Developing an algorithm capable of discriminating depressed mood in people with spinal cord injury

Study design: Cross-section design. Objectives: The development of reliable screen technology for predicting those at risk of depression in the long-term remains a challenge. The objective of this research was to determine factors that classify correctly adults with spinal cord injury (SCI) with depressed mood and to develop a diagnostic algorithm that could be applied for prediction of depressed mood in the long-term. Setting: SCI rehabilitation unit, rehabilitation outpatient clinic and Australian community. Methods: Participants included 107 adults with SCI. The assessment regimen included demographic and injury variables, negative mood states, pain intensity, health-related quality of life and self-efficacy. Participants were divided into those with `normal' mood versus those with elevated depressed mood. Discriminant function analysis (DFA) was then used to isolate factors that in combination, best classify the presence or absence of depressed mood. Results: At the time of assessment, 24 participants (22.4%) had elevated depressed mood. DFA identified six factors that discriminated between those with depressed mood (P < 0.01) and those with normal mood, explaining 61% of the variance. Factors consisted of pain intensity, mental health, emotional and social functioning, self-efficacy and fatigue. DFA correctly classified 91.7% (n=22 of 24) of those with depressed mood and 95.2% (n=79 of 83) of those without. Demographic, injury and physical health function variables were not found to discriminate depressed mood. Conclusion: Clinical implications of applying a diagnostic algorithm for detecting depression in adults with SCI are discussed. Prospective research is needed to test the predictive efficacy of the algorithm.