Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning
Abstract Sepsis is a highly variable condition, and tracking leukocyte patterns may offer insights for tailored treatment and prognosis. We used the MIMIC-IV database to analyze patients diagnosed with Sepsis-3 within 24 h of ICU admission. Latent class mixed models (LCMM) were applied to leukocyte...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-96718-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850201434574815232 |
|---|---|
| author | ShengHui Miao YiJing Liu Min Li Jing Yan |
| author_facet | ShengHui Miao YiJing Liu Min Li Jing Yan |
| author_sort | ShengHui Miao |
| collection | DOAJ |
| description | Abstract Sepsis is a highly variable condition, and tracking leukocyte patterns may offer insights for tailored treatment and prognosis. We used the MIMIC-IV database to analyze patients diagnosed with Sepsis-3 within 24 h of ICU admission. Latent class mixed models (LCMM) were applied to leukocyte trajectories to identify sepsis subtypes. The primary outcome was 28-day all-cause mortality, with secondary outcomes including the need for life-support therapies. Associations between leukocyte trajectories and outcomes were assessed using multivariate regression, and findings were externally validated with the eICU database. Use the XGBoost model to identify baseline characteristics of high-risk mortality sepsis subgroups for predicting subgroup allocation upon patient admission to the ICU, and apply the SHAP method to interpret the contributing variables of the model. Among 7410 sepsis patients, eight distinct leukocyte trajectory subtypes were identified. Among those subtypes, patients with persistently high leukocyte levels had the poorest prognosis (HR 3.00; 95% CI 2.48–3.62) and a significantly greater need for life-support therapies; Patients with persistently low white blood cell levels had a higher risk of death (HR 1.68; 95% CI 1.24–2.27) but were less likely to receive invasive mechanical ventilation. Incorporating early ICU baseline variables into an XGBoost algorithm enables effective prediction of high-mortality risk subgroups (AUC > 0.8). SHAP method reveals distinct early clinical characteristics between hyperinflammatory subtypes (class 4, 7, and 8) and the hypoinflammatory subtype (class 1). In ICU-admitted sepsis patients, eight leukocyte trajectories are identified, which is the key independent predictors of prognosis, separating from single leukocyte measurements. High-mortality risk subgroups exhibit distinct clinical characteristics at ICU admission, providing valuable insights for their prediction and personalized early intervention. |
| format | Article |
| id | doaj-art-bc9d6aedf2d441b69ee0d2b8a5eb05b4 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-bc9d6aedf2d441b69ee0d2b8a5eb05b42025-08-20T02:12:01ZengNature PortfolioScientific Reports2045-23222025-04-0115111010.1038/s41598-025-96718-9Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learningShengHui Miao0YiJing Liu1Min Li2Jing Yan3The Fourth Affiliated Hospital, International Institutes of Medicine, Zhejiang University School of MedicineDepartment of Second Clinical Medical College, Zhejiang Chinese Medicine UniversityThe Fourth Affiliated Hospital, International Institutes of Medicine, Zhejiang University School of MedicineZhejiang Hospital, Zhejiang University School of MedicineAbstract Sepsis is a highly variable condition, and tracking leukocyte patterns may offer insights for tailored treatment and prognosis. We used the MIMIC-IV database to analyze patients diagnosed with Sepsis-3 within 24 h of ICU admission. Latent class mixed models (LCMM) were applied to leukocyte trajectories to identify sepsis subtypes. The primary outcome was 28-day all-cause mortality, with secondary outcomes including the need for life-support therapies. Associations between leukocyte trajectories and outcomes were assessed using multivariate regression, and findings were externally validated with the eICU database. Use the XGBoost model to identify baseline characteristics of high-risk mortality sepsis subgroups for predicting subgroup allocation upon patient admission to the ICU, and apply the SHAP method to interpret the contributing variables of the model. Among 7410 sepsis patients, eight distinct leukocyte trajectory subtypes were identified. Among those subtypes, patients with persistently high leukocyte levels had the poorest prognosis (HR 3.00; 95% CI 2.48–3.62) and a significantly greater need for life-support therapies; Patients with persistently low white blood cell levels had a higher risk of death (HR 1.68; 95% CI 1.24–2.27) but were less likely to receive invasive mechanical ventilation. Incorporating early ICU baseline variables into an XGBoost algorithm enables effective prediction of high-mortality risk subgroups (AUC > 0.8). SHAP method reveals distinct early clinical characteristics between hyperinflammatory subtypes (class 4, 7, and 8) and the hypoinflammatory subtype (class 1). In ICU-admitted sepsis patients, eight leukocyte trajectories are identified, which is the key independent predictors of prognosis, separating from single leukocyte measurements. High-mortality risk subgroups exhibit distinct clinical characteristics at ICU admission, providing valuable insights for their prediction and personalized early intervention.https://doi.org/10.1038/s41598-025-96718-9SepsisClinical subtypesLeukocyte trajectoriesMachine learningLatent class analysis |
| spellingShingle | ShengHui Miao YiJing Liu Min Li Jing Yan Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning Scientific Reports Sepsis Clinical subtypes Leukocyte trajectories Machine learning Latent class analysis |
| title | Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| title_full | Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| title_fullStr | Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| title_full_unstemmed | Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| title_short | Clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| title_sort | clinical subtypes identification and feature recognition of sepsis leukocyte trajectories based on machine learning |
| topic | Sepsis Clinical subtypes Leukocyte trajectories Machine learning Latent class analysis |
| url | https://doi.org/10.1038/s41598-025-96718-9 |
| work_keys_str_mv | AT shenghuimiao clinicalsubtypesidentificationandfeaturerecognitionofsepsisleukocytetrajectoriesbasedonmachinelearning AT yijingliu clinicalsubtypesidentificationandfeaturerecognitionofsepsisleukocytetrajectoriesbasedonmachinelearning AT minli clinicalsubtypesidentificationandfeaturerecognitionofsepsisleukocytetrajectoriesbasedonmachinelearning AT jingyan clinicalsubtypesidentificationandfeaturerecognitionofsepsisleukocytetrajectoriesbasedonmachinelearning |