Abstract
Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL). A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models. After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83–0.89), 0.81 (0.76–0.85), 0.82 (0.78–0.85), and 0.77 (0.73–0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors. Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.
Similar content being viewed by others
Availability of data and materials
All data and materials are available.
References
Kachkoul R, Touimi GB, El Mouhri G et al (2023) Urolithiasis: history, epidemiology, aetiologic factors and management. Malays J Pathol 45(3):333–352
Tan S, Yuan D, Su H et al (2024) Prevalence of urolithiasis in China: a systematic review and meta-analysis. BJU Int 133(1):34–43. https://doi.org/10.1111/bju.16179
Zeng G, Mai Z, Xia S et al (2017) Prevalence of kidney stones in China: an ultrasonography based cross-sectional study. BJU Int 120(1):109–116. https://doi.org/10.1111/bju.13828
Ordon M, Andonian S, Blew B et al (2015) CUA Guideline: management of ureteral calculi. Can Urol Assoc J 9(11–12):E837–E851. https://doi.org/10.5489/cuaj.3483
Corbo J, Wang J (2019) Kidney and ureteral stones. Emerg Med Clin North Am 37(4):637–648. https://doi.org/10.1016/j.emc.2019.07.004
Antonelli JA, Maalouf NM, Pearle MS et al (2014) Use of the National Health and Nutrition Examination Survey to calculate the impact of obesity and diabetes on cost and prevalence of urolithiasis in 2030. Eur Urol 66(4):724–729. https://doi.org/10.1016/j.eururo.2014.06.036
Fontenelle LF, Sarti TD (2019) Kidney stones: treatment and prevention. Am Fam Physician 99(8):490–496
Knoll T, Traxer O (2021) Urolithiasis: medical and surgical treatment. Eur Urol Focus 7(1):1–2. https://doi.org/10.1016/j.euf.2021.01.013
Xie F, Deng S, Fei K et al (2023) Nomogram to predict the risk of adverse outcomes in patients with residual stones following percutaneous nephrolithotomy. Int Braz J Urol 49(5):599–607. https://doi.org/10.1590/S1677-5538.IBJU.2023.0111
Mazzon G, Choong S, Celia A (2023) Stone-scoring systems for predicting complications in percutaneous nephrolithotomy: a systematic review of the literature. Asian J Urol 10(3):226–238. https://doi.org/10.1016/j.ajur.2023.01.005
Zhao H, Li W, Li J, et al (2022) Predicting the stone-free status of percutaneous nephrolithotomy with the machine learning system: comparative analysis with guy’s stone score and the S.T.O.N.E score system. Front Mol Biosci 9:880291. https://doi.org/10.3389/fmolb.2022.880291
Reuzé S, Schernberg A, Orlhac F et al (2018) Radiomics in nuclear medicine applied to radiation therapy: methods, pitfalls, and challenges. Int J Radiat Oncol Biol Phys 102(4):1117–1142. https://doi.org/10.1016/j.ijrobp.2018.05.022
Hatt M, Le Rest CC, Tixier F et al (2019) Radiomics: data are also images. J Nucl Med 60(Suppl 2):38S-44S. https://doi.org/10.2967/jnumed.118.220582
Chu G, Ji X, Wang Y et al (2023) Integrated multiomics analysis and machine learning refine molecular subtypes and prognosis for muscle-invasive urothelial cancer. Mol Ther Nucleic Acids 33:110–126. https://doi.org/10.1016/j.omtn.2023.06.001
Suarez-Ibarrola R, Hein S, Reis G et al (2020) Current and future applications of machine and deep learning in urology: a review of the literature on urolithiasis, renal cell carcinoma, and bladder and prostate cancer. World J Urol 38(10):2329–2347. https://doi.org/10.1007/s00345-019-03000-5
Gurbani S, Morgan D, Jog V et al (2021) Evaluation of radiomics and machine learning in identification of aggressive tumor features in renal cell carcinoma (RCC). Abdom Radiol (NY) 46(9):4278–4288. https://doi.org/10.1007/s00261-021-03083-y
Wang YD, Huang CP, Yang YR et al (2023) Machine learning and radiomics of bone scintigraphy: their role in predicting recurrence of localized or locally advanced prostate cancer. Diagnostics (Basel) 13(21):3380. https://doi.org/10.3390/diagnostics13213380
De Perrot T, Hofmeister J, Burgermeister S et al (2019) Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning. Eur Radiol 29(9):4776–4782. https://doi.org/10.1007/s00330-019-6004-7
Zheng J, Yu H, Batur J et al (2021) A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning. Kidney Int 100(4):870–880. https://doi.org/10.1016/j.kint.2021.05.031
Tatanis V, Cracco CM, Liatsikos E (2023) Advances in percutaneous renal puncture: a comprehensive review of the literature. Curr Opin Urol 33(2):116–121. https://doi.org/10.1097/MOU.0000000000001059
de la Rosette J, Assimos D, Desai M et al (2011) The Clinical Research Office of the Endourological Society Percutaneous Nephrolithotomy Global Study: indications, complications, and outcomes in 5803 patients. J Endourol 25(1):11–17. https://doi.org/10.1089/end.2010.0424
Karani R, Arada RB, Okhunov Z et al (2021) Endoscopic guided percutaneous nephrolithotomy. J Endourol 35(S2):S62–S67. https://doi.org/10.1089/end.2020.0556
Grosso AA, Sessa F, Campi R et al (2021) Intraoperative and postoperative surgical complications after ureteroscopy, retrograde intrarenal surgery, and percutaneous nephrolithotomy: a systematic review. Minerva Urol Nephrol 73(3):309–332. https://doi.org/10.23736/S2724-6051.21.04294-4
Singla A, Khattar N, Nayyar R, et al (2017) How practical is the application of percutaneous nephrolithotomy scoring systems? Prospective study comparing Guy’s Stone Score, S.T.O.N.E. score and the Clinical Research Office of the Endourological Society (CROES) nomogram. Arab J Urol 15(1):7–16. https://doi.org/10.1016/j.aju.2016.11.005
Yarimoglu S, Bozkurt IH, Aydogdu O et al (2017) External validation and comparisons of the scoring systems for predicting percutaneous nephrolithotomy outcomes: a single center experience with 506 cases. J Laparoendosc Adv Surg Tech A 27(12):1284–1289. https://doi.org/10.1089/lap.2017.0355
Yarimoglu S, Bozkurt IH, Aydogdu O, et al (2017) External validation and comparison of the scoring systems (S.T.O.N.E, GUY, CROES, S-ReSC) for predicting percutaneous nephrolithotomy outcomes for staghorn stones: a single center experience with 160 cases. Kaohsiung J Med Sci 33(10):516–522. https://doi.org/10.1016/j.kjms.2017.06.017
Kaviani P, Primak A, Bizzo B et al (2023) Performance of threshold-based stone segmentation and radiomics for determining the composition of kidney stones from single-energy CT. Jpn J Radiol 41(2):194–200. https://doi.org/10.1007/s11604-022-01349-z
Zheng J, Zhang J, Cai J et al (2023) Development of a radiomics model to discriminate ammonium urate stones from uric acid stones in vivo: a remedy for the diagnostic pitfall of dual-energy computed tomography. Chin Med J (Engl). https://doi.org/10.1097/CM9.0000000000002866
Zhang H, Li Q, Li S et al (2019) A radiomic approach to differential diagnosis of renal cell carcinoma in patients with hydronephrosis and renal calculi. Nan Fang Yi Ke Da Xue Xue Bao 39(5):547–553. https://doi.org/10.12122/j.issn.1673-4254.2019.05.08
Aminsharifi A, Irani D, Tayebi S et al (2020) Predicting the postoperative outcome of percutaneous nephrolithotomy with machine learning system: software validation and comparative analysis with guy’s stone score and the CROES nomogram. J Endourol 34(6):692–699. https://doi.org/10.1089/end.2019.0475
Xun Y, Chen M, Liang P et al (2020) A novel clinical-radiomics model pre-operatively predicted the stone-free rate of flexible ureteroscopy strategy in kidney stone patients. Front Med (Lausanne) 7:576925. https://doi.org/10.3389/fmed.2020.576925
Wang Z, Yang G, Wang X, et al (2023) A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy. Urolithiasis 51(1):37. https://doi.org/10.1007/s00240-023-01405-x
Funding
This research was funded by the National Natural Science Foundation of China (Nos. 82260598, 81560420).
Author information
Authors and Affiliations
Contributions
XCZ designed this experiment, collected and organized data, and wrote the article. CWL and CHC collected the data and revised the article. RMY and MNJ participated in data compilation. TZ was responsible for capital acquisition, supervision and resources. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
All authors declared no competing interests.
Ethics approval and consent to participate
This study and its associated projects were approved by the Ethics Committee of the Second Affiliated Hospital of Nanchang University, and the requirement for informed consent was waived by the same Ethics Committee. All experiments were performed in accordance with relevant guidelines and regulations.
Consent for publication
All authors have read and agreed to submit this manuscript for publication.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zou, X.C., Luo, C.W., Yuan, R.M. et al. Develop a radiomics-based machine learning model to predict the stone-free rate post-percutaneous nephrolithotomy. Urolithiasis 52, 64 (2024). https://doi.org/10.1007/s00240-024-01562-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00240-024-01562-7