Advertisement

Machine Learning Models to Predict 24 Hour Urinary Abnormalities for Kidney Stone Disease

      Abstract

      OBJECTIVE

      To help guide empiric therapy for kidney stone disease, we sought to demonstrate the feasibility of predicting 24-hour urine abnormalities using machine learning methods.

      METHODS

      We trained a machine learning model (XGBoost [XG]) to predict 24-hour urine abnormalities from electronic health record-derived data (n = 1314). The machine learning model was compared to a logistic regression model [LR]. Additionally, an ensemble (EN) model combining both XG and LR models was evaluated as well. Models predicted binary 24-hour urine values for volume, sodium, oxalate, calcium, uric acid, and citrate; as well as a multiclass prediction of pH. We evaluated performance using area under the receiver operating curve (AUC-ROC) and identified predictors for each model.

      RESULTS

      The XG model was able to discriminate 24-hour urine abnormalities with fair performance, comparable to LR. The XG model most accurately predicted abnormalities of urine volume (accuracy = 98%, AUC-ROC = 0.59), uric acid (69%, 0.73) and elevated urine sodium (71%, 0.79). The LR model outperformed the XG model alone in prediction of abnormalities of urinary pH (AUC-ROC of 0.66 vs 0.57) and citrate (0.69 vs 0.64). The EN model most accurately predicted abnormalities of oxalate (accuracy = 65%, ROC-AUC = 0.70) and citrate (65%, 0.69) with overall similar predictive performance to either XG or LR alone. Body mass index, age, and gender were the three most important features for training the models for all outcomes.

      CONCLUSION

      Urine chemistry prediction for kidney stone disease appears to be feasible with machine learning methods. Further optimization of the performance could facilitate dietary or pharmacologic prevention.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Urology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Fink HA
        • Wilt TJ
        • Eidman KE
        • Garimella PS
        • MacDonald R.
        Recurrent nephrolithiasis in adults: comparative effectiveness of preventive medical strategies.
        Agency Healthc Res Qual. 2012; 61: 232
        • Uribarri J
        • Oh MS
        • Carroll HJ.
        The first kidney stone.
        Ann Intern Med. 1989; 111: 1006-1009https://doi.org/10.7326/0003-4819-111-12-1006
        • Pearle MS
        • Goldfarb DS
        • Assimos DG
        • et al.
        Medical management of kidney stones: AUA guideline.
        J Urol. 2014; 192: 316-324https://doi.org/10.1016/j.juro.2014.05.006
        • Milose JC
        • Kaufman SR
        • Hollenbeck BK
        • Wolf JS
        • Hollingsworth JM.
        Prevalence of 24-hour urine collection in high risk stone formers.
        J Urol. 2014; 191: 376-380https://doi.org/10.1016/j.juro.2013.08.080
        • Otto BJ
        • Bozorgmehri S
        • Kuo J
        • Canales M
        • Bird VG
        • Canales B.
        Age, body mass index, and gender predict 24-hour urine parameters in recurrent idiopathic calcium oxalate stone formers.
        J Endourol. 2017; 31: 1335-1341https://doi.org/10.1089/end.2017.0352
        • Abraham A
        • Kavoussi N
        • Sui W
        • Bejan C
        • Capra JA
        • Hsi R.
        Machine learning prediction of kidney stone composition using electronic health record-derived features.
        J Endourol. 2021; (Published online July 27)https://doi.org/10.1089/end.2021.0211
        • Danciu I
        • Cowan JD
        • Basford M
        • et al.
        Secondary use of clinical data: the Vanderbilt approach.
        J Biomed Inform. 2014; 52: 28-35https://doi.org/10.1016/j.jbi.2014.02.003
        • Harris PA
        • Taylor R
        • Minor BL
        • et al.
        The REDCap consortium: building an international community of software platform partners.
        J Biomed Inform. 2019; 95103208https://doi.org/10.1016/j.jbi.2019.103208
        • Harris PA
        • Taylor R
        • Thielke R
        • Payne J
        • Gonzalez N
        • Conde JG.
        Research electronic data capture (REDCap)—a metadata-driven methodology and workflow process for providing translational research informatics support.
        J Biomed Inform. 2009; 42: 377-381https://doi.org/10.1016/j.jbi.2008.08.010
        • Harris PA
        • Taylor R
        • Thielke R
        • Payne J
        • Gonzalez N
        • Conde JG.
        Research electronic data capture (REDCap)—a metadata-driven methodology and workflow process for providing translational research informatics support.
        J Biomed Inform. 2009; 42: 377-381
        • Harris PA
        • Taylor R
        • Minor BL
        • et al.
        The REDCap consortium: building an international community of software platform partners.
        J Biomed Inform. 2019; 95103208
        • Chen T
        • Guestrin C.
        XGBoost: a scalable tree boosting system.
        in: Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min. 2016https://doi.org/10.1145/2939672.2939785
        • Curhan GC
        • Willett WC
        • Speizer FE
        • Stampfer MJ.
        Twenty-four-hour urine chemistries and the risk of kidney stones among women and men.
        Kidney Int. 2001; 59: 2290-2298https://doi.org/10.1046/j.1523-1755.2001.00746.x
        • Bergstra J
        • Yamins D
        • Cox D.
        Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures.
        Presented at the 30th International Conference on Machine Learning (ICML 2013), Atlanta, Gerorgia, June 16 – 21, 2013. In JMLR Workshop and Conference Proceedings. 2013; 28: 115-123
        • Hsi RS
        • Yan PL
        • Goldfarb DS
        • et al.
        Comparison of selective versus empiric pharmacologic preventative therapy with kidney stone recurrence.
        Urology. 2021; 149: 81-88https://doi.org/10.1016/j.urology.2020.11.054
        • Hsi RS
        • Yan PL
        • Crivelli JJ
        • Goldfarb DS
        • Shahinian V
        • Hollingsworth JM.
        Comparison of selective vs empiric pharmacologic preventive therapy of kidney stone recurrence with high-risk features.
        Urology. 2022; (Published online February 17S0090-4295(22)00140-6)https://doi.org/10.1016/j.urology.2021.12.037
        • Maalouf NM
        • Sakhaee K
        • Parks JH
        • Coe FL
        • Adams-Huet B
        • Pak CYC.
        Association of urinary pH with body weight in nephrolithiasis.
        Kidney Int. 2004; 65: 1422-1425https://doi.org/10.1111/j.1523-1755.2004.00522.x
        • Lieske JC
        • Rule AD
        • Krambeck AE
        • et al.
        Stone composition as a function of age and sex.
        Clin J Am Soc Nephrol CJASN. 2014; 9: 2141-2146https://doi.org/10.2215/CJN.05660614