Biomarcadores de cáncer pancreático predictores de pancreatitis crónica: análisis mediante aprendizaje automático.
Saved in:
| Title: | Biomarcadores de cáncer pancreático predictores de pancreatitis crónica: análisis mediante aprendizaje automático. |
|---|---|
| Alternate Title: | Pancreatic Cancer Biomarkers Predictors of Chronic Pancreatitis: Analysis using Machine Learning. Biomarcadores de câncer de pâncreas indicativos de pancreatite crônica: análise mediante aprendizado de máquina. |
| Authors: | Tirado, Alberto Guevara1 albertoguevara1986@gmail.com |
| Source: | Revista Ciencias de la Salud. sep-dic2025, Vol. 23 Issue 3, p1-14. 14p. |
| Subjects: | PANCREATITIS diagnosis, CHRONIC disease diagnosis, CROSS-sectional method, PREDICTION models, CREATININE, T-test (Statistics), DATA analysis, TUMOR markers, CHI-squared test, PANCREATIC tumors, RESEARCH, STATISTICS, MACHINE learning, FACTOR analysis, DECISION trees, COMPARATIVE studies, SENSITIVITY & specificity (Statistics) |
| Abstract (English): | Introduction: Several studies have investigated biomarkers of pancreatic cancer, which would be useful for ruling out chronic pancreatic pathologies. The objective was to analyze and compare concentrations of plasma and urinary biomarkers of pancreatic cancer in patients with chronic pancreatitis and healthy people through supervised and unsupervised learning. Materials and methods: Analytical and cross-sectional study based on a secondary database. The variables were: chronic pancreatitis, REG1B, REG1A, TFF1 LYVE1, creatinine, and CA19.9. Student t tests, Spearman correlation, principal component analysis (pcA), multilayer perceptron and decision tree were used through automatic detection of interactions by Chi-square. Results: The average of biomarkers was higher in patients with chronic pancreatitis. Using multilayer perceptron, the most predictive biomarkers were: CA19.9, REG1B and TFF-1 (efficiency 91%). The decision tree classified TFF-1 and REG1B as predictors (REG1B equal to or less than 12.74ng/ml and TFF1 between 33.11-339ng/ml) and another node with TFF1 greater than 339ng/ml. The principal component analysis generated a component of biomarkers REG1B, REG1A, TFF1 LYVE1 and creatinine, creating a cut-off point of -0.55 for the presence or absence of chronic pancreatitis (sensitivity: 26%, and specificity: 93%) Conclusions: The biomarkers for pancreatic cancer REG1B, REG1A, TFF1 LYVE1, creatinine and CA19.9 are increased in chronic pancreatitis. Supervised learning tools allow efficient prediction and classification of biomarkers, with TFF1 and REG1B being the most relevant. Through unsupervised learning, the combination of REG1B, REG1A, TFF1 LYVE1 and creatinine is highly specific to rule out chronic pancreatic inflammation in healthy people. [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | Introducción: se realizan múltiples investigaciones orientadas a la búsqueda de biomarcadores de cáncer pancreático que serían útiles para el descarte de patologías pancreáticas crónicas. Objetivo: analizar y comparar concentraciones de biomarcadores plasmáticos y urinarios de cáncer pancreático en pacientes con pancreatitis crónica, y sanos mediante aprendizaje supervisado y no supervisado. Materiales y métodos: estudio analítico y transversal basado en una base de datos secundaria. Las variables fueron: pancreatitis crónica, REG1B, REG1A, TFF1, LYVE1, creatinina y CA19.9. Se usaron las pruebas t de Student, correlación de Spearman, análisis de componentes principales, perceptrón multicapa y árbol de decisiones mediante detección automática de interacciones por chi-cuadrado. Resultados: el promedio de biomarcadores fue mayor en pacientes con pancreatitis crónica. Mediante perceptrón multicapa, los biomarcadores más predictivos fueron: CA19.9, REG1B y TFF1 (eficiencia del 91 %). El árbol de decisiones clasificó como predictores a TFF1 y REG1B (REG1B ≤ 12,74 ng/ml y TFF1 entre 33,11 y 339 ng/ml) y otro nodo con TFF1 mayor a 339 ng/ml. El análisis de componentes principales generó un componente de biomarcadores REG1B, REG1A, TFF1, LYVE1 y creatinina, que creó un punto de corte de -0.55 para presencia o ausencia de pancreatitis crónica (sensibilidad: 26 % y especificidad: 93 %). Conclusiones: los biomarcadores para cáncer pancreático REG1B, REGIA, TFF1, LYVE1, creatinina y CA19.9 se incrementan en pancreatitis crónica. Las herramientas de aprendizaje supervisado permiten predecir y clasificar eficientemente los biomarcadores, siendo TFF1 y REG1B los más relevantes. Mediante aprendizaje no supervisado, la combinación de REG1B, REG1A, TFF1, LYVE1 y creatinina es altamente específico para descartar inflamación pancreática crónica en sanos. [ABSTRACT FROM AUTHOR] |
| Abstract (Portuguese): | Introdução: múltiplas pesquisas são realizadas para buscar biomarcadores de câncer de pâncreas, o que seria útil para a exclusão de patologias pancreáticas crônicas. O objetivo foi analisar e comparar as concentrações de biomarcadores plasmáticos e urinários de câncer de pâncreas em pacientes com pancreatite crônica e pacientes saudáveis mediante aprendizado de máquina supervisionado e não supervisionado. Materiais e métodos: estudo analítico e transversal baseado em um banco de dados secundário. As variáveis foram: pancreatite crônica, REG1B, REG1A, TFF1 LYVE1, creatinine, CA19.9. Foram usados testes t de Student, correlação de Spearman, análise de componentes principais, perceptron multicamadas e árvore de decisão por meio da detecção automática de interações qui-quadrado. Resultados: a média de biomarcadores foi maior em pacientes com pancreatite crônica. Usando perceptron multicamada, os biomarcadores mais preditivos foram: CA19.9, REG1B e TFF1 (91% de eficiência). A árvore de decisão classificou TFF1 e REG1B como preditores (REG1B igual ou menor que 12,74 ng/ml e TFF1 entre 33,11-339 ng/ml) e outro nó com TFF1 superior a 339 ng/ml. A análise de componentes principais gerou um componente de biomarcadores REG1B, REG1A, TFF1, LYVE1 e creatinina, criando um ponto de corte de -0,55 para a presença ou ausência de pancreatite crônica (sensibilidade: 26% e, especificidade: 93%). Conclusões: os biomarcadores para câncer de pâncreas REG1B, REG1A, TFF1, LYVE1, creatinina e CA19.9 se encontram aumentados na pancreatite crônica. As ferramentas de aprendizado de máquina supervisionado permitem prever e classificar eficientemente os biomarcadores, sendo TFF1 e REG1B os mais relevantes. Por meio do aprendizado não supervisionado, a combinação de REG1B, REGIA, TFF1, LYVE1 e creatinina é altamente específica para descartar inflamação crônica do pâncreas em pacientes saudáveis. [ABSTRACT FROM AUTHOR] |
| Copyright of Revista Ciencias de la Salud is the property of Colegio Mayor de Nuestra Senora del Rosario 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: 192606099 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Biomarcadores de cáncer pancreático predictores de pancreatitis crónica: análisis mediante aprendizaje automático. – Name: TitleAlt Label: Alternate Title Group: TiAlt Data: Pancreatic Cancer Biomarkers Predictors of Chronic Pancreatitis: Analysis using Machine Learning.<br />Biomarcadores de câncer de pâncreas indicativos de pancreatite crônica: análise mediante aprendizado de máquina. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Tirado%2C+Alberto+Guevara%22">Tirado, Alberto Guevara</searchLink><relatesTo>1</relatesTo><i> albertoguevara1986@gmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Revista+Ciencias+de+la+Salud%22">Revista Ciencias de la Salud</searchLink>. sep-dic2025, Vol. 23 Issue 3, p1-14. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22PANCREATITIS+diagnosis%22">PANCREATITIS diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22CHRONIC+disease+diagnosis%22">CHRONIC disease diagnosis</searchLink><br /><searchLink fieldCode="DE" term="%22CROSS-sectional+method%22">CROSS-sectional method</searchLink><br /><searchLink fieldCode="DE" term="%22PREDICTION+models%22">PREDICTION models</searchLink><br /><searchLink fieldCode="DE" term="%22CREATININE%22">CREATININE</searchLink><br /><searchLink fieldCode="DE" term="%22T-test+%28Statistics%29%22">T-test (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22DATA+analysis%22">DATA analysis</searchLink><br /><searchLink fieldCode="DE" term="%22TUMOR+markers%22">TUMOR markers</searchLink><br /><searchLink fieldCode="DE" term="%22CHI-squared+test%22">CHI-squared test</searchLink><br /><searchLink fieldCode="DE" term="%22PANCREATIC+tumors%22">PANCREATIC tumors</searchLink><br /><searchLink fieldCode="DE" term="%22RESEARCH%22">RESEARCH</searchLink><br /><searchLink fieldCode="DE" term="%22STATISTICS%22">STATISTICS</searchLink><br /><searchLink fieldCode="DE" term="%22MACHINE+learning%22">MACHINE learning</searchLink><br /><searchLink fieldCode="DE" term="%22FACTOR+analysis%22">FACTOR analysis</searchLink><br /><searchLink fieldCode="DE" term="%22DECISION+trees%22">DECISION trees</searchLink><br /><searchLink fieldCode="DE" term="%22COMPARATIVE+studies%22">COMPARATIVE studies</searchLink><br /><searchLink fieldCode="DE" term="%22SENSITIVITY+%26+specificity+%28Statistics%29%22">SENSITIVITY & specificity (Statistics)</searchLink> – Name: Abstract Label: Abstract (English) Group: Ab Data: Introduction: Several studies have investigated biomarkers of pancreatic cancer, which would be useful for ruling out chronic pancreatic pathologies. The objective was to analyze and compare concentrations of plasma and urinary biomarkers of pancreatic cancer in patients with chronic pancreatitis and healthy people through supervised and unsupervised learning. Materials and methods: Analytical and cross-sectional study based on a secondary database. The variables were: chronic pancreatitis, REG1B, REG1A, TFF1 LYVE1, creatinine, and CA19.9. Student t tests, Spearman correlation, principal component analysis (pcA), multilayer perceptron and decision tree were used through automatic detection of interactions by Chi-square. Results: The average of biomarkers was higher in patients with chronic pancreatitis. Using multilayer perceptron, the most predictive biomarkers were: CA19.9, REG1B and TFF-1 (efficiency 91%). The decision tree classified TFF-1 and REG1B as predictors (REG1B equal to or less than 12.74ng/ml and TFF1 between 33.11-339ng/ml) and another node with TFF1 greater than 339ng/ml. The principal component analysis generated a component of biomarkers REG1B, REG1A, TFF1 LYVE1 and creatinine, creating a cut-off point of -0.55 for the presence or absence of chronic pancreatitis (sensitivity: 26%, and specificity: 93%) Conclusions: The biomarkers for pancreatic cancer REG1B, REG1A, TFF1 LYVE1, creatinine and CA19.9 are increased in chronic pancreatitis. Supervised learning tools allow efficient prediction and classification of biomarkers, with TFF1 and REG1B being the most relevant. Through unsupervised learning, the combination of REG1B, REG1A, TFF1 LYVE1 and creatinine is highly specific to rule out chronic pancreatic inflammation in healthy people. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Spanish) Group: Ab Data: Introducción: se realizan múltiples investigaciones orientadas a la búsqueda de biomarcadores de cáncer pancreático que serían útiles para el descarte de patologías pancreáticas crónicas. Objetivo: analizar y comparar concentraciones de biomarcadores plasmáticos y urinarios de cáncer pancreático en pacientes con pancreatitis crónica, y sanos mediante aprendizaje supervisado y no supervisado. Materiales y métodos: estudio analítico y transversal basado en una base de datos secundaria. Las variables fueron: pancreatitis crónica, REG1B, REG1A, TFF1, LYVE1, creatinina y CA19.9. Se usaron las pruebas t de Student, correlación de Spearman, análisis de componentes principales, perceptrón multicapa y árbol de decisiones mediante detección automática de interacciones por chi-cuadrado. Resultados: el promedio de biomarcadores fue mayor en pacientes con pancreatitis crónica. Mediante perceptrón multicapa, los biomarcadores más predictivos fueron: CA19.9, REG1B y TFF1 (eficiencia del 91 %). El árbol de decisiones clasificó como predictores a TFF1 y REG1B (REG1B ≤ 12,74 ng/ml y TFF1 entre 33,11 y 339 ng/ml) y otro nodo con TFF1 mayor a 339 ng/ml. El análisis de componentes principales generó un componente de biomarcadores REG1B, REG1A, TFF1, LYVE1 y creatinina, que creó un punto de corte de -0.55 para presencia o ausencia de pancreatitis crónica (sensibilidad: 26 % y especificidad: 93 %). Conclusiones: los biomarcadores para cáncer pancreático REG1B, REGIA, TFF1, LYVE1, creatinina y CA19.9 se incrementan en pancreatitis crónica. Las herramientas de aprendizaje supervisado permiten predecir y clasificar eficientemente los biomarcadores, siendo TFF1 y REG1B los más relevantes. Mediante aprendizaje no supervisado, la combinación de REG1B, REG1A, TFF1, LYVE1 y creatinina es altamente específico para descartar inflamación pancreática crónica en sanos. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Abstract (Portuguese) Group: Ab Data: Introdução: múltiplas pesquisas são realizadas para buscar biomarcadores de câncer de pâncreas, o que seria útil para a exclusão de patologias pancreáticas crônicas. O objetivo foi analisar e comparar as concentrações de biomarcadores plasmáticos e urinários de câncer de pâncreas em pacientes com pancreatite crônica e pacientes saudáveis mediante aprendizado de máquina supervisionado e não supervisionado. Materiais e métodos: estudo analítico e transversal baseado em um banco de dados secundário. As variáveis foram: pancreatite crônica, REG1B, REG1A, TFF1 LYVE1, creatinine, CA19.9. Foram usados testes t de Student, correlação de Spearman, análise de componentes principais, perceptron multicamadas e árvore de decisão por meio da detecção automática de interações qui-quadrado. Resultados: a média de biomarcadores foi maior em pacientes com pancreatite crônica. Usando perceptron multicamada, os biomarcadores mais preditivos foram: CA19.9, REG1B e TFF1 (91% de eficiência). A árvore de decisão classificou TFF1 e REG1B como preditores (REG1B igual ou menor que 12,74 ng/ml e TFF1 entre 33,11-339 ng/ml) e outro nó com TFF1 superior a 339 ng/ml. A análise de componentes principais gerou um componente de biomarcadores REG1B, REG1A, TFF1, LYVE1 e creatinina, criando um ponto de corte de -0,55 para a presença ou ausência de pancreatite crônica (sensibilidade: 26% e, especificidade: 93%). Conclusões: os biomarcadores para câncer de pâncreas REG1B, REG1A, TFF1, LYVE1, creatinina e CA19.9 se encontram aumentados na pancreatite crônica. As ferramentas de aprendizado de máquina supervisionado permitem prever e classificar eficientemente os biomarcadores, sendo TFF1 e REG1B os mais relevantes. Por meio do aprendizado não supervisionado, a combinação de REG1B, REGIA, TFF1, LYVE1 e creatinina é altamente específica para descartar inflamação crônica do pâncreas em pacientes saudáveis. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Revista Ciencias de la Salud is the property of Colegio Mayor de Nuestra Senora del Rosario 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=192606099 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.12804/revistas.urosario.edu.co/revsalud/a.14382 Languages: – Code: spa Text: Spanish PhysicalDescription: Pagination: PageCount: 14 StartPage: 1 Subjects: – SubjectFull: PANCREATITIS diagnosis Type: general – SubjectFull: CHRONIC disease diagnosis Type: general – SubjectFull: CROSS-sectional method Type: general – SubjectFull: PREDICTION models Type: general – SubjectFull: CREATININE Type: general – SubjectFull: T-test (Statistics) Type: general – SubjectFull: DATA analysis Type: general – SubjectFull: TUMOR markers Type: general – SubjectFull: CHI-squared test Type: general – SubjectFull: PANCREATIC tumors Type: general – SubjectFull: RESEARCH Type: general – SubjectFull: STATISTICS Type: general – SubjectFull: MACHINE learning Type: general – SubjectFull: FACTOR analysis Type: general – SubjectFull: DECISION trees Type: general – SubjectFull: COMPARATIVE studies Type: general – SubjectFull: SENSITIVITY & specificity (Statistics) Type: general Titles: – TitleFull: Biomarcadores de cáncer pancreático predictores de pancreatitis crónica: análisis mediante aprendizaje automático. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Tirado, Alberto Guevara IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: sep-dic2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 16927273 Numbering: – Type: volume Value: 23 – Type: issue Value: 3 Titles: – TitleFull: Revista Ciencias de la Salud Type: main |
| ResultId | 1 |
