Dataset Information

Unsupervised learning of early post-arrest brain injury phenotypes.

ABSTRACT:

Introduction

Trials may be neutral when they do not appropriately target the experimental intervention. We speculated multimodality assessment of early hypoxic-ischemic brain injury would identify phenotypes likely to benefit from therapeutic interventions.

Methods

We performed a retrospective study including comatose patients resuscitated from out-of-hospital cardiac arrest (OHCA) by one of 126 emergency medical services or in-hospital arrest at one of 26 hospitals from 2011 to 2019. All patients were ultimately transported to a single tertiary center for care including standardized initial neurological examination, brain imaging and electroencephalography; targeted temperature management (TTM); hemodynamic optimization targeting mean arterial pressure (MAP) >80 mmHg; and, coronary angiography for clinical suspicion for acute coronary syndrome. We used unsupervised learning to identify brain injury phenotypes defined by admission neurodiagnostics. We tested for interactions between phenotype and TTM, hemodynamic management and cardiac catheterization in models predicting recovery.

Results

We included 1086 patients with mean (SD) age 58 (17) years of whom 955 (88%) were resuscitated from OHCA. Survival to hospital discharge was 27%, and 248 (23%) were discharged with Cerebral Performance Category (CPC) 1-3. We identified 5 clusters defining distinct brain injury phenotypes, each comprising 14% to 30% of the cohort with discharge CPC 1-3 in 59% to <1%. We found significant interactions between cluster and TTM strategy (P = 0.01), MAP (P < 0.001) and coronary angiography (P = 0.04) in models predicting outcomes.

Conclusions

We identified patterns of early hypoxic-ischemic injury based on multiple diagnostic modalities that predict responsiveness to several therapeutic interventions recently tested in neutral clinical trials.

SUBMITTER: Elmer J

PROVIDER: S-EPMC7390683 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The heterogeneity of traumatic brain injury (TBI) remains a core challenge for the success of interventional clinical trials. Data-driven approaches for patient stratification may help to identify TBI patient phenotypes during the acute injury period as well as facilitate targeted trial patient enrollment and analysis of treatment efficacy. In this study, we implemented an unsupervised machine learning approach to identify TBI subpopulations at injury baseline using data from 1213 TBI patients who participated in the Citicoline Brain Injury Treatment Trial (COBRIT) Trial. A wrapper framework utilizing generalized low-rank models automatically selected relevant clinical features that were subsequently used to cluster patients using a partitioning around medoids clustering algorithm. Using this approach, we identified three patient phenotypes with unique clinical injury profiles based on a subset of acute injury features. Phenotype-specific differences in long-term functional outcome trajectories were respectively observed at 3 and 6 months after injury. In comparison, when patients were grouped by baseline Glasgow Coma Scale (GCS), no differences in baseline clinical feature profiles or long-term outcomes were observed. To test phenotype reproducibility in an external validation data set, we used a K-nearest neighbors algorithm to classify subjects in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) Pilot data set into corresponding phenotypes, then measured the Gower's dissimilarities between TRACK-TBI and COBRIT subjects in each phenotype. No significant differences were found between trial subjects within two phenotypes, suggesting that these phenotypes may be generalizable within a broad range of TBI severity. Further, Extended Glasgow Outcome Scale (GOS-E) outcomes in the TRACK-TBI data set similarly demonstrated phenotype-specific differences in long-term outcomes. Our results suggest that unsupervised machine learning is a promising and effective approach for discovery of novel injury subpopulations over the conventional GCS-based method, and may improve patient selection in future TBI clinical trials.

Project description:This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.