Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients
Abstract Renal replacement therapy (RRT) is a crucial treatment for sepsis-associated acute kidney injury (S-AKI), but it is uncertain which S-AKI patients should receive immediate RRT. Identifying the characteristics of patients who may benefit the most from RRT is an important task. This retrospec...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-55653-x |
| _version_ | 1797266802391121920 |
|---|---|
| author | Guanggang Li Bo Li Bin Song Dandan Liu Yue Sun Hongyan Ju Xiuping Xu Jingkun Mao Feihu Zhou |
| author_facet | Guanggang Li Bo Li Bin Song Dandan Liu Yue Sun Hongyan Ju Xiuping Xu Jingkun Mao Feihu Zhou |
| author_sort | Guanggang Li |
| collection | DOAJ |
| description | Abstract Renal replacement therapy (RRT) is a crucial treatment for sepsis-associated acute kidney injury (S-AKI), but it is uncertain which S-AKI patients should receive immediate RRT. Identifying the characteristics of patients who may benefit the most from RRT is an important task. This retrospective study utilized a public database and enrolled S-AKI patients, who were divided into RRT and non-RRT groups. Uplift modeling was used to estimate the individual treatment effect (ITE) of RRT. The validity of different models was compared using a qini curve. After labeling the patients in the validation cohort, we characterized the patients who would benefit the most from RRT and created a nomogram. A total of 8289 patients were assessed, among whom 591 received RRT, and 7698 did not receive RRT. The RRT group had a higher severity of illness than the non-RRT group, with a Sequential Organ Failure Assessment (SOFA) score of 9 (IQR 6,11) vs. 5 (IQR 3,7). The 28-day mortality rate was higher in the RRT group than the non-RRT group (34.83% vs. 14.61%, p < 0.0001). Propensity score matching (PSM) was used to balance baseline characteristics, 458 RRT patients and an equal number of non-RRT patients were enrolled for further research. After PSM, 28-day mortality of RRT and non-RRT groups were 32.3% vs. 39.3%, P = 0.033. Using uplift modeling, we found that urine output, fluid input, mean blood pressure, body temperature, and lactate were the top 5 factors that had the most influence on RRT effect. The area under the uplift curve (AUUC) of the class transformation model was 0.068, the AUUC of SOFA was 0.018, and the AUUC of Kdigo-stage was 0.050. The class transformation model was more efficient in predicting individual treatment effect. A logistic regression model was developed, and a nomogram was drawn to predict whether an S-AKI patient can benefit from RRT. Six factors were taken into account (urine output, creatinine, lactate, white blood cell count, glucose, respiratory rate). Uplift modeling can better predict the ITE of RRT on S-AKI patients than conventional score systems such as Kdigo and SOFA. We also found that white blood cell count is related to the benefits of RRT, suggesting that changes in inflammation levels may be associated with the effects of RRT on S-AKI patients. |
| first_indexed | 2024-04-25T01:06:29Z |
| format | Article |
| id | doaj.art-d821c3ae139a4e7ab4e8c4bfec429329 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-25T01:06:29Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-d821c3ae139a4e7ab4e8c4bfec4293292024-03-10T12:13:07ZengNature PortfolioScientific Reports2045-23222024-03-0114111110.1038/s41598-024-55653-xUplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patientsGuanggang Li0Bo Li1Bin Song2Dandan Liu3Yue Sun4Hongyan Ju5Xiuping Xu6Jingkun Mao7Feihu Zhou8Medical School of Chinese PLADepartment of Automation, Tianjin University of TechnologyDepartment of Critical Care Medicine, The Seventh Medical Centre, Chinese PLA General HospitalDepartment of Critical Care Medicine, The Seventh Medical Centre, Chinese PLA General HospitalDepartment of Critical Care Medicine, The Seventh Medical Centre, Chinese PLA General HospitalDepartment of Critical Care Medicine, The Seventh Medical Centre, Chinese PLA General HospitalDepartment of Critical Care Medicine, The Seventh Medical Centre, Chinese PLA General HospitalDepartment of Automation, Tianjin University of TechnologyDepartment of Critical Care Medicine, The First Medical Centre, Chinese PLA General HospitalAbstract Renal replacement therapy (RRT) is a crucial treatment for sepsis-associated acute kidney injury (S-AKI), but it is uncertain which S-AKI patients should receive immediate RRT. Identifying the characteristics of patients who may benefit the most from RRT is an important task. This retrospective study utilized a public database and enrolled S-AKI patients, who were divided into RRT and non-RRT groups. Uplift modeling was used to estimate the individual treatment effect (ITE) of RRT. The validity of different models was compared using a qini curve. After labeling the patients in the validation cohort, we characterized the patients who would benefit the most from RRT and created a nomogram. A total of 8289 patients were assessed, among whom 591 received RRT, and 7698 did not receive RRT. The RRT group had a higher severity of illness than the non-RRT group, with a Sequential Organ Failure Assessment (SOFA) score of 9 (IQR 6,11) vs. 5 (IQR 3,7). The 28-day mortality rate was higher in the RRT group than the non-RRT group (34.83% vs. 14.61%, p < 0.0001). Propensity score matching (PSM) was used to balance baseline characteristics, 458 RRT patients and an equal number of non-RRT patients were enrolled for further research. After PSM, 28-day mortality of RRT and non-RRT groups were 32.3% vs. 39.3%, P = 0.033. Using uplift modeling, we found that urine output, fluid input, mean blood pressure, body temperature, and lactate were the top 5 factors that had the most influence on RRT effect. The area under the uplift curve (AUUC) of the class transformation model was 0.068, the AUUC of SOFA was 0.018, and the AUUC of Kdigo-stage was 0.050. The class transformation model was more efficient in predicting individual treatment effect. A logistic regression model was developed, and a nomogram was drawn to predict whether an S-AKI patient can benefit from RRT. Six factors were taken into account (urine output, creatinine, lactate, white blood cell count, glucose, respiratory rate). Uplift modeling can better predict the ITE of RRT on S-AKI patients than conventional score systems such as Kdigo and SOFA. We also found that white blood cell count is related to the benefits of RRT, suggesting that changes in inflammation levels may be associated with the effects of RRT on S-AKI patients.https://doi.org/10.1038/s41598-024-55653-xSepsis associated acute kidney injuryRenal replacement therapyIndividual treatment effect |
| spellingShingle | Guanggang Li Bo Li Bin Song Dandan Liu Yue Sun Hongyan Ju Xiuping Xu Jingkun Mao Feihu Zhou Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients Scientific Reports Sepsis associated acute kidney injury Renal replacement therapy Individual treatment effect |
| title | Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients |
| title_full | Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients |
| title_fullStr | Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients |
| title_full_unstemmed | Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients |
| title_short | Uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis-associated acute kidney injury patients |
| title_sort | uplift modeling to predict individual treatment effects of renal replacement therapy in sepsis associated acute kidney injury patients |
| topic | Sepsis associated acute kidney injury Renal replacement therapy Individual treatment effect |
| url | https://doi.org/10.1038/s41598-024-55653-x |
| work_keys_str_mv | AT guanggangli upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT boli upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT binsong upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT dandanliu upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT yuesun upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT hongyanju upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT xiupingxu upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT jingkunmao upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients AT feihuzhou upliftmodelingtopredictindividualtreatmenteffectsofrenalreplacementtherapyinsepsisassociatedacutekidneyinjurypatients |