Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study
Abstract Background While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as ‘mild’, ‘moderate’ or ‘severe’ based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothes...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-07-01
|
| Series: | Critical Care |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13054-022-04079-w |
| _version_ | 1818017944720900096 |
|---|---|
| author | Cecilia A. I. Åkerlund Anders Holst Nino Stocchetti Ewout W. Steyerberg David K. Menon Ari Ercole David W. Nelson the CENTER-TBI Participants and Investigators |
| author_facet | Cecilia A. I. Åkerlund Anders Holst Nino Stocchetti Ewout W. Steyerberg David K. Menon Ari Ercole David W. Nelson the CENTER-TBI Participants and Investigators |
| author_sort | Cecilia A. I. Åkerlund |
| collection | DOAJ |
| description | Abstract Background While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as ‘mild’, ‘moderate’ or ‘severe’ based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights. Methods We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset (N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation. Results Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with ‘moderate’ TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with ‘severe’ GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001). Conclusions Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates refining current TBI classifications with factors describing metabolic stress. Such data-driven clusters suggest TBI endotypes that merit investigation to identify bespoke treatment strategies to improve care. Trial registration The core study was registered with ClinicalTrials.gov, number NCT02210221 , registered on August 06, 2014, with Resource Identification Portal (RRID: SCR_015582). |
| first_indexed | 2024-04-14T07:33:28Z |
| format | Article |
| id | doaj.art-eef4f684b84247e194758b0a4b3652d4 |
| institution | Directory Open Access Journal |
| issn | 1364-8535 |
| language | English |
| last_indexed | 2024-04-14T07:33:28Z |
| publishDate | 2022-07-01 |
| publisher | BMC |
| record_format | Article |
| series | Critical Care |
| spelling | doaj.art-eef4f684b84247e194758b0a4b3652d42022-12-22T02:05:47ZengBMCCritical Care1364-85352022-07-0126111510.1186/s13054-022-04079-wClustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI studyCecilia A. I. Åkerlund0Anders Holst1Nino Stocchetti2Ewout W. Steyerberg3David K. Menon4Ari Ercole5David W. Nelson6the CENTER-TBI Participants and InvestigatorsSection of Perioperative Medicine and Intensive Care, Department of Physiology and Pharmacology, Karolinska InstitutetSchool of Electrical Engineering and Computer Science, KTH Royal Institute of TechnologyNeuroscience Intensive Care Unit, Department of Pathophysiology and Transplants, Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, University of MilanDepartment of Biomedical Data Sciences, Leiden University Medical CenterDivision of Anaesthesia, Department of Medicine, University of CambridgeDivision of Anaesthesia, Department of Medicine, University of CambridgeSection of Perioperative Medicine and Intensive Care, Department of Physiology and Pharmacology, Karolinska InstitutetAbstract Background While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as ‘mild’, ‘moderate’ or ‘severe’ based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights. Methods We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset (N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation. Results Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with ‘moderate’ TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with ‘severe’ GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001). Conclusions Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates refining current TBI classifications with factors describing metabolic stress. Such data-driven clusters suggest TBI endotypes that merit investigation to identify bespoke treatment strategies to improve care. Trial registration The core study was registered with ClinicalTrials.gov, number NCT02210221 , registered on August 06, 2014, with Resource Identification Portal (RRID: SCR_015582).https://doi.org/10.1186/s13054-022-04079-wTraumatic brain injuryEndotypesIntensive care unitCritical careUnsupervised clusteringMachine learning |
| spellingShingle | Cecilia A. I. Åkerlund Anders Holst Nino Stocchetti Ewout W. Steyerberg David K. Menon Ari Ercole David W. Nelson the CENTER-TBI Participants and Investigators Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study Critical Care Traumatic brain injury Endotypes Intensive care unit Critical care Unsupervised clustering Machine learning |
| title | Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study |
| title_full | Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study |
| title_fullStr | Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study |
| title_full_unstemmed | Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study |
| title_short | Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study |
| title_sort | clustering identifies endotypes of traumatic brain injury in an intensive care cohort a center tbi study |
| topic | Traumatic brain injury Endotypes Intensive care unit Critical care Unsupervised clustering Machine learning |
| url | https://doi.org/10.1186/s13054-022-04079-w |
| work_keys_str_mv | AT ceciliaaiakerlund clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT andersholst clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT ninostocchetti clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT ewoutwsteyerberg clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT davidkmenon clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT ariercole clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT davidwnelson clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy AT thecentertbiparticipantsandinvestigators clusteringidentifiesendotypesoftraumaticbraininjuryinanintensivecarecohortacentertbistudy |