Objective-Several predictors of treatment response in late-life depression have been reported in the literature. The aim of this analysis was to develop a clinically useful algorithm that would allow clinicians to predict which patients will likely respond to treatment and thereby guide clinical decision making.Method-A total of 461 patients with late-life depression were treated under structured conditions for up to 12 weeks and assessed weekly with the 17-item Hamilton Rating Scale for Depression . The authors developed a hierarchy of predictors of treatment response using signaldetection theory. The authors developed two models, one minimizing false predictions of future response and one minimizing false predictions of future nonresponse, to offer clinicians two clinically useful treatment algorithms.Results-In the first model, early symptom improvement (defined by the relative change in HAM-D-17 total score from baseline to week 4), lower baseline anxiety, and an older age of onset predict response at 12 weeks. In the second model, early symptom improvement represents the principal guide in tailoring treatment, followed by baseline anxiety level, baseline sleep disturbance, and-for a minority of patients-the adequacy of previous antidepressant treatment.Conclusions-Our two models, developed to help clinicians in different clinical circumstances, illustrate the possibility of tailoring the treatment of late-life depression based on clinical characteristics and confirm the importance of early observed changes in clinical status.Late-life major depression is associated with emotional suffering, disability, caregiver strain, suicide, and poor compliance with other medical treatments (1). Successful antidepressant treatment is one of the most effective ways to reduce disability, prevent morbidity, and improve quality of life in an older depressed patient (2,3). In many cases, patients appear to be resistant to treatment because their antidepressants are switched prematurely (4,5). If treating clinicians knew the probability of treatment response earlier in the course of treatment, they would be in a better position to advise patients about various treatment options. These options could include continuing the current medication, augmenting current pharmacotherapy, or switching to another approach (6,7). Previously, our group has shown that a patient's clinical status after 4 weeks of treatment predicts reliably their response status at week 12 (6). Furthermore, we have identified several biological, clinical, and psychosocial characteristics as predictors of treatment response in latelife major depression: allelic variation in the serotonin transporter promoter, REM sleep latency, cerebral glucose metabolism, age at onset of first episode, sleep disturbances at baseline, baseline Hamilton Depression Rating Scale (HAM-D) scores, baseline anxiety levels, suicidal ideation, response and adherence to previous antidepressant treatment, family support, and social inequalities (7-17). To our knowledge, there is n...