Combination of urinary biomarkers and machine-learning models provided a higher predictive accuracy to predict long-term treatment outcomes of patients with interstitial cystitis/bladder pain syndrome
Tóm tắt
To identify predictive factors for satisfactory treatment outcome of the patients with IC/BPS using urine biomarkers and machine-learning models. The IC/BPS patients were prospectively enrolled and provide urine samples. The targeted analytes included inflammatory cytokines, neurotrophins, and oxidative stress biomarkers. The patients with overall subjective symptom improvement of ≥ 50% were considered to have satisfactory results. Binary logistic regression, receiver-operating characteristic (ROC) curve, machine-learning decision tree, and random forest models were used to analyze urinary biomarkers to predict satisfactory results. Altogether, 57.4% of the 291 IC/BPS patients obtained satisfactory results. The patients with satisfactory results had lower levels of baseline urinary inflammatory cytokines and oxidative biomarkers than patients without satisfying results, including interleukin-6, monocyte chemoattractant protein-1 (MCP-1), C–X–C motif chemokine 10 (CXCL10), oxidative stress biomarkers 8-hydroxy-2'-deoxyguanosine (8-OHDG), 8-isoprostane, and total antioxidant capacity (TAC). Logistic regression and multivariable analysis revealed that lower levels of urinary CXCL10, MCP-1, 8-OHDG, and 8-isoprostane were independent factors. The ROC curve revealed that MCP-1 level had best area under curve (AUC: 0.797). In machine-learning decision tree model, combination of urinary C–C motif chemokine 5, 8-isoprostane, TAC, MCP-1, and 8-OHDG could predict satisfactory results (accuracy: 0.81). The random forest model revealed that urinary 8-isoprostance, MCP-1, and 8-OHDG levels had the most important influence on accuracy. Machine learning decision tree model provided a higher accuracy for predicting treatment outcome of patients with IC/BPS than logistic regression, and levels of 8-isoprostance, MCP-1, and 8-OHDG had the most important influence on accuracy.
Từ khóa
Tài liệu tham khảo
Hanno PM, Erickson D, Moldwin R, Faraday MM, American Urological A (2015) Diagnosis and treatment of interstitial cystitis/bladder pain syndrome: AUA guideline amendment. J Urol 193:1545–1553. https://doi.org/10.1016/j.juro.2015.01.086
Di XP, Luo DY, Jin X, Zhao WY, Li H, Wang KJ (2021) Efficacy and safety comparison of pharmacotherapies for interstitial cystitis and bladder pain syndrome: a systematic review and Bayesian network meta-analysis. Int Urogynecol J 32:1129–1141. https://doi.org/10.1007/s00192-020-04659-w
Jhang JF, Hsu YH, Jiang YH, Ho HC, Kuo HC (2021) Clinical relevance of bladder histopathological findings and their impact on treatment outcomes among patients with interstitial cystitis/bladder pain syndrome: an investigation of the European Society for the study of interstitial cystitis histopathological classification. J Urol 205:226–235. https://doi.org/10.1097/JU.0000000000001334
Yu WR, Jhang JF, Ho HC, Jiang YH, Lee CL, Hsu YH, Kuo HC (2021) Cystoscopic hydrodistention characteristics provide clinical and long-term prognostic features of interstitial cystitis after treatment. Sci Rep 11:455. https://doi.org/10.1038/s41598-020-80252-x
Siddiqui NY, Helfand BT, Andreev VP et al (2019) Biomarkers implicated in lower urinary tract symptoms: systematic review and pathway analyses. J Urol 202:880–889. https://doi.org/10.1097/JU.0000000000000257
Akiyama Y (2021) Biomarkers in interstitial cystitis/bladder pain syndrome with and without Hunner lesion: a review and future perspectives. Diagnostics (Basel). https://doi.org/10.3390/diagnostics11122238
Jiang YH, Jhang JF, Hsu YH, Ho HC, Wu YH, Kuo HC (2021) Urine biomarkers in ESSIC type 2 interstitial cystitis/bladder pain syndrome and overactive bladder with developing a novel diagnostic algorithm. Sci Rep 11:914. https://doi.org/10.1038/s41598-020-80131-5
Jiang YH, Kuo YC, Jhang JF, Lee CL, Hsu YH, Ho HC, Kuo HC (2020) Repeated intravesical injections of platelet-rich plasma improve symptoms and alter urinary functional proteins in patients with refractory interstitial cystitis. Sci Rep 10:15218. https://doi.org/10.1038/s41598-020-72292-0
Xiao J, Mo M, Wang Z, Zhou C, Shen J, Yuan J, He Y, Zheng Y (2022) The application and comparison of machine learning models for the prediction of breast cancer prognosis: retrospective cohort study. JMIR Med Inform 10:e33440. https://doi.org/10.2196/33440
Jiang YH, Jhang JF, Ho HC, Hsu YH, Kuo HC (2022) Diagnostic and prognostic value of urine biomarkers among women with dysfunctional voiding. Sci Rep 12:6608. https://doi.org/10.1038/s41598-022-10696-w
Jiang YH, Jhang JF, Hsu YH, Ho HC, Wu YH, Kuo HC (2020) Urine cytokines as biomarkers for diagnosing interstitial cystitis/bladder pain syndrome and mapping its clinical characteristics. Am J Physiol Renal Physiol 318:F1391–F1399. https://doi.org/10.1152/ajprenal.00051.2020
Akiyama Y, Hanno P (2019) Phenotyping of interstitial cystitis/bladder pain syndrome. Int J Urol 26(Suppl 1):17–19. https://doi.org/10.1111/iju.13969
Clemens JQ, Erickson DR, Varela NP, Lai HH (2022) Diagnosis and treatment of interstitial cystitis/bladder pain syndrome. J Urol 208:34–42. https://doi.org/10.1097/JU.0000000000002756
Ranganathan P, Pramesh CS, Aggarwal R (2017) Common pitfalls in statistical analysis: logistic regression. Perspect Clin Res 8:148–151. https://doi.org/10.4103/picr.PICR_87_17
Zorman M, Stiglic MM, Kokol P, Malcic I (1997) The limitations of decision trees and automatic learning in real world medical decision making. J Med Syst 21:403–415. https://doi.org/10.1023/a:1022876330390