Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease
Sepsis may lead to kidney function decline in patients with chronic kidney disease (CKD), and the deleterious effect may persist in patients who survive sepsis. We used a machine learning approach to predict the risk of end-stage renal disease (ESRD) in sepsis survivors. A total of 11,661 sepsis sur...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/10/3/546 |
| _version_ | 1797472760508710912 |
|---|---|
| author | Kuo-Hua Lee Yuan-Chia Chu Ming-Tsun Tsai Wei-Cheng Tseng Yao-Ping Lin Shuo-Ming Ou Der-Cherng Tarng |
| author_facet | Kuo-Hua Lee Yuan-Chia Chu Ming-Tsun Tsai Wei-Cheng Tseng Yao-Ping Lin Shuo-Ming Ou Der-Cherng Tarng |
| author_sort | Kuo-Hua Lee |
| collection | DOAJ |
| description | Sepsis may lead to kidney function decline in patients with chronic kidney disease (CKD), and the deleterious effect may persist in patients who survive sepsis. We used a machine learning approach to predict the risk of end-stage renal disease (ESRD) in sepsis survivors. A total of 11,661 sepsis survivors were identified from a single-center database of 112,628 CKD patients between 2010 and 2018. During a median follow-up of 3.5 years, a total of 1366 (11.7%) sepsis survivors developed ESRD after hospital discharge. We adopted the random forest, extra trees, extreme gradient boosting, light gradient boosting machine (LGBM), and gradient boosting decision tree (GBDT) algorithms to predict the risk of ESRD development among these patients. GBDT yielded the highest area under the receiver operating characteristic curve of 0.879, followed by LGBM (0.868), and extra trees (0.865). The GBDT model revealed the strong effect of estimated glomerular filtration rates <25 mL/min/1.73 m<sup>2</sup> at discharge in predicting ESRD development. In addition, hemoglobin and proteinuria were also essential predictors. Based on a large-scale dataset, we established a machine learning model computing the risk for ESRD occurrence among sepsis survivors with CKD. External validation is required to evaluate the generalizability of this model. |
| first_indexed | 2024-03-09T20:05:48Z |
| format | Article |
| id | doaj.art-66b1856ecea64e0e9ea09f499c1a1a9d |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-09T20:05:48Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-66b1856ecea64e0e9ea09f499c1a1a9d2023-11-24T00:31:49ZengMDPI AGBiomedicines2227-90592022-02-0110354610.3390/biomedicines10030546Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney DiseaseKuo-Hua Lee0Yuan-Chia Chu1Ming-Tsun Tsai2Wei-Cheng Tseng3Yao-Ping Lin4Shuo-Ming Ou5Der-Cherng Tarng6Division of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanInformation Management Office, Taipei Veterans General Hospital, Taipei 11217, TaiwanDivision of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanDivision of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanDivision of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanDivision of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanDivision of Nephrology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, TaiwanSepsis may lead to kidney function decline in patients with chronic kidney disease (CKD), and the deleterious effect may persist in patients who survive sepsis. We used a machine learning approach to predict the risk of end-stage renal disease (ESRD) in sepsis survivors. A total of 11,661 sepsis survivors were identified from a single-center database of 112,628 CKD patients between 2010 and 2018. During a median follow-up of 3.5 years, a total of 1366 (11.7%) sepsis survivors developed ESRD after hospital discharge. We adopted the random forest, extra trees, extreme gradient boosting, light gradient boosting machine (LGBM), and gradient boosting decision tree (GBDT) algorithms to predict the risk of ESRD development among these patients. GBDT yielded the highest area under the receiver operating characteristic curve of 0.879, followed by LGBM (0.868), and extra trees (0.865). The GBDT model revealed the strong effect of estimated glomerular filtration rates <25 mL/min/1.73 m<sup>2</sup> at discharge in predicting ESRD development. In addition, hemoglobin and proteinuria were also essential predictors. Based on a large-scale dataset, we established a machine learning model computing the risk for ESRD occurrence among sepsis survivors with CKD. External validation is required to evaluate the generalizability of this model.https://www.mdpi.com/2227-9059/10/3/546sepsischronic kidney diseasemachine learningartificial intelligenceend-stage renal disease |
| spellingShingle | Kuo-Hua Lee Yuan-Chia Chu Ming-Tsun Tsai Wei-Cheng Tseng Yao-Ping Lin Shuo-Ming Ou Der-Cherng Tarng Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease Biomedicines sepsis chronic kidney disease machine learning artificial intelligence end-stage renal disease |
| title | Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease |
| title_full | Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease |
| title_fullStr | Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease |
| title_full_unstemmed | Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease |
| title_short | Artificial Intelligence for Risk Prediction of End-Stage Renal Disease in Sepsis Survivors with Chronic Kidney Disease |
| title_sort | artificial intelligence for risk prediction of end stage renal disease in sepsis survivors with chronic kidney disease |
| topic | sepsis chronic kidney disease machine learning artificial intelligence end-stage renal disease |
| url | https://www.mdpi.com/2227-9059/10/3/546 |
| work_keys_str_mv | AT kuohualee artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT yuanchiachu artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT mingtsuntsai artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT weichengtseng artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT yaopinglin artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT shuomingou artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease AT dercherngtarng artificialintelligenceforriskpredictionofendstagerenaldiseaseinsepsissurvivorswithchronickidneydisease |