Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy
Pancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scann...
Saved in:
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2025-01-01
|
Series: | Advanced Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1002/aisy.202400308 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832592555655561216 |
---|---|
author | Sonia Hermoso‐Durán Nicolas Fraunhoffer Judith Millastre‐Bocos Oscar Sanchez‐Gracia Pablo F. Garrido Sonia Vega Ángel Lanas Juan Iovanna Adrián Velázquez‐Campoy Olga Abian |
author_facet | Sonia Hermoso‐Durán Nicolas Fraunhoffer Judith Millastre‐Bocos Oscar Sanchez‐Gracia Pablo F. Garrido Sonia Vega Ángel Lanas Juan Iovanna Adrián Velázquez‐Campoy Olga Abian |
author_sort | Sonia Hermoso‐Durán |
collection | DOAJ |
description | Pancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scanning calorimetry (DSC) of blood serum samples, thermal liquid biopsy (TLB), combined with machine‐learning (ML) analysis, may offer a more efficient method for diagnosing PDAC. Serum samples from a cohort of 212 PDAC patients and 184 healthy controls are studied. DSC thermograms are analyzed using ML models. The generated models are built applying algorithms based on penalized regression, resampling, categorization, cross validation, and variable selection. The ML‐based model demonstrates outstanding ability to discriminate between PDAC patients and control subjects, with a sensitivity of 90% and an area under the ROC receiver operating characteristic curve of 0.83 in the training and test groups. Application of the model to an independent validation cohort of 113 PDAC patients confirms its robustness and utility as a diagnosis tool. The application of ML to serum TLB data emerges as a promising methodology for early diagnosis, representing a significant advance for detecting and managing PDAC, envisaging a minimally invasive and more efficient methodology for identifying biomarkers. |
format | Article |
id | doaj-art-280024c06f1043d3bc2cc1b1c8065ccd |
institution | Kabale University |
issn | 2640-4567 |
language | English |
publishDate | 2025-01-01 |
publisher | Wiley |
record_format | Article |
series | Advanced Intelligent Systems |
spelling | doaj-art-280024c06f1043d3bc2cc1b1c8065ccd2025-01-21T07:26:27ZengWileyAdvanced Intelligent Systems2640-45672025-01-0171n/an/a10.1002/aisy.202400308Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid BiopsySonia Hermoso‐Durán0Nicolas Fraunhoffer1Judith Millastre‐Bocos2Oscar Sanchez‐Gracia3Pablo F. Garrido4Sonia Vega5Ángel Lanas6Juan Iovanna7Adrián Velázquez‐Campoy8Olga Abian9Institute of Biocomputation and Physics of Complex Systems (BIFI) Joint Units IQFR‐CSIC‐BIFI, and GBsC‐CSIC‐BIFI Universidad de Zaragoza 50018 Zaragoza SpainAix‐Marseille Université, CNRS, Centre Interdisciplinaire de Nanoscience de Marseille, Equipe Labélisée Ligue Nationale Contre le Cancer 13288 Marseille FranceHospital Clínico Universitario Lozano Blesa 50009 Zaragoza SpainDepartamento de Ingeniería Electrónica y Comunicaciones Universidad de Zaragoza 50018 Zaragoza SpainInstitute of Biocomputation and Physics of Complex Systems (BIFI) Joint Units IQFR‐CSIC‐BIFI, and GBsC‐CSIC‐BIFI Universidad de Zaragoza 50018 Zaragoza SpainInstitute of Biocomputation and Physics of Complex Systems (BIFI) Joint Units IQFR‐CSIC‐BIFI, and GBsC‐CSIC‐BIFI Universidad de Zaragoza 50018 Zaragoza SpainInstituto de Investigación Sanitaria Aragón (IIS Aragón) 50009 Zaragoza SpainAix‐Marseille Université, CNRS, Centre Interdisciplinaire de Nanoscience de Marseille, Equipe Labélisée Ligue Nationale Contre le Cancer 13288 Marseille FranceInstitute of Biocomputation and Physics of Complex Systems (BIFI) Joint Units IQFR‐CSIC‐BIFI, and GBsC‐CSIC‐BIFI Universidad de Zaragoza 50018 Zaragoza SpainInstitute of Biocomputation and Physics of Complex Systems (BIFI) Joint Units IQFR‐CSIC‐BIFI, and GBsC‐CSIC‐BIFI Universidad de Zaragoza 50018 Zaragoza SpainPancreatic ductal adenocarcinoma (PDAC) poses a considerable diagnostic and therapeutic challenge due to the lack of specific biomarkers and late diagnosis. Early detection is crucial for improving prognosis, but current techniques are insufficient. An innovative approach based on differential scanning calorimetry (DSC) of blood serum samples, thermal liquid biopsy (TLB), combined with machine‐learning (ML) analysis, may offer a more efficient method for diagnosing PDAC. Serum samples from a cohort of 212 PDAC patients and 184 healthy controls are studied. DSC thermograms are analyzed using ML models. The generated models are built applying algorithms based on penalized regression, resampling, categorization, cross validation, and variable selection. The ML‐based model demonstrates outstanding ability to discriminate between PDAC patients and control subjects, with a sensitivity of 90% and an area under the ROC receiver operating characteristic curve of 0.83 in the training and test groups. Application of the model to an independent validation cohort of 113 PDAC patients confirms its robustness and utility as a diagnosis tool. The application of ML to serum TLB data emerges as a promising methodology for early diagnosis, representing a significant advance for detecting and managing PDAC, envisaging a minimally invasive and more efficient methodology for identifying biomarkers.https://doi.org/10.1002/aisy.202400308biomarkersdiagnosesmachine‐learning algorithmspancreatic ductal adenocarcinomas (PDACs)thermal liquid biopsies (TLBs) |
spellingShingle | Sonia Hermoso‐Durán Nicolas Fraunhoffer Judith Millastre‐Bocos Oscar Sanchez‐Gracia Pablo F. Garrido Sonia Vega Ángel Lanas Juan Iovanna Adrián Velázquez‐Campoy Olga Abian Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy Advanced Intelligent Systems biomarkers diagnoses machine‐learning algorithms pancreatic ductal adenocarcinomas (PDACs) thermal liquid biopsies (TLBs) |
title | Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy |
title_full | Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy |
title_fullStr | Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy |
title_full_unstemmed | Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy |
title_short | Development of a Machine‐Learning Model for Diagnosis of Pancreatic Cancer from Serum Samples Analyzed by Thermal Liquid Biopsy |
title_sort | development of a machine learning model for diagnosis of pancreatic cancer from serum samples analyzed by thermal liquid biopsy |
topic | biomarkers diagnoses machine‐learning algorithms pancreatic ductal adenocarcinomas (PDACs) thermal liquid biopsies (TLBs) |
url | https://doi.org/10.1002/aisy.202400308 |
work_keys_str_mv | AT soniahermosoduran developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT nicolasfraunhoffer developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT judithmillastrebocos developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT oscarsanchezgracia developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT pablofgarrido developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT soniavega developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT angellanas developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT juaniovanna developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT adrianvelazquezcampoy developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy AT olgaabian developmentofamachinelearningmodelfordiagnosisofpancreaticcancerfromserumsamplesanalyzedbythermalliquidbiopsy |