Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information
ABSTRACT Predicting cisplatin‐induced acute kidney injury (Cis‐AKI) before its onset is important. We aimed to develop a predictive model for Cis‐AKI using patient clinical information based on an interpretable machine learning algorithm. This single‐center retrospective study included hospitalized...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Clinical and Translational Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1111/cts.70115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589757193912320 |
|---|---|
| author | Kaori Ambe Yuka Aoki Miho Murashima Chiharu Wachino Yuto Deki Masaya Ieda Masahiro Kondo Yoko Furukawa‐Hibi Kazunori Kimura Takayuki Hamano Masahiro Tohkin |
| author_facet | Kaori Ambe Yuka Aoki Miho Murashima Chiharu Wachino Yuto Deki Masaya Ieda Masahiro Kondo Yoko Furukawa‐Hibi Kazunori Kimura Takayuki Hamano Masahiro Tohkin |
| author_sort | Kaori Ambe |
| collection | DOAJ |
| description | ABSTRACT Predicting cisplatin‐induced acute kidney injury (Cis‐AKI) before its onset is important. We aimed to develop a predictive model for Cis‐AKI using patient clinical information based on an interpretable machine learning algorithm. This single‐center retrospective study included hospitalized patients aged ≥ 18 years who received the first course of cisplatin chemotherapy from January 1, 2011, to December 31, 2020, at Nagoya City University Hospital. Cis‐AKI‐positive patients were defined using the serum creatinine criteria of the Kidney Disease Improving Global Outcomes guideline within 14 days of the last day of cisplatin administration in the first course. Patients who received cisplatin but did not develop AKI were considered negative. The CatBoost classification model was constructed with 29 explanatory variables, including laboratory values, concomitant medications, medical history, and cisplatin administration information. In total, 1253 patients were included, of whom 119 developed Cis‐AKI (9.5%). The median time of AKI onset was 7 days, and the interquartile range was 5–8 days. The mean ± standard deviation of the total cisplatin dose in the initial treatment was 77.9 ± 27.1 mg/m2 in Cis‐AKI‐positive patients and 69.3 ± 22.6 mg/m2 in Cis‐AKI‐negative patients. The predictive performance was an ROC‐AUC of 0.78. Model interpretation using SHapley Additive exPlanations showed that concomitant use of intravenous magnesium preparations was negatively correlated with Cis‐AKI, whereas loop diuretics were positively correlated. This suggests the need for magnesium preparations to prevent AKI, although the effects of diuretics may be small. Our model can predict Cis‐AKI early and may be helpful for its avoidance. |
| format | Article |
| id | doaj-art-394094bc26314727a08f7aca0b824e15 |
| institution | Kabale University |
| issn | 1752-8054 1752-8062 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Clinical and Translational Science |
| spelling | doaj-art-394094bc26314727a08f7aca0b824e152025-01-24T08:17:46ZengWileyClinical and Translational Science1752-80541752-80622025-01-01181n/an/a10.1111/cts.70115Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record InformationKaori Ambe0Yuka Aoki1Miho Murashima2Chiharu Wachino3Yuto Deki4Masaya Ieda5Masahiro Kondo6Yoko Furukawa‐Hibi7Kazunori Kimura8Takayuki Hamano9Masahiro Tohkin10Department of Regulatory Science Nagoya City University Graduate School of Pharmaceutical Sciences Nagoya JapanDepartment of Regulatory Science Nagoya City University Graduate School of Pharmaceutical Sciences Nagoya JapanDepartment of Nephrology Nagoya City University Graduate School of Medical Sciences Nagoya JapanNagoya City University Graduate School of Medical Sciences Nagoya JapanDepartment of Regulatory Science Nagoya City University Graduate School of Pharmaceutical Sciences Nagoya JapanDepartment of Regulatory Science Nagoya City University Graduate School of Pharmaceutical Sciences Nagoya JapanNagoya City University Graduate School of Medical Sciences Nagoya JapanNagoya City University Graduate School of Medical Sciences Nagoya JapanNagoya City University Graduate School of Medical Sciences Nagoya JapanDepartment of Nephrology Nagoya City University Graduate School of Medical Sciences Nagoya JapanDepartment of Regulatory Science Nagoya City University Graduate School of Pharmaceutical Sciences Nagoya JapanABSTRACT Predicting cisplatin‐induced acute kidney injury (Cis‐AKI) before its onset is important. We aimed to develop a predictive model for Cis‐AKI using patient clinical information based on an interpretable machine learning algorithm. This single‐center retrospective study included hospitalized patients aged ≥ 18 years who received the first course of cisplatin chemotherapy from January 1, 2011, to December 31, 2020, at Nagoya City University Hospital. Cis‐AKI‐positive patients were defined using the serum creatinine criteria of the Kidney Disease Improving Global Outcomes guideline within 14 days of the last day of cisplatin administration in the first course. Patients who received cisplatin but did not develop AKI were considered negative. The CatBoost classification model was constructed with 29 explanatory variables, including laboratory values, concomitant medications, medical history, and cisplatin administration information. In total, 1253 patients were included, of whom 119 developed Cis‐AKI (9.5%). The median time of AKI onset was 7 days, and the interquartile range was 5–8 days. The mean ± standard deviation of the total cisplatin dose in the initial treatment was 77.9 ± 27.1 mg/m2 in Cis‐AKI‐positive patients and 69.3 ± 22.6 mg/m2 in Cis‐AKI‐negative patients. The predictive performance was an ROC‐AUC of 0.78. Model interpretation using SHapley Additive exPlanations showed that concomitant use of intravenous magnesium preparations was negatively correlated with Cis‐AKI, whereas loop diuretics were positively correlated. This suggests the need for magnesium preparations to prevent AKI, although the effects of diuretics may be small. Our model can predict Cis‐AKI early and may be helpful for its avoidance.https://doi.org/10.1111/cts.70115acute kidney injurycisplatinelectronic medical recordmachine learning |
| spellingShingle | Kaori Ambe Yuka Aoki Miho Murashima Chiharu Wachino Yuto Deki Masaya Ieda Masahiro Kondo Yoko Furukawa‐Hibi Kazunori Kimura Takayuki Hamano Masahiro Tohkin Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information Clinical and Translational Science acute kidney injury cisplatin electronic medical record machine learning |
| title | Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information |
| title_full | Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information |
| title_fullStr | Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information |
| title_full_unstemmed | Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information |
| title_short | Prediction of Cisplatin‐Induced Acute Kidney Injury Using an Interpretable Machine Learning Model and Electronic Medical Record Information |
| title_sort | prediction of cisplatin induced acute kidney injury using an interpretable machine learning model and electronic medical record information |
| topic | acute kidney injury cisplatin electronic medical record machine learning |
| url | https://doi.org/10.1111/cts.70115 |
| work_keys_str_mv | AT kaoriambe predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT yukaaoki predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT mihomurashima predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT chiharuwachino predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT yutodeki predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT masayaieda predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT masahirokondo predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT yokofurukawahibi predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT kazunorikimura predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT takayukihamano predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation AT masahirotohkin predictionofcisplatininducedacutekidneyinjuryusinganinterpretablemachinelearningmodelandelectronicmedicalrecordinformation |