Predicting type of psychiatric disorder from Strengths and Difficulties Questionnaire (SDQ) scores in child mental health clinics in London and Dhaka

A computerised algorithm was developed to predict child psychiatric diagnos es on the basis of the symptom and impact scores derived from Strengths and Difficulties Questionnaires (SDQs) completed by parents, teachers and youn g people. The predictive algorithm generates "unlikely", "possible" or "pro bable" ratings far four broad categories of disorder, namely conduct disord ers, emotional disorders, hyperactivity disorders, and any psychiatric diso rder. The algorithm was applied to patients attending child mental health c linics in Britain (N = 101) and Bangladesh (N = 89). The level of chance-co rrected agreement between SDQ prediction and an independent clinical diagno sis was substantial and highly significant (Kendall's tau b between 0.49 an d 0.73; p < 0.001). A "probable" SDQ prediction for any given disorder corr ectly identified 81-91% of the children who definitely had that clinical di agnosis. There were more false positives than false negatives, i.e. the SDQ categories were over-inclusive. The algorithm appears to be sufficiently a ccurate and robust to be of practical value in planning the assessment of n ew referrals to a child mental health service.