{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T15:37:23Z","timestamp":1789227443262,"version":"build-2803163510"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T00:00:00Z","timestamp":1710806400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Acute kidney injury (AKI) is a critical complication of immune checkpoint inhibitor therapy. Since the etiology of AKI in patients undergoing cancer therapy varies, clarifying underlying causes in individual cases is critical for optimal cancer treatment. Although it is essential to individually analyze immune checkpoint inhibitor-treated patients for underlying pathologies for each AKI episode, these analyses have not been realized. Herein, we aimed to individually clarify the underlying causes of AKI in immune checkpoint inhibitor-treated patients using a new clustering approach with Shapley Additive exPlanations (SHAP).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We developed a gradient-boosting decision tree-based machine learning model continuously predicting AKI within 7 days, using the medical records of 616 immune checkpoint inhibitor-treated patients. The temporal changes in individual predictive reasoning in AKI prediction models represented the key features contributing to each AKI prediction and clustered AKI patients based on the features with high predictive contribution quantified in time series by SHAP. We searched for common clinical backgrounds of AKI patients in each cluster, compared with annotation by three nephrologists.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>One hundred and twelve patients (18.2%) had at least one AKI episode. They were clustered per the key feature, and their SHAP value patterns, and the nephrologists assessed the clusters\u2019 clinical relevance. Receiver operating characteristic analysis revealed that the area under the curve was 0.880. Patients with AKI were categorized into four clusters with significant prognostic differences (p = 0.010). The leading causes of AKI for each cluster, such as hypovolemia, drug-related, and cancer cachexia, were all clinically interpretable, which conventional approaches cannot obtain.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Our results suggest that the clustering method of individual predictive reasoning in machine learning models can be applied to infer clinically critical factors for developing each episode of AKI among patients with multiple AKI risk factors, such as immune checkpoint inhibitor-treated patients.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0298673","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T17:23:48Z","timestamp":1710869028000},"page":"e0298673","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":12,"title":["Interpretable machine learning-based individual analysis of acute kidney injury in immune checkpoint inhibitor therapy"],"prefix":"10.1371","volume":"19","author":[{"given":"Minoru","family":"Sakuragi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eiichiro","family":"Uchino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noriaki","family":"Sato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeshi","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akihiko","family":"Ueda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6346-3999","authenticated-orcid":true,"given":"Yohei","family":"Mineharu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryosuke","family":"Kojima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Motoko","family":"Yanagita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-4208","authenticated-orcid":true,"given":"Yasushi","family":"Okuno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,3,19]]},"reference":[{"key":"pone.0298673.ref001","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.2215\/CJN.03140312","article-title":"Onco-nephrology: AKI in the cancer patient","volume":"7","author":"AQ Lam","year":"2012","journal-title":"Clin J Am Soc Nephrol"},{"key":"pone.0298673.ref002","doi-asserted-by":"crossref","first-page":"347","DOI":"10.2215\/CJN.03530412","article-title":"Incidence rate, clinical correlates, and outcomes of AKI in patients admitted to a comprehensive cancer center","volume":"8","author":"AK Salahudeen","year":"2013","journal-title":"Clin J Am Soc Nephrol"},{"key":"pone.0298673.ref003","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1053\/j.ajkd.2015.04.042","article-title":"Onco-nephrology: core curriculum 2015","volume":"66","author":"EP Cohen","year":"2015","journal-title":"Am J Kidney Dis"},{"key":"pone.0298673.ref004","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1056\/NEJMra1703481","article-title":"Immune-related adverse events associated with immune checkpoint blockade","volume":"378","author":"MA Postow","year":"2018","journal-title":"N Engl J Med"},{"key":"pone.0298673.ref005","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1053\/j.ajkd.2019.03.433","article-title":"Kidney complications of immune checkpoint inhibitors: a review","volume":"74","author":"R Shingarev","year":"2019","journal-title":"Am J Kidney Dis"},{"key":"pone.0298673.ref006","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1016\/j.kint.2016.04.008","article-title":"Clinicopathological features of acute kidney injury associated with immune checkpoint inhibitors","volume":"90","author":"FB Cortazar","year":"2016","journal-title":"Kidney Int"},{"key":"pone.0298673.ref007","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1053\/j.ajkd.2016.02.057","article-title":"Association of acute interstitial nephritis with programmed cell death 1 Inhibitor Therapy in Lung Cancer Patients","volume":"68","author":"AC Shirali","year":"2016","journal-title":"Am J Kidney Dis"},{"key":"pone.0298673.ref008","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1186\/s40425-018-0478-8","article-title":"Nephrotoxicity of immune checkpoint inhibitors beyond tubulointerstitial nephritis: single-center experience","volume":"7","author":"O Mamlouk","year":"2019","journal-title":"J Immunother Cancer"},{"key":"pone.0298673.ref009","doi-asserted-by":"crossref","first-page":"e0252978","DOI":"10.1371\/journal.pone.0252978","article-title":"Immune checkpoint inhibitor-associated acute kidney injury and mortality: an observational study","volume":"16","author":"MS Koks","year":"2021","journal-title":"PLOS ONE"},{"key":"pone.0298673.ref010","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1007\/s10157-020-02008-1","article-title":"Incidence and risk factors of acute kidney injury, and its effect on mortality among Japanese patients receiving immune check point inhibitors: a single-center observational study","volume":"25","author":"Y Shimamura","year":"2021","journal-title":"Clin Exp Nephrol"},{"key":"pone.0298673.ref011","first-page":"887","article-title":"Acute kidney injury as a risk factor for mortality in oncological patients receiving checkpoint inhibitors","volume":"37","author":"C Garc\u00eda-Carro","year":"2022","journal-title":"Nephrol Dial Transplant"},{"key":"pone.0298673.ref012","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.2215\/CJN.00990119","article-title":"The incidence, causes, and risk factors of acute kidney injury in patients receiving immune checkpoint inhibitors","volume":"14","author":"H Seethapathy","year":"2019","journal-title":"Clin J Am Soc Nephrol"},{"issue":"2020","key":"pone.0298673.ref013","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1681\/ASN.2019070676","article-title":"Clinical features and outcomes of immune checkpoint inhibitor-associated Aki: A Multicenter Study","volume":"31","author":"FB Cortazar","year":"2020","journal-title":"J Am Soc Nephrol"},{"key":"pone.0298673.ref014","doi-asserted-by":"crossref","first-page":"e000467","DOI":"10.1136\/jitc-2019-000467","article-title":"Acute kidney injury associated with immune checkpoint inhibitor therapy: incidence, risk factors and outcomes","volume":"8","author":"A Meraz-Mu\u00f1oz","year":"2020","journal-title":"J Immunother Cancer"},{"key":"pone.0298673.ref015","doi-asserted-by":"crossref","first-page":"e003467","DOI":"10.1136\/jitc-2021-003467","article-title":"Acute kidney injury in patients treated with immune checkpoint inhibitors","volume":"9","author":"S Gupta","year":"2021","journal-title":"J Immunother Cancer"},{"issue":"10","key":"pone.0298673.ref016","doi-asserted-by":"crossref","first-page":"1881","DOI":"10.1093\/ckj\/sfac109","article-title":"Risk factors associated with immune checkpoint inhibitor\u2014induced acute kidney injury compared with other immune-related adverse events: a case\u2014control study","volume":"15","author":"AO G\u00e9rard","year":"2022","journal-title":"Clin Kidney J"},{"key":"pone.0298673.ref017","doi-asserted-by":"crossref","first-page":"18752","DOI":"10.1038\/s41598-022-21912-y","article-title":"Incidence, risk factors and prognosis of acute kidney injury in patients treated with immune checkpoint inhibitors: a retrospective study","volume":"12","author":"MS Ji","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0298673.ref018","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"pone.0298673.ref019","first-page":"1","article-title":"Kidney disease: improving global outcomes (KDIGO) acute kidney injury work group. KDIGO clinical practice guideline for acute kidney injury","volume":"2","author":"JA Kellum","year":"2012","journal-title":"Kidney Int Suppl"},{"key":"pone.0298673.ref020","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume":"30","author":"G Ke","year":"2017","journal-title":"NIPS 2017"},{"key":"pone.0298673.ref021","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pone.0298673.ref022","doi-asserted-by":"crossref","first-page":"17298","DOI":"10.1038\/s41598-018-35487-0","article-title":"Feature ranking in predictive models for hospital-acquired acute kidney injury","volume":"8","author":"L Wu","year":"2018","journal-title":"Sci Rep"},{"key":"pone.0298673.ref023","doi-asserted-by":"crossref","first-page":"1070","DOI":"10.1097\/CCM.0000000000003123","article-title":"The development of a machine learning inpatient acute kidney injury prediction model","volume":"46","author":"JL Koyner","year":"2018","journal-title":"Crit Care Med"},{"key":"pone.0298673.ref024","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1093\/jamiaopen\/ooy043","article-title":"Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records","volume":"2","author":"J He","year":"2019","journal-title":"JAMIA Open"},{"key":"pone.0298673.ref025","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","article-title":"A clinically applicable approach to continuous prediction of future acute kidney injury","volume":"572","author":"N Toma\u0161ev","year":"2019","journal-title":"Nature"},{"key":"pone.0298673.ref026","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1186\/s12882-020-01980-w","article-title":"Changing relative risk of clinical factors for hospital-acquired acute kidney injury across age groups: a retrospective cohort study","volume":"21","author":"L Wu","year":"2020","journal-title":"BMC Nephrol"},{"key":"pone.0298673.ref027","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41746-020-00346-8","article-title":"Deep-learning-based real-time prediction of acute kidney injury outperforms human predictive performance","volume":"3","author":"N Rank","year":"2020","journal-title":"npj Digit Med"},{"key":"pone.0298673.ref028","doi-asserted-by":"crossref","first-page":"e0199839","DOI":"10.1371\/journal.pone.0199839","article-title":"Predicting acute kidney injury in cancer patients using heterogeneous and irregular data","volume":"13","author":"N Park","year":"2018","journal-title":"PLOS ONE"},{"key":"pone.0298673.ref029","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1681\/ASN.2019070745","article-title":"A time-updated, parsimonious model to predict AKI in hospitalized children","volume":"31","author":"I Sandokji","year":"2020","journal-title":"J Am Soc Nephrol"},{"key":"pone.0298673.ref030","doi-asserted-by":"crossref","first-page":"1927313","DOI":"10.1080\/2162402X.2021.1927313","article-title":"Incidence, predictors, and survival impact of acute kidney injury in patients with melanoma treated with immune checkpoint inhibitors: a 10-year single-institution analysis","volume":"10","author":"M Abdelrahim","year":"2021","journal-title":"Oncoimmunology"},{"key":"pone.0298673.ref031","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1038\/s41467-020-17431-x","article-title":"Explainable artificial intelligence model to predict acute critical illness from electronic health records","volume":"11","author":"SM Lauritsen","year":"2020","journal-title":"Nat Commun"},{"key":"pone.0298673.ref032","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1186\/s12967-021-02990-4","article-title":"An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation","volume":"19","author":"Y Zhang","year":"2021","journal-title":"J Transl Med"},{"key":"pone.0298673.ref033","first-page":"2472","article-title":"Exploring features contributing to the early prediction of sepsis using machine learning","volume":"20241","author":"E Shakeri","year":"2021","journal-title":"annu. Int. Conf. IEEE Eng Med Biol Soc"},{"key":"pone.0298673.ref034","doi-asserted-by":"crossref","first-page":"217","DOI":"10.3390\/jpm12020217","article-title":"Systemic periodontal risk score using an innovative machine learning strategy: an observational study","volume":"12","author":"P Monsarrat","year":"2022","journal-title":"J Pers Med"},{"key":"pone.0298673.ref035","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/s41746-021-00426-3","article-title":"Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?","volume":"4","author":"BK Beaulieu-Jones","year":"2021","journal-title":"npj Digit Med"},{"key":"pone.0298673.ref036","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/s41666-022-00114-1","article-title":"Explainable artificial intelligence for predictive modeling in healthcare","volume":"6","author":"CC Yang","year":"2022","journal-title":"J Healthc Inform Res"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0298673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T17:24:16Z","timestamp":1710869056000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0298673"}},"subtitle":[],"editor":[{"given":"Giuseppe","family":"Remuzzi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,19]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0298673","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,19]]}}}