Data-driven phenotypes across the full AKI severity spectrum in patients admitted to the ICU.
Saved in:
| Title: | Data-driven phenotypes across the full AKI severity spectrum in patients admitted to the ICU. |
|---|---|
| Alternate Title: | Fenotipos basados en datos en todo el espectro de gravedad de la insuficiencia renal aguda en pacientes ingresados en la UCI. |
| Authors: | Fathi, Mohammad1, Markazi Moghaddam, Nader1,2, Markazi Moghadam, Hamed3, Fathi, Mahdis1,4, Hajiesmaeili, Mohammadreza5, Nooraei, Navid1, Malekpour Alamdari, Nasser1, Zargar Balaye Jame, Sanaz2 sanazzargar@ajaums.ac.ir |
| Source: | Nefrologia. Apr2026, Vol. 46 Issue 4, p1-9. 9p. |
| Subjects: | PHENOTYPES, HIERARCHICAL clustering (Cluster analysis), ACUTE kidney failure, PROGNOSIS, AT-risk people, INTENSIVE care units, ELECTRONIC health records |
| Abstract (English): | Background and objectives Acute kidney injury (AKI) is a frequent and heterogeneous complication among critically ill patients in the intensive care unit (ICU), often associated with adverse outcomes. This study aimed to identify phenotypic subtypes of ICU patients with AKI and to evaluate their association with clinical outcomes. Materials and methods A secondary analysis was conducted using the MIMIC-IV database, including a cohort of adults with varying stages of AKI, as well as patients without AKI. Factorial analysis of mixed data, followed by hierarchical clustering, was used to identify patient phenotypes based on a wide range of clinical, demographic, laboratory, and treatment variables. Cluster profiling was conducted using a multivariable logistic regression model. Results Among 1372 patients evenly distributed across stages 0 (non-AKI) to 3 (n = 343 per stage), two distinct clusters were identified. Cluster 2 (n = 671) had significantly higher in-hospital mortality (54.7% vs. 21.9%, p < 0.001), and a greater prevalence of higher AKI stages (p < 0.001). Moreover, cluster 2 showed a significantly greater frequency of sepsis, vasopressors and diuretics administration, chronic kidney disease, heart failure, and also higher respiratory and heart rate, and phosphorus. Patients in cluster 2 were a little younger and had a lower arterial O2 pressure and blood pH. A logistic regression profiling model achieved an accuracy (95% CI) of 91.4% (89.8%, 92.8%) in predicting cluster assignment. Conclusions There are two clinically distinct phenotypes in patients admitted to the ICU concerning AKI with strong prognostic implications. The findings highlight the potential of routine ICU data to enable phenotype-based risk stratification in AKI. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | Antecedentes y objetivos La insuficiencia renal aguda (IRA) es una complicación frecuente y heterogénea entre los pacientes críticos ingresados en la Unidad de Cuidados Intensivos (UCI), a menudo asociada a resultados adversos. El objetivo de este estudio fue identificar los subtipos fenotípicos de los pacientes de la UCI con IRA y evaluar su asociación con los resultados clínicos. Materiales y métodos Se realizó un análisis secundario utilizando la base de datos MIMIC-IV, que incluye una cohorte de adultos con diferentes estadios de LRA, así como pacientes sin LRA. Se utilizó un análisis factorial de datos mixtos, seguido de un agrupamiento jerárquico, para identificar los fenotipos de los pacientes basándose en una amplia gama de variables clínicas, demográficas, de laboratorio y de tratamiento. El perfil de los grupos se realizó utilizando un modelo de regresión logística multivariable. Resultados Entre los 1.372 pacientes distribuidos uniformemente entre los estadios 0 (sin LRA) y 3 (n = 343 por estadio), se identificaron dos grupos distintos. El grupo 2 (n = 671) presentó una mortalidad hospitalaria significativamente mayor (54,7% frente a 21,9%, p < 0,001) y una mayor prevalencia de estadios más avanzados de IRA (p < 0,001). Además, el grupo 2 mostró una frecuencia significativamente mayor de sepsis, administración de vasopresores y diuréticos, enfermedad renal crónica, insuficiencia cardíaca y también una frecuencia respiratoria y cardíaca más alta, y fósforo. Los pacientes del grupo 2 eran un poco más jóvenes y tenían una presión arterial de O2 y un pH sanguíneo más bajos. Un modelo de perfil de regresión logística alcanzó una precisión (IC del 95%) del 91,4% (89,8%, 92,8%) en la predicción de la asignación de clústeres. Conclusiones Existen dos fenotipos clínicamente distintos en los pacientes ingresados en la UCI en relación con la LRA, con fuertes implicaciones pronósticas. Los resultados ponen de relieve el potencial de los datos rutinarios de la UCI para permitir la estratificación del riesgo basada en el fenotipo en la LRA. [ABSTRACT FROM AUTHOR] |
| Copyright of Nefrologia is the property of Revista Nefrologia 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: 192970710 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Data-driven phenotypes across the full AKI severity spectrum in patients admitted to the ICU. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: Fenotipos basados en datos en todo el espectro de gravedad de la insuficiencia renal aguda en pacientes ingresados en la UCI. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Fathi%2C+Mohammad%22">Fathi, Mohammad</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Markazi+Moghaddam%2C+Nader%22">Markazi Moghaddam, Nader</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Markazi+Moghadam%2C+Hamed%22">Markazi Moghadam, Hamed</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Fathi%2C+Mahdis%22">Fathi, Mahdis</searchLink><relatesTo>1,4</relatesTo><br /><searchLink fieldCode="AR" term="%22Hajiesmaeili%2C+Mohammadreza%22">Hajiesmaeili, Mohammadreza</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22Nooraei%2C+Navid%22">Nooraei, Navid</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Malekpour+Alamdari%2C+Nasser%22">Malekpour Alamdari, Nasser</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Zargar+Balaye+Jame%2C+Sanaz%22">Zargar Balaye Jame, Sanaz</searchLink><relatesTo>2</relatesTo><i> sanazzargar@ajaums.ac.ir</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Nefrologia%22">Nefrologia</searchLink>. Apr2026, Vol. 46 Issue 4, p1-9. 9p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22PHENOTYPES%22">PHENOTYPES</searchLink><br /><searchLink fieldCode="DE" term="%22HIERARCHICAL+clustering+%28Cluster+analysis%29%22">HIERARCHICAL clustering (Cluster analysis)</searchLink><br /><searchLink fieldCode="DE" term="%22ACUTE+kidney+failure%22">ACUTE kidney failure</searchLink><br /><searchLink fieldCode="DE" term="%22PROGNOSIS%22">PROGNOSIS</searchLink><br /><searchLink fieldCode="DE" term="%22AT-risk+people%22">AT-risk people</searchLink><br /><searchLink fieldCode="DE" term="%22INTENSIVE+care+units%22">INTENSIVE care units</searchLink><br /><searchLink fieldCode="DE" term="%22ELECTRONIC+health+records%22">ELECTRONIC health records</searchLink> – Name: Abstract Label: Abstract (English) Group: Ab Data: Background and objectives Acute kidney injury (AKI) is a frequent and heterogeneous complication among critically ill patients in the intensive care unit (ICU), often associated with adverse outcomes. This study aimed to identify phenotypic subtypes of ICU patients with AKI and to evaluate their association with clinical outcomes. Materials and methods A secondary analysis was conducted using the MIMIC-IV database, including a cohort of adults with varying stages of AKI, as well as patients without AKI. Factorial analysis of mixed data, followed by hierarchical clustering, was used to identify patient phenotypes based on a wide range of clinical, demographic, laboratory, and treatment variables. Cluster profiling was conducted using a multivariable logistic regression model. Results Among 1372 patients evenly distributed across stages 0 (non-AKI) to 3 (n = 343 per stage), two distinct clusters were identified. Cluster 2 (n = 671) had significantly higher in-hospital mortality (54.7% vs. 21.9%, p < 0.001), and a greater prevalence of higher AKI stages (p < 0.001). Moreover, cluster 2 showed a significantly greater frequency of sepsis, vasopressors and diuretics administration, chronic kidney disease, heart failure, and also higher respiratory and heart rate, and phosphorus. Patients in cluster 2 were a little younger and had a lower arterial O2 pressure and blood pH. A logistic regression profiling model achieved an accuracy (95% CI) of 91.4% (89.8%, 92.8%) in predicting cluster assignment. Conclusions There are two clinically distinct phenotypes in patients admitted to the ICU concerning AKI with strong prognostic implications. The findings highlight the potential of routine ICU data to enable phenotype-based risk stratification in AKI. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Spanish) Group: Ab Data: Antecedentes y objetivos La insuficiencia renal aguda (IRA) es una complicación frecuente y heterogénea entre los pacientes críticos ingresados en la Unidad de Cuidados Intensivos (UCI), a menudo asociada a resultados adversos. El objetivo de este estudio fue identificar los subtipos fenotípicos de los pacientes de la UCI con IRA y evaluar su asociación con los resultados clínicos. Materiales y métodos Se realizó un análisis secundario utilizando la base de datos MIMIC-IV, que incluye una cohorte de adultos con diferentes estadios de LRA, así como pacientes sin LRA. Se utilizó un análisis factorial de datos mixtos, seguido de un agrupamiento jerárquico, para identificar los fenotipos de los pacientes basándose en una amplia gama de variables clínicas, demográficas, de laboratorio y de tratamiento. El perfil de los grupos se realizó utilizando un modelo de regresión logística multivariable. Resultados Entre los 1.372 pacientes distribuidos uniformemente entre los estadios 0 (sin LRA) y 3 (n = 343 por estadio), se identificaron dos grupos distintos. El grupo 2 (n = 671) presentó una mortalidad hospitalaria significativamente mayor (54,7% frente a 21,9%, p < 0,001) y una mayor prevalencia de estadios más avanzados de IRA (p < 0,001). Además, el grupo 2 mostró una frecuencia significativamente mayor de sepsis, administración de vasopresores y diuréticos, enfermedad renal crónica, insuficiencia cardíaca y también una frecuencia respiratoria y cardíaca más alta, y fósforo. Los pacientes del grupo 2 eran un poco más jóvenes y tenían una presión arterial de O2 y un pH sanguíneo más bajos. Un modelo de perfil de regresión logística alcanzó una precisión (IC del 95%) del 91,4% (89,8%, 92,8%) en la predicción de la asignación de clústeres. Conclusiones Existen dos fenotipos clínicamente distintos en los pacientes ingresados en la UCI en relación con la LRA, con fuertes implicaciones pronósticas. Los resultados ponen de relieve el potencial de los datos rutinarios de la UCI para permitir la estratificación del riesgo basada en el fenotipo en la LRA. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Nefrologia is the property of Revista Nefrologia 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=192970710 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.nefro.2025.501469 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 9 StartPage: 1 Subjects: – SubjectFull: PHENOTYPES Type: general – SubjectFull: HIERARCHICAL clustering (Cluster analysis) Type: general – SubjectFull: ACUTE kidney failure Type: general – SubjectFull: PROGNOSIS Type: general – SubjectFull: AT-risk people Type: general – SubjectFull: INTENSIVE care units Type: general – SubjectFull: ELECTRONIC health records Type: general Titles: – TitleFull: Data-driven phenotypes across the full AKI severity spectrum in patients admitted to the ICU. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Fathi, Mohammad – PersonEntity: Name: NameFull: Markazi Moghaddam, Nader – PersonEntity: Name: NameFull: Markazi Moghadam, Hamed – PersonEntity: Name: NameFull: Fathi, Mahdis – PersonEntity: Name: NameFull: Hajiesmaeili, Mohammadreza – PersonEntity: Name: NameFull: Nooraei, Navid – PersonEntity: Name: NameFull: Malekpour Alamdari, Nasser – PersonEntity: Name: NameFull: Zargar Balaye Jame, Sanaz IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 02116995 Numbering: – Type: volume Value: 46 – Type: issue Value: 4 Titles: – TitleFull: Nefrologia Type: main |
| ResultId | 1 |
