities for further clinical and scientific practice were also summarized.

Congenital Adrenal Hyperplasia-Current Insights in Pathophysiology, Diagnostics, and Management

Congenital adrenal hyperplasia (CAH) is a group of autosomal recessive disorders affecting cortisol biosynthesis. Reduced activity of an enzyme required for cortisol production leads to chronic overstimulation of the adrenal cortex and accumulation of precursors proximal to the blocked enzymatic step. The most common form of CAH is caused by steroid 21-hydroxylase deficiency due to mutations in CYP21A2. Since the last publication summarizing CAH in Endocrine Reviews in 2000, there have been numerous new developments. These include more detailed understanding of steroidogenic pathways, refinements in neonatal screening, improved diagnostic measurements utilizing chromatography and mass spectrometry coupled with steroid profiling, and improved genotyping methods. Clinical trials of alternative medications and modes of delivery have been recently completed or are under way. Genetic and cell-based treatments are being explored. A large body of data concerning long-term outcomes in patients affected by CAH, including psychosexual well-being, has been enhanced by the establishment of disease registries. This review provides the reader with current insights in CAH with special attention to these new developments.

Artificial intelligence-driven phenotyping of zebrafish psychoactive drug responses

Zebrafish (Danio rerio) are rapidly emerging in biomedicine as promising tools for disease modelling and drug discovery. The use of zebrafish for neuroscience research is also growing rapidly, necessitating novel reliable and unbiased methods of neurophenotypic data collection and analyses. Here, we applied the artificial intelligence (AI) neural network-based algorithms to a large dataset of adult zebrafish locomotor tracks collected previously in a series of in vivo experiments with multiple established psychotropic drugs. We first trained AI to recognize various drugs from a wide range of psychotropic agents tested, and then confirmed prediction accuracy of trained AI by comparing several agents with known similar behavioral and pharmacological profiles. Presenting a framework for innovative neurophenotyping, this proof-of-concept study aims to improve AI-driven movement pattern classification in zebrafish, thereby fostering drug discovery and development utilizing this key model organism.

Discovery of compounds inhibiting SARS-COV-2 multi-targets

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has become a pandemic that has devastated the lives of millions. Researchers around the world are relentlessly working in hopes of finding a cure. Even though the virus shares similarities with reported SARS-CoV and MERS-CoV at the genomic and proteomic level, efforts to repurpose already known drugs against SARS-CoV-2 have resulted ineffective. In this succinct review, we discuss the different potential targets in SARS-CoV-2 at both the genomic and proteomic levels. In addition, we analyze the compounds inhibiting individual target protein as well as multiple targets of SARS-CoV-2. ACE-2 receptor in humans has also been considered a target, keeping the role of the receptor in mind. The mechanism of action of these compounds has also been highlighted along with their clinical manifestation. Towards the end of the review, a brief note on the drugs currently in clinical trials and the current status of the vaccines are also examined. In conclusion, compounds targeting multiple targets of the virus hold the key in putting an end to the coronavirus malady.Communicated by Ramaswamy H. Sarma.

Clinical Pharmacology in Drug Development for Rare Diseases in Neurology: Contributions and Opportunities

Several challenges are associated with rare disease drug development in neurology. In this article, we summarize the US Food and Drug Administration's experience with clinical drug development for rare neurological diseases and discuss clinical pharmacology's critical contributions to drug development for rare diseases. We used publicly available information to identify and screen drug products approved for rare neurological indications between 1983 and 2019. We highlighted cases in which clinical pharmacology contributed to the evidence of drug efficacy, dose selection for pivotal clinical trials, dose optimization based on intrinsic and extrinsic factors, pharmacokinetic bridging for formulations, and efficacy bridging across different racial groups. Fifty-one approved drug products were identified since the introduction of the Orphan Drug Act in 1983. Interestingly, the number of approvals in the last few years increased significantly, probably due to advances in genomic research and targeted drug modalities. Evaluation of dose selection in patient populations showed that in 52% of cases, the sponsors did not evaluate efficacy for more than one or two dose levels throughout the development program. Clinical pharmacology studies to evaluate the effect of intrinsic or extrinsic factors were adequately characterized in most of the applications. With the expansion of model informed drug development applications, (e.g., quantitative systems pharmacology and deep learning neural network models), the role and impact of clinical pharmacology is expected to grow exponentially in the next decade and enhance the development of novel treatment modalities for neurological rare diseases.

Deep Learning-Based Microscopic Diagnosis of Odontogenic Keratocysts and Non-Keratocysts in Haematoxylin and Eosin-Stained Incisional Biopsies

Background: The goal of the study was to create a histopathology image classification automation system that could identify odontogenic keratocysts in hematoxylin and eosin-stained jaw cyst sections. Methods: From 54 odontogenic keratocysts, 23 dentigerous cysts, and 20 radicular cysts, about 2657 microscopic pictures with 400× magnification were obtained. The images were annotated by a pathologist and categorized into epithelium, cystic lumen, and stroma of keratocysts and non-keratocysts. Preprocessing was performed in two steps; the first is data augmentation, as the Deep Learning techniques (DLT) improve their performance with increased data size. Secondly, the epithelial region was selected as the region of interest. Results: Four experiments were conducted using the DLT. In the first, a pre-trained VGG16 was employed to classify after-image augmentation. In the second, DenseNet-169 was implemented for image classification on the augmented images. In the third, DenseNet-169 was trained on the two-step preprocessed images. In the last experiment, two and three results were averaged to obtain an accuracy of 93% on OKC and non-OKC images. Conclusions: The proposed algorithm may fit into the automation system of OKC and non-OKC diagnosis. Utmost care was taken in the manual process of image acquisition (minimum 28–30 images/slide at 40× magnification covering the entire stretch of epithelium and stromal component). Further, there is scope to improve the accuracy rate and make it human bias free by using a whole slide imaging scanner for image acquisition from slides.

Artificial Intelligence in Medical Imaging and its Impact on the Rare Disease Community: Threats, Challenges and Opportunities

Almost 1 in 10 individuals can suffer from one of many rare diseases (RDs). The average time to diagnosis for an RD patient is as high as 7 years. Artificial intelligence (AI)-based positron emission tomography (PET), if implemented appropriately, has tremendous potential to advance the diagnosis of RDs. Patient advocacy groups must be active stakeholders in the AI ecosystem if we are to avoid potential issues related to the implementation of AI into health care. AI medical devices must not only be RD-aware at each stage of their conceptualization and life cycle but also should be trained on diverse and augmented datasets representative of the end-user population including RDs. Inability to do so leads to potential harm and unsustainable deployment of AI-based medical devices (AIMDs) into clinical practice.

Opportunities and Challenges for Machine Learning in Rare Diseases

Rare diseases (RDs) are complicated health conditions that are difficult to be managed at several levels. The scarcity of available data chiefly determines an intricate scenario even for experts and specialized clinicians, which in turn leads to the so called “diagnostic odyssey” for the patient. This situation calls for innovative solutions to support the decision process via quantitative and automated tools. Machine learning brings to the stage a wealth of powerful inference methods; however, matching the health conditions with advanced statistical techniques raises methodological, technological, and even ethical issues. In this contribution, we critically point to the specificities of the dialog of rare diseases with machine learning techniques concentrating on the key steps and challenges that may hamper or create actionable knowledge and value for the patient together with some on-field methodological suggestions and considerations.

Rare disease patients’ needs: an up-to-date analysis and future directions

The interest to rare diseases has increased in the recent decades. Legislation seeks to facilitate patients’ access to innovative and effective treatment and to define incentives for pharmaceutical and biotechnology companies to develop new medicines for rare diseases.The current review presents the current knowledge and adopted solutions in the field of rare diseases and discusses the future issues and unmet needs that should be resolved for affected patients and their families. Along with the positive trends in the field of rare diseases, there are still issues related to diagnosis and inequal care for some patients groups that should be solved over the next decade. The innovative digital health methods, which have been improved continuously in the recent years, implementation of improved versions of patient-centered policy plans and programs and investment in advanced therapies could move forward the rare diseases to new horizons giving them the opportunity to overcome the main barriers and challenges in the whole journey of the patients – from diagnosis through treatment to follow-up.

Establishing a second-generation artificial intelligence-based system for improving diagnosis, treatment, and monitoring of patients with rare diseases

Patients with rare diseases are a major challenge for healthcare systems. These patients face three major obstacles: late diagnosis and misdiagnosis, lack of proper response to therapies, and absence of valid monitoring tools. We reviewed the relevant literature on first-generation artificial intelligence (AI) algorithms which were designed to improve the management of chronic diseases. The shortage of big data resources and the inability to provide patients with clinical value limit the use of these AI platforms by patients and physicians. In the present study, we reviewed the relevant literature on the obstacles encountered in the management of patients with rare diseases. Examples of currently available AI platforms are presented. The use of second-generation AI-based systems that are patient-tailored is presented. The system provides a means for early diagnosis and a method for improving the response to therapies based on clinically meaningful outcome parameters. The system may offer a patient-tailored monitoring tool that is based on parameters that are relevant to patients and caregivers and provides a clinically meaningful tool for follow-up. The system can provide an inclusive solution for patients with rare diseases and ensures adherence based on clinical responses. It has the potential advantage of not being dependent on large datasets and is a dynamic system that adapts to ongoing changes in patients' disease and response to therapy.

Artificial Intelligence for Hospital Health Care: Application Cases and Answers to Challenges in European Hospitals

The development and implementation of artificial intelligence (AI) applications in health care contexts is a concurrent research and management question. Especially for hospitals, the expectations regarding improved efficiency and effectiveness by the introduction of novel AI applications are huge. However, experiences with real-life AI use cases are still scarce. As a first step towards structuring and comparing such experiences, this paper is presenting a comparative approach from nine European hospitals and eleven different use cases with possible application areas and benefits of hospital AI technologies. This is structured as a current review and opinion article from a diverse range of researchers and health care professionals. This contributes to important improvement options also for pandemic crises challenges, e.g., the current COVID-19 situation. The expected advantages as well as challenges regarding data protection, privacy, or human acceptance are reported. Altogether, the diversity of application cases is a core characteristic of AI applications in hospitals, and this requires a specific approach for successful implementation in the health care sector. This can include specialized solutions for hospitals regarding human-computer interaction, data management, and communication in AI implementation projects.

Human and Machine Intelligence Together Drive Drug Repurposing in Rare Diseases

Repurposing is an increasingly attractive method within the field of drug development for its efficiency at identifying new therapeutic opportunities among approved drugs at greatly reduced cost and time of more traditional methods. Repurposing has generated significant interest in the realm of rare disease treatment as an innovative strategy for finding ways to manage these complex conditions. The selection of which agents should be tested in which conditions is currently informed by both human and machine discovery, yet the appropriate balance between these approaches, including the role of artificial intelligence (AI), remains a significant topic of discussion in drug discovery for rare diseases and other conditions. Our drug repurposing team at Vanderbilt University Medical Center synergizes machine learning techniques like phenome-wide association study-a powerful regression method for generating hypotheses about new indications for an approved drug-with the knowledge and creativity of scientific, legal, and clinical domain experts. While our computational approaches generate drug repurposing hits with a high probability of success in a clinical trial, human knowledge remains essential for the hypothesis creation, interpretation, "go-no go" decisions with which machines continue to struggle. Here, we reflect on our experience synergizing AI and human knowledge toward realizable patient outcomes, providing case studies from our portfolio that inform how we balance human knowledge and machine intelligence for drug repurposing in rare disease.

Artificial Intelligence in Epigenetic Studies: Shedding Light on Rare Diseases

More than 7,000 rare diseases (RDs) exist worldwide, affecting approximately 350 million people, out of which only 5% have treatment. The development of novel genome sequencing techniques has accelerated the discovery and diagnosis in RDs. However, most patients remain undiagnosed. Epigenetics has emerged as a promise for diagnosis and therapies in common disorders (e.g., cancer) with several epimarkers and epidrugs already approved and used in clinical practice. Hence, it may also become an opportunity to uncover new disease mechanisms and therapeutic targets in RDs. In this “big data” age, the amount of information generated, collected, and managed in (bio)medicine is increasing, leading to the need for its rapid and efficient collection, analysis, and characterization. Artificial intelligence (AI), particularly deep learning, is already being successfully applied to analyze genomic information in basic research, diagnosis, and drug discovery and is gaining momentum in the epigenetic field. The application of deep learning to epigenomic studies in RDs could significantly boost discovery and therapy development. This review aims to collect and summarize the application of AI tools in the epigenomic field of RDs. The lower number of studies found, specific for RDs, indicate that this is a field open to expansion, following the results obtained for other more common disorders.

Drug Repurposing for Rare Diseases

Currently, there are about 7000 identified rare diseases, together affecting 10% of the population. However, fewer than 6% of all rare diseases have an approved treatment option, highlighting their tremendous unmet needs in drug development. The process of repurposing drugs for new indications, compared with the development of novel orphan drugs, is a time-saving and cost-efficient method resulting in higher success rates, which can therefore drastically reduce the risk of drug development for rare diseases. Although drug repurposing is not novel, new strategies have been developed in recent years to do it in a systematic and rational way. Here, we review applied methodologies, recent accomplished progress, and the challenges associated in drug repurposing for rare diseases.

The EuRRECa Project as a Model for Data Access and Governance Policies for Rare Disease Registries That Collect Clinical Outcomes

Rare disease (RD) registries are important platforms that facilitate communication between health care professionals, patients and other members of the multidisciplinary team. RD registries enable data sharing and promotion of research and audits, often in an international setting, with the overall aim of improving patient care. RD registries also have a fundamental role in supporting the work of clinical networks such as the European Reference Networks (ERNs) for rare diseases. With the recent expansion of RD registries, it has become even more essential to outline standards of good practice in relation to governance, infrastructure, documentation, training, audits and adopting the Findable, Accessible, Interoperable and Reusable (FAIR) data principles to maintain registries of high quality. For the purpose of this paper, we highlight vital aspects of data access and data governance policies for RD registries, using the European Registries for Rare Endocrine Conditions (EuRRECa) as an example of a project that aims to promote good standards of practice for improving the quality of utilization of RD registries.

The case for open science: rare diseases

The premise of Open Science is that research and medical management will progress faster if data and knowledge are openly shared. The value of Open Science is nowhere more important and appreciated than in the rare disease (RD) community. Research into RDs has been limited by insufficient patient data and resources, a paucity of trained disease experts, and lack of therapeutics, leading to long delays in diagnosis and treatment. These issues can be ameliorated by following the principles and practices of sharing that are intrinsic to Open Science. Here, we describe how the RD community has adopted the core pillars of Open Science, adding new initiatives to promote care and research for RD patients and, ultimately, for all of medicine. We also present recommendations that can advance Open Science more globally.

Identification of risk features for complication in Gaucher's disease patients: a machine learning analysis of the Spanish registry of Gaucher disease

BACKGROUND

Since enzyme replacement therapy for Gaucher disease (MIM#230800) has become available, both awareness of and the natural history of the disease have changed. However, there remain unmet needs such as the identification of patients at risk of developing bone crisis during therapy and late complications such as cancer or parkinsonism. The Spanish Gaucher Disease Registry has worked since 1993 to compile demographic, clinical, genetic, analytical, imaging and follow-up data from more than 400 patients. The aims of this study were to discover correlations between patients' characteristics at diagnosis and to identify risk features for the development of late complications; for this a machine learning approach involving correlation networks and decision trees analyses was applied.

RESULTS

A total of 358 patients, 340 type 1 Gaucher disease and 18 type 3 cases were selected. 18% were splenectomyzed and 39% had advanced bone disease. 81% of cases carried heterozygous genotype. 47% of them were diagnosed before the year 2000. Mean age at diagnosis and therapy were 28 and 31.5 years old (y.o.) respectively. 4% developed monoclonal gammopathy undetermined significance or Parkinson Disease, 6% cancer, and 10% died before this study. Previous splenectomy correlates with the development of skeletal complications and severe bone disease (p = 0.005); serum levels of IgA, delayed age at start therapy (> 9.5 y.o. since diagnosis) also correlates with severe bone disease at diagnosis and with the incidence of bone crisis during therapy. High IgG (> 1750 mg/dL) levels and age over 60 y.o. at diagnosis were found to be related with the development of cancer. When modelling the decision tree, patients with a delayed diagnosis and therapy were the most severe and with higher risk of complications.

CONCLUSIONS

Our work confirms previous observations, highlights the importance of early diagnosis and therapy and identifies new risk features such as high IgA and IgG levels for long-term complications.

Drug targets for COVID-19 therapeutics: Ongoing global efforts

The current global pandemic COVID-19 caused by the SARS-CoV-2 virus has already inflicted insurmountable damage both to the human lives and global economy. There is an immediate need for identification of effective drugs to contain the disastrous virus outbreak. Global efforts are already underway at a war footing to identify the best drug combination to address the disease. In this review, an attempt has been made to understand the SARS-CoV-2 life cycle, and based on this information potential druggable targets against SARS-CoV-2 are summarized. Also, the strategies for ongoing and future drug discovery against the SARS-CoV-2 virus are outlined. Given the urgency to find a definitive cure, ongoing drug repurposing efforts being carried out by various organizations are also described. The unprecedented crisis requires extraordinary efforts from the scientific community to effectively address the issue and prevent further loss of human lives and health.

A primer on artificial intelligence for the paediatric cardiologist

The combination of pediatric cardiology being both a perceptual and a cognitive subspecialty demands a complex decision-making model which makes artificial intelligence a particularly attractive technology with great potential. The prototypical artificial intelligence system would autonomously impute patient data into a collaborative database that stores, syncs, interprets and ultimately classifies the patient's profile to specific disease phenotypes to compare against a large aggregate of shared peer health data and outcomes, the current medical body of literature and ongoing trials to offer morbidity and mortality prediction, drug therapy options targeted to each patient's genetic profile, tailored surgical plans and recommendations for timing of sequential imaging. The focus of this review paper is to offer a primer on artificial intelligence and paediatric cardiology by briefly discussing the history of artificial intelligence in medicine, modern and future applications in adult and paediatric cardiology across selected concentrations, and current barriers to implementation of these technologies.

The use of machine learning in rare diseases: a scoping review

Background

Emerging machine learning technologies are beginning to transform medicine and healthcare and could also improve the diagnosis and treatment of rare diseases. Currently, there are no systematic reviews that investigate, from a general perspective, how machine learning is used in a rare disease context. This scoping review aims to address this gap and explores the use of machine learning in rare diseases, investigating, for example, in which rare diseases machine learning is applied, which types of algorithms and input data are used or which medical applications (e.g., diagnosis, prognosis or treatment) are studied.

Methods

Using a complex search string including generic search terms and 381 individual disease names, studies from the past 10 years (2010–2019) that applied machine learning in a rare disease context were identified on PubMed. To systematically map the research activity, eligible studies were categorized along different dimensions (e.g., rare disease group, type of algorithm, input data), and the number of studies within these categories was analyzed.

Results

Two hundred eleven studies from 32 countries investigating 74 different rare diseases were identified. Diseases with a higher prevalence appeared more often in the studies than diseases with a lower prevalence. Moreover, some rare disease groups were investigated more frequently than to be expected (e.g., rare neurologic diseases and rare systemic or rheumatologic diseases), others less frequently (e.g., rare inborn errors of metabolism and rare skin diseases). Ensemble methods (36.0%), support vector machines (32.2%) and artificial neural networks (31.8%) were the algorithms most commonly applied in the studies. Only a small proportion of studies evaluated their algorithms on an external data set (11.8%) or against a human expert (2.4%). As input data, images (32.2%), demographic data (27.0%) and “omics” data (26.5%) were used most frequently. Most studies used machine learning for diagnosis (40.8%) or prognosis (38.4%) whereas studies aiming to improve treatment were relatively scarce (4.7%). Patient numbers in the studies were small, typically ranging from 20 to 99 (35.5%).

Conclusion

Our review provides an overview of the use of machine learning in rare diseases. Mapping the current research activity, it can guide future work and help to facilitate the successful application of machine learning in rare diseases.

Diagnosis support systems for rare diseases: a scoping review

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.