Prediction of preoperative the Stone-Free rate in percutaneous nephrolithotomy based on CT clinical-radiomics nomogram: a comparative study with Guy’s stone score and S.T.O.N.E score.

Prediction of preoperative the Stone-Free rate in percutaneous nephrolithotomy based on CT clinical-radiomics nomogram: a comparative study with Guy’s stone score and S.T.O.N.E score. | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Prediction of preoperative the Stone-Free rate in percutaneous nephrolithotomy based on CT clinical-radiomics nomogram: a comparative study with Guy’s stone score and S.T.O.N.E score. Xin Chang Zou, Jianbiao Huang, Rong Man Yuan, Meng Ni Jin, Tao Zeng, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3767593/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Purpose : This study aimed to develop a clinical-radiomics nomogram by combining clinical factors and radiomics features.The objective of the nomogram was to predict the stone-free rate(SFR) in percutaneous nephrolithotomy (PCNL). Additionally, the predictive performance of the nomogram was compared with Guy's stone score (GSS) and S.T.O.N.E score. Patients and methods : A retrospective analysis was conducted on 109 suitable patients with solitary kidney stones who underwent PCNL at the Second Affiliated Hospital of Nanchang University from April 2021 to October 2022.The preoperative clinical data and non-contrast-enhanced CT images of all patients were collected.Radiomic features were extracted from the CT images after preprocessing steps such as wavelet transformation, logization, and resampling. The least absolute shrinkage and selection operator (LASSO) method was used to screen the radiomics features and calculate the radiomics score for each patient using lasso regression coefficient.Multivariate logistic regression analysis was performed to determine the clinical independent predictive factors. These factors were combined with radiomics to construct a clinical-radiomics model, which was visualized using a nomogram.The GSS and S.T.O.N.E score of each patient were calculated and analyzed. The predictive performance of the clinical-radiomics nomogram,Guy’s stone score (GSS),and S.T.O.N.E score was compared and analyzed through identification,calibration,and clinical benefit. Results : The postoperative statistics revealed a stone-free rate of 65.1%. The results from multivariate logistic regression analysis indicated that the number and diameter of stones were independent risk factors for residual stones after percutaneous nephrolithotomy (PCNL). In the training set, the clinical-radiomics nomogram, GSS and S.T.O.N.E score showed area under the receiver operating curve (ROC) values of 0.925, 0.772 and 0.712, respectively. In the validation set, the AUCs for the clinical-radiomics nomogram, GSS and S.T.O.N.E score were 0.944, 0.786 and 0.714, respectively.The Delong test demonstrated that the clinical-radiomics nomogram exhibited better discrimination ability than GSS and S.T.O.N.E score (p<0.05).The calibration curve and Hosmer-Lemeshow (HL) test confirmed the good calibration ability and fit of the clinical-radiomics nomogram.Furthermore, the decision curve analysis (DCA) revealed that the clinical-radiomics nomogram provided a better net benefit compared to GSS and S.T.O.N.E score. Conclusion :The clinical-radiomics nomogram constructed based on clinical characteristics and radiomics features can well predict the stone-free rate after PCNL, and its predictive performance is better than the GSS and S.T.O.N.E score. clinical-radiomics nomogram Guy’s stone score S.T.O.N.E score percutaneous nephrolithotomy stone-free rate Figures Figure 1 Figure 2 Figure 3 Introduction As one of the most common diseases in urology,the incidence and prevalence of kidney stones are gradually increasing around the world. In North America, the incidence rate can reach 7% to 13%. Men are more likely to suffer from the disease than women because of kidney stones.In acute cases, treatment is expensive [1- 2] .Currently,the main treatments for kidney stones include drug therapy,extracorporeal shock wave lithotripsy (ESWL),transureteroscopic lithotomy (flexible ureterolithotomy and rigid ureterolithotomy),percutaneous nephrolithotomy,etc [3- 4] .Due to its high stone-clearing rate and minimal invasiveness,PCNL has become one of the first-line therapies for the treatment of kidney stones,especially suitable for complex kidney stones such as stones ＞2cm in diameter, multiple stones,and cast stones [5- 6] . Although PCNL technology is constantly updated, the problem of residual stones is still inevitable [7] . Regarding the stone-free rate after PCNL for kidney stones, Guy’s stone score, S.T.O.N.E score,CROES nomogram and S-ReSC score are currently available.The GSS has been widely used due to its simplicity of operation.The S.T.O.N.E score is obtained through CT imaging.Stone characteristics, measuring maximum cross-sectional area (S),puncture channel length (T), degree of obstruction (O),involved renal calyces (N),stone density (E), including many stone characteristics,CROES nomogram uses quantitative impact Patients with kidney stones are scored based on clinical factors. The S-ReSC scoring system relies on the location of the stone to grade the complexity of the disease.Currently, the GSS and S.T.O.N.E score have received widespread attention,but the predictive effect has been controversial [8- 10] . Radiomics is the study of clinical diseases by quantitatively extracting high-throughput features from imaging images,combined with clinical factors,demographics, genomics or independently [11] . Radiomics was initially used in clinical research on urinary tumors. CT-based radiomics nomograms have been used in the prediction of survival rate of clear cell renal cell carcinoma and the identification of clear cell renal cell carcinoma and angiomyolipomas,which has demonstrated greater value [12- 13] .The successful application of radiomics in malignant tumors of the urinary system has led people to consider its value in benign diseases.The clinical-radiomics nomogram constructed by combining CT radiomics features and clinical features has been proven to be effective in preoperative prediction.The stone-free rate of flexible transurethral ureteroscopy. In addition,radiomics has also shown great value in the diagnosis of uric acid stones. Radiomics has indicated that it is better than traditional models in building prediction models [14- 16] . In this study,we combined clinically independent predictors and radiomics features to develop a clinical-radiomics nomogram that can be used to predict postoperative stone-free rate in PCNL and compared it with traditional GSS and S.T.O.N.E score Compare the prediction effects. Surgical Method Rigid ureteroscopy is routinely used to examine the bladder and ureter on the surgical side before surgery. Then the 5F ureteral catheter is inserted into the ureter on the surgical side,ascends 25-28cm,is fixed with the urethra,and is connected to the infusion set to form artificial hydronephrosis. Under the guidance of B-ultrasound, the renal calyx was punctured between the subscapular angle line and the posterior axillary line of the eleventh intercostal space on the operative side. After the needle core was pulled out and urine was detected,a renal puncture guidewire was inserted along the puncture needle sheath.Using the guide wire as a guide,use the F10 fascia dilator to gradually expand the channel to F18 in 2F steps,insert the F18 tearable sheath,and insert the nephroscope into the sheath. Once the stone location is determined, the holmium laser is used to crush the stones and remove the small stones by rushing.In all cases,the F6 double J tube was left in place for about 4 weeks after surgery. Patients And Methods Patients The Institutional Review Board approved this retrospective study and waived the requirement for patient informed consent. The clinical data and imaging images of all 109 patients with simple kidney stones who underwent PCNL at the Second Affiliated Hospital of Nanchang University from April 2021 to October 2022 were retrospectively collected.Inclusion criteria: (1) Kidney stones were confirmed by non-contrast-enhanced CT scan; (2) All underwent complete PCNL surgical treatment; (3) Clinical data and imaging data were completely preserved. Exclusion criteria: (1) Combined with malignant tumors of the urinary system on the same side; (2) Severe liver and kidney dysfunction or systemic coagulation insufficiency; (3) Severe atrophy of the ipsilateral kidney. Judgment criteria for stone clearance: no residual stones or stone fragments ＜4 mm were found in plain radiographs or CT scans of the urinary tract about 1 week after surgery.All patients were randomly divided into a training set of 76 cases and a validation set of 33 cases in a ratio of 7:3. Clinical data collected before surgery include gender, age, BMI,hypertension,diabetes,preoperative urine white blood cells, preoperative stone surgery history, etc.Stone characteristics, including stone diameter (maximum cross-sectional diameter),stone number, stone location,and stone characteristics,are recorded.CT value (maximum cross-sectional average CT value), etc.The stone system score was jointly calculated and entered by 2 urologists with more than 6 years of working experience based on the GSS and S.T.O.N.E score,using the patient‘s preoperative CT images and clinical data. CT image acquisition, stone area of interest segmentation and radiomic feature extraction CT equipment parameters: tube voltage is 80-140kV, tube current is 10-200ma, pitch is 1, rotation time is 0.5s, and layer thickness is 5mm. All CT images were collected using picture archiving and communication system (PACS) and stored in DICOM format.All DICOM files were imported into the open source software 3D slicer (version 5.50, http://download.slicer.org/),and Radiomics were constructed. Database, using a semi-automatic method (using software to automatically identify similar density stone tissue in CT, and then manually improving the ROI edge) to outline the stone ROI in all sections of the CT image (see Figure 1),and simultaneously outline the coronal,sagittal and transverse images.When outlining the stone outline, in order to distinguish the kidney, perirenal tissue, surrounding bone tissue, arterial calcification, etc.The relevant window width is manually set to 350Hu and the window level is 40Hu, making the ROI division more accurate; in order to reduce human error, all The patient’s stone ROI area was jointly outlined by a professional radiologist and two professional urologists, and was finally examined and corrected by a urologist with a senior professional title. Save the CT source file and the outlined ROI label in nrrd format, use the computer programming language tool Python (version 3.7), and extract the ROI region image group through the PyRadiomics language analysis package (https://pypi.org/project/pyradiomics/) learning characteristics. As a flexible open source software package, Pyradiomics has covered all current image texture analysis algorithms.It can use its specific open source professional modules to decode images in DICOM and extract a large number of quantitative features. Radiomic feature selection and signature construction The extracted radiomic features are normalized using the formula (X-Xmin)/(Xmax-Xmin), and the obtained value is between 0 and 1.The least absolute shrinkage and selection operator regression (Lasso) was used to screen the radiomic features most relevant to stone residue after PCNL,and Pearson correlation analysis was used to test feature correlation. Correlation coefficients ＞0.9 were considered to have multicollinearity. A radiomics formula was created by using the linear combination of the lasso regression coefficients of the selected features to calculate the radscore for each patient. Construction and visualization of clinical-radiomics model In the training set,clinical variables with statistical significance through univariate analysis were subjected to univariate logistic regression analysis,and multivariable logistic regression analysis was performed in combination with radscore to determine clinical independent predictive factors,and clinical independent predictive factors and radscore were combined.And use multi-factor logistic regression to build a clinical-radiomics model.To provide a visualization tool that can aid clinical decision-making,a clinical-radiomics nomogram was developed and the predictive performance of the nomogram was tested in a validation set. Model comparison The predictive performance of the clinical-radiomics nomogram and GSS and S.T.O.N.E score were compared by drawing ROC curves and Delong tests.DCA curves were drawn to evaluate the net benefits of the clinical-radiomics nomogram and GSS and S.T.O.N.E scores.A calibration curve was drawn to evaluate the prediction accuracy of the clinical-radiomics nomogram,and the Hosmer-Lemeshow (HL) test was performed to evaluate the goodness of fit of the clinical-radiomics nomogram. Statistical analysis SPSS 27.0,R language software (version 4.3.1, http://www.r-project.org/) or python language software (https://www.python/downloads/release/python-380/) were used to analyze and processe the data.All measurement data were expressed as mean ± standard deviation,and categorical variables were expressed as numbers (%). Single-factor analysis was used to compare the differences in clinical factors. Measurement data were measured using t test or Mann-Whitney U test,categorical variables use chi-square test or Fisher’s exact test, double test p＜0.05 is considered statistically significant, use the lars package of R language to perform lasso regression, use python’s matplotlib package to draw ROC curves and DCA decision curves. Results Clinical features A total of 109 patients were included in this study, of whom 71 had no residual stones and 38 had residual stones.The normality test showed that the age of the measurement data was normally distributed (Kolmogorov-smirnov test,two-sided p > 0.05),and the rest were non-normally distributed.Univariate analysis showed that there were significant differences in the number, location, diameter and CT value of stones between the two groups (p < 0.05) (Table 1 ). GSS and S.T.O.N.E score are shown in Table 1 . Table 1 Clinical features (%), ‾x ± S, M༈P25, P75༉ Factor Non-SF(n = 38) SF(n = 71) Z(t)/X 2 P Age, mean ± sd, (years) 55.45 ± 11.62 52.92 ± 13.20 0.994 0.323 Gender n(%) Male Female 23(60.5%) 15(39.5%) 45(63.4%) 26(36.6%) 0.086 0.769 BMI, mean ± sd, (kg/㎡) 23.27(20.62, 25.33) 23.32(21.48, 25.10) 0.134 0.894 Pre-stenting/nephrostomy n(%) NO Yes 37(97.4%) 1(2.6%) 67(94.4%) 4(5.6%) 0.510 0.475 History of stone sugery,n(%) no PCNL Other sugery 27(71.1%) 6(15.8%) 5(13.1%) 56(78.9%) 6(8.4%) 9(12.7%) 1.414 0.493 Pre-infection,n(%) - + ++ +++ 3(7.9%) 18(47.4%) 8(21.0%) 9(23.7%) 8(11.3%) 39(54.9%) 13(18.3%) 11(15.5%) 1.551 0.670 hypertension,n(%) No Yes 24(63.2%) 14(36.8%) 56(78.9%) 15(21.1%) 3.131 0.077 diabetes,n(%) No Yes 34(94.9%) 4(5.1%) 67(93.4%) 4(6.6%) 0.300 0.584 Stone laterality,n(%) Both Left Right 0(0.0%) 15(39.5%) 23(60.5%) 1(1.4%) 30(42.3%) 40(56.3%) 0.657 0.720 Stones number(piece) 5(4, 6) 3(2, 4) -5.007 ༜0.001 Stone location,n(%) Simple renel pelvis/ calyx Pelvis and calyx 5(13.2%) 33(86.8%) 30(42.3%) 41(57.7%) 9.612 0.002 Stone diameter(cm) 2.7(2.3, 3.8) 2.0(1.6, 2.5) -4.565 ༜0.001 Stone CT value(HU) 1213(1030, 1386) 1060(950, 1200) -2.929 0.003 Hydronephrosis,n(%) No Mild Moderate Severe 1(2.6%) 24(63.2%) 8(21.1%) 5(13.1%) 10(14.1%) 42(59.1%) 12(16.9%) 7(9.9%) 3.760 0.289 Experience of operator,n(%) PCNL༜100 PCNL༞100 11(28.9%) 27(71.1%) 10(14.1%) 61(85.9%) 3.515 0.061 GSS 3(2, 3) 2(2, 2) -5.063 ༜0.001 S.T.O.N.E 9(7, 9) 8(7, 8) -3.808 ༜0.001 Note: BMI: body mass index; non-PCNL procedures include transurethral ureteroscopy (rigid and flexible), open surgery, and extracorporeal shock wave lithotripsy Radiomic features selection and radiomic signature construction 1619 radiomic features were obtained from each stone ROI area, including 14 stone morphological features,270 first-order stone statistical features,and 360 Gray-Level Co-occurrence Matrix(GLCM) features describing entropy and texture information,240 Gray-Level Run-Length Matrix (GLRLM) features that reflect information such as ROI area granularity,and 240 Gray-Level Size Zone Matrix (GLSZM) features that describe relatively uniform,multi-dimensional information.75 Neighborhood GrayTone Difference Matrix (NGTDM) that quantify the difference between pixels and predefined pixels,and 420 Gray Level Dependence Matrix(GLDM) grayscale correlation matrices that describe the relationship between the central pixel and its neighbors and other information.Lasso regression screened out 9 radiomics features that were most relevant to the SFR after PCNL.The maximum value of Pearson’s correlation coefficient is less than 0.9,and there were no seriously related variables.The radscore of each patient was calculated through the linear combination of lasso regression coefficient and radiomics features. The radiomics score calculation formula is: Radscore = 0.031911768×exponential_ngtdm_Coarseness +(-0.021220610)×lbp-2D_firstorder_10Percentile + 0.878314468×logarithm_ngtdm_Busyness + 0.004262516×wavelet-HLH_glrlm_LongRunLowGrayLevelEmphasis + 0.314685233×wavelet-HHH_glszm_SizeZoneNonUniformity +(-0.077994374)×gradient_glcm_MCC + 0.050846883×lbp-2D_glszm_SmallAreaEmphasis +(-0.119795401)×wavelet-HLH_firstorder_Median + 0.034245990×wavelet-HHL_firstorder_Energy Clinical-radiomics model construction and visualization Univariate logistic regression analysis in the training set revealed that there were statistically significant differences in stone location, stone number,and stone diameter between SF and Non-SF(p༜0.05). Multivariate logistic regression analysis showed that the number of stones, the diameter of stones and radscore are clinically independent risk factors for SF and Non-SF(p༜0.05) in Table 2 .Combined with clinical independent risk factors and radscore,multi-factor logistic regression was used to construct a clinical-radiomics model,and a clinical-radiomics nomogram was developed to visualize the model ( Fig. 2 ). Table 2 Logistic regression analysis in the training set. characteristic Univariate logistic Multivariate logistic OR(95%CI) P OR(95%CI) P Stones number 0.537(0.368 ~ 0.764) 0.001 0.573(0.345 ~ 0.949) 0.031 Stone location Simple pelvis/calyx Pelvis and calyx Reference 0.251(0.075 ~ 0.837) 0.025 Reference 1.088(0.207, 5.712) 0.921 Stone diameter 0.182(0.073 ~ 0.452) ༜0.001 0.162(0.048 ~ 0.551) 0.004 Stone CT value 0.998(0.996 ~ 1.000) 0.110 Radscore ༜0.001(༜0.001 ~ 0.006) ༜0.001 ༜0.001(༜0.001 ~ 0.109) 0.013 model comparison In the training set, the AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E stone score were 0.925 and 0.772、0.712 respectively.In the validation set,the AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E stone score were 0.944 and 0.786、0.714 ,Fig. 2 for details.Delong test showed that the discriminative ability of clinical-radiomics nomogram was better than that of GSS and S.T.O.N.E stone score(p༜0.05).The DCA decision curve shows that at each threshold probability,the net benefit of the clinical-radiomics nomogram is better than that of the GSS and STONE stone score(Figure 3 ).When using the clinical-radiomics nomogram to decide whether to undergo PCNL treatment, it is better than all treatments and no treatment significantly increases returns.The calibration curve and Hosmer-Lemeshow (HL) test (p༞0.05) showed that the clinical-radiomics nomogram has good calibration ability and fit. Discussion PCNL is gradually becoming the mainstream method for the treatment of kidney stones due to its minimally invasive and high stone-free rate [17–18] . For most patients with kidney stones,PCNL can not only relieve pain,but also greatly help symptoms such as nausea, urinary discomfort, and mental distress.In addition,PCNL intervention has a tendency to improve renal function damaged by kidney stones before surgery [19–20] .Due to the different conditions of patients and the characteristics of stones,residual stones will still occur in PCNL. The number, size, and location of stones are considered to be related to the residual stones after PCNL.The remaining stones will significantly extend the hospitalization time and increase the number of secondary visit risks of surgery [21–22] .There have been a variety of scoring systems used to predict the stone-free rate of patients with kidney stones after PCNL.Guy’s stone score is used to comprehensively evaluate the number of stones,stone shape and anatomical distribution,and classifies kidney stone patients into Ⅰ-Ⅳ grades.The higher it is,the more complex the stones are,and the higher the risk of residual stones after PCNL [23] . The S.T.O.N.E score comprehensively evaluates the complexity of kidney stones by quantifying the maximum cross-sectional area of stones, stone density, degree of kidney damage and PCNL puncture channel,thereby predicting the postoperative outcomes of PCNL.In addition, the stone score relies on multi-center data to establish The CROES nomogram and the S-ReSC score,which focuses on the distribution of stones in the collecting system,also play a certain role in the stone-free rate after PCNL [24–25] .Although traditional stone scores have certain value in post-PCNL outcomes,they have shown shortcomings when compared with machine learning and artificial intelligence [26–27] .With the successful application of radiomics in renal cancer, prostate cancer, etc. people remain optimistic about its value in urinary tract stones. Radiomics has shown great value in the identification of urinary tract stones and prediction of treatment outcomes [16] .At the same time, radiomics also plays an auxiliary role in predicting the burden of kidney stones and the degree of kidney damage, and making decisions on treatment strategies [28] .Therefore,a comparative study of radiomics and traditional stone scoring systems in predicting postoperative outcomes of PCNL is meaningful and conditional. In our study, 9 radiomics features that were strongly correlated with whether stones remained after PCNL were screened, and the radiomics score was calculated based on the lasso regression coefficient and linear combination.Some studies have shown that a single strong risk factor may not be able to evaluate postoperative outcomes well, and prediction models built by combining multiple factors often have better prediction effects [29–30] .Therefore,we collected many clinical characteristics related to stone clearance rate after PCNL in previous studies, determined clinical independent risk factors through univariate and multivariate logistic regression analysis,and combined with radiomics scores to jointly construct a clinical-radiomics nomogram, and compare the prediction effect with GSS and S.T.O.N.E score.The AUC of the clinical-radiomics nomogram and the GSS 、S.T.O.N.E score in the training set were 0.925 and 0.772、0.712 respectively.The AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E score in the validation set were 0.944 and 0.786、0.714 respectively.In addition,the delong test and the DCA curve showed that the clinical-radiomics nomogram has better discrimination ability and clinical benefit. The current study has several limitations. First, this is a retrospective study and selection bias may still exist despite strict inclusion and exclusion criteria.Second, the included samples are relatively insufficient. Third,this study is based on single-center data,and multi-center prospective studies are needed to further validate the results. Conclusion The clinical-radiomics nomogram constructed in this study was compared with the traditional GSS and S.T.O.N.E score and showed that the clinical-radiomics nomogram can be more successful in predicting the stone clearance rate after PCNL. As a result, it can provide effective assistance for clinical decision-making before PCNL surgery. Declarations 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. Funding This research was funded by the National Natural Science Foundation of China（Nos.82260598,81560420）. Author contributions XCZ designed this experiment, collected and organized data, and wrote the article.JBH 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. Availability of data and materials All data and materials are available. Consent for publication All authors have read and agreed to submit this manuscript for publication. competing interests All authors declared no competing interests. References Stamatelou K,Goldfarb DS.Epidemiology of Kidney Stones. Healthcare (Basel).2023;11(3):424.doi:10.3390/healthcare11030424. Sorokin I,Mamoulakis C,Miyazawa K,et al.Epidemiology of stone disease across the world. World J Urol.2017;35(9):1301–1320.doi:10.1007/s00345-017-2008-6. D'Ambrosio V,Moochhala S,Unwin RJ,et al.Why is diagnosis, investigation,and improved management of kidney stone disease important?Non-pharmacological and pharmacological treatments for nephrolithiasis.Expert Rev Clin Pharmacol.2022;15(4):407–414.doi: 10.1080/17512433.2022.2082943. Tzelves L,Geraghty RM,Hughes T,et al.Innovations in Kidney Stone Removal.Res Rep Urol.2023;15:131–139.doi:10.2147/RRU.S386844. De Lorenzis E,Zanetti SP,Boeri L,et al.Is There Still a Place for Percutaneous Nephrolithotomy in Current Times?J Clin Med.2022;11(17):5157.doi:10.3390/jcm11175157. Grosso AA,Sessa F,Campi R,et al.Intraoperative and postoperative surgical complications after ureteroscopy,retrograde intrarenal surgery,and percutaneous nephrolithotomy:a systematic review.Minerva Urol Nephrol.2021;73(3):309–332.doi:10.23736/S2724-6051.21.04294-4. Kallidonis P,Tsaturyan A,Lattarulo M,et al.Minimally invasive percutaneous nephrolithotomy (PCNL):Techniques and outcomes. Turk J Urol.2020;46(Supp. 1):S58-S63.doi:10.5152/tud.2020.20161. Wu WJ,Okeke Z.Current clinical scoring systems of percutaneous nephrolithotomy outcomes.Nat Rev Urol.2017;14(8):459–469.doi:10.1038/nrurol.2017.71. Srivastava A,Yadav P,Madhavan K,et al.Inter-observer variability amongst surgeons and radiologists in assessment of Guy's Stone Score and S.T.O.N.E. nephrolithometry score:A prospective evaluation. Arab J Urol.2019;18(2):118–123.doi:10.1080/2090598X.2019.1703278. Singla A,Khattar N,Nayyar R,et al.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. 2017;15(1):7–16.doi:10.1016/j.aju.2016.11.005. Mayerhoefer ME,Materka A,Langs G,et al.Introduction to Radiomics.J Nucl Med.2020;61(4):488–495.doi:10.2967/jnumed.118.222893. Yan L,Yang G,Cui J,et al.Radiomics Analysis of Contrast-Enhanced CT Predicts Survival in Clear Cell Renal Cell Carcinoma.Front Oncol. 2021;11:671420.doi:10.3389/fonc.2021.671420. Ma Y,Ma W,Xu X,et al.A convention-radiomics CT nomogram for differentiating fat-poor angiomyolipoma from clear cell renal cell carcinoma.Sci Rep.2021;11(1):4644.doi:10.1038/s41598-021-84244-3. Xun Y,Chen M,Liang P,et al.A Novel Clinical-Radiomics Model Pre-operatively Predicted the Stone-Free Rate of Flexible Ureteroscopy Strategy in Kidney Stone Patients.Front Med (Lausanne).2020;7:576925.doi:10.3389/fmed.2020.576925. Wang Z,Yang G,Wang X,et al.A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy.Urolithiasis.2023;51(1):37.doi:10.1007/s00240-023-01405-x. Lim EJ,Castellani D,So WZ,et al.Radiomics in Urolithiasis: Systematic Review of Current Applications,Limitations,and Future Directions.J Clin Med.2022;11(17):5151.doi:10.3390/jcm11175151. Jiao B,Luo Z,Huang T,et al.A systematic review and meta-analysis of minimally invasive vs.standard percutaneous nephrolithotomy in the surgical management of renal stones.Exp Ther Med.2021;21(3):213.doi:10.3892/etm.2021.9645. Kamal W,Kallidonis P,Kyriazis I,et al.Minituriazed percutaneous nephrolithotomy:what does it mean?Urolithiasis.2016;44(3):195–201.doi:10.1007/s00240-016-0881-x. Gaur AS,Mandal S,Pandey A,et al.Efficacy of PCNL in the resolution of symptoms of nephrolithiasis.Urolithiasis.2022;50(4):487–491.doi:10.1007/s00240-022-01334-1. Reeves T,Pietropaolo A,Gadzhiev N,et al.Role of Endourological Procedures (PCNL and URS) on Renal Function:a Systematic Review. Curr Urol Rep.2020;21(5):21.doi: 10.1007/s11934-020-00973-4. Borofsky MS,Wollin DA,Reddy T,et al.Salvage Percutaneous Nephrolithotomy:Analysis of Outcomes following Initial Treatment Failure.J Urol. 2016;195(4Pt 1):977 − 81.doi:10.1016/j.juro.2015.10.176. Doizi S,Bensalah K,Lebacle C,et al.Complications en endo-urologie:urétéroscopie et néphrolithotomie percutanée [Complications in endourology:Ureteroscopy and percutaneous nephrolithotomy].Prog Urol.2022;32(14):966–976.French.doi:10.1016/j.purol.2022.09.002. Choi SW, Bae WJ, Ha US,et al.Prediction of stone-free status and complication rates after tubeless percutaneous nephrolithotomy: a comparative and retrospective study using three stone-scoring systems and preoperative parameters.World J Urol.2017;35(3):449–457.doi:10.1007/s00345-016-1891-6. Bibi M,Sellami A,Chaker K,et al.Les scores radiologiques peuvent-t-ils prédire le succès de la NLPC ?Étude comparative du Guy's stone score,du STONE score,du CROES nomogram,et du S-ReSc score [Do the nephrolithometry scoring systems predict the success of percutaneous nephrolithotomy.Comparison of 4 scores: The Guy's stone score,STONE Score,CROES nomogram and S-ReSC score].Prog Urol.2019;29(8–9):432–439.French.doi:10.1016/j.purol.2019.05.007. Al Adl AM,Mohey A,Abdel Aal A,et al.Percutaneous Nephrolithotomy Outcomes Based on S.T.O.N.E.,GUY, CROES,and S-ReSC Scoring Systems:The First Prospective Study. J Endourol. 2020;34(12):1223–1228.doi:10.1089/end.2019.0856. Zhao H,Li W,Li J,et al.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.2022;9:880291.doi:10.3389/fmolb.2022.880291. Nedbal C,Cerrato C,Jahrreiss V,et al.The role of 'artificial intelligence,machine learning,virtual reality,and radiomics' in PCNL:a review of publication trends over the last 30 years.Ther Adv Urol. 2023;15:17562872231196676.doi:10.1177/17562872231196676. Homayounieh F, Doda Khera R, Bizzo BC, et al.Prediction of burden and management of renal calculi from whole kidney radiomics:a multicenter study.Abdom Radiol(NY).2021;46(5):2097–2106.doi:10.1007/s00261-020-02865-0. Vickers AJ.Prediction models: revolutionary in principle,but do they do more good than harm?J Clin Oncol.2011;29(22):2951-2.doi:10.1200/JCO.2011.36.1329. Resorlu B, Unsal A, Gulec H, et al.A new scoring system for predicting stone-free rate after retrograde intrarenal surgery:the "resorlu-unsal stone score".Urology.2012;80(3):512-8.doi:10.1016/j.urology.2012.02.072. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3767593","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":263424773,"identity":"29a9e483-8938-49bd-b99d-b808230356da","order_by":0,"name":"Xin Chang Zou","email":"","orcid":"","institution":"Second Affiliated Hospital of Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"Chang","lastName":"Zou","suffix":""},{"id":263424774,"identity":"7f2f7437-0687-4e3f-8937-6a1ad6ae3a8f","order_by":1,"name":"Jianbiao Huang","email":"","orcid":"","institution":"Second Affiliated Hospital of Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Jianbiao","middleName":"","lastName":"Huang","suffix":""},{"id":263424775,"identity":"c1e4f4b2-fec3-48a5-b1f7-ce3495416c6f","order_by":2,"name":"Rong Man Yuan","email":"","orcid":"","institution":"Chengde Medical University","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"Man","lastName":"Yuan","suffix":""},{"id":263424776,"identity":"060930e7-a46b-43fd-a0f0-640232c9b436","order_by":3,"name":"Meng Ni Jin","email":"","orcid":"","institution":"Second Affiliated Hospital of Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"Ni","lastName":"Jin","suffix":""},{"id":263424777,"identity":"6f1667c1-aea4-4a2a-a325-6a5d1b07b50c","order_by":4,"name":"Tao Zeng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYBADZjb5h40PPjBIEFbKA6XZ+RmSDxvOIEULv2RDWpo0D161UGDPfvjwh487aqUNDpwxk7b5Y5HH38D88NENfLbwpCUYzjxz3NjgYI+xdW6bRLHEATZj4xy8DssxSOZtO5ZscJjH8HZug0RiwwEeNmm8WvjfGBz+23asfsMxHgNpiz8SifMJapHIMWxmbKthluxhS5JmYJNI3EBQy41nyYy9bQeY+SWYDxv2tkkkbjxMwC/s/cmHP/xsq2Nmk2BsfPDjT13ivOPNDx/j0wIFh5HYzISVg0AdccpGwSgYBaNgZAIAOOxLc2Irp0MAAAAASUVORK5CYII=","orcid":"","institution":"Second Affiliated Hospital of Nanchang University","correspondingAuthor":true,"prefix":"","firstName":"Tao","middleName":"","lastName":"Zeng","suffix":""},{"id":263424778,"identity":"8bc2528c-f0ae-4071-8bae-9d4196dde2af","order_by":5,"name":"Hai Chao Chao","email":"","orcid":"","institution":"Second Affiliated Hospital of Nanchang University","correspondingAuthor":false,"prefix":"","firstName":"Hai","middleName":"Chao","lastName":"Chao","suffix":""}],"badges":[],"createdAt":"2023-12-17 14:29:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3767593/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3767593/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":49076302,"identity":"36f75247-49e5-4a35-97d5-c23df02fa01e","added_by":"auto","created_at":"2024-01-02 18:37:41","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":65962,"visible":true,"origin":"","legend":"\u003cp\u003eStone ROI area delineation: original image (A), delineated image (B) and stone three-dimensional (C).\u003c/p\u003e","description":"","filename":"F1.png","url":"https://assets-eu.researchsquare.com/files/rs-3767593/v1/5c10aa8c62d0c56453529563.png"},{"id":49076303,"identity":"ad3a4022-f6cc-46ca-a068-72e5bbabdf23","added_by":"auto","created_at":"2024-01-02 18:37:41","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":91275,"visible":true,"origin":"","legend":"\u003cp\u003eA is the clinical-radiomics nomogram,B and C are the ROC curves of the training set and validation set respectively. D and E are the calibration curves of the training set and validation set of the clinical-radiomics nomogram\u003c/p\u003e","description":"","filename":"F2.png","url":"https://assets-eu.researchsquare.com/files/rs-3767593/v1/4468804e856f31e49f2dafaf.png"},{"id":49076304,"identity":"3bff329b-b93a-4f05-8053-c3d30c220c33","added_by":"auto","created_at":"2024-01-02 18:37:41","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":106392,"visible":true,"origin":"","legend":"\u003cp\u003eDCA decision curve of clinical-radiomics nomogram, GSS, and STONE stone score\u003c/p\u003e","description":"","filename":"F3.png","url":"https://assets-eu.researchsquare.com/files/rs-3767593/v1/2048c9c9451af72077e03b48.png"},{"id":60141712,"identity":"4092f320-6d15-454c-9407-cebcb35faa48","added_by":"auto","created_at":"2024-07-12 09:09:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":848517,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3767593/v1/11267e8c-b936-423b-be31-b0b6a63e66ef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of preoperative the Stone-Free rate in percutaneous nephrolithotomy based on CT clinical-radiomics nomogram: a comparative study with Guy’s stone score and S.T.O.N.E score.","fulltext":[{"header":"Introduction","content":"\u003cp\u003eAs one of the most common diseases in urology,the incidence and prevalence of kidney stones are gradually increasing around the world. \u0026nbsp;In North America, the incidence rate can reach 7% to 13%. \u0026nbsp;Men are more likely to suffer from the disease than women because of kidney stones.In acute cases, treatment is expensive\u003csup\u003e[1-\u003c/sup\u003e\u003csup\u003e2]\u003c/sup\u003e.Currently,the main treatments for kidney stones include drug therapy,extracorporeal shock wave lithotripsy (ESWL),transureteroscopic lithotomy (flexible ureterolithotomy and\u0026nbsp;rigid ureterolithotomy),percutaneous nephrolithotomy,etc\u003csup\u003e[3-\u003c/sup\u003e\u003csup\u003e4]\u003c/sup\u003e.Due to its high stone-clearing rate and minimal invasiveness,PCNL has become one of the first-line therapies for the treatment of kidney stones,especially suitable for complex kidney stones such as stones\u0026nbsp;＞2cm in diameter, multiple stones,and cast stones\u003csup\u003e[5-\u003c/sup\u003e\u003csup\u003e6]\u003c/sup\u003e. Although PCNL technology is constantly updated, the problem of residual stones is still inevitable\u003csup\u003e[7]\u003c/sup\u003e. Regarding the stone-free rate after PCNL for kidney stones, Guy\u0026rsquo;s stone score, S.T.O.N.E score,CROES nomogram and S-ReSC score are currently available.The GSS has been widely used due to its simplicity of operation.The S.T.O.N.E score is obtained through CT imaging.Stone characteristics, measuring maximum cross-sectional area (S),puncture channel length (T), degree of obstruction (O),involved renal calyces (N),stone density (E), including many stone characteristics,CROES nomogram uses quantitative impact Patients with kidney stones are scored based on clinical factors. The S-ReSC scoring system relies on the location of the stone to grade the complexity of the disease.Currently, the GSS and S.T.O.N.E score have received widespread attention,but the predictive effect has been controversial\u003csup\u003e[8-\u003c/sup\u003e\u003csup\u003e10]\u003c/sup\u003e.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eRadiomics is the study of clinical diseases by quantitatively extracting high-throughput features from imaging images,combined with clinical factors,demographics, genomics or independently\u003csup\u003e[11]\u003c/sup\u003e. Radiomics was initially used in clinical research on urinary tumors. CT-based radiomics nomograms have been used in the prediction of survival rate of clear cell renal cell carcinoma and the identification of clear cell renal cell carcinoma and angiomyolipomas,which has demonstrated greater value\u003csup\u003e[12-\u003c/sup\u003e\u003csup\u003e13]\u003c/sup\u003e.The successful application of radiomics in malignant tumors of the urinary system has led people to consider its value in benign diseases.The clinical-radiomics nomogram constructed by combining CT radiomics features and clinical features has been proven to be effective in preoperative prediction.The stone-free rate of flexible transurethral ureteroscopy. In addition,radiomics has also shown great value in the diagnosis of uric acid stones. Radiomics has indicated that it is better than traditional models in building prediction models\u0026nbsp;\u003csup\u003e[14-\u003c/sup\u003e\u003csup\u003e16]\u003c/sup\u003e.\u003c/p\u003e\n\u003cp\u003eIn this study,we combined clinically independent predictors and radiomics features to develop a clinical-radiomics nomogram that can be used to predict postoperative stone-free rate in PCNL and compared it with traditional GSS and S.T.O.N.E score Compare the prediction effects.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSurgical Method\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eRigid ureteroscopy is routinely used to examine the bladder and ureter on the surgical side before surgery. Then the 5F ureteral catheter is inserted into the ureter on the surgical side,ascends 25-28cm,is fixed with the urethra,and is connected to the infusion set to form artificial hydronephrosis. Under the guidance of B-ultrasound, the renal calyx was punctured between the subscapular angle line and the posterior axillary line of the eleventh intercostal space on the operative side. After the needle core was pulled out and urine was detected,a renal puncture guidewire was inserted along the puncture needle sheath.Using the guide wire as a guide,use the F10 fascia dilator to gradually expand the channel to F18 in 2F steps,insert the F18 tearable sheath,and insert the nephroscope into the sheath. Once the stone location is determined, the holmium laser is used to crush the stones and remove the small stones by rushing.In all cases,the F6 double J tube was left in place for about 4 weeks after surgery.\u003c/p\u003e"},{"header":"Patients And Methods","content":"\u003cp\u003e\u003cstrong\u003ePatients\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe\u0026nbsp; Institutional Review Board approved this retrospective study and waived the requirement for patient informed consent. The clinical data and imaging images of all 109 patients with simple kidney stones who underwent PCNL at the Second Affiliated Hospital of Nanchang University from April 2021 to October 2022 were retrospectively collected.Inclusion criteria: (1) Kidney stones were confirmed by non-contrast-enhanced CT scan; (2) All underwent complete PCNL surgical treatment; (3) Clinical data and imaging data were completely preserved. Exclusion criteria: (1) Combined with malignant tumors of the urinary system on the same side; (2) Severe liver and kidney dysfunction or systemic coagulation insufficiency; (3) Severe atrophy of the ipsilateral kidney. Judgment criteria for stone clearance: no residual stones or stone fragments ＜4 mm were found in plain radiographs or CT scans of the urinary tract about 1 week after surgery.All patients were randomly divided into a training set of 76 cases and a validation set of 33 cases in a ratio of 7:3. Clinical data collected before surgery include gender, age, BMI,hypertension,diabetes,preoperative urine white blood cells, preoperative stone surgery history, etc.Stone characteristics, including stone diameter (maximum cross-sectional diameter),stone number, stone location,and stone characteristics,are recorded.CT value (maximum cross-sectional average CT value), etc.The stone system score was jointly calculated and entered by 2 urologists with more than 6 years of working experience based on the GSS and S.T.O.N.E score,using the patient\u0026lsquo;s preoperative CT images and clinical data.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCT image acquisition, stone area of interest segmentation and radiomic feature extraction\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;CT equipment parameters: tube voltage is 80-140kV, tube current is 10-200ma, pitch is 1, rotation time is 0.5s, and layer thickness is 5mm.\u0026nbsp; All CT images were collected using picture archiving and communication system (PACS) and stored in DICOM format.All DICOM files were imported into the open source software 3D slicer (version 5.50, http://download.slicer.org/),and Radiomics were constructed. Database, using a semi-automatic method (using software to automatically identify similar density stone tissue in CT, and then manually improving the ROI edge) to outline the stone ROI in all sections of the CT image (see Figure 1),and simultaneously outline the coronal,sagittal and transverse images.When outlining the stone outline, in order to distinguish the kidney, perirenal tissue, surrounding bone tissue, arterial calcification, etc.The relevant window width is manually set to 350Hu and the window level is 40Hu, making the ROI division more accurate; in order to reduce human error, all The patient\u0026rsquo;s stone ROI area was jointly outlined by a professional radiologist and two professional urologists, and was finally examined and corrected by a urologist with a senior professional title.\u0026nbsp; Save the CT source file and the outlined ROI label in nrrd format, use the computer programming language tool Python (version 3.7), and extract the ROI region image group through the PyRadiomics language analysis package (https://pypi.org/project/pyradiomics/) learning characteristics.\u0026nbsp; As a flexible open source software package, Pyradiomics has covered all current image texture analysis algorithms.It can use its specific open source professional modules to decode images in DICOM and extract a large number of quantitative features.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRadiomic feature selection and\u0026nbsp;signature construction\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe extracted radiomic features are normalized using the formula (X-Xmin)/(Xmax-Xmin), and the obtained value is between 0 and 1.The least absolute shrinkage and selection operator regression (Lasso) was used to screen the radiomic features most relevant to stone residue after PCNL,and Pearson correlation analysis was used to test feature correlation. Correlation coefficients ＞0.9 were considered to have multicollinearity. A radiomics formula was created by using the linear combination of the lasso regression coefficients of the selected features to calculate the radscore for each patient.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConstruction and visualization of clinical-radiomics model\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;In the training set,clinical variables with statistical significance through univariate analysis were subjected to univariate logistic regression analysis,and multivariable logistic regression analysis was performed in combination with radscore to determine clinical independent predictive factors,and clinical independent predictive factors and radscore were combined.And use multi-factor logistic regression to build a clinical-radiomics model.To provide a visualization tool that can aid clinical decision-making,a clinical-radiomics nomogram was developed and the predictive performance of the nomogram was tested in a validation set.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eModel comparison\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe predictive performance of the clinical-radiomics nomogram and GSS and S.T.O.N.E score were compared by drawing ROC curves and Delong tests.DCA curves were drawn to evaluate the net benefits of the clinical-radiomics nomogram and GSS and S.T.O.N.E scores.A calibration curve was drawn to evaluate the prediction accuracy of the clinical-radiomics nomogram,and the Hosmer-Lemeshow (HL) test was performed to evaluate the goodness of fit of the clinical-radiomics nomogram.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatistical analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSPSS 27.0,R language software (version 4.3.1, http://www.r-project.org/) or python language software (https://www.python/downloads/release/python-380/) were used to analyze and processe the data.All measurement data were expressed as mean \u0026plusmn; standard deviation,and categorical variables were expressed as numbers (%). Single-factor analysis was used to compare the differences in clinical factors. Measurement data were measured using t test or Mann-Whitney U test,categorical variables use chi-square test or Fisher\u0026rsquo;s exact test, double test p＜0.05 is considered statistically significant, use the lars package of R language to perform lasso regression, use python\u0026rsquo;s matplotlib package to draw ROC curves and DCA decision curves.\u003c/p\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\n \u003ch2\u003eClinical features\u003c/h2\u003e\n \u003cp\u003eA total of 109 patients were included in this study, of whom 71 had no residual stones and 38 had residual stones.The normality test showed that the age of the measurement data was normally distributed (Kolmogorov-smirnov test,two-sided p\u0026thinsp;\u0026gt;\u0026thinsp;0.05),and the rest were non-normally distributed.Univariate analysis showed that there were significant differences in the number, location, diameter and CT value of stones between the two groups (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05) (Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). GSS and S.T.O.N.E score are shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab1\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eClinical features (%), \u0026oline;x\u0026thinsp;\u0026plusmn;\u0026thinsp;S, M༈P25, P75༉\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eFactor\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eNon-SF(n\u0026thinsp;=\u0026thinsp;38)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eSF(n\u0026thinsp;=\u0026thinsp;71)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eZ(t)/X\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eP\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eAge, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;sd, (years)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e55.45\u0026thinsp;\u0026plusmn;\u0026thinsp;11.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e52.92\u0026thinsp;\u0026plusmn;\u0026thinsp;13.20\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.994\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.323\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGender n(%)\u003c/p\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23(60.5%)\u003c/p\u003e\n \u003cp\u003e15(39.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e45(63.4%)\u003c/p\u003e\n \u003cp\u003e26(36.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.086\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.769\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eBMI, mean\u0026thinsp;\u0026plusmn;\u0026thinsp;sd, (kg/㎡)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23.27(20.62, 25.33)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e23.32(21.48, 25.10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.134\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.894\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePre-stenting/nephrostomy n(%)\u003c/p\u003e\n \u003cp\u003eNO\u003c/p\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e37(97.4%)\u003c/p\u003e\n \u003cp\u003e1(2.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e67(94.4%)\u003c/p\u003e\n \u003cp\u003e4(5.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.510\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.475\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHistory of stone sugery,n(%)\u003c/p\u003e\n \u003cp\u003eno\u003c/p\u003e\n \u003cp\u003ePCNL\u003c/p\u003e\n \u003cp\u003eOther sugery\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e27(71.1%)\u003c/p\u003e\n \u003cp\u003e6(15.8%)\u003c/p\u003e\n \u003cp\u003e5(13.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e56(78.9%)\u003c/p\u003e\n \u003cp\u003e6(8.4%)\u003c/p\u003e\n \u003cp\u003e9(12.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e1.414\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.493\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ePre-infection,n(%)\u003c/p\u003e\n \u003cp\u003e-\u003c/p\u003e\n \u003cp\u003e+\u003c/p\u003e\n \u003cp\u003e++\u003c/p\u003e\n \u003cp\u003e+++\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3(7.9%)\u003c/p\u003e\n \u003cp\u003e18(47.4%)\u003c/p\u003e\n \u003cp\u003e8(21.0%)\u003c/p\u003e\n \u003cp\u003e9(23.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8(11.3%)\u003c/p\u003e\n \u003cp\u003e39(54.9%)\u003c/p\u003e\n \u003cp\u003e13(18.3%)\u003c/p\u003e\n \u003cp\u003e11(15.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e1.551\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.670\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ehypertension,n(%)\u003c/p\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e24(63.2%)\u003c/p\u003e\n \u003cp\u003e14(36.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e56(78.9%)\u003c/p\u003e\n \u003cp\u003e15(21.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e3.131\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.077\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003ediabetes,n(%)\u003c/p\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e34(94.9%)\u003c/p\u003e\n \u003cp\u003e4(5.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e67(93.4%)\u003c/p\u003e\n \u003cp\u003e4(6.6%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.300\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.584\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStone laterality,n(%)\u003c/p\u003e\n \u003cp\u003eBoth\u003c/p\u003e\n \u003cp\u003eLeft\u003c/p\u003e\n \u003cp\u003eRight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0(0.0%)\u003c/p\u003e\n \u003cp\u003e15(39.5%)\u003c/p\u003e\n \u003cp\u003e23(60.5%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1(1.4%)\u003c/p\u003e\n \u003cp\u003e30(42.3%)\u003c/p\u003e\n \u003cp\u003e40(56.3%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.657\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.720\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStones number(piece)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5(4, 6)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3(2, 4)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-5.007\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStone location,n(%)\u003c/p\u003e\n \u003cp\u003eSimple renel pelvis/ calyx\u003c/p\u003e\n \u003cp\u003ePelvis and calyx\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e5(13.2%)\u003c/p\u003e\n \u003cp\u003e33(86.8%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e30(42.3%)\u003c/p\u003e\n \u003cp\u003e41(57.7%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e9.612\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.002\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStone diameter(cm)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.7(2.3, 3.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2.0(1.6, 2.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-4.565\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eStone CT value(HU)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1213(1030, 1386)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1060(950, 1200)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-2.929\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.003\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eHydronephrosis,n(%)\u003c/p\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003cp\u003eMild\u003c/p\u003e\n \u003cp\u003eModerate\u003c/p\u003e\n \u003cp\u003eSevere\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e1(2.6%)\u003c/p\u003e\n \u003cp\u003e24(63.2%)\u003c/p\u003e\n \u003cp\u003e8(21.1%)\u003c/p\u003e\n \u003cp\u003e5(13.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10(14.1%)\u003c/p\u003e\n \u003cp\u003e42(59.1%)\u003c/p\u003e\n \u003cp\u003e12(16.9%)\u003c/p\u003e\n \u003cp\u003e7(9.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e3.760\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.289\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eExperience of operator,n(%)\u003c/p\u003e\n \u003cp\u003ePCNL༜100\u003c/p\u003e\n \u003cp\u003ePCNL༞100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e11(28.9%)\u003c/p\u003e\n \u003cp\u003e27(71.1%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e10(14.1%)\u003c/p\u003e\n \u003cp\u003e61(85.9%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e3.515\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.061\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eGSS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e3(2, 3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e2(2, 2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-5.063\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eS.T.O.N.E\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e9(7, 9)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e8(7, 8)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e-3.808\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003ctfoot\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"5\"\u003eNote: BMI: body mass index; non-PCNL procedures include transurethral ureteroscopy (rigid and flexible), open surgery, and extracorporeal shock wave lithotripsy\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tfoot\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\n \u003ch2\u003eRadiomic features selection and radiomic signature construction\u003c/h2\u003e\n \u003cp\u003e1619 radiomic features were obtained from each stone ROI area, including 14 stone morphological features,270 first-order stone statistical features,and 360 Gray-Level Co-occurrence Matrix(GLCM) features describing entropy and texture information,240 Gray-Level Run-Length Matrix (GLRLM) features that reflect information such as ROI area granularity,and 240 Gray-Level Size Zone Matrix (GLSZM) features that describe relatively uniform,multi-dimensional information.75 Neighborhood GrayTone Difference Matrix (NGTDM) that quantify the difference between pixels and predefined pixels,and 420 Gray Level Dependence Matrix(GLDM) grayscale correlation matrices that describe the relationship between the central pixel and its neighbors and other information.Lasso regression screened out 9 radiomics features that were most relevant to the SFR after PCNL.The maximum value of Pearson\u0026rsquo;s correlation coefficient is less than 0.9,and there were no seriously related variables.The radscore of each patient was calculated through the linear combination of lasso regression coefficient and radiomics features. The radiomics score calculation formula is:\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\n \u003cp\u003eRadscore\u0026thinsp;=\u0026thinsp;0.031911768\u0026times;exponential_ngtdm_Coarseness\u003c/p\u003e\n \u003cdiv id=\"Sec16\" class=\"Section3\"\u003e\n \u003cp\u003e+(-0.021220610)\u0026times;lbp-2D_firstorder_10Percentile\u003c/p\u003e\n \u003cdiv id=\"Sec17\" class=\"Section4\"\u003e\n \u003cp\u003e+\u0026thinsp;0.878314468\u0026times;logarithm_ngtdm_Busyness\u003c/p\u003e\n \u003cp\u003e+\u0026thinsp;0.004262516\u0026times;wavelet-HLH_glrlm_LongRunLowGrayLevelEmphasis\u003c/p\u003e\n \u003c/div\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\n \u003cp\u003e+\u0026thinsp;0.314685233\u0026times;wavelet-HHH_glszm_SizeZoneNonUniformity\u003c/p\u003e\n \u003cdiv id=\"Sec19\" class=\"Section3\"\u003e\n \u003cp\u003e+(-0.077994374)\u0026times;gradient_glcm_MCC\u003c/p\u003e\n \u003cdiv id=\"Sec20\" class=\"Section4\"\u003e\n \u003cp\u003e+\u0026thinsp;0.050846883\u0026times;lbp-2D_glszm_SmallAreaEmphasis +(-0.119795401)\u0026times;wavelet-HLH_firstorder_Median\u003c/p\u003e\n \u003cp\u003e+\u0026thinsp;0.034245990\u0026times;wavelet-HHL_firstorder_Energy\u003c/p\u003e\n \u003c/div\u003e\n \u003c/div\u003e\n \u003cdiv id=\"Sec21\" class=\"Section3\"\u003e\n \u003ch2\u003eClinical-radiomics model construction and visualization\u003c/h2\u003e\n \u003cp\u003eUnivariate logistic regression analysis in the training set revealed that there were statistically significant differences in stone location, stone number,and stone diameter between SF and Non-SF(p༜0.05). Multivariate logistic regression analysis showed that the number of stones, the diameter of stones and radscore are clinically independent risk factors for SF and Non-SF(p༜0.05) in Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.Combined with clinical independent risk factors and radscore,multi-factor logistic regression was used to construct a clinical-radiomics model,and a clinical-radiomics nomogram was developed to visualize the model ( Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e\n \u003cdiv class=\"gridtable\"\u003e\u0026nbsp;\u003ctable id=\"Tab2\" border=\"1\"\u003e\n \u003ccaption language=\"En\"\u003e\n \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n \u003cdiv class=\"CaptionContent\"\u003e\n \u003cp\u003eLogistic regression analysis in the training set.\u003c/p\u003e\n \u003c/div\u003e\n \u003c/caption\u003e\n \u003ccolgroup cols=\"6\"\u003e\u003c/colgroup\u003e\n \u003cthead\u003e\n \u003ctr\u003e\n \u003cth align=\"left\" rowspan=\"2\"\u003e\n \u003cp\u003echaracteristic\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eUnivariate logistic\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\" colspan=\"2\"\u003e\n \u003cp\u003eMultivariate logistic\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eOR(95%CI)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eP\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eOR(95%CI)\u003c/p\u003e\n \u003c/th\u003e\n \u003cth align=\"left\"\u003e\n \u003cp\u003eP\u003c/p\u003e\n \u003c/th\u003e\n \u003c/tr\u003e\n \u003c/thead\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eStones number\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.537(0.368\u0026thinsp;~\u0026thinsp;0.764)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.573(0.345\u0026thinsp;~\u0026thinsp;0.949)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.031\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eStone location\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003eSimple pelvis/calyx\u003c/p\u003e\n \u003cp\u003ePelvis and calyx\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003cp\u003e0.251(0.075\u0026thinsp;~\u0026thinsp;0.837)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.025\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003cp\u003e1.088(0.207, 5.712)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e0.921\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eStone diameter\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.182(0.073\u0026thinsp;~\u0026thinsp;0.452)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.162(0.048\u0026thinsp;~\u0026thinsp;0.551)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.004\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eStone CT value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.998(0.996\u0026thinsp;~\u0026thinsp;1.000)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.110\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd align=\"left\"\u003e\n \u003cp\u003e\u003cstrong\u003eRadscore\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001(༜0.001\u0026thinsp;~\u0026thinsp;0.006)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e༜0.001(༜0.001\u0026thinsp;~\u0026thinsp;0.109)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd align=\"char\"\u003e\n \u003cp\u003e0.013\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n \u003c/div\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec22\" class=\"Section2\"\u003e\n \u003ch2\u003emodel comparison\u003c/h2\u003e\n \u003cp\u003eIn the training set, the AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E stone score were 0.925 and 0.772、0.712 respectively.In the validation set,the AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E stone score were 0.944 and 0.786、0.714 ,Fig. \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e for details.Delong test showed that the discriminative ability of clinical-radiomics nomogram was better than that of GSS and S.T.O.N.E stone score(p༜0.05).The DCA decision curve shows that at each threshold probability,the net benefit of the clinical-radiomics nomogram is better than that of the GSS and STONE stone score(Figure \u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e).When using the clinical-radiomics nomogram to decide whether to undergo PCNL treatment, it is better than all treatments and no treatment significantly increases returns.The calibration curve and Hosmer-Lemeshow (HL) test (p༞0.05) showed that the clinical-radiomics nomogram has good calibration ability and fit.\u003c/p\u003e\n \u003cdiv id=\"Sec25\" class=\"Section3\"\u003e\n \u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n \u003c/div\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003ePCNL is gradually becoming the mainstream method for the treatment of kidney stones due to its minimally invasive and high stone-free rate\u003csup\u003e[17\u0026ndash;18]\u003c/sup\u003e. For most patients with kidney stones,PCNL can not only relieve pain,but also greatly help symptoms such as nausea, urinary discomfort, and mental distress.In addition,PCNL intervention has a tendency to improve renal function damaged by kidney stones before surgery\u003csup\u003e[19\u0026ndash;20]\u003c/sup\u003e.Due to the different conditions of patients and the characteristics of stones,residual stones will still occur in PCNL. The number, size, and location of stones are considered to be related to the residual stones after PCNL.The remaining stones will significantly extend the hospitalization time and increase the number of secondary visit risks of surgery\u003csup\u003e[21\u0026ndash;22]\u003c/sup\u003e.There have been a variety of scoring systems used to predict the stone-free rate of patients with kidney stones after PCNL.Guy\u0026rsquo;s stone score is used to comprehensively evaluate the number of stones,stone shape and anatomical distribution,and classifies kidney stone patients into Ⅰ-Ⅳ grades.The higher it is,the more complex the stones are,and the higher the risk of residual stones after PCNL\u003csup\u003e[23]\u003c/sup\u003e. The S.T.O.N.E score comprehensively evaluates the complexity of kidney stones by quantifying the maximum cross-sectional area of stones, stone density, degree of kidney damage and PCNL puncture channel,thereby predicting the postoperative outcomes of PCNL.In addition, the stone score relies on multi-center data to establish The CROES nomogram and the S-ReSC score,which focuses on the distribution of stones in the collecting system,also play a certain role in the stone-free rate after PCNL \u003csup\u003e[24\u0026ndash;25]\u003c/sup\u003e.Although traditional stone scores have certain value in post-PCNL outcomes,they have shown shortcomings when compared with machine learning and artificial intelligence\u003csup\u003e[26\u0026ndash;27]\u003c/sup\u003e.With the successful application of radiomics in renal cancer, prostate cancer, etc. people remain optimistic about its value in urinary tract stones. Radiomics has shown great value in the identification of urinary tract stones and prediction of treatment outcomes\u003csup\u003e[16]\u003c/sup\u003e.At the same time, radiomics also plays an auxiliary role in predicting the burden of kidney stones and the degree of kidney damage, and making decisions on treatment strategies\u003csup\u003e[28]\u003c/sup\u003e.Therefore,a comparative study of radiomics and traditional stone scoring systems in predicting postoperative outcomes of PCNL is meaningful and conditional.\u003c/p\u003e \u003cp\u003eIn our study, 9 radiomics features that were strongly correlated with whether stones remained after PCNL were screened, and the radiomics score was calculated based on the lasso regression coefficient and linear combination.Some studies have shown that a single strong risk factor may not be able to evaluate postoperative outcomes well, and prediction models built by combining multiple factors often have better prediction effects \u003csup\u003e[29\u0026ndash;30]\u003c/sup\u003e.Therefore,we collected many clinical characteristics related to stone clearance rate after PCNL in previous studies, determined clinical independent risk factors through univariate and multivariate logistic regression analysis,and combined with radiomics scores to jointly construct a clinical-radiomics nomogram, and compare the prediction effect with GSS and S.T.O.N.E score.The AUC of the clinical-radiomics nomogram and the GSS 、S.T.O.N.E score in the training set were 0.925 and 0.772、0.712 respectively.The AUC of the clinical-radiomics nomogram and the GSS、S.T.O.N.E score in the validation set were 0.944 and 0.786、0.714 respectively.In addition,the delong test and the DCA curve showed that the clinical-radiomics nomogram has better discrimination ability and clinical benefit.\u003c/p\u003e \u003cp\u003eThe current study has several limitations. First, this is a retrospective study and selection bias may still exist despite strict inclusion and exclusion criteria.Second, the included samples are relatively insufficient. Third,this study is based on single-center data,and multi-center prospective studies are needed to further validate the results.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThe clinical-radiomics nomogram constructed in this study was compared with the traditional GSS and S.T.O.N.E score and showed that the clinical-radiomics nomogram can be more successful in predicting the stone clearance rate after PCNL. As a result, it can provide effective assistance for clinical decision-making before PCNL surgery.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics\u0026nbsp;approval\u0026nbsp;and\u0026nbsp;consent\u0026nbsp;to\u0026nbsp;participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis 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.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis research was funded by the National Natural Science Foundation of China（Nos.82260598,81560420）.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eXCZ designed this experiment, collected and organized data, and wrote the article.JBH 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.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data and materials are available.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have read and agreed to submit this manuscript for publication.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ecompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors declared no competing interests.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eStamatelou K,Goldfarb DS.Epidemiology of Kidney Stones. Healthcare (Basel).2023;11(3):424.doi:10.3390/healthcare11030424.\u003c/li\u003e\n\u003cli\u003eSorokin I,Mamoulakis C,Miyazawa K,et al.Epidemiology of stone disease across the world. World J Urol.2017;35(9):1301\u0026ndash;1320.doi:10.1007/s00345-017-2008-6.\u003c/li\u003e\n\u003cli\u003eD'Ambrosio V,Moochhala S,Unwin RJ,et al.Why is diagnosis, investigation,and improved management of kidney stone disease important?Non-pharmacological and pharmacological treatments for nephrolithiasis.Expert Rev Clin Pharmacol.2022;15(4):407\u0026ndash;414.doi: 10.1080/17512433.2022.2082943.\u003c/li\u003e\n\u003cli\u003eTzelves L,Geraghty RM,Hughes T,et al.Innovations in Kidney Stone Removal.Res Rep Urol.2023;15:131\u0026ndash;139.doi:10.2147/RRU.S386844.\u003c/li\u003e\n\u003cli\u003eDe Lorenzis E,Zanetti SP,Boeri L,et al.Is There Still a Place for Percutaneous Nephrolithotomy in Current Times?J Clin Med.2022;11(17):5157.doi:10.3390/jcm11175157.\u003c/li\u003e\n\u003cli\u003eGrosso AA,Sessa F,Campi R,et al.Intraoperative and postoperative surgical complications after ureteroscopy,retrograde intrarenal surgery,and percutaneous nephrolithotomy:a systematic review.Minerva Urol Nephrol.2021;73(3):309\u0026ndash;332.doi:10.23736/S2724-6051.21.04294-4.\u003c/li\u003e\n\u003cli\u003eKallidonis P,Tsaturyan A,Lattarulo M,et al.Minimally invasive percutaneous nephrolithotomy (PCNL):Techniques and outcomes. Turk J Urol.2020;46(Supp. 1):S58-S63.doi:10.5152/tud.2020.20161.\u003c/li\u003e\n\u003cli\u003eWu WJ,Okeke Z.Current clinical scoring systems of percutaneous nephrolithotomy outcomes.Nat Rev Urol.2017;14(8):459\u0026ndash;469.doi:10.1038/nrurol.2017.71.\u003c/li\u003e\n\u003cli\u003eSrivastava A,Yadav P,Madhavan K,et al.Inter-observer variability amongst surgeons and radiologists in assessment of Guy's Stone Score and S.T.O.N.E. nephrolithometry score:A prospective evaluation. Arab J Urol.2019;18(2):118\u0026ndash;123.doi:10.1080/2090598X.2019.1703278.\u003c/li\u003e\n\u003cli\u003eSingla A,Khattar N,Nayyar R,et al.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. 2017;15(1):7\u0026ndash;16.doi:10.1016/j.aju.2016.11.005.\u003c/li\u003e\n\u003cli\u003eMayerhoefer ME,Materka A,Langs G,et al.Introduction to Radiomics.J Nucl Med.2020;61(4):488\u0026ndash;495.doi:10.2967/jnumed.118.222893.\u003c/li\u003e\n\u003cli\u003eYan L,Yang G,Cui J,et al.Radiomics Analysis of Contrast-Enhanced CT Predicts Survival in Clear Cell Renal Cell Carcinoma.Front Oncol. 2021;11:671420.doi:10.3389/fonc.2021.671420.\u003c/li\u003e\n\u003cli\u003eMa Y,Ma W,Xu X,et al.A convention-radiomics CT nomogram for differentiating fat-poor angiomyolipoma from clear cell renal cell carcinoma.Sci Rep.2021;11(1):4644.doi:10.1038/s41598-021-84244-3.\u003c/li\u003e\n\u003cli\u003eXun Y,Chen M,Liang P,et al.A Novel Clinical-Radiomics Model Pre-operatively Predicted the Stone-Free Rate of Flexible Ureteroscopy Strategy in Kidney Stone Patients.Front Med (Lausanne).2020;7:576925.doi:10.3389/fmed.2020.576925.\u003c/li\u003e\n\u003cli\u003eWang Z,Yang G,Wang X,et al.A combined model based on CT radiomics and clinical variables to predict uric acid calculi which have a good accuracy.Urolithiasis.2023;51(1):37.doi:10.1007/s00240-023-01405-x.\u003c/li\u003e\n\u003cli\u003eLim EJ,Castellani D,So WZ,et al.Radiomics in Urolithiasis: Systematic Review of Current Applications,Limitations,and Future Directions.J Clin Med.2022;11(17):5151.doi:10.3390/jcm11175151.\u003c/li\u003e\n\u003cli\u003eJiao B,Luo Z,Huang T,et al.A systematic review and meta-analysis of minimally invasive vs.standard percutaneous nephrolithotomy in the surgical management of renal stones.Exp Ther Med.2021;21(3):213.doi:10.3892/etm.2021.9645.\u003c/li\u003e\n\u003cli\u003eKamal W,Kallidonis P,Kyriazis I,et al.Minituriazed percutaneous nephrolithotomy:what does it mean?Urolithiasis.2016;44(3):195\u0026ndash;201.doi:10.1007/s00240-016-0881-x.\u003c/li\u003e\n\u003cli\u003eGaur AS,Mandal S,Pandey A,et al.Efficacy of PCNL in the resolution of symptoms of nephrolithiasis.Urolithiasis.2022;50(4):487\u0026ndash;491.doi:10.1007/s00240-022-01334-1.\u003c/li\u003e\n\u003cli\u003eReeves T,Pietropaolo A,Gadzhiev N,et al.Role of Endourological Procedures (PCNL and URS) on Renal Function:a Systematic Review. Curr Urol Rep.2020;21(5):21.doi: 10.1007/s11934-020-00973-4.\u003c/li\u003e\n\u003cli\u003eBorofsky MS,Wollin DA,Reddy T,et al.Salvage Percutaneous Nephrolithotomy:Analysis of Outcomes following Initial Treatment Failure.J Urol. 2016;195(4Pt 1):977\u0026thinsp;\u0026minus;\u0026thinsp;81.doi:10.1016/j.juro.2015.10.176.\u003c/li\u003e\n\u003cli\u003eDoizi S,Bensalah K,Lebacle C,et al.Complications en endo-urologie:ur\u0026eacute;t\u0026eacute;roscopie et n\u0026eacute;phrolithotomie percutan\u0026eacute;e [Complications in endourology:Ureteroscopy and percutaneous nephrolithotomy].Prog Urol.2022;32(14):966\u0026ndash;976.French.doi:10.1016/j.purol.2022.09.002.\u003c/li\u003e\n\u003cli\u003eChoi SW, Bae WJ, Ha US,et al.Prediction of stone-free status and complication rates after tubeless percutaneous nephrolithotomy: a comparative and retrospective study using three stone-scoring systems and preoperative parameters.World J Urol.2017;35(3):449\u0026ndash;457.doi:10.1007/s00345-016-1891-6.\u003c/li\u003e\n\u003cli\u003eBibi M,Sellami A,Chaker K,et al.Les scores radiologiques peuvent-t-ils pr\u0026eacute;dire le succ\u0026egrave;s de la NLPC ?\u0026Eacute;tude comparative du Guy's stone score,du STONE score,du CROES nomogram,et du S-ReSc score [Do the nephrolithometry scoring systems predict the success of percutaneous nephrolithotomy.Comparison of 4 scores: The Guy's stone score,STONE Score,CROES nomogram and S-ReSC score].Prog Urol.2019;29(8\u0026ndash;9):432\u0026ndash;439.French.doi:10.1016/j.purol.2019.05.007.\u003c/li\u003e\n\u003cli\u003eAl Adl AM,Mohey A,Abdel Aal A,et al.Percutaneous Nephrolithotomy Outcomes Based on S.T.O.N.E.,GUY, CROES,and S-ReSC Scoring Systems:The First Prospective Study. J Endourol. 2020;34(12):1223\u0026ndash;1228.doi:10.1089/end.2019.0856.\u003c/li\u003e\n\u003cli\u003eZhao H,Li W,Li J,et al.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.2022;9:880291.doi:10.3389/fmolb.2022.880291.\u003c/li\u003e\n\u003cli\u003eNedbal C,Cerrato C,Jahrreiss V,et al.The role of 'artificial intelligence,machine learning,virtual reality,and radiomics' in PCNL:a review of publication trends over the last 30 years.Ther Adv Urol. 2023;15:17562872231196676.doi:10.1177/17562872231196676.\u003c/li\u003e\n\u003cli\u003eHomayounieh F, Doda Khera R, Bizzo BC, et al.Prediction of burden and management of renal calculi from whole kidney radiomics:a multicenter study.Abdom Radiol(NY).2021;46(5):2097\u0026ndash;2106.doi:10.1007/s00261-020-02865-0.\u003c/li\u003e\n\u003cli\u003eVickers AJ.Prediction models: revolutionary in principle,but do they do more good than harm?J Clin Oncol.2011;29(22):2951-2.doi:10.1200/JCO.2011.36.1329.\u003c/li\u003e\n\u003cli\u003eResorlu B, Unsal A, Gulec H, et al.A new scoring system for predicting stone-free rate after retrograde intrarenal surgery:the \"resorlu-unsal stone score\".Urology.2012;80(3):512-8.doi:10.1016/j.urology.2012.02.072.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"clinical-radiomics nomogram, Guy’s stone score, S.T.O.N.E score, percutaneous nephrolithotomy, stone-free rate","lastPublishedDoi":"10.21203/rs.3.rs-3767593/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3767593/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003ePurpose\u003c/strong\u003e: This study aimed to develop a clinical-radiomics nomogram by combining clinical factors and radiomics features.The objective of the nomogram was to predict the stone-free rate(SFR) in percutaneous nephrolithotomy (PCNL). Additionally, the predictive performance of the nomogram was compared with Guy's stone score (GSS) and S.T.O.N.E score.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePatients and methods\u003c/strong\u003e: A retrospective analysis was conducted on 109 suitable patients with solitary kidney stones who underwent PCNL at the Second Affiliated Hospital of Nanchang University from April 2021 to October 2022.The preoperative clinical data and non-contrast-enhanced CT images of all patients were collected.Radiomic features were extracted from the CT images after preprocessing steps such as wavelet transformation, logization, and resampling. The least absolute shrinkage and selection operator (LASSO) method was used to screen the radiomics features and calculate the radiomics score for each patient using lasso regression coefficient.Multivariate logistic regression analysis was performed to determine the clinical independent predictive factors. These factors were combined with radiomics to construct a clinical-radiomics model, which was visualized using a nomogram.The GSS and S.T.O.N.E score of each patient were calculated and analyzed. The predictive performance of the clinical-radiomics nomogram,Guy’s stone score (GSS),and S.T.O.N.E score was compared and analyzed through identification,calibration,and clinical benefit.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: The postoperative statistics revealed a stone-free rate of 65.1%. The results from multivariate logistic regression analysis indicated that the number and diameter of stones were independent risk factors for residual stones after percutaneous nephrolithotomy (PCNL). In the training set, the clinical-radiomics nomogram, GSS and S.T.O.N.E score showed area under the receiver operating curve (ROC) values of 0.925, 0.772 and 0.712, respectively. In the validation set, the AUCs for the clinical-radiomics nomogram, GSS and S.T.O.N.E score were 0.944, 0.786 \u0026nbsp;and 0.714, respectively.The Delong test demonstrated that the clinical-radiomics nomogram exhibited better discrimination ability than GSS and S.T.O.N.E score (p\u0026lt;0.05).The calibration curve and Hosmer-Lemeshow (HL) test confirmed the good calibration ability and fit of the clinical-radiomics nomogram.Furthermore, the decision curve analysis (DCA) revealed that the clinical-radiomics nomogram provided a better net benefit compared to GSS and S.T.O.N.E score.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e:The clinical-radiomics nomogram constructed based on clinical characteristics and radiomics features can well predict the stone-free rate after PCNL, and its predictive performance is better than the GSS and S.T.O.N.E score.\u003c/p\u003e","manuscriptTitle":"Prediction of preoperative the Stone-Free rate in percutaneous nephrolithotomy based on CT clinical-radiomics nomogram: a comparative study with Guy’s stone score and S.T.O.N.E score.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-02 18:37:37","doi":"10.21203/rs.3.rs-3767593/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"095e2294-60a4-407c-8c5c-5188d4e2a9af","owner":[],"postedDate":"January 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-07-12T09:01:49+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-02 18:37:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3767593","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3767593","identity":"rs-3767593","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}