Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients
Abstract Early prediction of acute kidney injury (AKI) may provide a crucial opportunity for AKI prevention. To date, no prediction model targeting AKI among general hospitalized patients in developing countries has been published. Here we show a simple, real-time, interpretable AKI prediction model...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-024-55629-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559327068913664 |
|---|---|
| author | Yuhui Zhang Damin Xu Jianwei Gao Ruiguo Wang Kun Yan Hong Liang Juan Xu Youlu Zhao Xizi Zheng Lingyi Xu Jinwei Wang Fude Zhou Guopeng Zhou Qingqing Zhou Zhao Yang Xiaoli Chen Yulan Shen Tianrong Ji Yunlin Feng Ping Wang Jundong Jiao Li Wang Jicheng Lv Li Yang |
| author_facet | Yuhui Zhang Damin Xu Jianwei Gao Ruiguo Wang Kun Yan Hong Liang Juan Xu Youlu Zhao Xizi Zheng Lingyi Xu Jinwei Wang Fude Zhou Guopeng Zhou Qingqing Zhou Zhao Yang Xiaoli Chen Yulan Shen Tianrong Ji Yunlin Feng Ping Wang Jundong Jiao Li Wang Jicheng Lv Li Yang |
| author_sort | Yuhui Zhang |
| collection | DOAJ |
| description | Abstract Early prediction of acute kidney injury (AKI) may provide a crucial opportunity for AKI prevention. To date, no prediction model targeting AKI among general hospitalized patients in developing countries has been published. Here we show a simple, real-time, interpretable AKI prediction model for general hospitalized patients developed from a large tertiary hospital in China, which has been validated across five independent, geographically distinct, different tiered hospitals. The model containing 20 readily available variables demonstrates consistent, high levels of predictive discrimination in validation cohort, with AUCs for serum creatinine-based AKI and severe AKI within 48 h ranging from 0.74–0.85 and 0.83–0.90 for transported models and from 0.81–0.90 and 0.88–0.95 for refitted models, respectively. With optimal probability cutoffs, the refitted model could predict AKI at a median of 72 (24–198) hours in advance in internal validation, and 54–90 h in advance in external validation. Broad application of the model in the future may provide an effective, convenient and cost-effective approach for AKI prevention. |
| format | Article |
| id | doaj-art-ef8f8259cf7547d792db7732f78201c3 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-ef8f8259cf7547d792db7732f78201c32025-01-05T12:38:47ZengNature PortfolioNature Communications2041-17232025-01-0116111710.1038/s41467-024-55629-5Development and validation of a real-time prediction model for acute kidney injury in hospitalized patientsYuhui Zhang0Damin Xu1Jianwei Gao2Ruiguo Wang3Kun Yan4Hong Liang5Juan Xu6Youlu Zhao7Xizi Zheng8Lingyi Xu9Jinwei Wang10Fude Zhou11Guopeng Zhou12Qingqing Zhou13Zhao Yang14Xiaoli Chen15Yulan Shen16Tianrong Ji17Yunlin Feng18Ping Wang19Jundong Jiao20Li Wang21Jicheng Lv22Li Yang23Renal Division, Peking University First HospitalRenal Division, Peking University First HospitalArtificial Intelligence Institute, Digital Health China Technologies Co. LtdArtificial Intelligence Institute, Digital Health China Technologies Co. LtdSchool of Computer Science, Peking UniversitySchool of Software and Microelectronics, Peking UniversityArtificial Intelligence Institute, Digital Health China Technologies Co. LtdRenal Division, Peking University First HospitalRenal Division, Peking University First HospitalRenal Division, Peking University First HospitalRenal Division, Peking University First HospitalRenal Division, Peking University First HospitalInformation Department, Peking University First HospitalRenal Division, Peking University First HospitalOffice of Academic Research, Peking University First HospitalRenal Division, Taiyuan Central HospitalRenal Division, Beijing Miyun District HospitalDepartment of Nephrology, The Second Affiliated Hospital of Harbin Medical UniversityDepartment of Nephrology, Sichuan Provincial People’s HospitalNational Engineering Research Center for Software Engineering, Peking UniversityDepartment of Nephrology, The Second Affiliated Hospital of Harbin Medical UniversityDepartment of Nephrology, Sichuan Provincial People’s HospitalRenal Division, Peking University First HospitalRenal Division, Peking University First HospitalAbstract Early prediction of acute kidney injury (AKI) may provide a crucial opportunity for AKI prevention. To date, no prediction model targeting AKI among general hospitalized patients in developing countries has been published. Here we show a simple, real-time, interpretable AKI prediction model for general hospitalized patients developed from a large tertiary hospital in China, which has been validated across five independent, geographically distinct, different tiered hospitals. The model containing 20 readily available variables demonstrates consistent, high levels of predictive discrimination in validation cohort, with AUCs for serum creatinine-based AKI and severe AKI within 48 h ranging from 0.74–0.85 and 0.83–0.90 for transported models and from 0.81–0.90 and 0.88–0.95 for refitted models, respectively. With optimal probability cutoffs, the refitted model could predict AKI at a median of 72 (24–198) hours in advance in internal validation, and 54–90 h in advance in external validation. Broad application of the model in the future may provide an effective, convenient and cost-effective approach for AKI prevention.https://doi.org/10.1038/s41467-024-55629-5 |
| spellingShingle | Yuhui Zhang Damin Xu Jianwei Gao Ruiguo Wang Kun Yan Hong Liang Juan Xu Youlu Zhao Xizi Zheng Lingyi Xu Jinwei Wang Fude Zhou Guopeng Zhou Qingqing Zhou Zhao Yang Xiaoli Chen Yulan Shen Tianrong Ji Yunlin Feng Ping Wang Jundong Jiao Li Wang Jicheng Lv Li Yang Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients Nature Communications |
| title | Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients |
| title_full | Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients |
| title_fullStr | Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients |
| title_full_unstemmed | Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients |
| title_short | Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients |
| title_sort | development and validation of a real time prediction model for acute kidney injury in hospitalized patients |
| url | https://doi.org/10.1038/s41467-024-55629-5 |
| work_keys_str_mv | AT yuhuizhang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT daminxu developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT jianweigao developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT ruiguowang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT kunyan developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT hongliang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT juanxu developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT youluzhao developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT xizizheng developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT lingyixu developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT jinweiwang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT fudezhou developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT guopengzhou developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT qingqingzhou developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT zhaoyang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT xiaolichen developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT yulanshen developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT tianrongji developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT yunlinfeng developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT pingwang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT jundongjiao developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT liwang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT jichenglv developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients AT liyang developmentandvalidationofarealtimepredictionmodelforacutekidneyinjuryinhospitalizedpatients |