View in EDS PDF Full Text

AI-Driven risk prediction models for hypertensive emergencies in diabetic patients: validation in multi-ethnic cohorts.

Saved in:
Bibliographic Details
Title: AI-Driven risk prediction models for hypertensive emergencies in diabetic patients: validation in multi-ethnic cohorts.
Alternate Title: Modelos de predicción de riesgo basados en IA para emergencias hipertensivas en pacientes diabéticos: Validación en cohortes multiétnicas.
Authors: Madina, Khikmatova1 hikmatova.madina@bsmi.uz, Baxtiyor, Sanoyev2 sanoyev.baxtiyor@bsmi.uz, Mexriniso, Ismatova3 mexrinisoismatova79@gmail.com, Muslima, Abdullaeva4 abdullayeva.muslima@bsmi.uz, Iroda, Alimova5 alimovairoda304@gmail.com, Erkin, Khudoykulov6 erkinxudaykulov4330@gmail.com, Bekchanova, Madina7 madinabekchanova262@gmail.com, Zavqiddin, Ravshanov8 zavqiddinnaruto@gmail.com
Source: Revista Latinoamericana de Hipertensión. 2025, Vol. 20 Issue 8, p561-567. 7p.
Subjects: ARTIFICIAL intelligence, HYPERTENSIVE crisis, RISK assessment, SOCIAL determinants of health, MACHINE learning, CULTURAL pluralism, MODEL validation, PEOPLE with diabetes
Abstract (English): The study was undertaken to confirm artificial intelligence (AI) risk models of hypertensive emergencies among diabetic patients in multiethnic populations. The study was a multicenter historical cohort involving 24,718 diabetic and hypertensive patients from various ethnic groups (European, African, South Asian, Hispanic, East Asian, and Middle Eastern). The performances of three machine learning algorithms (XGBoost, neural network, and random forest) were contrasted with logistic regression. The outcomes showed that the XGBoost model, which recorded AUC values of 0.89 for Cohort B and 0.85 for Cohort B, was significantly better compared to standard models and had a high ability to identify evolving patterns such as systolic blood pressure fluctuation and kidney function changes. However, subgroup analyses revealed significant ethnic differences in model performance: sensitivity was lower in African-American (76.2%) compared to South Asian (88.1%) patients, and positive predictive value was 15% lower in Hispanics compared with East Asians. Additionally, poor calibration in high-risk groups (African-Americans) and the influence of social determinants of health on predictive accuracy were observed. These findings reaffirm the importance of validating models in every ethnic environment, including social variables, and developing dynamic calibration procedures to provide equitable and accurate treatment. [ABSTRACT FROM AUTHOR]
Abstract (Spanish): El estudio se realizó para confirmar los modelos de riesgo basados en inteligencia artificial (IA) para emergencias hipertensivas en pacientes diabéticos de poblaciones multiétnicas. El estudio consistió en una cohorte histórica multicéntrica que incluyó a 24.718 pacientes diabéticos e hipertensos de diversos grupos étnicos (europeos, africanos, del sur de Asia, hispanos, del este de Asia y de Oriente Medio). Se comparó el rendimiento de tres algoritmos de aprendizaje automático (XGBoost, redes neuronales y bosque aleatorio) con regresión logística. Los resultados mostraron que el modelo XGBoost, que registró valores de AUC de 0,89 y 0,85 para la cohorte B, fue significativamente mejor que los modelos estándar y mostró una alta capacidad para identificar patrones evolutivos, como fluctuaciones de la presión arterial sistólica y cambios en la función renal. Sin embargo, los análisis de subgrupos revelaron diferencias étnicas significativas en el rendimiento del modelo: la sensibilidad fue menor en pacientes afroamericanos (76,2%) que en pacientes del sur de Asia (88,1%), y el valor predictivo positivo fue un 15% menor en pacientes hispanos que en pacientes del este de Asia. Además, se observó una calibración deficiente en grupos de alto riesgo (afroamericanos) y la influencia de los determinantes sociales de la salud en la precisión predictiva. Estos hallazgos reafirman la importancia de validar los modelos en todos los entornos étnicos, incluyendo las variables sociales, y de desarrollar procedimientos de calibración dinámicos para proporcionar un tratamiento equitativo y preciso. [ABSTRACT FROM AUTHOR]
Copyright of Revista Latinoamericana de Hipertensión is the property of Revista Latinoamericana de Hipertension and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: MedicLatina
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: lth
DbLabel: MedicLatina
An: 188614621
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: AI-Driven risk prediction models for hypertensive emergencies in diabetic patients: validation in multi-ethnic cohorts.
– Name: TitleAlt
  Label: Alternate Title
  Group: TiAlt
  Data: Modelos de predicción de riesgo basados en IA para emergencias hipertensivas en pacientes diabéticos: Validación en cohortes multiétnicas.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Madina%2C+Khikmatova%22">Madina, Khikmatova</searchLink><relatesTo>1</relatesTo><i> hikmatova.madina@bsmi.uz</i><br /><searchLink fieldCode="AR" term="%22Baxtiyor%2C+Sanoyev%22">Baxtiyor, Sanoyev</searchLink><relatesTo>2</relatesTo><i> sanoyev.baxtiyor@bsmi.uz</i><br /><searchLink fieldCode="AR" term="%22Mexriniso%2C+Ismatova%22">Mexriniso, Ismatova</searchLink><relatesTo>3</relatesTo><i> mexrinisoismatova79@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Muslima%2C+Abdullaeva%22">Muslima, Abdullaeva</searchLink><relatesTo>4</relatesTo><i> abdullayeva.muslima@bsmi.uz</i><br /><searchLink fieldCode="AR" term="%22Iroda%2C+Alimova%22">Iroda, Alimova</searchLink><relatesTo>5</relatesTo><i> alimovairoda304@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Erkin%2C+Khudoykulov%22">Erkin, Khudoykulov</searchLink><relatesTo>6</relatesTo><i> erkinxudaykulov4330@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Bekchanova%2C+Madina%22">Bekchanova, Madina</searchLink><relatesTo>7</relatesTo><i> madinabekchanova262@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Zavqiddin%2C+Ravshanov%22">Zavqiddin, Ravshanov</searchLink><relatesTo>8</relatesTo><i> zavqiddinnaruto@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Revista+Latinoamericana+de+Hipertensión%22">Revista Latinoamericana de Hipertensión</searchLink>. 2025, Vol. 20 Issue 8, p561-567. 7p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22ARTIFICIAL+intelligence%22">ARTIFICIAL intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22HYPERTENSIVE+crisis%22">HYPERTENSIVE crisis</searchLink><br /><searchLink fieldCode="DE" term="%22RISK+assessment%22">RISK assessment</searchLink><br /><searchLink fieldCode="DE" term="%22SOCIAL+determinants+of+health%22">SOCIAL determinants of health</searchLink><br /><searchLink fieldCode="DE" term="%22MACHINE+learning%22">MACHINE learning</searchLink><br /><searchLink fieldCode="DE" term="%22CULTURAL+pluralism%22">CULTURAL pluralism</searchLink><br /><searchLink fieldCode="DE" term="%22MODEL+validation%22">MODEL validation</searchLink><br /><searchLink fieldCode="DE" term="%22PEOPLE+with+diabetes%22">PEOPLE with diabetes</searchLink>
– Name: Abstract
  Label: Abstract (English)
  Group: Ab
  Data: The study was undertaken to confirm artificial intelligence (AI) risk models of hypertensive emergencies among diabetic patients in multiethnic populations. The study was a multicenter historical cohort involving 24,718 diabetic and hypertensive patients from various ethnic groups (European, African, South Asian, Hispanic, East Asian, and Middle Eastern). The performances of three machine learning algorithms (XGBoost, neural network, and random forest) were contrasted with logistic regression. The outcomes showed that the XGBoost model, which recorded AUC values of 0.89 for Cohort B and 0.85 for Cohort B, was significantly better compared to standard models and had a high ability to identify evolving patterns such as systolic blood pressure fluctuation and kidney function changes. However, subgroup analyses revealed significant ethnic differences in model performance: sensitivity was lower in African-American (76.2%) compared to South Asian (88.1%) patients, and positive predictive value was 15% lower in Hispanics compared with East Asians. Additionally, poor calibration in high-risk groups (African-Americans) and the influence of social determinants of health on predictive accuracy were observed. These findings reaffirm the importance of validating models in every ethnic environment, including social variables, and developing dynamic calibration procedures to provide equitable and accurate treatment. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label: Abstract (Spanish)
  Group: Ab
  Data: El estudio se realizó para confirmar los modelos de riesgo basados en inteligencia artificial (IA) para emergencias hipertensivas en pacientes diabéticos de poblaciones multiétnicas. El estudio consistió en una cohorte histórica multicéntrica que incluyó a 24.718 pacientes diabéticos e hipertensos de diversos grupos étnicos (europeos, africanos, del sur de Asia, hispanos, del este de Asia y de Oriente Medio). Se comparó el rendimiento de tres algoritmos de aprendizaje automático (XGBoost, redes neuronales y bosque aleatorio) con regresión logística. Los resultados mostraron que el modelo XGBoost, que registró valores de AUC de 0,89 y 0,85 para la cohorte B, fue significativamente mejor que los modelos estándar y mostró una alta capacidad para identificar patrones evolutivos, como fluctuaciones de la presión arterial sistólica y cambios en la función renal. Sin embargo, los análisis de subgrupos revelaron diferencias étnicas significativas en el rendimiento del modelo: la sensibilidad fue menor en pacientes afroamericanos (76,2%) que en pacientes del sur de Asia (88,1%), y el valor predictivo positivo fue un 15% menor en pacientes hispanos que en pacientes del este de Asia. Además, se observó una calibración deficiente en grupos de alto riesgo (afroamericanos) y la influencia de los determinantes sociales de la salud en la precisión predictiva. Estos hallazgos reafirman la importancia de validar los modelos en todos los entornos étnicos, incluyendo las variables sociales, y de desarrollar procedimientos de calibración dinámicos para proporcionar un tratamiento equitativo y preciso. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Revista Latinoamericana de Hipertensión is the property of Revista Latinoamericana de Hipertension and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=lth&AN=188614621
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.5281/zenodo.17020084
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 7
        StartPage: 561
    Subjects:
      – SubjectFull: ARTIFICIAL intelligence
        Type: general
      – SubjectFull: HYPERTENSIVE crisis
        Type: general
      – SubjectFull: RISK assessment
        Type: general
      – SubjectFull: SOCIAL determinants of health
        Type: general
      – SubjectFull: MACHINE learning
        Type: general
      – SubjectFull: CULTURAL pluralism
        Type: general
      – SubjectFull: MODEL validation
        Type: general
      – SubjectFull: PEOPLE with diabetes
        Type: general
    Titles:
      – TitleFull: AI-Driven risk prediction models for hypertensive emergencies in diabetic patients: validation in multi-ethnic cohorts.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Madina, Khikmatova
      – PersonEntity:
          Name:
            NameFull: Baxtiyor, Sanoyev
      – PersonEntity:
          Name:
            NameFull: Mexriniso, Ismatova
      – PersonEntity:
          Name:
            NameFull: Muslima, Abdullaeva
      – PersonEntity:
          Name:
            NameFull: Iroda, Alimova
      – PersonEntity:
          Name:
            NameFull: Erkin, Khudoykulov
      – PersonEntity:
          Name:
            NameFull: Bekchanova, Madina
      – PersonEntity:
          Name:
            NameFull: Zavqiddin, Ravshanov
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 18564550
          Numbering:
            – Type: volume
              Value: 20
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Revista Latinoamericana de Hipertensión
              Type: main
ResultId 1