{"id":31195,"date":"2022-08-23T09:33:40","date_gmt":"2022-08-23T14:33:40","guid":{"rendered":"https:\/\/saluddigital.com\/?p=31195"},"modified":"2025-10-20T11:16:09","modified_gmt":"2025-10-20T17:16:09","slug":"herramienta-de-aprendizaje-automatico-logra-predecir-diabetes-en-pacientes-de-alto-riesgo","status":"publish","type":"post","link":"https:\/\/saluddigital.com\/en\/big-data\/herramienta-de-aprendizaje-automatico-logra-predecir-diabetes-en-pacientes-de-alto-riesgo\/","title":{"rendered":"Machine learning tool succeeds in predicting diabetes in high-risk patients"},"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

Worldwide, the prevalence of diabetes in adults is 9.3%, affecting more than 436 million people.<\/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

Current estimates of the prevalence of diabetes globally are not entirely accurate, as there are millions of patients without a diagnosis of diabetes. In addition, diabetes is preceded by prediabetes, so there are also millions of people who are prone to developing diabetes, but also prevent diabetes effectively.<\/p>

In this sense, as in other chronic diseases, it is important to develop public health strategies and tools for the early detection of prediabetes and diabetes. Screening for diabetes and prediabetes is primarily based on measurement of blood glucose and hemoglobin (HbA1c) concentrations. Both of these tests are often invasive and difficult to implement in low-resource settings, making detection of these conditions difficult.<\/p>

In this regard, in order to develop a simple-to-implement strategy for early diagnosis of these conditions, researchers in India presented a machine learning model, combined with the non-invasive features of the electrocardiogram (ECG).<\/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

The study published in BMJ Innovations<\/em>, used data from another study on diabetes conducted in families from Pagpur, India, a population belonging to the Sindhi ethnic group, which used the oral glucose tolerance test and HbA1c estimation, both invasive. The dataset included clinical information from 1,262 people and 10,461 digitally recorded time-aligned heartbeats.<\/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

\u201cMinority oversampling was performed to balance the training data set before the start of training. Extreme gradient boosting (XGBoost) was used to train the classifier that used the signal-processed ECG as input and predicted membership in the classes of "no diabetes," prediabetes, or type 2 diabetes," the study explains.<\/p>

The prevalence of type 2 diabetes and prediabetes was 30% and 14%, respectively. Also, the independent test set used the DiaBeats algorithm, which predicted diabetes classes. Based on beat morphology, machine learning detected diabetes and prediabetes with an accuracy of 97%, a recall of 96%, and an F1 score of 96%.<\/p>

\u201cThe machine learning-based DiaBeats algorithm using ECG signal data accurately predicted diabetes-related classes. This algorithm may help in the early detection of diabetes and prediabetes after robust validation on external datasets,\u201d the authors conclude.<\/p>

The researchers explained that DiaBeats can be used to stratify people based on their risk of diabetes and prediabetes, and is ideal for replication in low-resource settings.<\/p>

Consult the full study by clicking on the following link:<\/p>

https:\/\/innovations.bmj.com\/content\/early\/2022\/07\/06\/bmjinnov-2021-000759<\/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

BMJ INNOVATIONS<\/strong><\/p>

https:\/\/innovations.bmj.com\/content\/early\/2022\/07\/06\/bmjinnov-2021-000759<\/a><\/p>

HEALTH IT ANALYTICS<\/strong><\/p>

https:\/\/healthitanalytics.com\/news\/ai-tool-predicts-pre-diabetes-diabetes-in-high-risk-patients<\/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":"

A nivel mundial la prevalencia de diabetes en adultos es 9,3%, y afecta a m\u00e1s de 436 millones de personas. Las estimaciones actuales de la prevalencia de diabetes a nivel global no son del todo precisas, ya que existen millones de pacientes sin un diagn\u00f3stico de diabetes. Adem\u00e1s, la diabetes esta precedida por la prediabetes, por lo que existen tambi\u00e9n millones de personas que son propensas a desarrollar diabetes, pero tambi\u00e9n a prevenir la diabetes de manera eficaz. En este sentido al igual que en otras enfermedades cr\u00f3nicas, es importante desarrollar estrategias y herramientas de salud p\u00fablica para la detecci\u00f3n temprana de prediabetes y diabetes. La detecci\u00f3n de diabetes y prediabetes se basa principalmente en la medici\u00f3n de glucosa en sangre y las concentraciones de hemoglobina (HbA1c). Ambas pruebas suelen ser invasivas y dif\u00edciles de implementar en entornos de bajos recursos, lo que dificulta la detecci\u00f3n de estas afecciones. En este sentido, con el fin de desarrollar una estrategia sencilla de implementar, para el diagn\u00f3stico temprano de estas condiciones, investigadores en India presentaron un modelo de aprendizaje autom\u00e1tico, combinado con las caracter\u00edsticas no invasivas del electrocardiograma (ECG). El estudio publicado en BMJ Innovations, utiliz\u00f3 datos del otro estudio sobre diabetes realizado en familias de Pagpur, India, poblaci\u00f3n perteneciente a la etnia sindhi, el cual utiliz\u00f3 la prueba de tolerancia oral a la glucosa y la estimaci\u00f3n de HbA1c, ambas invasivas. El conjunto de datos incluy\u00f3 informaci\u00f3n cl\u00ednica de 1,262 personas y 10,461 latidos card\u00edacos alineados en el tiempo registrados digitalmente. \u201cSe realiz\u00f3 un sobremuestreo minoritario para equilibrar el conjunto de datos de entrenamiento antes del inicio del entrenamiento. Se us\u00f3 el refuerzo de gradiente extremo (XGBoost) para entrenar el clasificador que us\u00f3 el ECG procesado por se\u00f1al como entrada y predijo la pertenencia a las clases de “sin diabetes”, prediabetes o diabetes tipo 2\u201d, explica el estudio. La prevalencia de diabetes tipo 2 y prediabetes fue de 30% y 14%, respectivamente. Asimismo, el conjunto de prueba independiente, utiliz\u00f3 el algoritmo DiaBeats, que predijo las clases de diabetes. Seg\u00fan la morfolog\u00eda de los latidos, el aprendizaje autom\u00e1tico detect\u00f3 diabetes y prediabetes con una precisi\u00f3n del 97%, una recuperaci\u00f3n del 96% y una puntuaci\u00f3n F1 del 96%. \u201cEl algoritmo DiaBeats basado en aprendizaje autom\u00e1tico que utiliza datos de se\u00f1ales de ECG predijo con precisi\u00f3n las clases relacionadas con la diabetes. Este algoritmo puede ayudar en la detecci\u00f3n temprana de diabetes y prediabetes despu\u00e9s de una validaci\u00f3n s\u00f3lida en conjuntos de datos externos\u201d, concluyen los autores. Los investigadores explicaron que DiaBeats puede utilizarse para estratificar a las personas seg\u00fan su riesgo de diabetes y prediabetes, adem\u00e1s es ideal para replicarse en entornos de bajos recursos. Consulta el estudio completo haciendo clic en el siguiente enlace: https:\/\/innovations.bmj.com\/content\/early\/2022\/07\/06\/bmjinnov-2021-000759 BIBLIOGRAF\u00cdA BMJ INNOVATIONS https:\/\/innovations.bmj.com\/content\/early\/2022\/07\/06\/bmjinnov-2021-000759 HEALTH IT ANALYTICS https:\/\/healthitanalytics.com\/news\/ai-tool-predicts-pre-diabetes-diabetes-in-high-risk-patients<\/p>","protected":false},"author":1,"featured_media":31196,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[156,3400,160],"tags":[145],"class_list":["post-31195","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-big-data","category-diagnostico","category-noticias","tag-noticias"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/31195","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=31195"}],"version-history":[{"count":0,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/posts\/31195\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media\/31196"}],"wp:attachment":[{"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/media?parent=31195"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/categories?post=31195"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/saluddigital.com\/en\/wp-json\/wp\/v2\/tags?post=31195"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}