Discover. Oncology最新文献

筛选
英文 中文
Improving molecular subtypes and prognosis of pancreatic cancer through multi group analysis and machine learning.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-28 DOI: 10.1007/s12672-025-01841-8
Xue-Jian Zhang, Fang-Fang Lin, Ya-Qing Wen, Kun-Ping Guan
{"title":"Improving molecular subtypes and prognosis of pancreatic cancer through multi group analysis and machine learning.","authors":"Xue-Jian Zhang, Fang-Fang Lin, Ya-Qing Wen, Kun-Ping Guan","doi":"10.1007/s12672-025-01841-8","DOIUrl":"https://doi.org/10.1007/s12672-025-01841-8","url":null,"abstract":"<p><strong>Background: </strong>Pancreatic cancer (PAC) has a complex tumor immune microenvironment, and currently, there is a lack of accurate personalized treatment. Establishing a novel consensus machine learning driven signature (CMLS) that offers a unique predictive model and possible treatment targets for this condition was the goal of this study.</p><p><strong>Methods: </strong>This study integrated multiple omics data of PAC patients, applied ten clustering techniques and ten machine learning approaches to construct molecular subtypes for PAC, and created a new CMLS.</p><p><strong>Results: </strong>Using multi-omics clustering, we discovered two cancer subtypes (CSs) associated with prognosis, among which CS1 exhibited poor prognostic outcomes. Subsequently, 13 central genes were identified through screening, constituting CMLS with a significant prognostic ability. The low CMLS group had a better prognosis and was more likely to possess a \"hot\" tumor phenotype. The prognosis for the high CMLS group was dismal. Still, the tumor mutation burden (TMB) and tumor neoantigen burden (TNB) levels in this group of patients were higher than in the low CMLS group, which were more favorable for immune therapy response.</p><p><strong>Conclusion: </strong>This study emphasizes that CMLS provides a beneficial instrument for early prediction of patient prognosis and screening of probable patients appropriate for immunotherapy and has broad implications for clinical practice.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"96"},"PeriodicalIF":2.8,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The usage of the paris classification system in urine cytology in the diagnosis of non-muscle-invasive bladder cancer: a retrospective single-center study.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-025-01828-5
Perttu Saarinen, Otto Jokelainen, Liida Ruotsalainen, Essi Ikonen, Timo K Nykopp
{"title":"The usage of the paris classification system in urine cytology in the diagnosis of non-muscle-invasive bladder cancer: a retrospective single-center study.","authors":"Perttu Saarinen, Otto Jokelainen, Liida Ruotsalainen, Essi Ikonen, Timo K Nykopp","doi":"10.1007/s12672-025-01828-5","DOIUrl":"https://doi.org/10.1007/s12672-025-01828-5","url":null,"abstract":"<p><strong>Purpose: </strong>This retrospective single-center study aimed to determine the correlation between The Paris System (TPS) urine cytology classification, cystoscopy findings, and non-muscle-invasive bladder cancer diagnosis. In addition, we sought to identify factors that might explain the abnormal cytology classification in cases in which no malignancy was detected.</p><p><strong>Methods: </strong>A Total of 855 patients evaluated with urine cytology between 2017 and 2020 at Kuopio University Hospital were included. Histological diagnoses and urinalysis results were correlated with cytology (TPS). Chi-squared and Fisher's exact tests were used to calculate statistical significance.</p><p><strong>Results: </strong>In the absence of exophytic tumors on cystoscopy, the risks of bladder cancer was 0.1% for NHGUC, 1.5% for AUC, 22.7% for SHGUC, and 83.3% for HGUC. Positive urinalysis corresponded to lower cytological diagnostic categories in both males and females. A statistically significant difference was observed in males with respect to moderate pyuria, hematuria, and higher cytological categories.</p><p><strong>Conclusions: </strong>This study provides evidence that a biopsy or follow-up may not be necessary for patients without a prior history of urothelial carcinoma and without exophytic tumors observed on cystoscopy, when the cytological diagnosis is NHGUC or AUC. Furthermore, concurrent hematuria and pyuria may result in a higher cytological classification.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"95"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143051608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
AURKB affects the proliferation of clear cell renal cell carcinoma by regulating fatty acid metabolism.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-024-01352-y
Yang Yang, Dan Li, Zhigang Liu, Kai Zhou, Wenxing Li, Yanqi Yang, Ruifang Sun, Yulong Li
{"title":"AURKB affects the proliferation of clear cell renal cell carcinoma by regulating fatty acid metabolism.","authors":"Yang Yang, Dan Li, Zhigang Liu, Kai Zhou, Wenxing Li, Yanqi Yang, Ruifang Sun, Yulong Li","doi":"10.1007/s12672-024-01352-y","DOIUrl":"10.1007/s12672-024-01352-y","url":null,"abstract":"<p><strong>Background: </strong>Clear cell renal cell carcinoma (ccRCC) is the most common subtype of kidney cancer with a high metastatic rate and high mortality rate. The molecular mechanism of ccRCC development, however, needs further study. Aurora kinase B (AURKB) functions as an important oncogene in various tumors; therefore, in the present study, we aimed to explore the mechanism by which AURKB affects ccRCC development.</p><p><strong>Methods: </strong>We performed bioinformatics analysis, CCK-8 assay, RNA sequencing, RT-PCR and Western blot to analyze the function and mechanism of AURKB in ccRCC.</p><p><strong>Results: </strong>TIMER2.0 showed that AURKB was overexpressed in Kidney Renal Clear Cell Carcinoma (KIRC), the UALCAN database showed the survival rate of KIRC patients with different expression levels of AURKB and different gender indicated in the same gender, high AURKB expression predicts lower survival rate. Silencing of AURKB expression inhibits the proliferation of ccRCC cells. RNA-seq data suggested that AURKB is involved in fatty acid metabolism. Silencing of AURKB inhibited the expression of fatty acid synthase (FASN). FASN is a key gene involved in fatty acid metabolism. TIMER2.0 showed that FASN is upregulated in KIRC. Silencing of FASN inhibited the proliferation of ccRCC cells.</p><p><strong>Conclusions: </strong>AURKB induces the proliferation of ccRCC cells by regulating fatty acid metabolism.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"91"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
To describe the subsets of malignant epithelial cells in gastric cancer, their developmental trajectories and drug resistance characteristics.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-024-01715-5
Tingting Xu, Tianying Zhang, Yan Sun, Sijia Wu
{"title":"To describe the subsets of malignant epithelial cells in gastric cancer, their developmental trajectories and drug resistance characteristics.","authors":"Tingting Xu, Tianying Zhang, Yan Sun, Sijia Wu","doi":"10.1007/s12672-024-01715-5","DOIUrl":"https://doi.org/10.1007/s12672-024-01715-5","url":null,"abstract":"<p><p>Gastric cancer is an aggressive malignancy characterized by significant clinical heterogeneity arising from complex genetic and environmental interactions. This study employed single-cell RNA sequencing, using the 10 × Genomics platform, to analyze 262,532 cells from gastric cancer samples, identifying 32 distinct clusters and 10 major cell types, including immune cells (e.g., T cells, monocytes) and epithelial subpopulations. Among 27 epithelial subgroups, five malignant subpopulations were identified, each defined by unique marker gene expressions and playing diverse roles in tumor progression. Developmental trajectory analysis revealed potential stem-like characteristics in certain clusters, suggesting their involvement in therapeutic resistance and disease recurrence. Cell-cell communication analysis uncovered a dynamic network of interactions within the tumor microenvironment, potentially influencing tumor growth and metastasis. Differential gene expression analysis identified key genes (LDHA, GPC3, MIF, CD44, and TFF3) that were used to construct a prognostic risk score model. This model demonstrated robust predictive power, achieving AUC values of 0.77, 0.77, and 0.76 for 1-, 3-, and 5-year overall survival in the TCGA training dataset, with validation across independent cohorts. These findings deepen our understanding of gastric cancer's cellular and molecular heterogeneity, offering insights into potential therapeutic targets and biomarkers. By facilitating the development of targeted therapies and personalized treatment strategies, these results hold promise for improving clinical outcomes in gastric cancer patients.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"93"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Investigating causal relationship among inflammatory cytokines and oropharyngeal cancer: Mendelian randomization.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-025-01809-8
Sibo Xu, Yiguo Li, Wei Chen, Ke Wang
{"title":"Investigating causal relationship among inflammatory cytokines and oropharyngeal cancer: Mendelian randomization.","authors":"Sibo Xu, Yiguo Li, Wei Chen, Ke Wang","doi":"10.1007/s12672-025-01809-8","DOIUrl":"https://doi.org/10.1007/s12672-025-01809-8","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to use Mendelian randomisation to identify the causal relationship between a spectrum of 41 inflammatory cytokines and the development of oropharyngeal cancer.</p><p><strong>Methods: </strong>This study investigated genetic variants that have been associated with oral and oropharyngeal cancer using data from a large GWAS. Inflammatory cytokine data were obtained from 8293 asymptomatic individuals. The study primarily used inverse variance weighted and MR-Egger methods to determine the causal relationship between inflammatory cytokines and cancer incidence, complemented by a series of sensitivity analyses including MR-Egger, simple mode, weighted mode, weighted median and leave-one-out approaches.</p><p><strong>Results: </strong>Our study demonstrates that higher levels of interleukin-7 (IL-7) and interleukin-5 (IL-5) slightly increase the odds of oropharyngeal cancer by 0.07% [OR: 1.0007, p = 0.005] and 0.04% [OR: 1.0004, p = 0.015], corresponding to a modest increase. Similarly, increased PDGF-bb and CTACK levels are modestly associated with increased odds of oral and oropharyngeal cancer by 0.22% [OR: 1.0022, p = 0.031] and 0.17% [OR: 1.0017, p = 0.043], respectively.</p><p><strong>Conclusion: </strong>This investigation posits that IL-5 and IL-7 may be pertinent factors in the etiology of Oropharyngeal cancer, while PDGF bb and CTACK are likely implicated in the pathogenesis of both oral and oropharyngeal cancers.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"92"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Correction: Identified VCAM1 as prognostic gene in gastric cancer by co-expression network analysis.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-025-01766-2
Wenjuan Li, Hong Gao, Jianjun Liu
{"title":"Correction: Identified VCAM1 as prognostic gene in gastric cancer by co-expression network analysis.","authors":"Wenjuan Li, Hong Gao, Jianjun Liu","doi":"10.1007/s12672-025-01766-2","DOIUrl":"https://doi.org/10.1007/s12672-025-01766-2","url":null,"abstract":"","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"90"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A pan-cancer analysis: predictive role of ZNF32 in cancer prognosis and immunotherapy response.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-27 DOI: 10.1007/s12672-025-01803-0
Minghan Li, Chang Su, Qianru Wang, Yuetong Chen, Di Jiang, Weijia Wang, Shunjin Chen, Xiangping Li, Ming Fu, Juan Lu
{"title":"A pan-cancer analysis: predictive role of ZNF32 in cancer prognosis and immunotherapy response.","authors":"Minghan Li, Chang Su, Qianru Wang, Yuetong Chen, Di Jiang, Weijia Wang, Shunjin Chen, Xiangping Li, Ming Fu, Juan Lu","doi":"10.1007/s12672-025-01803-0","DOIUrl":"https://doi.org/10.1007/s12672-025-01803-0","url":null,"abstract":"<p><p>The zinc finger protein 32 (ZNF32) has been associated with high expression in various cancers, underscoring its significant function in both cancer biology and immune response. To further elucidate the biological role of ZNF32 and identify potential immunotherapy targets in cancer, we conducted an in-depth analysis of ZNF32. We comprehensively investigated the expression of ZNF32 across tumors using diverse databases, including TCGA, CCLE, TIMER2.0, KM-Plotter, cBioPortal, ImmuCellAI. We investigated correlations between ZNF32 expression and various factors such as prognosis, immune infiltration, immunotherapy, DNA methylation, and biological functions. Furthermore, we performed in vitro research to validate the significance of ZNF32 in head and neck cancer (HNSC). Our study revealed that ZNF32 was high in various types of cancer, including ACC, BRCA, and others, indicating its important potential as a prognostic biomarker. Significant changes in CNA and DNA methylation were associated with high ZNF32 expression. ZNF32 was notably linked to various immune characteristics, including immune cell infiltration, MSI, TMB and immune checkpoint gene expression, indicating its potential in informing immunotherapy approaches. Interestingly, in FaDu and CAL27 cell lines, the group with elevated ZNF32 expression exhibited increased levels of immune checkpoint markers, such as CTLA-4 and PD-L1. Overexpression of ZNF32 significantly enhanced proliferation and migration in FaDu and CAL27 cell lines, as demonstrated through CCK-8 assays, colony formation, flow cytometry, Transwell migration, and Boyden invasion assays. Our in vitro experiments confirmed that ZNF32 promotes malignant behavior by driving HNSC cell proliferation and migration. These results imply that ZNF32 might be a promising target for tumor prognosis and immunotherapy. Our results highlight the important role of ZNF32 in tumorigenesis and provide novel perspectives for potential cancer treatment strategies.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"94"},"PeriodicalIF":2.8,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143051994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A panel of cancer testis antigens in squamous cell carcinoma of the lung, head and neck, and esophagus: implication for biomarkers and therapeutic targets.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-26 DOI: 10.1007/s12672-025-01804-z
Lin Li, Xin Zhang, Jiayao Yan, Jingyi Guo, Fangcen Liu, Xiao Wei, Qin Liu, Kongcheng Wang, Baorui Liu
{"title":"A panel of cancer testis antigens in squamous cell carcinoma of the lung, head and neck, and esophagus: implication for biomarkers and therapeutic targets.","authors":"Lin Li, Xin Zhang, Jiayao Yan, Jingyi Guo, Fangcen Liu, Xiao Wei, Qin Liu, Kongcheng Wang, Baorui Liu","doi":"10.1007/s12672-025-01804-z","DOIUrl":"10.1007/s12672-025-01804-z","url":null,"abstract":"<p><p>This study aims to investigate the expression of seven cancer testis antigens (MAGE-A1, MAGE-A4, MAGE-A10, MAGE-A11, PRAME, NY-ESO-1 and KK-LC-1) in pan squamous cell carcinoma and their prognostic value, thus assessing the potential of these CTAs as immunotherapeutic targets. The protein expression of these CTAs was evaluated by immunohistochemistry in 60 lung squamous cell carcinoma (LUSC), 62 esophageal squamous cell carcinoma (ESCA) and 62 head and neck squamous cell carcinoma (HNSC). The relationship between CTAs expression and progression-free survival (PFS) was assessed. PD-L1 expression and tumor-infiltrating lymphocytes were also collected and correlated with CTAs expression. The prognostic impact of CTAs gene expression was evaluated using the Kaplan-Meier Plotter website. CTAs expression was 0-48% in ESCA, 3%-77% in LUSC, and 3%-71% in HNSC. Analysis of PFS showed that MAGE-A1 expression in HNSC (**p < 0.01), PRAME in LUSC (p = 0.008, **p < 0.01), MAGE-A10 (p = 0.012, *p < 0.05) and PRAME (p = 0.021, *p < 0.05) in ESCA were significantly correlated with PFS. In all three cancers, coexpression of three CTAs was used as a cutoff value for grouping, and the results showed a significant difference in PFS between these two groups. Moreover, CTAs expression was significantly correlated with PD-L1 expression and T cell infiltration. These findings indicate a high incidence of CTA expression in HNSC, LUSC and ESCA, which was correlated with PD-L1 expression, T cell infiltration, and tumor progression. The results suggest that cancer testis antigens could be feasible vaccine targets in squamous cell carcinoma.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"88"},"PeriodicalIF":2.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143037512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Revolutionizing acute myeloid leukemia treatment: a systematic review of immune-based therapies.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-26 DOI: 10.1007/s12672-025-01797-9
Ugochi Ebinama, Binsah George
{"title":"Revolutionizing acute myeloid leukemia treatment: a systematic review of immune-based therapies.","authors":"Ugochi Ebinama, Binsah George","doi":"10.1007/s12672-025-01797-9","DOIUrl":"10.1007/s12672-025-01797-9","url":null,"abstract":"<p><p>The established protocol for the management of acute myeloid leukemia (AML) has traditionally involved the administration of induction chemotherapy, followed by consolidation chemotherapy, and subsequent allogeneic stem cell transplantation for eligible patients. However, the prognosis for individuals with relapsed and refractory AML remains unfavorable. In response to the necessity for more efficacious therapeutic modalities, targeted immunotherapy has emerged as a promising advancement in AML treatment. This comprehensive review article specifically examines classical unconjugated and toxin-conjugated monoclonal antibodies, which are currently in the preclinical phase or undergoing evaluation in clinical trials. The review delves into the proposed mechanisms through which these monoclonal antibodies elicit anti-tumor activity and identifies the challenges associated with designing targeted immunotherapy. The review focuses on targeting specific antigens in AML, including FLT3/CD125, CLL-1, CD33, CD38, CD47, CD70, and CD123.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"89"},"PeriodicalIF":2.8,"publicationDate":"2025-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143037515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies.
IF 2.8 4区 医学
Discover. Oncology Pub Date : 2025-01-25 DOI: 10.1007/s12672-025-01836-5
Alireza Maleki, Mohammad Mahdi Mirza Ali Mohammadi, Shahab Gholizadeh, Behnaz Dalvandi, Mohammad Rahimi, Aidin Tarokhian
{"title":"Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies.","authors":"Alireza Maleki, Mohammad Mahdi Mirza Ali Mohammadi, Shahab Gholizadeh, Behnaz Dalvandi, Mohammad Rahimi, Aidin Tarokhian","doi":"10.1007/s12672-025-01836-5","DOIUrl":"10.1007/s12672-025-01836-5","url":null,"abstract":"<p><strong>Purpose: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusion: </strong>Machine learning models, such as the Naive Bayes classifier developed in this study, can accurately stratify cancer risk in patients with positive paraneoplastic autoantibodies.</p>","PeriodicalId":11148,"journal":{"name":"Discover. Oncology","volume":"16 1","pages":"87"},"PeriodicalIF":2.8,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11762019/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143037514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信