Lipidomic analysis coupled with machine learning identifies unique urinary lipid signatures in patients with interstitial cystitis/bladder pain syndrome

被引：0

作者：

Takuya Iwaki ^{[1
]}

Makoto Kurano ^{[2
]}

Masahiko Sumitani ^{[3
]}

Aya Niimi ^{[4
]}

Akira Nomiya ^{[1
]}

Jun Kamei ^{[5
]}

Satoru Taguchi ^{[1
]}

Yuta Yamada ^{[1
]}

Yusuke Sato ^{[1
]}

Masaki Nakamura ^{[1
]}

Daisuke Yamada ^{[6
]}

Tomonori Minagawa ^{[7
]}

Hiroshi Fukuhara ^{[1
]}

Haruki Kume ^{[8
]}

Yukio Homma ^{[9
]}

Yoshiyuki Akiyama ^{[1
]}

机构：

[1] Department of Urology, Graduate School of Medicine, The University of Tokyo, Tokyo

[2] Department of Urology, Chiba Tokushukai Hospital, Chiba

[3] Department of Clinical Laboratory Medicine, The University of Tokyo, Tokyo

[4] Department of Pain and Palliative Medicine, The University of Tokyo Hospital, Tokyo

[5] Department of Urology, Japan Organization of Occupational Health and Safety, Kanto Rosai Hospital, Kanagawa

[6] Department of Urology, Tokyo Metropolitan Tama Medical Center, Tokyo

[7] Department of Urology, NTT Medical Center Tokyo, Tokyo

[8] Department of Urology, Shinshu University School of Medicine, Nagano

[9] Department of Urology, Kyorin University School of Medicine, Tokyo

[10] Department of Interstitial Cystitis Medicine, Kyorin University School of Medicine, Tokyo

来源：

World Journal of Urology | / 43卷 / 1期

基金：

日本学术振兴会;

关键词：

Biomarker; Bladder pain syndrome; Hunner; IC; IC/BPS; Interstitial cystitis; Learning; Lipidomics; Machine; Urinary;

D O I：

10.1007/s00345-025-05628-y

中图分类号：

学科分类号：

摘要：

Purpose: To identify biomarkers for diagnosis and classification of interstitial cystitis/bladder pain syndrome (IC/BPS) by urinary lipidomics coupled with machine learning. Methods: Urine samples from 138 patients with IC/BPS, including 116 with Hunner lesion (HL) and 22 with no HL, and 71 controls were assessed by lipid chromatography-tandem mass spectrometry. Single and paired lipid analyses of differentially expressed lipids in each group were conducted to assess their diagnostic ability. Machine learning models were constructed based on the identified urinary lipids and patient demographic data, and a five-fold cross-validation method was applied for internal validation. Levels of urinary lipids were adjusted to account for urinary creatinine levels. Results: A total of 218 urinary lipids were identified. Single lipid analysis revealed that urinary levels of C24 ceramide and LPC (14:0) distinguished HL and no HL, with an area under the receiver operating characteristics curve of 0.792 and 0.656, respectively. Paired lipid analysis revealed that summed urinary levels of C24 ceramide and LPI (18:3), and subtraction of PG (36:5) from PC (38:2) distinguished HL and no HL even more accurately, with an area under the curve of 0.805 and 0.752, respectively. A machine learning model distinguished HL and no HL, with the highest area under the curve being 0.873 and 0.750, respectively. Limitations include the opaque black box nature of machine learning techniques. Conclusions: Urinary levels of C24 ceramide, along with those of C24 ceramide plus LPI (18:3), could be potential biomarkers for HL. Machine learning-coupled urinary lipidomics may play an important role in the next-generation AI- driven diagnostic systems for IC/BPS. © The Author(s) 2025.

引用

共 26 条

[11]

Choi R.H., Tatum S.M., Symons J.D., Et al., Ceramides and other sphingolipids as drivers of cardiovascular disease, Nat Rev Cardiol, 18, pp. 701-711, (2021)

[12]

Vandanmagsar B., Youm Y.H., Ravussin A., Et al., The NLRP3 inflammasome instigates obesity-induced inflammation and insulin resistance, Nat Med, 17, pp. 179-188, (2011)

[13]

Serhan C.N., Chiang N., Van Dyke T.E., Resolving inflammation: dual anti-inflammatory and pro-resolution lipid mediators, Nat Rev Immunol, 8, pp. 349-361, (2008)

[14]

Sugimoto N., Morita Y., Sakai E., Et al., Modulations of urinary lipid mediators in acute bladder cystitis, Prostaglandins Other Lipid Mediat, 164, (2023)

[15]

Han X., The emerging role of lipidomics in prediction of diseases, Nat Rev Endocrinol, 18, pp. 335-336, (2022)

[16]

O'Leary M.P., Sant G.R., Fowler F.J., Et al., The interstitial cystitis symptom index and problem index, Urology, 49, pp. 58-63, (1997)

[17]

Fluss R., Faraggi D., Reiser B., Estimation of the Youden index and its associated cutoff point, Biom J, 47, pp. 458-472, (2005)

[18]

Chen T., Guestrin C., Xgboost: A scalable tree boosting system, Presented at the Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794, (2016)

[19]

Sokolova M., Lapalme G., A systematic analysis of performance measures for classification tasks, Inf Process Manag, 45, pp. 427-437, (2009)

[20]

Pedregosa F., Varoquaux G., Gramfort A., Et al., Scikit-learn: machine learning in Python, J Mach Learn Res, 12, pp. 2825-2830, (2011)

← 1 2 3 →