Mingzhen Chen1, Jiannan Yang2, Junlin Lu3, Ziling Zhou4, Kun Huang5, Sihan Zhang3, Guanjie Yuan1, Qingpeng Zhang6, Zhen Li7. 1. Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No.1095 Jiefang Avenue, Wuhan, Hubei, 430030, China. 2. School of Data Science, City University of Hong Kong, Kowloon, Hong Kong, 999077, China. 3. Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China. 4. Biomedical Engineering Department, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China. 5. School of Information and Technology, University of Science and Technology of China, Hefei, China. 6. School of Data Science, City University of Hong Kong, Kowloon, Hong Kong, 999077, China. qingpeng.zhang@cityu.edu.hk. 7. Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No.1095 Jiefang Avenue, Wuhan, Hubei, 430030, China. zhenli@hust.edu.cn.
Abstract
OBJECTIVES: To explore the utility of radiomics and deep learning model in assessing the risk factors for sepsis after flexible ureteroscopy lithotripsy (FURL) or percutaneous nephrolithotomy (PCNL) in patients with ureteral calculi. METHODS: This retrospective analysis included 847 patients with treatment-naive proximal ureteral calculi who received FURL or PCNL. All participants were preoperatively conducted non-contrast computed tomography scans, and relevant clinical information was meanwhile collected. After propensity score matching, the radiomics model was established to predict the onset of sepsis. A deep learning model was also adapted to further improve the prediction accuracy. Performance of these trained models was verified in another independent external validation set including 40 cases of ureteral calculi patients. RESULTS: The overall incidence of sepsis after FURL or PCNL was 5.9%. The least absolute shrinkage and selection operator (LASSO) regression analysis revealed 26 predictive variables, with an overall AUC of 0.881 (95% CI, 0.813-0.931) and an AUC of 0.783 (95% CI, 0.766-0.801) in external validation cohort. Judicious adaption of a deep neural network (DNN) model to our dataset improved the AUC to 0.920 (95% CI, 0.906-0.933) in the internal validation. To eliminate the overfitting, external validation was carried out for DNN model (AUC = 0.874 (95% CI, 0.858-0.891)). CONCLUSIONS: The DNN was more effective than the LASSO model in revealing risk factors for sepsis after FURL or PCNL in single ureteral calculi patients, and females are more susceptible to sepsis than males. Deep learning models have the potential to act as gatekeepers to facilitate patient stratification. KEY POINTS: • Both the least absolute shrinkage and selection operator (LASSO) and deep neural network (DNN) models were shown to be effective in sepsis prediction. • The DNN model achieved superior prediction capability, with an AUC of 0.920 (95% CI, 0.906-0.933). • DNN-assisted model has potential to serve as a gatekeeper to facilitate patient stratification.
OBJECTIVES: To explore the utility of radiomics and deep learning model in assessing the risk factors for sepsis after flexible ureteroscopy lithotripsy (FURL) or percutaneous nephrolithotomy (PCNL) in patients with ureteral calculi. METHODS: This retrospective analysis included 847 patients with treatment-naive proximal ureteral calculi who received FURL or PCNL. All participants were preoperatively conducted non-contrast computed tomography scans, and relevant clinical information was meanwhile collected. After propensity score matching, the radiomics model was established to predict the onset of sepsis. A deep learning model was also adapted to further improve the prediction accuracy. Performance of these trained models was verified in another independent external validation set including 40 cases of ureteral calculi patients. RESULTS: The overall incidence of sepsis after FURL or PCNL was 5.9%. The least absolute shrinkage and selection operator (LASSO) regression analysis revealed 26 predictive variables, with an overall AUC of 0.881 (95% CI, 0.813-0.931) and an AUC of 0.783 (95% CI, 0.766-0.801) in external validation cohort. Judicious adaption of a deep neural network (DNN) model to our dataset improved the AUC to 0.920 (95% CI, 0.906-0.933) in the internal validation. To eliminate the overfitting, external validation was carried out for DNN model (AUC = 0.874 (95% CI, 0.858-0.891)). CONCLUSIONS: The DNN was more effective than the LASSO model in revealing risk factors for sepsis after FURL or PCNL in single ureteral calculi patients, and females are more susceptible to sepsis than males. Deep learning models have the potential to act as gatekeepers to facilitate patient stratification. KEY POINTS: • Both the least absolute shrinkage and selection operator (LASSO) and deep neural network (DNN) models were shown to be effective in sepsis prediction. • The DNN model achieved superior prediction capability, with an AUC of 0.920 (95% CI, 0.906-0.933). • DNN-assisted model has potential to serve as a gatekeeper to facilitate patient stratification.
Authors: Christian Türk; Aleš Petřík; Kemal Sarica; Christian Seitz; Andreas Skolarikos; Michael Straub; Thomas Knoll Journal: Eur Urol Date: 2015-08-28 Impact factor: 20.096
Authors: Andreas Skolarikos; Michael Straub; Thomas Knoll; Kemal Sarica; Christian Seitz; Ales Petřík; Christian Türk Journal: Eur Urol Date: 2014-11-20 Impact factor: 20.096
Authors: Jaap D Legemate; Nienke J Wijnstok; Tadashi Matsuda; Willem Strijbos; Tibet Erdogru; Beat Roth; Hidefumi Kinoshita; Judith Palacios-Ramos; Roberto M Scarpa; Jean J de la Rosette Journal: World J Urol Date: 2017-03-20 Impact factor: 4.226
Authors: B K Somani; G Giusti; Y Sun; P J Osther; M Frank; M De Sio; B Turna; J de la Rosette Journal: World J Urol Date: 2016-08-04 Impact factor: 4.226