Vocational/educational prognosis in adolescents and young adults with acquired brain injury: a nationwide cohort study

OBJECTIVE

To determine prognostic factors for work ability and employment/educational status among young patients referred to outpatient neurorehabilitation clinics after an acquired brain injury.

METHODS

A nationwide cohort study of 471 15-30-year-old patients who attended an interdisciplinary clinical assessment and provided questionnaire data at baseline and after one year. The outcomes were the Work Ability Score (WAS, 0-10 (best)) and employment/educational status after one year. Prognostic performance was analyzed using univariable regression and multivariable Ridge regression in a five-fold cross-validated procedure.

RESULTS

Preinjury, 86% of the patients were employed, while the percentage had decreased to 55% at baseline and 52% at follow-up. The model, which included clinical measures of function, showed moderate prognostic performance with respect to WAS (R2=0.29) and employment/educational status (area under the curve (AUC)=0.77). Glasgow Outcome Scale Extended (R2=0.15, AUC=0.68) and the cognitive subscale of the Functional Independence Measure (R2=0.09, AUC=0.64), along with fatigue measured with the Multidimensional Fatigue Inventory (R2=0.15, AUC=0.60) were the single predictors with the highest predictive performance.

CONCLUSION

Despite generally high scores in motor and cognitive tests, only about half of the patients were employed at baseline and this proportion remained stable. Global disability, cognitive sequelae and fatigue had the highest prognostic performance.

Symptoms of depression in parents after discharge from NICU associated with family-centred care

Aims

The aim of this study was to examine the potential association of family‐centred care as perceived by parents during a NICU stay with parents’ depressive symptoms at discharge and at 4 months corrected for infant age.

Design

A longitudinal, multicentre cohort study was conducted from 2018 to 2020 in 23 NICUs across 15 countries.

Methods

Parents (n = 635 mothers, n = 466, fathers) of infants (n = 739) born before 35 weeks of gestation and admitted to the participating NICUs were enrolled to the study during the first weeks of their infants’ hospitalizations. They responded to Digi‐FCC daily text messages inquiring about their perception of family‐centred care provided by NICU staff. In addition, they completed a questionnaire assessing their overall perception of family‐centred care at discharge. Parents’ depressive symptoms were measured by the Edinburgh Postnatal Depression Scale at discharge and again after discharge when their infants were at 4 months corrected for age.

Results

The mothers’ and the fathers’ perceptions of family‐centred care were associated with their depressive symptoms at discharge and at 4 months corrected age, controlling for gestational age, multiple birth, parent education and relationship status. Parents’ participation in infant care, care‐related decisions and emotional support provided to parents by staff explained the variation in the parents’ perceptions of family‐centred care. The factors facilitating the implementation of family‐centred care included unlimited access to the unit for the parents and for their significant others, as well as amenities for parents.

Conclusions

Our study shows that family‐centred NICU care associates with parents’ depressive symptoms after a NICU stay.

Impact

Depression is common in parents of preterm infants. The provision of family‐centred care may protect the mental well‐being of parents of preterm infants.

A systematic review of the effectiveness of machine learning for predicting psychosocial outcomes in acquired brain injury: Which algorithms are used and why?

Clinicians working in the field of acquired brain injury (ABI, an injury to the brain sustained after birth) are challenged to develop suitable care pathways for an individual client's needs. Being able to predict psychosocial outcomes after ABI would enable clinicians and service providers to make advance decisions and better tailor care plans. Machine learning (ML, a predictive method from the field of artificial intelligence) is increasingly used for predicting ABI outcomes. This review aimed to examine the efficacy of using ML to make psychosocial predictions in ABI, evaluate the methodological quality of studies, and understand researchers' rationale for their choice of ML algorithms. Nine studies were reviewed from five databases, predicting a range of psychosocial outcomes from stroke, traumatic brain injury, and concussion. Eleven types of ML were employed with a total of 75 ML models. Every model was evaluated as having high risk of bias, unable to provide adequate evidence for predictive performance due to poor methodological quality. Overall, there was limited rationale for the choice of ML algorithms and poor evaluation of the methodological limitations by study authors. Considerations for overcoming methodological shortcomings are discussed, along with suggestions for assessing the suitability of data and suitability of ML algorithms for different ABI research questions.