2026-10-11T22:10:19Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33815370 2026-09-15T18:06:25Z category_7 category_13 category_15 category_45 category_734 category_931 category_64 portal_63 item_type_3 month_year_09_2026

Salivary Glycoprofiling via a Machine Learning-Augmented Lectin Microarray for Noninvasive Risk Stratification of Lung Cancer Fan Zhang (46132) Zhen Tang (2977569) Haoqi Du (6939434) Biyue Ma (24950688) Xia Liu (117318) Ziyi Chang (14118450) Zeyu Zhao (3222273) Xinyu Zhang (14029) Jinying Wang (2038141) Changchang Zhang (4740444) Boyu Wei (12704939) Jian Shu (1422517) Chen Zhang (66790) Mingwei Chen (1668166) Hailong Xie (500553) Zheng Li (26302) Medicine Genetics Neuroscience Sociology Biological Sciences not elsewhere classified Information Systems not elsewhere classified Cancer prospective multicenter validation noninvasive risk stratification logistic regression models internal validation sets distinguish pulmonary disease benign pulmonary disease independent test cohort four lectin signals 36 %, 94 00 %, respectively salivary glycoprofiling via 307 participants using augmented lectin microarray lc risk stratification 831 – 0 lectin microarray development cohort 44 %, salivary glycopatterns 80 participants 227 participants separate nom resulting nom profiled saliva prespecified cutoff machine learning lung cancer five task findings support closely associated clinical variables auxiliary tool 976 ); Although aberrant glycosylation is closely associated with lung cancer (LC), salivary glycopatterns and their discriminatory value across healthy individuals, benign pulmonary disease, and LC remain insufficiently characterized. We profiled saliva from 307 participants using a lectin microarray, comprising a development cohort of 227 participants and an independent test cohort of 80 participants. Five task-specific LASSO-logistic regression models were constructed to distinguish pulmonary disease, LC, and LC subtypes. A separate Nom-LC model combined consensus lectin features selected by LASSO and support vector machine recursive feature elimination with clinical variables. Salivary glycopatterns differed among healthy volunteers, benign pulmonary disease, and LC groups, and the five task-specific models showed discriminatory performance across pulmonary disease, LC, and exploratory subtype classification tasks. The resulting Nom-LC model incorporated smoking history and four lectin signals (HHL, PNA, RCA120, and PWM), yielding AUCs of 0.908 and 0.907 in the training and internal validation sets. In the independent test cohort, the AUC was 0.903 (95% CI, 0.831–0.976); at the prespecified cutoff, sensitivity, specificity, and accuracy were 86.36%, 94.44%, and 90.00%, respectively. These findings support further evaluation of salivary glycopatterns as an auxiliary tool for LC risk stratification, but prospective multicenter validation is required. 2026-09-15T00:00:00Z Dataset Dataset 10.1021/acs.jproteome.6c00376.s002 https://figshare.com/articles/dataset/Salivary_Glycoprofiling_via_a_Machine_Learning-Augmented_Lectin_Microarray_for_Noninvasive_Risk_Stratification_of_Lung_Cancer/33815370 CC BY-NC 4.0