Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases: From Real-World Data Toward a Personalized Medicine Approach
Abstract
1. Introduction
2. Materials and Methods
2.1. Research Question
2.2. Search Strategy
2.3. Inclusion Criteria
- –
- Peer-reviewed original research articles, systematic reviews, meta-analyses, and narrative reviews.
- –
- Publications directly addressing AI applications in pediatric rare disease diagnostics, including variant interpretation, phenotype–genotype correlations, clinical decision support, or large language models.
- –
- Articles published in English.
2.4. Exclusion Criteria
- –
- Studies focusing exclusively on adult populations.
- –
- Purely technical AI model development papers without clinical or diagnostic relevance.
- –
- Conference abstracts, editorials, and commentaries without peer-reviewed full text.
2.5. Study Selection
3. Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases
3.1. The Role of AI in Genomic Data Interpretation
3.1.1. AI Tools for Variant Interpretation
3.1.2. Role of Large Language Models (LLMs)
3.2. Phenotype–Genotype Integration Through Automated Tools
3.3. Real-World Data: Opportunities and Challenges for AI-Assisted Rare Disease Diagnosis
3.4. Comparative Diagnostic Performance of AI and Human Experts
3.5. Challenges in Clinical Implementation
3.6. Ethical Considerations in Pediatric Settings
3.7. Future Directions
4. Limitations of This Study
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Abbreviations
AI | Artificial Intelligence |
LLM/LLMs | Large Language Model(s) |
NGS | Next-Generation Sequencing |
WES | Whole-Exome Sequencing |
WGS | Whole-Genome Sequencing |
HPO | Human Phenotype Ontology |
RF | Reverse Phenotyping |
VUS | Variant of Uncertain Significance |
NLP | Natural Language Processing |
EMR/EMRs | Electronic Medical Record(s) |
EHR/EHRs | Electronic Health Record(s) |
RWD | Real-World Data |
RCT/RCTs | Randomized Controlled Trial(s) |
OMIM | Online Mendelian Inheritance in Man |
References
- Bauskis, A.; Strange, C.; Molster, C.; Fisher, C. The diagnostic odyssey: Insights from parents of children living with an undiagnosed condition. Orphanet J. Rare Dis. 2022, 17, 233. [Google Scholar] [CrossRef]
- The Voice of 12,000 Patients. EURORDIS-Rare Diseases Europe. Available online: https://www.eurordis.org/publications/the-voice-of-12000-patients/ (accessed on 13 July 2025).
- Aldharman, S.S.; Al-Jabr, K.H.; Alharbi, Y.S.; Alnajar, N.K.; Alkhanani, J.J.; Alghamdi, A.; Abdellatif, R.A.; Allouzi, A.; Almallah, A.M.; Jamil, S.F. Implications of Early Diagnosis and Intervention in the Management of Neurodevelopmental Delay (NDD) in Children: A Systematic Review and Meta-Analysis. Cureus 2023, 15, e38745. [Google Scholar] [CrossRef] [PubMed]
- Bowling, K.M.; Thompson, M.L.; Amaral, M.D.; Finnila, C.R.; Hiatt, S.M.; Engel, K.L.; Cochran, J.N.; Brothers, K.B.; East, K.M.; Gray, D.E.; et al. Genomic diagnosis for children with intellectual disability and/or developmental delay. Genome Med. 2017, 9, 43. [Google Scholar] [CrossRef]
- Kufel, J.; Bargieł-Łączek, K.; Kocot, S.; Koźlik, M.; Bartnikowska, W.; Janik, M.; Czogalik, Ł.; Dudek, P.; Magiera, M.; Lis, A.; et al. What Is Machine Learning, Artificial Neural Networks and Deep Learning?—Examples of Practical Applications in Medicine. Diagnostics 2023, 13, 2582. [Google Scholar] [CrossRef]
- Ao, G.; Chen, M.; Li, J.; Nie, H.; Zhang, L.; Chen, Z. Comparative analysis of large language models on rare disease identification. Orphanet J. Rare Dis. 2025, 20, 150. [Google Scholar] [CrossRef]
- Sánchez Fernández, I.; Loddenkemper, T.; Gaínza-Lein, M.; Sheidley, B.R.; Poduri, A. Diagnostic yield of genetic tests in epilepsy: A meta-analysis and cost-effectiveness study. Neurology 2019, 92, e418–e428. [Google Scholar] [CrossRef] [PubMed]
- Sun, Y.; Peng, J.; Liang, D.; Ye, X.; Xu, N.; Chen, L.; Yan, D.; Zhang, H.; Xiao, B.; Qiu, W.; et al. Genome sequencing demonstrates high diagnostic yield in children with undiagnosed global developmental delay/intellectual disability: A prospective study. Hum. Mutat. 2022, 43, 568–581. [Google Scholar] [CrossRef] [PubMed]
- Best, S.; Yu, J.; Lord, J.; Roche, M.; Watson, C.M.; Bevers, R.P.J.; Stuckey, A.; Madhusudhan, S.; Jewell, R.; Sisodiya, S.M.; et al. Uncovering the burden of hidden ciliopathies in the 100 000 Genomes Project: A reverse phenotyping approach. J. Med. Genet. 2022, 59, 1151–1164. [Google Scholar] [CrossRef]
- Burdick, K.J.; Cogan, J.D.; Rives, L.C.; Robertson, A.K.; Koziura, M.E.; Brokamp, E.; Duncan, L.; Hannig, V.; Pfotenhauer, J.; Vanzo, R.; et al. Limitations of exome sequencing in detecting rare and undiagnosed diseases. Am. J. Med. Genet. A 2020, 182, 1400–1406. [Google Scholar] [CrossRef]
- Abbasi, A.; Alexandrov, L.B. Significance and limitations of the use of next-generation sequencing technologies for detecting mutational signatures. DNA Repair 2021, 107, 103200. [Google Scholar] [CrossRef]
- Austin-Tse, C.A.; Jobanputra, V.; Perry, D.L.; Bick, D.; Taft, R.J.; Venner, E.; Gibbs, R.A.; Young, T.; Barnett, S.; Belmont, J.W.; et al. Best practices for the interpretation and reporting of clinical whole genome sequencing. npj Genom. Med. 2022, 7, 27. [Google Scholar] [CrossRef]
- Richards, S.; Aziz, N.; Bale, S.; Bick, D.; Das, S.; Gastier-Foster, J.; Grody, W.W.; Hegde, M.; Lyon, E.; Spector, E.; et al. 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, 405–424. [Google Scholar] [CrossRef]
- Alvarez-Costes, S. Deciphering Genomic Complexity: The Role of Explainable AI in Evolutionary Genomics. Methods Mol. Biol. 2025, 2927, 221–234. [Google Scholar] [CrossRef]
- Aster, A.; Laupichler, M.C.; Rockwell-Kollmann, T.; Masala, G.; Bala, E.; Raupach, T. ChatGPT and Other Large Language Models in Medical Education—Scoping Literature Review. Med. Sci. Educ. 2024, 35, 555–567. [Google Scholar] [CrossRef]
- Ji, Z.; Lee, N.; Frieske, R.; Yu, T.; Su, D.; Xu, Y.; Ishii, E.; Bang, Y.J.; Madotto, A.; Fung, P. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. 2023, 55, 248:1–248:38. [Google Scholar] [CrossRef]
- Sharma, J.; Goel, P. The Use of AI for Phenotype-Genotype Mapping. Methods Mol. Biol. 2025, 2952, 369–410. [Google Scholar] [CrossRef] [PubMed]
- Obermeyer, Z.; Powers, B.; Vogeli, C.; Mullainathan, S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019, 366, 447–453. [Google Scholar] [CrossRef]
- Deng, J.; Zubair, A.; Park, Y.-J. Limitations of large language models in medical applications. Postgrad. Med. J. 2023, 99, 1298–1299. [Google Scholar] [CrossRef] [PubMed]
- Carbonari, V.; Veltri, P.; Guzzi, P.H. Decoding Rarity: Large Language Models in the Diagnosis of Rare Diseases. arXiv 2025, arXiv:2505.17065. [Google Scholar] [CrossRef]
- Iqbal, U.; Tanweer, A.; Rahmanti, A.R.; Greenfield, D.; Lee, L.T.-J.; Li, Y.-C.J. Impact of large language model (ChatGPT) in healthcare: An umbrella review and evidence synthesis. J. Biomed. Sci. 2025, 32, 45. [Google Scholar] [CrossRef] [PubMed]
- Wilczewski, C.M.; Obasohan, J.; Paschall, J.E.; Zhang, S.; Singh, S.; Maxwell, G.L.; Similuk, M.; Wolfsberg, T.G.; Turner, C.; Biesecker, L.G.; et al. Genotype first: Clinical genomics research through a reverse phenotyping approach. Am. J. Hum. Genet. 2023, 110, 3–12. [Google Scholar] [CrossRef]
- Smail, C.; Ge, B.; Keever-Keigher, M.R.; Schwendinger-Schreck, C.; Cheung, W.A.; Johnston, J.J.; Barrett, C.; Feldman, K.; Cohen, A.S.A.; Farrow, E.G.; et al. Complex trait associations in rare diseases and impacts on Mendelian variant interpretation. Nat. Commun. 2024, 15, 8196. [Google Scholar] [CrossRef]
- Gargano, M.A.; Matentzoglu, N.; Coleman, B.; Addo-Lartey, E.B.; Anagnostopoulos, A.V.; Anderton, J.; Avillach, P.; Bagley, A.M.; Bakštein, E.; Balhoff, J.P.; et al. The Human Phenotype Ontology in 2024: Phenotypes around the world. Nucleic Acids Res. 2024, 52, D1333–D1346. [Google Scholar] [CrossRef]
- Bajwa, J.; Munir, U.; Nori, A.; Williams, B. Artificial intelligence in healthcare: Transforming the practice of medicine. Future Healthc. J. 2021, 8, e188–e194. [Google Scholar] [CrossRef] [PubMed]
- Garcelon, N.; Neuraz, A.; Salomon, R.; Bahi-Buisson, N.; Amiel, J.; Picard, C.; Mahlaoui, N.; Benoit, V.; Burgun, A.; Rance, B. Next generation phenotyping using narrative reports in a rare disease clinical data warehouse. Orphanet J. Rare Dis. 2018, 13, 85. [Google Scholar] [CrossRef] [PubMed]
- Mishima, H.; Suzuki, H.; Doi, M.; Miyazaki, M.; Watanabe, S.; Matsumoto, T.; Morifuji, K.; Moriuchi, H.; Yoshiura, K.-I.; Kondoh, T.; et al. Evaluation of Face2Gene using facial images of patients with congenital dysmorphic syndromes recruited in Japan. J. Hum. Genet. 2019, 64, 789–794. [Google Scholar] [CrossRef]
- Birgmeier, J.; Haeussler, M.; Deisseroth, C.A.; Steinberg, E.H.; Jagadeesh, K.A.; Ratner, A.J.; Guturu, H.; Wenger, A.M.; Diekhans, M.E.; Stenson, P.D.; et al. AMELIE speeds Mendelian diagnosis by matching patient phenotype and genotype to primary literature. Sci. Transl. Med. 2020, 12, eaau9113. [Google Scholar] [CrossRef] [PubMed]
- Rao, A.; Joseph, T.; Saipradeep, V.G.; Kotte, S.; Sivadasan, N.; Srinivasan, R. PRIORI-T: A tool for rare disease gene prioritization using MEDLINE. PLoS ONE 2020, 15, e0231728. [Google Scholar] [CrossRef]
- Kafkas, Ş.; Abdelhakim, M.; Althagafi, A.; Toonsi, S.; Alghamdi, M.; Schofield, P.N.; Hoehndorf, R. The application of Large Language Models to the phenotype-based prioritization of causative genes in rare disease patients. Sci. Rep. 2025, 15, 15093. [Google Scholar] [CrossRef]
- Tudur Smith, C.; Williamson, P.R.; Beresford, M.W. Methodology of clinical trials for rare diseases. Best Pract. Res. Clin. Rheumatol. 2014, 28, 247–262. [Google Scholar] [CrossRef]
- Liu, J.; Barrett, J.S.; Leonardi, E.T.; Lee, L.; Roychoudhury, S.; Chen, Y.; Trifillis, P. Natural History and Real-World Data in Rare Diseases: Applications, Limitations, and Future Perspectives. J. Clin. Pharmacol. 2022, 62, S38–S55. [Google Scholar] [CrossRef]
- Sherman, R.E.; Anderson, S.A.; Dal Pan, G.J.; Gray, G.W.; Gross, T.; Hunter, N.L.; LaVange, L.; Marinac-Dabic, D.; Marks, P.W.; Robb, M.A.; et al. Real-World Evidence—What Is It and What Can It Tell Us? N. Engl. J. Med. 2016, 375, 2293–2297. [Google Scholar] [CrossRef]
- Hampson, G.; Towse, A.; Dreitlein, W.B.; Henshall, C.; Pearson, S.D. Real-world evidence for coverage decisions: Opportunities and challenges. J. Comp. Eff. Res. 2018, 7, 1133–1143. [Google Scholar] [CrossRef]
- Orsini, L.S.; Berger, M.; Crown, W.; Daniel, G.; Eichler, H.-G.; Goettsch, W.; Graff, J.; Guerino, J.; Jonsson, P.; Lederer, N.M.; et al. Improving Transparency to Build Trust in Real-World Secondary Data Studies for Hypothesis Testing—Why, What, and How: Recommendations and a Road Map from the Real-World Evidence Transparency Initiative. Value Health 2020, 23, 1128–1136. [Google Scholar] [CrossRef] [PubMed]
- Weiss, A.; Michels, C.; Burgmer, P.; Mussweiler, T.; Ockenfels, A.; Hofmann, W. Trust in everyday life. J. Pers. Soc. Psychol. 2021, 121, 95–114. [Google Scholar] [CrossRef] [PubMed]
- Han, J. Everything About DeepSeek: Key Features, Usage, and Technical Advantages. PopAi. 2025. Available online: https://www.popai.pro/resources/everything-about-deepseek/ (accessed on 6 June 2025).
- Germain, D.P.; Gruson, D.; Malcles, M.; Garcelon, N. Applying artificial intelligence to rare diseases: A literature review highlighting lessons from Fabry disease. Orphanet J. Rare Dis. 2025, 20, 186. [Google Scholar] [CrossRef]
- Wojtara, M.; Rana, E.; Rahman, T.; Khanna, P.; Singh, H. Artificial intelligence in rare disease diagnosis and treatment. Clin. Transl. Sci. 2023, 16, 2106–2111. [Google Scholar] [CrossRef]
- Ilić, N.; Marić, N.; Cvetković, D.; Bogosavljević, M.; Bukara-Radujković, G.; Krstić, J.; Paunović, Z.; Begović, N.; Panić Zarić, S.; Todorović, S.; et al. The Artificial Intelligence-Assisted Diagnosis of Skeletal Dysplasias in Pediatric Patients: A Comparative Benchmark Study of Large Language Models and a Clinical Expert Group. Genes 2025, 16, 762. [Google Scholar] [CrossRef]
- Jandoubi, B.; Akhloufi, M.A. Multimodal Artificial Intelligence in Medical Diagnostics. Information 2025, 16, 591. [Google Scholar] [CrossRef]
- Harada, T.; Shimizu, T.; Kaji, Y.; Suyama, Y.; Matsumoto, T.; Kosaka, C.; Shimizu, H.; Nei, T.; Watanuki, S. A Perspective from a Case Conference on Comparing the Diagnostic Process: Human Diagnostic Thinking vs. Artificial Intelligence (AI) Decision Support Tools. Int. J. Environ. Res. Public Health 2020, 17, 6110. [Google Scholar] [CrossRef]
- Brasil, S.; Pascoal, C.; Francisco, R.; Dos Reis Ferreira, V.; Videira, P.A.; Valadão, A.G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter? Genes 2019, 10, 978. [Google Scholar] [CrossRef]
- Rubeis, G.; Dubbala, K.; Metzler, I. “Democratizing” artificial intelligence in medicine and healthcare: Mapping the uses of an elusive term. Front. Genet. 2022, 13, 902542. [Google Scholar] [CrossRef] [PubMed]
- Holmes, J.H.; Beinlich, J.; Boland, M.R.; Bowles, K.H.; Chen, Y.; Cook, T.S.; Demiris, G.; Draugelis, M.; Fluharty, L.; Gabriel, P.E.; et al. Why Is the Electronic Health Record So Challenging for Research and Clinical Care? Methods Inf. Med. 2021, 60, 32–48. [Google Scholar] [CrossRef]
- Kersloot, M.G.; van Putten, F.J.P.; Abu-Hanna, A.; Cornet, R.; Arts, D.L. Natural language processing algorithms for mapping clinical text fragments onto ontology concepts: A systematic review and recommendations for future studies. J. Biomed. Semant. 2020, 11, 14. [Google Scholar] [CrossRef] [PubMed]
- Li, Y.-H.; Li, Y.-L.; Wei, M.-Y.; Li, G.-Y. Innovation and challenges of artificial intelligence technology in personalized healthcare. Sci. Rep. 2024, 14, 18994. [Google Scholar] [CrossRef]
- Karalis, V.D. The Integration of Artificial Intelligence into Clinical Practice. Appl. Biosci. 2024, 3, 14–44. [Google Scholar] [CrossRef]
- Holzinger, A.; Zatloukal, K.; Müller, H. Is human oversight to AI systems still possible? New Biotechnol. 2025, 85, 59–62. [Google Scholar] [CrossRef]
- London, A.J. Artificial Intelligence and Black-Box Medical Decisions: Accuracy versus Explainability. Hastings Cent. Rep. 2019, 49, 15–21. [Google Scholar] [CrossRef]
- ISO/IEC 23894:2023—Information Technology—Artificial Intelligence—Guidance on Risk Management. 2023. Available online: https://www.iso.org/standard/77304.html (accessed on 21 August 2024).
- Natri, H.M.; Chapman, C.R.; Heraty, S.; Dwyer, P.; Walker, N.; Kapp, S.K.; Dron, H.A.; Martinez-Agosto, J.A.; Mikkola, L.; Doherty, M. Ethical challenges in autism genomics: Recommendations for researchers. Eur. J. Med. Genet. 2023, 66, 104810. [Google Scholar] [CrossRef]
- Murdoch, B. Privacy and artificial intelligence: Challenges for protecting health information in a new era. BMC Med. Ethics 2021, 22, 122. [Google Scholar] [CrossRef]
- Rigby, M.J. Ethical Dimensions of Using Artificial Intelligence in Health Care. AMA J. Ethics 2019, 21, 121–124. [Google Scholar] [CrossRef]
- Saint James Aquino, Y. Making decisions: Bias in artificial intelligence and data—Driven diagnostic tools. Aust. J. Gen. Pract. 2023, 52, 439–442. [Google Scholar] [CrossRef] [PubMed]
- Polemi, N.; Praça, I.; Kioskli, K.; Bécue, A. Challenges and efforts in managing AI trustworthiness risks: A state of knowledge. Front. Big Data 2024, 7, 1381163. [Google Scholar] [CrossRef]
- Kolbinger, F.R.; Veldhuizen, G.P.; Zhu, J.; Truhn, D.; Kather, J.N. Reporting guidelines in medical artificial intelligence: A systematic review and meta-analysis. Commun. Med. 2024, 4, 71. [Google Scholar] [CrossRef]
- Mennella, C.; Maniscalco, U.; De Pietro, G.; Esposito, M. Ethical and regulatory challenges of AI technologies in healthcare: A narrative review. Heliyon 2024, 10, e26297. [Google Scholar] [CrossRef]
- Muralidharan, V.; Burgart, A.; Daneshjou, R.; Rose, S. Recommendations for the use of pediatric data in artificial intelligence and machine learning ACCEPT-AI. npj Digit. Med. 2023, 6, 166. [Google Scholar] [CrossRef]
- Salih, A.M.; Menegaz, G.; Pillay, T.; Boyle, E.M. Explainable Artificial Intelligence in Paediatric: Challenges for the Future. Health Sci. Rep. 2024, 7, e70271. [Google Scholar] [CrossRef]
- Chng, S.Y.; Tern, M.J.W.; Lee, Y.S.; Cheng, L.T.-E.; Kapur, J.; Eriksson, J.G.; Chong, Y.S.; Savulescu, J. Ethical considerations in AI for child health and recommendations for child-centered medical AI. npj Digit. Med. 2025, 8, 152. [Google Scholar] [CrossRef] [PubMed]
- Devnath, L.; Summons, P.; Luo, S.; Wang, D.; Shaukat, K.; Hameed, I.A.; Aljuaid, H. Computer-Aided Diagnosis of Coal Workers’ Pneumoconiosis in Chest X-ray Radiographs Using Machine Learning: A Systematic Literature Review. Int. J. Environ. Res. Public Health 2022, 19, 6439. [Google Scholar] [CrossRef] [PubMed]
Application Area | Description | Example Tools/Platforms |
---|---|---|
Variant Prioritization | Automated ranking of genetic variants based on pathogenicity predictions, allele frequencies, and gene–disease associations | MOON (Diploid), Fabric Genomics, Emedgene, GEM |
Phenotype–Genotype Matching | Linking patients’ phenotypic features (HPO terms) to known gene–disease relationships | Phenomizer, GEM |
Reverse Phenotyping | AI-driven re-evaluation of clinical features based on unexpected or novel genetic findings | LLM-assisted reverse phenotyping workflows |
Natural Language Processing | Extracting structured phenotypic information from unstructured clinical notes | NLP modules integrated within genomic AI pipelines |
Clinical Summarization and Decision Support | Generating diagnostic hypotheses and literature-informed interpretations | ChatGPT (GPT 4.5, OpenAI), DeepSeek Medical AI |
Tool | Function | Integration | Validation Status |
---|---|---|---|
MOON | Variant prioritization based on the phenotype–genotype correlation | Standalone; requires manual HPO input | Used in clinical diagnostics; validated in internal benchmarking |
GEM | AI-based interpretation and scoring of variants | Integrated with the Fabric Genomics platform | Deployed in hospital settings; comparative benchmarking with human panels |
Phenomizer | Suggests differential diagnoses from HPO terms | Standalone; research use | Open-access tool; used in academic projects |
Face2Gene | Image-based facial phenotype recognition | Mobile/web platform | High accuracy in syndromic conditions; not validated for nonsyndromic cases |
Emedgene | AI-supported variant analysis with automated reporting | Commercial clinical platform | Cleared by regulatory agencies in some jurisdictions; limited open-access data |
DeepPhen | Phenotype-driven gene ranking using ML | Research use; experimental | Experimental validation in selected cohorts |
Feature | Phenotype-Driven Algorithms | Large Language Models (LLMs) |
---|---|---|
Primary Input Type | Structured data (HPO terms) | Natural language, unstructured text |
Strengths | Precise gene–disease matching, standardized outputs | Flexible interpretation, literature summarization, clinical reasoning |
Limitations | Dependence on structured inputs, limited in ambiguous cases | Potential hallucinations, interpretability concerns |
Examples | MOON, GEM, Phenomizer | ChatGPT, DeepSeek Medical AI |
Ideal Use Case | Variant prioritization with detailed phenotypic data | Complex differential diagnosis, summarizing patient histories |
Challenge | Category | Impact on Diagnosis | Addressable by: |
---|---|---|---|
Unstructured EMR data | Data issue | Limits phenotypic precision; weakens AI inputs | NLP tools; structured phenotyping |
Lack of interoperability | Data/workflow | Prevents integration with AI tools and databases | Cross-platform EMR integration |
Clinician skepticism and unfamiliarity | Workflow/human factor | Delays adoption; mistrust of AI recommendations | Targeted training, demonstration studies |
Hallucination risk in LLMs | Algorithmic/technical | Produces plausible but false diagnoses | Validation, hybrid expert oversight |
Regulatory ambiguity | Legal/ethical | Unclear liability; discourages clinical use | Guidelines, legal frameworks |
Bias in training data | Ethical/data quality | Overlooks underrepresented populations | Diverse datasets, fairness auditing |
Challenge | Description | Potential Solutions |
---|---|---|
Data Interoperability | Lack of standardized EMR 1 and genomic data integration | Harmonized data standards |
Workflow Integration | AI tools functioning as standalone systems | Seamless integration into hospital information systems |
Clinician Training and Trust | Limited familiarity with AI methodologies | Targeted educational programs— demonstration projects |
Validation and Regulation | Lack of universal validation standards | Development of regulatory frameworks specific to AI diagnostics |
Resource Constraints | Infrastructure and cost barriers in low-resource settings | Cloud-based AI platforms, tiered implementation models |
Ethical Domain | Key Issues | Proposed Mitigations |
---|---|---|
Transparency and Explainability | “Black box” decision-making processes | Develop interpretable AI models, provide output rationales |
Informed Consent | Complexity of explaining AI involvement to parents | Tailored consent forms detailing AI’s role, benefits, and limitations |
Equity and Bias | Underrepresentation of certain ethnic groups in training datasets | Diversify training data, continuous model revalidation |
Privacy and Data Security | Handling identifiable genomic and phenotypic data | Robust encryption, compliance with pediatric data protection laws |
Psychosocial Impact | Emotional burden of AI-generated diagnoses | Ensure clinician-led communication with empathy and support |
Aspect | Advantages of the AI Approach | Limitations of the AI Approach |
---|---|---|
Speed | Rapid analysis of large-scale genomic and phenotypic datasets | Limited validation for ultra-rare and atypical cases |
Accuracy | High precision for syndromically well-defined conditions (e.g., achondroplasia) | Reduced accuracy in genetically heterogeneous or phenotypically ambiguous disorders |
Accessibility | Expands the diagnostic capacity in settings lacking subspecialty expertise | Dependent on data quality and input standardization |
Result Interpretability | Transparent algorithms in some platforms allow reasoning review | “Black box” models hinder interpretability and trust |
Cost-effectiveness | Long-term reduction in diagnostic odyssey costs | Initial investment required for infrastructure and training |
Ethical Considerations | Enables faster diagnosis and personalized therapies | Risks of bias propagation and unequal diagnostic accuracy across populations |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ilić, N.; Sarajlija, A. Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases: From Real-World Data Toward a Personalized Medicine Approach. J. Pers. Med. 2025, 15, 407. https://doi.org/10.3390/jpm15090407
Ilić N, Sarajlija A. Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases: From Real-World Data Toward a Personalized Medicine Approach. Journal of Personalized Medicine. 2025; 15(9):407. https://doi.org/10.3390/jpm15090407
Chicago/Turabian StyleIlić, Nikola, and Adrijan Sarajlija. 2025. "Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases: From Real-World Data Toward a Personalized Medicine Approach" Journal of Personalized Medicine 15, no. 9: 407. https://doi.org/10.3390/jpm15090407
APA StyleIlić, N., & Sarajlija, A. (2025). Artificial Intelligence in the Diagnosis of Pediatric Rare Diseases: From Real-World Data Toward a Personalized Medicine Approach. Journal of Personalized Medicine, 15(9), 407. https://doi.org/10.3390/jpm15090407