120017
论文已发表
注册即可获取德孚的最新动态
IF 收录期刊
- 3.6 Breast Cancer (Dove Med Press)
- 4.3 Clin Epidemiol
- 2.6 Cancer Manag Res
- 3.2 Infect Drug Resist
- 4.1 Clin Interv Aging
- 6.1 Drug Des Dev Ther
- 4.1 Int J Chronic Obstr
- 8.7 Int J Nanomed
- 2.5 Int J Women's Health
- 3.2 Neuropsych Dis Treat
- 2.4 OncoTargets Ther
- 2.6 Patient Prefer Adher
- 2.6 Ther Clin Risk Manag
- 3.1 J Pain Res
- 3.5 Diabet Metab Synd Ob
- 4.5 Psychol Res Behav Ma
- 3.4 Nat Sci Sleep
- 2.4 Pharmgenomics Pers Med
- 2.6 Risk Manag Healthc Policy
- 4.6 J Inflamm Res
- 2.3 Int J Gen Med
- 3.9 J Hepatocell Carcinoma
- 3.3 J Asthma Allergy
- 2.5 Clin Cosmet Investig Dermatol
- 3.0 J Multidiscip Healthc
已发表论文
基于机器学习识别成人 1 型糖尿病患者的血清代谢特征
Authors Wang C , Lan Y, Zhao M, Zhu J, Tan H, Li X, Ding Y, Zheng X, Liu S, Gu Z
Received 30 September 2025
Accepted for publication 13 January 2026
Published 3 February 2026 Volume 2026:19 569281
DOI https://doi.org/10.2147/DMSO.S569281
Checked for plagiarism Yes
Review by Single anonymous peer review
Peer reviewer comments 2
Editor who approved publication: Dr Pablo Corral
Chaofan Wang,1,* Yuhe Lan,2,* Minzhe Zhao,3 Jiangyu Zhu,3 Huiling Tan,3 Xingyu Li,3 Yu Ding,3 Xueying Zheng,3 Sihua Liu,4 Zhaohe Gu3
1Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Diabetology, Guangzhou, Guangdong, 510630, People’s Republic of China; 2Huiqiao Medical Center, Southern Medical University Nanfang Hospital, Guangzhou, Guangdong, 510515, People’s Republic of China; 3Department of Endocrinology, Institute of Endocrine and Metabolic Diseases, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, Clinical Research Hospital of Chinese Academy of Sciences (Hefei), University of Science and Technology of China, Hefei, Anhui, 230001, People’s Republic of China; 4Department of Epidemiology and Biostatistics, School of Public Health, Anhui Medical University, Hefei, Anhui, 231200, People’s Republic of China
*These authors contributed equally to this work
Correspondence: Zhaohe Gu, Email guzhaohe@mail.ustc.edu.cn Sihua Liu, Email 2546010056@stu.ahmu.edu.cn
Background: Metabolomic profiling via machine learning can reveal signatures of host metabolism and identify useful biomarkers. We aimed to investigate metabolomic profiles and biomarkers in adult patients with type 1 diabetes (T1D) via machine learning.
Methods: We recruited 29 adult patients with T1D and matched them with 29 healthy controls on the basis of age, sex, and body mass index (BMI). We collected serum samples from both groups and performed nontargeted metabolomics with liquid chromatography‒mass spectrometry (LC‒MS). Four machine learning algorithms (logistic regression, support vector machine, Gaussian naive Bayes, and random forest) were used to screen potential T1D-related biomarkers.
Results: We identified 328 differently abundant metabolites between the T1D group and the control group that were significantly enriched in three metabolic pathways (purine metabolism, ketone body synthesis and degradation, and methyl butyrate metabolism), with P values less than 0.05. Ten metabolites were identified as T1D-related indicators, including L-fucopyranose, hept-2-ulose, L-rhamnose, docosahexaenoic acid, pumiliotoxin 251d, 9,12-octadecadienal, oleamide, estrane, (e,e)-2,4-heptadienal, and hexadecanamide. The predictive value of the ten candidate metabolites, as measured by the area under the curve (AUC), ranged from 0.86 to 0.95.
Conclusion: In this study, we identified purine metabolism, synthesis and degradation of ketone bodies, and impaired methyl butyrate metabolism as metabolic pathways that are altered in adult patients with T1D. Our findings present an extensive profile of metabolic changes in adult patients with T1D, and the identified biomarkers may have important clinical significance in the diagnosis of T1D and the monitoring of responses to therapeutic interventions.
Keywords: biomarkers, type 1 diabetes mellitus, machine learning, metabolic disorders, metabolomic
1Department of Endocrinology and Metabolism, The Third Affiliated Hospital of Sun Yat-Sen University, Guangdong Provincial Key Laboratory of Diabetology, Guangzhou, Guangdong, 510630, People’s Republic of China; 2Huiqiao Medical Center, Southern Medical University Nanfang Hospital, Guangzhou, Guangdong, 510515, People’s Republic of China; 3Department of Endocrinology, Institute of Endocrine and Metabolic Diseases, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, Clinical Research Hospital of Chinese Academy of Sciences (Hefei), University of Science and Technology of China, Hefei, Anhui, 230001, People’s Republic of China; 4Department of Epidemiology and Biostatistics, School of Public Health, Anhui Medical University, Hefei, Anhui, 231200, People’s Republic of China
*These authors contributed equally to this work
Correspondence: Zhaohe Gu, Email guzhaohe@mail.ustc.edu.cn Sihua Liu, Email 2546010056@stu.ahmu.edu.cn
Background: Metabolomic profiling via machine learning can reveal signatures of host metabolism and identify useful biomarkers. We aimed to investigate metabolomic profiles and biomarkers in adult patients with type 1 diabetes (T1D) via machine learning.
Methods: We recruited 29 adult patients with T1D and matched them with 29 healthy controls on the basis of age, sex, and body mass index (BMI). We collected serum samples from both groups and performed nontargeted metabolomics with liquid chromatography‒mass spectrometry (LC‒MS). Four machine learning algorithms (logistic regression, support vector machine, Gaussian naive Bayes, and random forest) were used to screen potential T1D-related biomarkers.
Results: We identified 328 differently abundant metabolites between the T1D group and the control group that were significantly enriched in three metabolic pathways (purine metabolism, ketone body synthesis and degradation, and methyl butyrate metabolism), with P values less than 0.05. Ten metabolites were identified as T1D-related indicators, including L-fucopyranose, hept-2-ulose, L-rhamnose, docosahexaenoic acid, pumiliotoxin 251d, 9,12-octadecadienal, oleamide, estrane, (e,e)-2,4-heptadienal, and hexadecanamide. The predictive value of the ten candidate metabolites, as measured by the area under the curve (AUC), ranged from 0.86 to 0.95.
Conclusion: In this study, we identified purine metabolism, synthesis and degradation of ketone bodies, and impaired methyl butyrate metabolism as metabolic pathways that are altered in adult patients with T1D. Our findings present an extensive profile of metabolic changes in adult patients with T1D, and the identified biomarkers may have important clinical significance in the diagnosis of T1D and the monitoring of responses to therapeutic interventions.
Keywords: biomarkers, type 1 diabetes mellitus, machine learning, metabolic disorders, metabolomic