Artificial intelligence in predicting urinary stone composition： applications and prospects

Wang Xiaochen; Yang Boyu; Zhao Youquan; Wang Xiaochuan; Sun Manjiang; Li Jun

doi:null

您当前的位置：

首页 >

文章列表页 >

Artificial intelligence in predicting urinary stone composition： applications and prospects

更新时间：2025-11-18

- Artificial intelligence in predicting urinary stone composition： applications and prospects
- Journal of Chongqing Medical University Pages: 1-5(2025)
- 作者机构：
  
  首都医科大学附属北京友谊医院泌尿外科，北京 100000
- 作者简介：
- 基金信息：
- DOI：
  CLC： R69
- Received：01 July 2025，
  
  Published Online：18 November 2025，
- 稿件说明：
移动端阅览
王笑晨,杨博宇,赵有权等.人工智能在结石成分预测中的应用与展望[J].重庆医科大学学报,

Wang Xiaochen,Yang Boyu,Zhao Youquan,et al.Artificial intelligence in predicting urinary stone composition： applications and prospects[J].Journal of Chongqing Medical University,
王笑晨,杨博宇,赵有权等.人工智能在结石成分预测中的应用与展望[J].重庆医科大学学报, DOI：10.13406/j.cnki.cyxb..

Wang Xiaochen,Yang Boyu,Zhao Youquan,et al.Artificial intelligence in predicting urinary stone composition： applications and prospects[J].Journal of Chongqing Medical University, DOI：10.13406/j.cnki.cyxb..

摘要

泌尿系结石作为一种发病率与复发率持续攀升的全球性健康问题，其精准诊疗依赖于结石成分的准确分析。传统方法如红外光谱与计算机断层扫描（computed tomography，CT）因成本昂贵及鉴别能力有限而难以满足临床需求。近年来，人工智能（artificial intelligence，AI）技术通过整合CT影像特征、生化指标及电子健康记录等多模态数据，在无创结石成分预测中实现了重大突破。然而，AI技术的临床转化仍面临多重障碍：数据缺乏统一标准削弱模型泛化能力；深度学习模型的“黑箱”特性降低了使用者信任度；高昂经济成本与设备兼容性问题阻碍技术普及；数据隐私与算法偏见引发的伦理争议仍需解决。未来研究应聚焦多模态数据融合、基于联合学习的跨机构安全协作机制，以及符合临床需求的解释性标准化语言（如自然语言生成的决策报告）。通过推动数据集标准化合作、前瞻性临床试验验证及伦理-监管体系完善，AI驱动的结石成分分析有望突破创新技术与临床应用间的壁垒，最终推动泌尿系结石管理向精准医学转型，减少侵入性操作并改善患者预后。

Abstract

Urinary stones are a global health issue with continuously rising incidence and recurrence rates，and their precision treatment rely on an accurate stone composition analysis. Traditional methods，such as infrared spectroscopy and computed tomography （CT），struggle to meet clinical demands due to their high costs and limited discrimination capabilities. In recent years，artificial intelligence（AI） technology has achieved significant breakthroughs in non-invasive stone composition prediction by integrating multimodal data including CT features，biochemical indicators，and electronic health records. However，the clinical translation of AI technology still faces multiple obstacles： data heterogeneity weakens models’ generalization ability；the “black box” nature of deep learning models reduces clinical trust；high computational costs and device compatibility issues hinder technology adoption；ethical concerns arising from data privacy and algorithmic bias still need to be addressed. Future research should focus on multimodal data fusion，cross-institutional secure collaboration mechanisms based on federated learning，and explanatory standardized language that meets clinical needs（such as decision reports generated with natural language）. Through promoting cooperation in dataset standardization，prospective clinical trial validation，and the improvement of ethical-regulatory systems，AI-driven stone composition analysis has the potential to break through the barriers from innovative technology to clinical application，ultimately driving the transformation of urinary stone management towards precision medicine，reducing invasive procedures，and improving patient outcomes.

关键词

Keywords

references

Yang BY ， Zhao FZ ， Li J ， et al . Epitranscriptomic profiling of m6A RNA methylation in renal epithelial tubular cells stimulated with calcium oxalate crystals through microarray analysis [J ] . Urolithiasis ， 2023 ， 51 （ 1 ）： 57 .

Yang BY ， Zhao MS ， Lv JC ， et al . Porous Se@SiO 2 nanospheres inhibit calcium oxalate kidney stone formation by oxidation resistance [J ] . Ceramics International ， 2023 ， 49 ： 8856 - 8862 .

Sorokin I ， Mamoulakis C ， Miyazawa K ， et al . Epidemiology of stone disease across the world [J ] . World J Urol ， 2017 ， 35 （ 9 ）： 1301 - 1320 .

Daudon M ， Bader CA ， Jungers P . Urinary calculi： Review of classification methods and correlations with etiology [J ] . Scanning Microsc ， 1993 ， 7 （ 3 ）： 1081 - 1104 .

Sakhaee K . Recent advances in the pathophysiology of nephrolithiasis [J ] . Kidney Int ， 2009 ， 75 （ 6 ）： 585 - 595 .

Türk C ， Petřík A ， Sarica K ， et al . EAU Guidelines on Diagnosis and Conservative Management of Urolithiasis [J ] . Eur Urol ， 2016 ， 69 （ 3 ）： 468 - 474 .

Hesse A ， Tiselius HG ， Siener R . Urinary Stones： Diagnosis，Treatment，and Prevention of Recurrence [M ] . 3rd ed . Basel ： Karger ， 2009 .

Zarse CA ， McAteer JA ， Tann M ， et al . Helical CT accurately reports urinary stone composition using attenuation values [J ] . Urology ， 2004 ， 63 （ 5 ）： 828 - 833 .

Van Appledorn S ， Ball AJ ， et al . Limitations of Noncontrast CT for Measuring Ureteral Stones [J ] . J Endourol ， 2003 ， 17 （ 10 ）： 851 - 854 .

Litjens G ， Kooi T ， Bejnordi BE ， et al . A survey on deep learning in medical image analysis [J ] . Med Image Anal ， 2017 ， 42 ： 60 - 88 .

Kocak B ， Kus EA ， Kilickesmez O . How to read and review papers on machine learning and artificial intelligence in radiology： A survival guide to key methodological concepts [J ] . Eur Radiol ， 2021 ， 31 （ 4 ）： 1819 - 1830 .

Coe FL ， Evan AP ， Worcester EM . Kidney stone disease [J ] . J Clin Investig ， 2005 ， 115 （ 10 ）： 2598 - 2608 .

Daudon M ， Jungers P . Clinical value of crystalluria and quantitative morphoconstitutional analysis of urinary calculi [J ] . Nephron Physiol ， 2004 ， 98 （ 2 ）： 31 - 36 .

Qiao LD ， Chen XH ， Wu WQ ， et al . Interpretation of Chinese Expert Consensus on Diagnosis and Treatment of Upper Urinary Tract Infectious Stones （2024 Edition） [J ] . J Clin Urol ， 2025 ， 40 （ 02 ）： 101 - 104 .

Moe OW . Kidney stones： Pathophysiology and medical management [J ] . Lancet ， 2006 ， 367 （ 9507 ）： 333 - 344 .

Liu Y ， Song H ， Luo D ， et al .Zhang G and Li J（ 2025 ） Integrated radiomics and deep learning model for identifying medullary sponge kidney stones . Front Med ，12： 1623850 . doi： 10.3389/fmed.2025.1623850 http://dx.doi.org/10.3389/fmed.2025.1623850

Kambadakone AR ， Eisner BH ， Catalano OA ， et al . New and evolving concepts in the imaging and management of urolithiasis [J ] . Radiographics ， 2010 ， 30 （ 3 ）： 603 - 623 .

Jendeberg J ， Thunberg P ， Popiolek M ， et al . Single-energy CT predicts uric acid stones with accuracy comparable to dual-energy CT—prospective validation of a quantitative method [J ] . Eur Radiol ， 2021 ， 31 ： 5980 – 5989 .

Pearle MS ， Goldfarb DS ， Assimos DG ， et al . Medical Management of Kidney Stones：AUA Guideline [J ] . J Urol ， 2014 ， 192 （ 2 ）： 316 - 324 .

Zhan XF . Establishment and validation of a predictive model for urinary stone composition based on artificial intelligence and CT images [D ] . Baoding ： Hebei University ， 2022 .

Sutton RS ， Barto AG . Reinforcement Learning： An Introduction [M ] . 2nd ed . Cambridge ： MIT Press ， 2018 .

Ronneberger O ， Fischer P ， Brox T . U-Net：Convolutional networks for biomedical image segmentation [J ] . Med Image Anal ， 2015 ： 234 - 241 .

Dayan I ， Roth HR ， Zhong A ， et al . Federated learning for predicting clinical outcomes in patients with COVID-19 [J ] . Nat Med ， 2021 ， 27 （ 10 ）： 1735 - 1743 .

Zilberman DE ， Ferrandino MN ， Preminger GM ， et al . In vivo determination of urinary stone composition using dual energy CT with advanced post-acquisition processing [J ] . J Urol ， 2010 ， 184 （ 6 ）： 2354 - 2359 .

Lundberg SM ， Lee SI . A unified approach to interpreting model predictions [C ] . Advances in Neural Information Processing Systems ， 2017 ， 30 ： 4765 - 4774 .

Kazemi Y ， Mirroshandel SA . A novel method for predicting kidney stone type using ensemble learning [J ] . Artif Intell Med ， 2018 ， 84 ： 117 - 126 .

Lundberg SM ， Nair B ， Vavilala MS ， et al . Explainable machine-learning predictions for the prevention of hypoxaemia during surgery [J ] . Nat Biomed Eng ， 2018 ， 2 （ 10 ）： 749 - 760 .

Topol EJ . High-performance medicine：the convergence of human and artificial intelligence [J ] . Nat Med ， 2019 ， 25 （ 1 ）： 44 - 56 .

Zhao YQ ， Yang BY ， Wang XC ， et al . Exploring the Interplay between Calcium Oxalate Crystals and Renal Tubular Epithelial Cell Injury： Implications for the Formation and Prevention of Kidney Stones [J ] . Integr Med Nephrol Androl ， 2024 ， 11 ： e23-00022 .

Wang J ， Chen D ， Huang W ， et al . Aptamer-functionalized field-effect transistor biosensors for disease diagnosis and environmental monitoring [J ] . Exploration ， 2023 ， 3 ： 20210027 .

You C ， Shen Y ， Sun S ， et al . Artificial intelligence in breast imaging： Current situation and clinical challenges [J ] . Exploration ， 2023 ， 3 ： 20230007 .

Tang Q ， Wu GW ， Sun L ， et al . Diagnostic value of a dual-source CT-based imaging model for upper urinary tract stones in children [J ] . Chin J CT MRI ， 2025 （ 01 ）： 143 - 146 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research advances in artificial intelligence for difficult airway prediction

Advances in the application of ultrasound combined with radiomics and artificial intelligence in the diagnosis and prognostic evaluation of gastrointestinal stromal tumors

Optimization strategy and practice analysis of airway management based on artificial intelligence

Advance and prospect of PMCT in forensic pathology

Improvement in bone age assessment efficiency of physicians based on the artificial intelligence-assisted bone age assessment system

Related Author

Shao Jianlin

Zhou Guilin

Liu Yang

He Xuemei

Guo Xiangyang

Han Yongzheng

Wang Mingya

Zhao Meiyu

Related Institution

Department of Anesthesiology，The First Affiliated Hospital of Kunming Medical University

Department of Ultrasound，The First Affiliated Hospital of Chongqing Medical University

China Academy of Information and Communications Technology

Department of Anesthesiology， Peking University Third Hospital

Shenyang Municipal People’s Procuratorate of Liaoning Province

⁰