Traumatic brain injury (TBI) patients constitute a highly heterogeneous population, with varying risks for New-onset Psychiatric Disorders (NPDs).
While most studies have examined the relationship between various predictors and NPDs following TBI, none have explored the heterogeneity in the relationship between demographics, injury, psychiatric history and NPDs in TBI patients.
Funding acknowledgement: This work is supported by the Canada Graduate Scholarships Doctoral Award (CGS D) and Dalhousie Department of Surgery.
While most studies have examined the relationship between various predictors and NPDs following TBI, none have explored the heterogeneity in the relationship between demographics, injury, psychiatric history and NPDs in TBI patients.
Funding acknowledgement: This work is supported by the Canada Graduate Scholarships Doctoral Award (CGS D) and Dalhousie Department of Surgery.
💡
Research questions
- What is the effect of TBI on the development of NPDs in a propensity-matched sample of TBI patients and controls?
- Within the TBI cohort, are there specific phenotypes which differ with respect to demographics, injury variables, and pre-injury psychiatric conditions?
- Are these phenotypes associated with the development of NPDs?
- Can phenotype membership be accurately predicted using Machine Learning (ML) models?
🔎
Methodology
📝
Results
- A total of 3,453 TBI patients were included in the analysis.
- In a conditional regression involving propensity matched TBI and control patients, TBI was significantly associated with the development of NPDs.
- Eight distinct latent classes were identified which differed in the incidence of NPDs.
- Four classes displayed a 53% (RR:1.53; 95% CI: 1.31-1.78), 48% (RR:1.48; 95% CI: 1.26-1.74), 28% (RR:1.28; 95% CI: 1.08-1.54), and 20% (RR: 1.20, 95%CI: 1.03-1.39), increased risk NPD risk.
- Random forest and Xtreme gradient boosting accurately predicted class membership.
📑
Posters
📃
Publication