Development and validation of a new artificial intelligence tool (GeneClin) for the clinical diagnosis of genetic diseases
Introduction: Advances in the field of Artificial Intelligence (AI) and Machine Learning (ML) have considerable potential to improve the diagnosis and management of rare genetic diseases, due to the human inability to memorize information on a multitude of these diseases, which AI tools could store, analyze and integrate. Objective: to develop and validate a new AI tool for the clinical diagnosis of genetic diseases. Methods: A prospective, cross-sectional, analytical, observational study was conducted at the application level, with a qualitative-quantitative approach and contributing to a technological development project. It was characterized by four stages: selection of the AI tool, selection of the knowledge base, development of the virtual assistant, validation process and implementation in the clinic. Results: A total of 246 patients with genetic diseases and congenital defects were evaluated. The most predominant genetic category was monogenic genetic syndromes with 223 patients who attended the consultation (90.7%). A success rate of 84.1% was obtained and a success/no success ratio of 4.34. The highest percentage of successes was achieved in monogenic or Mendelian syndromes. There were no significant differences between successes and failures in both chromosomal aberrations and congenital defects of environmental etiology. Conclusions: Through this research, an AI virtual assistant has been validated for the clinical diagnosis of genetic diseases with a high percentage of effectiveness of 84%, which confirms its usefulness to support the clinical diagnosis of cases with genetic diseases.
Authors
- Norma Elena de León Ojeda
- Roberto Lardoeyt Ferrer (ORCID: https://orcid.org/0000-0002-4921-5630)
- Noel Taboada Lugo (ORCID: https://orcid.org/0000-0002-1254-8087)
- José Pérez Trujillo (ORCID: https://orcid.org/0000-0002-9499-0468)
- Paulina Araceli Lantigua Cruz
- Haydeé Rodríguez Guas
- Lourdes Rey (ORCID: https://orcid.org/0000-0003-1394-1646)
- D.A López
- Yamilé Lozada Mengana
- Rodolfo Arrieta (ORCID: https://orcid.org/0000-0003-1408-7648)
- Diana Martín-Garcia (ORCID: https://orcid.org/0000-0002-5848-9051)
- Y Robert (ORCID: https://orcid.org/0000-0001-5724-4979)
- Estela Morales Peralta (ORCID: https://orcid.org/0000-0002-2663-4138)
- Daniel Quintana Hernández (ORCID: https://orcid.org/0000-0001-9838-5591)
- Gloria Lidia Peña Martínez (ORCID: https://orcid.org/0009-0000-3353-1412)
- César Dilú Sorzano
- Melek Dáger Salomón
- Margarita Arguelles Arza (ORCID: https://orcid.org/0000-0003-3423-0077)
- João Ernesto
- Yelena Pereira Perera (ORCID: https://orcid.org/0000-0003-0336-1904)
- Gisel Pérez Breff (ORCID: https://orcid.org/0000-0002-4489-4523)
Institutions
- Universidad Mayor de San Andrés (BO)
- Universidad de Ciego de Ávila (CU)
- University of Holguín (CU)
- Universidad de Oriente (CU)
- Secretaría de Salud de Jalisco (MX)
- Clínica Diagonal (ES)
- Hospital Oncológico Docente "Conrado Benítez García" (CU)
- Ministerio de Salud Pública (CU)
- Instituto Superior Politécnico Metropolitano de Angola (AO)
- Hospital Materno-Infantil (ES)
- Centro de Ingeniería Genética y Biotecnología (CU)
- Centro Nacional de Investigaciones Científicas (CU)
- Centro de Neumologia Pediatrica (PR)
- Universidad de Ciencias Médicas de Sancti Spíritus (CU)
- University of Sancti Spíritus José Martí Pérez (CU)
- Universidade Lusíada de Angola (AO)
Publication Details
- Journal
- Data & Metadata
- Published
- 2025-03-19
- DOI
- https://doi.org/10.56294/dm2025857
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00