Scholarlink

Background <p>Diagnostic genetic testing in gastroenterology has gained relevance due to high-throughput methods such as whole-exome (WES) and whole-genome sequencing (WGS) as well as technological advancements in testing procedures and data analysis. This is particularly true in the case of children with immunological, metabolic, or syndromic diseases. At the same time, the sheer number of variants and volume of phenotypic information place high demands on medical interpretation, which it would be almost impossible to meet without the application of artificial intelligence (AI).</p> Methods <p>This article provides an overview of the current status of AI application in diagnostic genetic testing for (pediatric) gastroenterological diseases. In addition to discussing the AI tools already available, focus is placed on perspectives for clinical integration and validation as well as the associated ethical and regulatory frameworks.</p> Methods <p>A selective narrative review of the current literature was performed via PubMed (U.S. National Library of Medicine®, Bethesda, MD, USA; stand: June 2025) with a particular focus on AI-supported systems for classification of variants, clinical decision-support systems (CDSS), and case examples from (pediatric) gastroenterology.</p> Results <p>The AI systems can efficiently prioritize variants, predict splice sites, automate the American College of Medical Genetics and Genomics (ACMG) criteria, and arrive at differential diagnoses of rare diseases via integration of human phenotype ontology (HPO). In combination with multimodal data (clinical symptoms, laboratory tests, imaging), a new quality of precision medicine is emerging. However, significant limitations remain due to data quality, bias, the lack of explainability and transparency (black box), and regulatory uncertainty.</p> Conclusion <p>In (pediatric) gastroenterological genetic testing, AI is no longer a vision of the future but already clinically useful, albeit with significant challenges. Solutions must be validated, transparent, embedded within a multiprofessional framework, and undergo continuous further development. Ethical patient-centered implementation of AI and extended genetic testing represents an integral component of the (pediatric) gastroenterology of the future.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Verbindung zwischen klinischer Symptomatik, Genotypisierung und künstlicher Intelligenz bei (kinder-)gastroenterologischen Erkrankungen

  • 期刊论文

  • 发表日期：

    2026年3月23日

查看全文
  • Jan de Laffolie,
  • Axel Weber

摘要

Background

Diagnostic genetic testing in gastroenterology has gained relevance due to high-throughput methods such as whole-exome (WES) and whole-genome sequencing (WGS) as well as technological advancements in testing procedures and data analysis. This is particularly true in the case of children with immunological, metabolic, or syndromic diseases. At the same time, the sheer number of variants and volume of phenotypic information place high demands on medical interpretation, which it would be almost impossible to meet without the application of artificial intelligence (AI).

Methods

This article provides an overview of the current status of AI application in diagnostic genetic testing for (pediatric) gastroenterological diseases. In addition to discussing the AI tools already available, focus is placed on perspectives for clinical integration and validation as well as the associated ethical and regulatory frameworks.

Methods

A selective narrative review of the current literature was performed via PubMed (U.S. National Library of Medicine®, Bethesda, MD, USA; stand: June 2025) with a particular focus on AI-supported systems for classification of variants, clinical decision-support systems (CDSS), and case examples from (pediatric) gastroenterology.

Results

The AI systems can efficiently prioritize variants, predict splice sites, automate the American College of Medical Genetics and Genomics (ACMG) criteria, and arrive at differential diagnoses of rare diseases via integration of human phenotype ontology (HPO). In combination with multimodal data (clinical symptoms, laboratory tests, imaging), a new quality of precision medicine is emerging. However, significant limitations remain due to data quality, bias, the lack of explainability and transparency (black box), and regulatory uncertainty.

Conclusion

In (pediatric) gastroenterological genetic testing, AI is no longer a vision of the future but already clinically useful, albeit with significant challenges. Solutions must be validated, transparent, embedded within a multiprofessional framework, and undergo continuous further development. Ethical patient-centered implementation of AI and extended genetic testing represents an integral component of the (pediatric) gastroenterology of the future.