Problemi speciali
L’intelligenza artificiale nel percorso diagnostico terapeutico delle malattie rare: facciamo il punto…
Artificial Intelligence in diagnostica and therapeutic work-up for rare diseases: the state of the art and future perspectives
Casieri F, Vitale D, Selicorni A.
Aprile 2026 - pagg. 235 -240 | DOI: 10.53126/MEB45235
Abstract
Artificial Intelligence (AI) is playing an increasingly pivotal role in the field of rare diseases, where diagnostic complexity and the limited availability of therapeutic options still pose significant challenges. Machine learning and deep learning models are now widely employed in clinical genetics and offer a valuable support throughout the diagnostic process: from assisting in the phenotypic recognition, to analysing/processing genomic data and interpreting genetic variants. In the field of dysmorphology advanced facial recognition tools, such as ‘Face2Gene’, have showed a remarkable ability to recognise phenotypic features associated with rare genetic conditions. Therefore, diagnostic precision has been substantially enhanced and more patients have been able to receive timely and accurate evaluations (thereby reducing the ‘diagnostic odyssey’ that affects many patients with ultra-rare conditions). AI is also a strategic resource to use innovative therapies, namely drug repurposing strategies that enable to identify new indications for already approved drugs and reduce research and development overall burden in an effective and automated way. The application of AI-based tools opens up new perspectives on personalised therapy, as it enables the correlation of patients’ clinical, biochemical and genomic data and leads to the proposal of individualised interventions. Starting from a clinical report in which the application of facial recognition tools has led to a definitive diagnosis, the article aims to describe the current state of the art and the future perspective for AI in the field of medical genetics.
Riassunto
L’Intelligenza Artificiale (IA) sta assumendo un ruolo sempre più rilevante nel campo delle malattie rare, dove la complessità diagnostica e la limitata disponibilità di opzioni terapeutiche continuano a rappresentare sfide ancora irrisolte. Modelli di machine learning e deep learning si stanno affermando quali strumenti in grado di supportare il genetista in ogni fase del percorso diagnostico genetico: dal riconoscimento del fenotipo, all’analisi/elaborazione dei dati genomici e interpretazione del significato delle varianti genetiche. In ambito dismorfologico, strumenti avanzati di riconoscimento facciale, come “Face2Gene”, hanno dimostrato una notevole capacità nel riconoscimento di caratteristiche fenotipiche associate a sindromi genetiche rare, contribuendo in modo sostanziale alla riduzione della “odissea diagnostica” che accompagna numerosi pazienti affetti da condizioni ultra-rare. L’IA si configura, inoltre, come risorsa strategica nell’applicazione di terapie innovative: strategie di riposizionamento farmacologico (drug repurposing) consentono in maniera efficace e automatizzata di ipotizzare e validare nuove indicazioni per farmaci già approvati, riducendo tempi e costi di ricerca e sviluppo. L’applicazione di strumenti basati su IA apre prospettive inedite sulla personalizzazione terapeutica consentendo di correlare dati clinici, biochimici, e genomici del paziente e proporre gli interventi su base individuale. Dal racconto di un caso in cui l’applicazione di strumenti di riconoscimento facciale ha condotto ad una diagnosi definitiva, l’articolo intende descrivere stato dell’arte e potenzialità future dell’IA in ambito genetico.
Classificazione MeSH
Contenuto riservato
Per leggere l'articolo completo è necessario effettuare il login.
Non sei ancora registrato? Registrati
Bibliografia
1. Scherman D, Fetro C. Drug repositioning for rare diseases: knowledge-based success stories. Therapie 2020;75:161-7. doi: 10.1016/j.therap.2020.02.
2. Haendel M, Vasilevsky N, Unni D, et al. How many rare diseases are there? Nat Rev Drug Discov 2020;19:77-8. doi: 10.1038/ d41573-019-00180-y
3. Kundaje A, Pollard KS, Ma J, Chang X, Chen M, Rohs R. Artificial intelligence in molecular biology. Mol Cell 2025;85(2):193-8. doi: 10.1016/j.molcel.2024.12.013.
4. Aradhya S, Facio FM, Metz H, et al. Applications of artificial intelligence in clinical laboratory genomics. Am J Med Genet C Semin Med Genet 2023;193(3):e32057. doi: 10.1002/ajmg.c.32057.
5. Gomes B, Ashley EA. Artificial Intelligence in Molecular Medicine. N Engl J Med 2023;388(26):2456-65. doi: 10.1056/NEJMra2204787.
6. Solomon BD, Chung WK. Artificial intelligence and the impact on medical genetics. Am J Med Genet C Semin Med Genet 2023; 193(3):e32060. doi: 10.1002/ajmg.c.32060.
7. Riesselman AJ, Ingraham JB, Marks DS. Deep generative models of genetic variation capture the effects of mutations. Nat Methods 2018;15:816-22. doi: 10.1038/ s41592-018-0138-4
8. Quang D, Chen Y, Xie X. DANN: a deep learning approach for annotating the pathogenicity of genetic variants. Bioinformatics 2015;31(5):761-3. doi: 10.1093/bioinformatics/btu703.
9. Richards S, Aziz N, Bale S, et al.; ACMG Laboratory Quality Assurance Committee. Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med 2015;17(5):405-24. doi: 10.1038/gim. 2015.30.
10. Wilcox EH, Sarmady M, Wulf B, Wright MW, Rehm HL, Biesecker LG, Abou Tayoun AN. Evaluating the impact of in silico predictors on clinical variant classification. Genet Med 2022;24(4):924-30. doi: 10.1016/j.gim. 2021.11.018.
11. Cortial L, Montero V, Tourlet S, Del Bano J, Blin O. Artificial intelligence in drug repurposing for rare diseases: a mini-review. Front Med (Lausanne) 2024;11:1404338. doi: 10.3389/fmed.2024.1404338.
12. Esmail S, Danter WR. Artificially induced pluripotent stem cell-derived whole-brain organoid for modelling the pathophysiology of metachromatic leukodystrophy and drug repurposing. Biomedicines 2021;9(4):440. doi: 10.3390/biomedicines9040440.
13. Cong Y, Shintani M, Imanari F, Osada N, Endo T. A new approach to drug repurposing with two-stage prediction, machine learning, and unsupervised clustering of gene expression. OMICS 2022;26(6):339-47. doi: 10.1089/omi.2022.0026.
14. Every Cure. Unlocking the hidden potential of existing drugs to save lives (2024).
15. INNLifes. Quando l’IA ti salva la vita: il caso della malattia di Castleman. INNLifes, (2023).
16. AFM Téléthon. I-Stem, coordinateur du consortium de recherche européen DREAMS associant intelligence artificielle, cellules souches et criblage pharmacologique pour traiter des maladies neuromusculaires (2024).
17. Spiga O. Towards a precision medicine approach based on machine learning for tailoring medical treatment in Alkaptonuria. International Journal of Molecular Sciences 2021;22(3):1187. doi: 10.3390/ijms22031187
18. Germain DP, Gruson D, Malcles M, Garcelon N. Applying artificial intelligence to rare diseases: A literature review highlighting lessons from Fabry disease. Orphanet Journal of Rare Diseases 2023;18(1):228. doi: 10.1186/s13023-023-02752-2.
19. Abdallah S, Sharifa M, I Kh Almadhoun MK, et al. The Impact of Artificial Intelligence on Optimizing Diagnosis and Treatment Plans for Rare Genetic Disorders. Cureus 2023; 15(10):e46860. doi: 10.7759/cureus.46860.
Corrispondenza: daniele.vitale@unimi.it