Predicting the impact of hospital health information technology adoption on patient satisfaction

摘要: Objectives: To develop and explore the predictability of patient perceptions satisfaction through hospital adoption health information technology (HIT), leading to a better understanding benefits increased HIT investment. Data methods: The solution proposed is based on comparing predictive capability artificial neural networks (ANNs) with adaptive neuro-fuzzy inference system (ANFIS). latter integrates fuzzy logic can handle certain complex problems that include fuzziness in human perception, non-normal non-linear data. Secondary data from two surveys were combined model. Hospital use indicators Canadian province Ontario used as inputs, while healthcare services acute hospitals outputs. Results: Eight different types models trained tested for each four dimensions. accuracy model was evaluated statistical performance measures, including root mean square error (RMSE), adjusted coefficient determination R^2"A"d"j"u"s"t"e"d. For all indicators, ANFIS found be more effective (R"A"d"j"u"s"t"e"d^2=0.99) when compared results ANN modeling predicting impact (R"A"d"j"u"s"t"e"d^2=0.86-0.88). Conclusions: obtained scenarios using simulations. simulation revealed full implementation lead significant improvement satisfaction. We conclude technique decision support mechanism assist government policy makers resulting