Background: Antipsychotic induced weight gain occurs frequently and may lead to obesity. In this field, long term impacts of dietary treatment remain unknown. Objective: the aim of this study was to assess long term weight evolution in relation to initial weight changes in order to better predict potential benefits of continuation or interruption of dietary treatment. Method: We reviewed the charts of twelve outpatients treated by antipsychotics and followed by a dietician for at least six months. Results: Increase of body mass index during the first 6 months seems to predict further and/or sustained weight gain. Patients were classified as either weight losers or weight gainers and their classifications compared at months 3, 6, 9, 12, 15, 18, 21 and 24. Conclusions: The 6 month classification was found to be the best predictor of the weight loser/weight gainer proportion in the following 9 months.