Scholarlink

<p>Depression affects approximately 30% of individuals after traumatic brain injury (TBI), yet long-term depression trends and their determinants are poorly understood. This study aimed to model depression trajectories over 10&#xa0;years post-TBI, compare the predictive performance of population-level predictions alone versus predictions incorporating both population-level and subject-specific effects, and assess the model’s clinical utility for predicting depression in unseen and existing patients. Data were obtained from the Traumatic Brain Injury Model System (TBIMS) National Data Bank. Depression was measured using the Patient Health Questionnaire-9 (PHQ-9) and collected at 1, 2, 5, and 10&#xa0;years after injury. Covariates included age, sex, race, employment, education, functional measures, injury severity, pre-injury mental health, and substance use. A zero-inflated negative-binomial mixed-effects model was used to identify depression trends and factors associated with depression, accommodating the overdispersed, zero-inflated distribution of PHQ-9 scores. Predictive performance was evaluated using mean absolute error (MAE) and root mean squared error (RMSE). The sample comprised 18,667 individuals (mean age 43). Depression scores showed a small decrease over time among those with pre-injury mental health treatment history, but this change was not clinically meaningful. The strongest predictor of Year 1 depression was pre-injury mental health treatment (IRR = 1.33), followed by female sex (IRR = 1.15) and prior head injuries (IRR = 1.06 per additional injury). When forecasting Year-5 PHQ-9 for existing patients with prior observations, subject-specific predictions achieved MAE = 3.48 PHQ-9 points; for previously unseen patients, population-average predictions achieved mean MAE = 4.19 points (SD = 0.12) across 30 repeated holdout splits. Subject-specific predictions consistently outperformed population-average predictions. Depression trajectories following TBI exhibit substantial individual heterogeneity. Population-level models alone inadequately capture this complexity, while models incorporating both population and subject-level variations significantly improve predictive performance. This modeling approach demonstrates the potential for predicting depression trajectories in clinical settings, thereby facilitating individualized assessment and intervention.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Longitudinal Trends of Depression in Traumatic Brain Injury: The Role of Individual Heterogeneity in Clinical Prediction

  • 期刊论文

  • 发表日期：

    2026年5月8日

查看全文
  • Nelofar Kureshi,
  • David B. Clarke,
  • Abraham Nunes,
  • Cindy Feng,
  • Syed Sibte Raza Abidi

摘要

Depression affects approximately 30% of individuals after traumatic brain injury (TBI), yet long-term depression trends and their determinants are poorly understood. This study aimed to model depression trajectories over 10 years post-TBI, compare the predictive performance of population-level predictions alone versus predictions incorporating both population-level and subject-specific effects, and assess the model’s clinical utility for predicting depression in unseen and existing patients. Data were obtained from the Traumatic Brain Injury Model System (TBIMS) National Data Bank. Depression was measured using the Patient Health Questionnaire-9 (PHQ-9) and collected at 1, 2, 5, and 10 years after injury. Covariates included age, sex, race, employment, education, functional measures, injury severity, pre-injury mental health, and substance use. A zero-inflated negative-binomial mixed-effects model was used to identify depression trends and factors associated with depression, accommodating the overdispersed, zero-inflated distribution of PHQ-9 scores. Predictive performance was evaluated using mean absolute error (MAE) and root mean squared error (RMSE). The sample comprised 18,667 individuals (mean age 43). Depression scores showed a small decrease over time among those with pre-injury mental health treatment history, but this change was not clinically meaningful. The strongest predictor of Year 1 depression was pre-injury mental health treatment (IRR = 1.33), followed by female sex (IRR = 1.15) and prior head injuries (IRR = 1.06 per additional injury). When forecasting Year-5 PHQ-9 for existing patients with prior observations, subject-specific predictions achieved MAE = 3.48 PHQ-9 points; for previously unseen patients, population-average predictions achieved mean MAE = 4.19 points (SD = 0.12) across 30 repeated holdout splits. Subject-specific predictions consistently outperformed population-average predictions. Depression trajectories following TBI exhibit substantial individual heterogeneity. Population-level models alone inadequately capture this complexity, while models incorporating both population and subject-level variations significantly improve predictive performance. This modeling approach demonstrates the potential for predicting depression trajectories in clinical settings, thereby facilitating individualized assessment and intervention.