Cost prediction of antipsychotic medication of psychiatric disorder using artificial neural network model.

摘要: BACKGROUND Antipsychotic monotherapy or polypharmacy (concurrent use of two more antipsychotics) are used for treating patients with psychiatric disorders (PDs). Usually, antipsychotic has a lower cost than polypharmacy. This study aimed to predict the medications (AM) in Iran. MATERIALS AND METHODS For this purpose, 790 PDs who were discharged between June and September 2010 selected from Razi Psychiatric Hospital, Tehran, prediction AM PD, neural network (NN) multiple linear regression (MLR) models used. Analysis data was performed R 2.15.1 software. RESULTS Mean ± standard deviation (SD) duration hospitalization (days) on 31.19 15.55 36.69 15.93, respectively (P < 0.001). median costs medication (n = 507) $8.25 $6.23 =192) $13.30 $9.48, The important variables hospitalization, type treatment, ward MLR model, diagnosed disorder, age, Chlorpromazine dosage, disorder NN model. CONCLUSION Our findings showed that artificial (ANN) model can be as flexible AM.