OTCohortThe Journal of head trauma rehabilitation2019

Using Decision Tree Methodology to Predict Employment After Moderate to Severe Traumatic Brain Injury.

Katharine A Stromberg, Amma A Agyemang, Kristin M Graham and 8 others

PMID 30234849

WHAT IT FOUND

After moderate to severe traumatic brain injury, shorter post-traumatic amnesia was the strongest predictor of later competitive employment.

Preinjury job type and higher education also appeared. This was a prediction model, not treatment evidence.

Key findings

01Post-traumatic amnesia duration was the primary split in the employment prediction models.

02Participants with shorter post-traumatic amnesia duration, preinjury employment, and higher education were more likely to be competitively employed across the models.

03The models showed reasonable predictability, and predictability was largely retained in independent test sets.

STILL TO COME

How it was doneWhat they foundWhat it means for OTs

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The analysis excluded people younger than 18 and older than 60 at injury, so it does not describe students, retirees, or older adults. It included people treated through TBIMS centers and inpatient rehabilitation, so it may not apply to people with traumatic brain injury who do not receive inpatient rehabilitation. Race and ethnicity were not included in the models. Preinjury income, mental health problems, postinjury psychological symptoms, substance use, and social support were not analysed because they were unavailable or had uninterpretable definitions. The decision tree method may have less predictive power than regression models, and small terminal nodes limited further branching. Participants could be included in one year's analysis but not another. The final analysed sample was 4927 at 5 years, compared with 7867 at 1 year and 6783 at 2 years.

Declared interests

The authors declared no conflicts of interest. The TBIMS National Database was funded by the National Institute on Disability, Independent Living, and Rehabilitation Research.

The easy way to misread this

Do not read this as evidence that any intervention improves employment. The paper built prediction models from existing data and did not test an intervention. Post-traumatic amnesia duration is a predictor, not a proven cause of employment outcome.

Read it on PubMed →