Subphenotyping heterogeneous patients with chronic critical illness to guide individualised fluid balance treatment using machine learning: a retrospective cohort study.
Peizhao Liu, Sicheng Li, Tao Zheng, Jie Wu, Yong Fan, Xiaoli Liu, Wenbin Gong, Haohao Xie, Juanhan Liu, Yangguang Li, Haiyang Jiang, Fan Zhao, Jinpeng Zhang, Lei Wu, Huajian Ren, Zhiwu Hong, Jun Chen, Guosheng Gu, Gefei Wang, Zhengbo Zhang, Xiuwen Wu, Yun Zhao, Jianan Ren
Author Information
Peizhao Liu: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Sicheng Li: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Tao Zheng: Department of General Surgery, BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210019, China.
Jie Wu: Department of General Surgery, BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210019, China.
Yong Fan: Center for Artificial Intelligence in Medicine, Chinese PLA General Hospital, Beijing, 100039, China.
Xiaoli Liu: Center for Artificial Intelligence in Medicine, Chinese PLA General Hospital, Beijing, 100039, China.
Wenbin Gong: School of Medicine, Southeast University, Nanjing, 210002, China.
Haohao Xie: Department of General Surgery, BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210019, China.
Juanhan Liu: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Yangguang Li: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Haiyang Jiang: Department of General Surgery, BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210019, China.
Fan Zhao: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Jinpeng Zhang: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Lei Wu: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Huajian Ren: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Zhiwu Hong: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Jun Chen: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Guosheng Gu: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Gefei Wang: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Zhengbo Zhang: Center for Artificial Intelligence in Medicine, Chinese PLA General Hospital, Beijing, 100039, China.
Xiuwen Wu: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Yun Zhao: Department of General Surgery, BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210019, China.
Jianan Ren: Research Institute of General Surgery, Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, China.
Background: The great heterogeneity of patients with chronic critical illness (CCI) leads to difficulty for intensive care unit (ICU) management. Identifying subphenotypes could assist in individualized care, which has not yet been explored. In this study, we aim to identify the subphenotypes of patients with CCI and reveal the heterogeneous treatment effect of fluid balance for them. Methods: In this retrospective study, we defined CCI as an ICU length of stay over 14 days and coexists with persistent organ dysfunction (cardiovascular Sequential Organ Failure Assessment (SOFA) score ≥1 or score in any other organ system ≥2) at Day 14. Data from five electronic healthcare record datasets covering geographically distinct populations (the US, Europe, and China) were studied. These five datasets include (1) subset of Derivation (MIMIC-IV v1.0, US) cohort (2008-2019); (2) subset Derivation (MIMIC-III v1.4 'CareVue', US) cohort (2001-2008); (3) Validation I (eICU-CRD, US) cohort (2014-2015); (4) Validation II (AmsterdamUMCdb/AUMC, Euro) cohort (2003-2016); (5) Validation III (Jinling, CN) cohort (2017-2021). Patients who meet the criteria of CCI in their first ICU admission period were included in this study. Patients with age over 89 or under 18 years old were excluded. Three unsupervised clustering algorithms were employed independently for phenotypes derivation and validation. Extreme Gradient Boosting (XGBoost) was used for phenotype classifier construction. A parametric G-formula model was applied to estimate the cumulative risk under different daily fluid management strategies in different subphenotypes of ICU mortality. Findings: We identified four subphenotypes as Phenotype A, B, C, and D in a total of 8145 patients from three countries. Phenotype A is the mildest and youngest subgroup; Phenotype B is the most common group, of whom patients showed the oldest age, significant acid-base abnormality, and low white blood cell count; Patients with Phenotype C have hypernatremia, hyperchloremia, and hypercatabolic status; and in Phenotype D, patients accompany with the most severe multiple organ failure. An easy-to-use classifier showed good effectiveness. Phenotype characteristics showed robustness across all cohorts. The beneficial fluid balance threshold intervals of subphenotypes were different. Interpretation: We identified four novel phenotypes that revealed the different patterns and significant heterogeneous treatment effects of fluid therapy within patients with CCI. A prospective study is needed to validate our findings, which could inform clinical practice and guide future research on individualized care. Funding: This study was funded by 333 High Level Talents Training Project of Jiangsu Province (BRA2019011), General Program of Medical Research from the Jiangsu Commission of Health (M2020052), and Key Research and Development Program of Jiangsu Province (BE2022823).
