Opportunities and Challenges for Machine Learning in Rare Diseases

Abstract

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.

A Formative Study of the Implementation of Whole Genome Sequencing in Northern Ireland

“…Whilst participants were overwhelmingly in favour of WGS for improving rare disease outcomes, there is a clear need for improved awareness and education surrounding rare diseases and molecular diagnostics. Further research using multiomics and in-depth computational analysis is proving essential to refine putative disease-causing variants, thereby increasing the diagnostic yield and facilitating clinical decision making [ 48 , 52 , 59 , 60 , 61 , 62 ]. Interprofessional, multidisciplinary collaboration between healthcare professionals, clinical/biomedical laboratory scientists, academia, industry, bioinformaticists/data scientists, and patient representatives is essential for optimised rare disease research and clinical practice.…”

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

“…Recently, AI and ML techniques have been successfully applied to basic research, diagnosis, drug discovery and clinical trials [ 20 , 23 ]. AI has been used in a significant manner in the field of underrepresented and mis/undiagnosed rare diseases [ 20 ].…”

Inteligencia artificial, telemedicina y salud digital

“…Así, la generación de una gran cantidad de datos (y de calidad) y la transformación digital son dos ingredientes fundamentales en el proceso de producción de sistemas de IA dirigidos al ámbito de decisiones clínicas en EERR (FIGURA 3) 17 .…”

“…La obtención de datos (ómicos, imágenes), esencial para la producción de cualquier sistema de IA, se realiza primordialmente a través de dos fuentes, que son los registros o las bases de datos abiertas 17 , que se alimentan a través de distintas vías, como internet (estrategia de búsqueda de usuarios, datos derivados del comercio electrónico y redes sociales), la tecnología móvil (sen-sores, aplicaciones, etc.) y los datos biomédicos (tests genéticos, pruebas de imagen, historia clínica, etc.)…”