Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation
BackgroundSepsis-associated acute kidney injury (S-AKI) has a significant impact on patient survival, with continuous renal replacement therapy (CRRT) being a crucial intervention. However, the optimal timing for CRRT initiation remains controversial.MethodsUsing the MIMIC-IV database for model deve...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1483710/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591658443603968 |
|---|---|
| author | Chuanren Zhuang Ruomeng Hu Ke Li Zhengshuang Liu Songjie Bai Sheng Zhang Xuehuan Wen |
| author_facet | Chuanren Zhuang Ruomeng Hu Ke Li Zhengshuang Liu Songjie Bai Sheng Zhang Xuehuan Wen |
| author_sort | Chuanren Zhuang |
| collection | DOAJ |
| description | BackgroundSepsis-associated acute kidney injury (S-AKI) has a significant impact on patient survival, with continuous renal replacement therapy (CRRT) being a crucial intervention. However, the optimal timing for CRRT initiation remains controversial.MethodsUsing the MIMIC-IV database for model development and the eICU database for external validation, we analyzed patients with S-AKI to compare survival rates between early and late CRRT initiation groups. Propensity score matching was performed to address potential selection bias. Subgroup analyses stratified patients by disease severity using SOFA scores (low ≤10, medium 11–15, high >15) and creatinine levels (low ≤3 mg/dL, medium 3–5 mg/dL, high >5 mg/dL). Multiple machine learning models were developed and evaluated to predict patient prognosis, with Shapley Additive exPlanations (SHAP) analysis identifying key prognostic factors.ResultsAfter propensity score matching, late CRRT initiation was associated with improved survival probability, but led to increased hospital and ICU stays. Subgroup analyses showed consistent trends favoring late CRRT across all SOFA categories, with the most pronounced effect in high SOFA scores (>15, p = 0.058). The GBM model demonstrated robust predictive performance (average C-index 0.694 in validation and test sets). SHAP analysis identified maximum lactate levels, age, and minimum SpO2 as the strongest predictors of mortality, while CRRT timing showed relatively lower impact on outcome prediction.ConclusionWhile later initiation of CRRT in S-AKI patients was associated with improved survival, this benefit comes with increased healthcare resource utilization. The clinical parameters, rather than CRRT timing, are the primary determinants of patient outcomes, suggesting the need for a more personalized approach to CRRT initiation based on overall illness severity. |
| format | Article |
| id | doaj-art-a83cd650f3964f6a943b7b88745e5d88 |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-a83cd650f3964f6a943b7b88745e5d882025-01-22T07:14:18ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-01-011110.3389/fmed.2024.14837101483710Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiationChuanren Zhuang0Ruomeng Hu1Ke Li2Zhengshuang Liu3Songjie Bai4Sheng Zhang5Xuehuan Wen6Department of Laboratory Medicine, Cangnan Hospital of Traditional Chinese Medicine, Wenzhou, Zhejiang, ChinaDepartment of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, ChinaDepartment of Critical Care Medicine, The People’s Hospital of Cangnan Zhejiang, Wenzhou Medical University, Wenzhou, Zhejiang, ChinaDepartment of Critical Care Medicine, Cangnan Hospital of Traditional Chinese Medicine, Wenzhou, Zhejiang, ChinaDepartment of Cardiovascular Surgery, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, ChinaDepartment of Critical Care Medicine, Taizhou Hospital of Zhejiang Province, Wenzhou Medical University, Taizhou, ChinaDepartment of Oncology, The People’s Hospital of Cangnan Zhejiang, Wenzhou Medical University, Wenzhou, Zhejiang, ChinaBackgroundSepsis-associated acute kidney injury (S-AKI) has a significant impact on patient survival, with continuous renal replacement therapy (CRRT) being a crucial intervention. However, the optimal timing for CRRT initiation remains controversial.MethodsUsing the MIMIC-IV database for model development and the eICU database for external validation, we analyzed patients with S-AKI to compare survival rates between early and late CRRT initiation groups. Propensity score matching was performed to address potential selection bias. Subgroup analyses stratified patients by disease severity using SOFA scores (low ≤10, medium 11–15, high >15) and creatinine levels (low ≤3 mg/dL, medium 3–5 mg/dL, high >5 mg/dL). Multiple machine learning models were developed and evaluated to predict patient prognosis, with Shapley Additive exPlanations (SHAP) analysis identifying key prognostic factors.ResultsAfter propensity score matching, late CRRT initiation was associated with improved survival probability, but led to increased hospital and ICU stays. Subgroup analyses showed consistent trends favoring late CRRT across all SOFA categories, with the most pronounced effect in high SOFA scores (>15, p = 0.058). The GBM model demonstrated robust predictive performance (average C-index 0.694 in validation and test sets). SHAP analysis identified maximum lactate levels, age, and minimum SpO2 as the strongest predictors of mortality, while CRRT timing showed relatively lower impact on outcome prediction.ConclusionWhile later initiation of CRRT in S-AKI patients was associated with improved survival, this benefit comes with increased healthcare resource utilization. The clinical parameters, rather than CRRT timing, are the primary determinants of patient outcomes, suggesting the need for a more personalized approach to CRRT initiation based on overall illness severity.https://www.frontiersin.org/articles/10.3389/fmed.2024.1483710/fullsepsisacute kidney injurycontinuous renal replacement therapymachine learningmortalityCRRT timing |
| spellingShingle | Chuanren Zhuang Ruomeng Hu Ke Li Zhengshuang Liu Songjie Bai Sheng Zhang Xuehuan Wen Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation Frontiers in Medicine sepsis acute kidney injury continuous renal replacement therapy machine learning mortality CRRT timing |
| title | Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation |
| title_full | Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation |
| title_fullStr | Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation |
| title_full_unstemmed | Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation |
| title_short | Machine learning prediction models for mortality risk in sepsis-associated acute kidney injury: evaluating early versus late CRRT initiation |
| title_sort | machine learning prediction models for mortality risk in sepsis associated acute kidney injury evaluating early versus late crrt initiation |
| topic | sepsis acute kidney injury continuous renal replacement therapy machine learning mortality CRRT timing |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1483710/full |
| work_keys_str_mv | AT chuanrenzhuang machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT ruomenghu machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT keli machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT zhengshuangliu machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT songjiebai machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT shengzhang machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation AT xuehuanwen machinelearningpredictionmodelsformortalityriskinsepsisassociatedacutekidneyinjuryevaluatingearlyversuslatecrrtinitiation |