Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies

Abstract Purpose Paraneoplastic syndromes (PNS) are a group of rare disorders triggered by an immune response to malignancy, characterized by diverse neurological, muscular, and systemic symptoms. This study aims to leverage machine learning to develop a predictive model for cancer diagnosis in pati...

Full description

Saved in:
Bibliographic Details
Main Authors: Alireza Maleki, Mohammad Mahdi Mirza Ali Mohammadi, Shahab Gholizadeh, Behnaz Dalvandi, Mohammad Rahimi, Aidin Tarokhian
Format: Article
Language:English
Published: Springer 2025-01-01
Series:Discover Oncology
Subjects:
Online Access:https://doi.org/10.1007/s12672-025-01836-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832585666917040128
author Alireza Maleki
Mohammad Mahdi Mirza Ali Mohammadi
Shahab Gholizadeh
Behnaz Dalvandi
Mohammad Rahimi
Aidin Tarokhian
author_facet Alireza Maleki
Mohammad Mahdi Mirza Ali Mohammadi
Shahab Gholizadeh
Behnaz Dalvandi
Mohammad Rahimi
Aidin Tarokhian
author_sort Alireza Maleki
collection DOAJ
description Abstract Purpose Paraneoplastic syndromes (PNS) are a group of rare disorders triggered by an immune response to malignancy, characterized by diverse neurological, muscular, and systemic symptoms. This study aims to leverage machine learning to develop a predictive model for cancer diagnosis in patients with paraneoplastic autoantibodies. Methods Demographic data included age and sex, and presenting symptoms were recorded. Laboratory data comprised serum or cerebrospinal fluid (CSF) paraneoplastic autoantibody panels. The study included participants who tested positive for at least one autoantibody. Naive Bayes model was used to predict cancer presence. Model performance was evaluated using sensitivity, specificity, likelihood ratios, predictive values, AUC-ROC, Brier score, and overall accuracy. Feature importance was assessed using SHapley Additive exPlanations (SHAP) values. A graphical user interface (GUI)-based application was developed to facilitate model use. Results The study included 116 participants, with an average age of 57.1 years and a higher proportion of females (53.4%). The most common presenting symptom was ‘‘Motor’’ (40.5%), followed by ‘‘Cognitive’’ (17.2%) and ‘‘Bulbar’’ (15.5%) symptoms. Cancer was present in 23 participants (19.8%). The Naive Bayes model demonstrated high performance with a sensitivity of 85.71% and specificity of 100.00%. The AUC-ROC was 0.9795, indicating excellent diagnostic capability. Age and the presence or absence of specific autoantibodies were significant predictors of cancer. Conclusion Machine learning models, such as the Naive Bayes classifier developed in this study, can accurately stratify cancer risk in patients with positive paraneoplastic autoantibodies.
format Article
id doaj-art-c3e0c4f3dc1049c295c9d496397a9861
institution Kabale University
issn 2730-6011
language English
publishDate 2025-01-01
publisher Springer
record_format Article
series Discover Oncology
spelling doaj-art-c3e0c4f3dc1049c295c9d496397a98612025-01-26T12:39:54ZengSpringerDiscover Oncology2730-60112025-01-011611910.1007/s12672-025-01836-5Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodiesAlireza Maleki0Mohammad Mahdi Mirza Ali Mohammadi1Shahab Gholizadeh2Behnaz Dalvandi3Mohammad Rahimi4Aidin Tarokhian5College of Management, University of TehranDepartment of Electrical Engineering, Iran University of Science and TechnologyChaloos Razi HospitalTehran Medical Branch, Islamic Azad UniversityStudent Research Committee, Hamadan University of Medical SciencesSchool of Medicine, Hamadan University of Medical SciencesAbstract Purpose Paraneoplastic syndromes (PNS) are a group of rare disorders triggered by an immune response to malignancy, characterized by diverse neurological, muscular, and systemic symptoms. This study aims to leverage machine learning to develop a predictive model for cancer diagnosis in patients with paraneoplastic autoantibodies. Methods Demographic data included age and sex, and presenting symptoms were recorded. Laboratory data comprised serum or cerebrospinal fluid (CSF) paraneoplastic autoantibody panels. The study included participants who tested positive for at least one autoantibody. Naive Bayes model was used to predict cancer presence. Model performance was evaluated using sensitivity, specificity, likelihood ratios, predictive values, AUC-ROC, Brier score, and overall accuracy. Feature importance was assessed using SHapley Additive exPlanations (SHAP) values. A graphical user interface (GUI)-based application was developed to facilitate model use. Results The study included 116 participants, with an average age of 57.1 years and a higher proportion of females (53.4%). The most common presenting symptom was ‘‘Motor’’ (40.5%), followed by ‘‘Cognitive’’ (17.2%) and ‘‘Bulbar’’ (15.5%) symptoms. Cancer was present in 23 participants (19.8%). The Naive Bayes model demonstrated high performance with a sensitivity of 85.71% and specificity of 100.00%. The AUC-ROC was 0.9795, indicating excellent diagnostic capability. Age and the presence or absence of specific autoantibodies were significant predictors of cancer. Conclusion Machine learning models, such as the Naive Bayes classifier developed in this study, can accurately stratify cancer risk in patients with positive paraneoplastic autoantibodies.https://doi.org/10.1007/s12672-025-01836-5Machine learningParaneoplastic syndromeCancerAutoantibody
spellingShingle Alireza Maleki
Mohammad Mahdi Mirza Ali Mohammadi
Shahab Gholizadeh
Behnaz Dalvandi
Mohammad Rahimi
Aidin Tarokhian
Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
Discover Oncology
Machine learning
Paraneoplastic syndrome
Cancer
Autoantibody
title Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
title_full Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
title_fullStr Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
title_full_unstemmed Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
title_short Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies
title_sort machine learning assisted cancer diagnosis in patients with paraneoplastic autoantibodies
topic Machine learning
Paraneoplastic syndrome
Cancer
Autoantibody
url https://doi.org/10.1007/s12672-025-01836-5
work_keys_str_mv AT alirezamaleki machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies
AT mohammadmahdimirzaalimohammadi machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies
AT shahabgholizadeh machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies
AT behnazdalvandi machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies
AT mohammadrahimi machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies
AT aidintarokhian machinelearningassistedcancerdiagnosisinpatientswithparaneoplasticautoantibodies