Quantitative structure activity relationship studies were applied on a series of 22 molecules of thiazolidine-2,4-dione, The compounds used are potent inhibitors of the 15-hydroxyprostaglandin dehydrogenase (15-PGDH). The present study was performed using multiple regression analysis (MLR) and artificial neural network (ANN)to predict a QSAR model using molecular descriptors. Our results suggest QSAR model based of the following descriptors: polarizability (Pol), molar volume (MV), hydration energy (HE), Surface area grid (SAG), molar weight (MW), Energy of frontier orbital’s EHOMO (The Highest Occupied Molecular Orbital) and ELUMO (The Lowest Unoccupied Molecular Orbital) and atomic net charges (qN3, qC4, qC5 and qO7) for the inhibitory activities of 15-hydroxyprostaglandin dehydrogenase. The best predictive models by MLR and ANN methods gave highly significant square correlation coefficient (R2) values of 0.9623 and 0.9963 respectively. The model also exhibited good predictive power confirmed by the high value of R2pred (0.7839and 0.6324 respectively).