{"id":22653,"date":"2021-11-12T09:49:46","date_gmt":"2021-11-12T15:49:46","guid":{"rendered":"https:\/\/saluddigital.com\/?p=22653"},"modified":"2025-10-21T11:29:57","modified_gmt":"2025-10-21T17:29:57","slug":"los-10-principios-rectores-para-las-buenas-practicas-de-aprendizaje-automatico-en-dispositivos-medicos","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/los-10-principios-rectores-para-las-buenas-practicas-de-aprendizaje-automatico-en-dispositivos-medicos\/","title":{"rendered":"The 10 Guiding Principles for Machine Learning Best Practices in Medical Devices"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

The US Food and Drug Administration (FDA), Health Canada, and the UK Medicines and Healthcare Products Regulatory Agency (MHRA) have identified principles for good machine learning practice.<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The FDA, Health Canada, and the MHRA jointly identified the ten guiding principles for the development of machine learning best practices (GMLP). The main idea is to promote the use of safe, regulated and quality medical devices that use Artificial Intelligence (AI) and machine learning.<\/p>

\u201cWith artificial intelligence and machine learning progressing so rapidly, our three regulatory agencies together see a global opportunity to help foster machine learning best practices by providing guiding principles that we believe will support the development and maturation of best practices. machine learning,\u201d explained Bakul Patel, director of the FDA Digital Health Center of Excellence.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

He also explained that the guiding principles that worked with the health authorities of Canada and the United Kingdom will provide decisive support to developers of devices based on machine learning that \u201chave the potential to significantly improve the quality of patient care and transform medical care. \u201d, according to Patel.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The "Guide to Good Practices of machine learning for the development of medical devices: guiding principles", was published on October 27, 2021. In summary, the ten principles are the following:<\/p>

  1. Multidisciplinary expertise is leveraged throughout the product lifecycle<\/li>
  2. Good security and software engineering practices are implemented<\/li>
  3. Clinical study participants and data sets are representative of the intended patient population<\/li>
  4. The training data sets are independent of the test sets.<\/li>
  5. Selected reference data sets are based on best available methods<\/li>
  6. Model design is tailored to available data and reflects the intended use of the product<\/li>
  7. The focus is on the performance of the AI human team<\/li>
  8. Tests demonstrate device performance under clinically relevant conditions<\/li>
  9. Users receive clear and essential information: Users have easy access to clear and contextually relevant information that is appropriate for the intended audience (such as healthcare providers or patients)<\/li>
  10. Deployed models are monitored for performance and retraining risks are managed<\/li><\/ol>

    You can consult the complete guide in the following link: https:\/\/www.gov.uk\/government\/publications\/good-machine-learning-practice-for-medical-device-development-guiding-principles\/good-machine-learning-practice-for-medical-device-development-guiding-principles<\/a><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t

    \n\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t
    \n\t\t\t\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t BIBLIOGRAPHY<\/a>\n\t\t\t\t\t<\/div>\n\n\t\t\t\t\t

    AI MEAS<\/strong><\/p>

    https:\/\/ai-med.io\/more-news\/fda-health-canada-and-mhra-publish-good-ai-ml-practice-for-medical-devices\/<\/a><\/p>

    FDA<\/strong><\/p>

    https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-brief-fda-collaborates-health-canada-and-uks-mhra-foster-good-machine-learning-practice<\/a><\/p>

    UK GOV<\/strong><\/p>

    https:\/\/www.gov.uk\/government\/publications\/good-machine-learning-practice-for-medical-device-development-guiding-principles\/good-machine-learning-practice-for-medical-device-development-guiding-principles<\/a><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

    La Administraci\u00f3n de Alimentos y Medicamentos de EE.UU. (FDA), Health Canada y la Agencia Reguladora de Medicamentos y Productos Sanitarios (MHRA) del Reino Unido, identificaron los principios para las buenas pr\u00e1cticas de aprendizaje autom\u00e1tico. La FDA, Health Canada, y la MHRA, identificaron de manera conjunta los diez principios rectores para el desarrollo de buenas pr\u00e1cticas de aprendizaje autom\u00e1tico (GMLP, en ingl\u00e9s).  La idea principal es promover el uso de dispositivos m\u00e9dicos seguros, regulados y de calidad que utilicen Inteligencia Artificial (IA) y aprendizaje autom\u00e1tico. \u201cCon la inteligencia artificial y el aprendizaje autom\u00e1tico progresando tan r\u00e1pidamente, nuestras tres agencias reguladoras, juntas, ven una oportunidad global para ayudar a fomentar las buenas pr\u00e1cticas de aprendizaje autom\u00e1tico al proporcionar principios rectores que creemos respaldar\u00e1n el desarrollo y la maduraci\u00f3n de las buenas pr\u00e1cticas de aprendizaje autom\u00e1tico\u201d, explic\u00f3 Bakul Patel director del Centro de Excelencia de Salud Digital de la FDA. Tambi\u00e9n explic\u00f3 que los principios rectores que trabajaron con las autoridades sanitarias de Canad\u00e1 y Reino Unido brindar\u00e1n un apoyo determinante a los desarrolladores de dispositivos basados en aprendizaje autom\u00e1tico que \u201ctienen el potencial de mejorar significativamente la calidad de la atenci\u00f3n al paciente y transformar la atenci\u00f3n m\u00e9dica\u201d, seg\u00fan resalt\u00f3 Patel. La “Gu\u00eda de Buenas pr\u00e1cticas de aprendizaje autom\u00e1tico para el desarrollo de dispositivos m\u00e9dicos: principios rectores”, fue publicada el 27 de octubre de 2021.  De manera resumida los diez principios son los siguientes: La experiencia multidisciplinar se aprovecha a lo largo de todo el ciclo de vida del producto Se implementan buenas pr\u00e1cticas de ingenier\u00eda de software y seguridad Los participantes del estudio cl\u00ednico y los conjuntos de datos son representativos de la poblaci\u00f3n de pacientes prevista Los conjuntos de datos de entrenamiento son independientes de los conjuntos de prueba Los conjuntos de datos de referencia seleccionados se basan en los mejores m\u00e9todos disponibles El dise\u00f1o del modelo se adapta a los datos disponibles y refleja el uso previsto del producto La atenci\u00f3n se centra en el rendimiento del equipo humano de la IA Las pruebas demuestran el rendimiento del dispositivo en condiciones cl\u00ednicamente relevantes Los usuarios reciben informaci\u00f3n clara y esencial: Los usuarios tienen f\u00e1cil acceso a informaci\u00f3n clara y contextualmente relevante que es apropiada para la audiencia a la que va dirigida (como los proveedores de atenci\u00f3n m\u00e9dica o los pacientes) Los modelos desplegados se supervisan en cuanto a su rendimiento y se gestionan los riesgos de reentrenamiento Puedes consultar la gu\u00eda completa en el siguiente enlace: https:\/\/www.gov.uk\/government\/publications\/good-machine-learning-practice-for-medical-device-development-guiding-principles\/good-machine-learning-practice-for-medical-device-development-guiding-principles BIBLIOGRAF\u00cdA AI MED https:\/\/ai-med.io\/more-news\/fda-health-canada-and-mhra-publish-good-ai-ml-practice-for-medical-devices\/ FDA https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-brief-fda-collaborates-health-canada-and-uks-mhra-foster-good-machine-learning-practice GOV UK https:\/\/www.gov.uk\/government\/publications\/good-machine-learning-practice-for-medical-device-development-guiding-principles\/good-machine-learning-practice-for-medical-device-development-guiding-principles<\/p>","protected":false},"author":1,"featured_media":22655,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3393,160],"tags":[145],"class_list":["post-22653","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-inteligencia-artificial-y-ciencia","category-noticias","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/22653","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/comments?post=22653"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/22653\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/22655"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=22653"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=22653"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=22653"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}