A computer expert system is an alternative method of training and providing real-time clinical decision support for nurses to advance their practices from a novice to a proficient level. The purpose of this study was twofold: (1) to develop a prototype of a computer expert system for mechanically ventilated neonates (ES-MVN) and (2) to assess the impact of the ES-MVN on the clinical judgment and information access capability of nurses. Five steps used in developing the prototype are described in this article. The ES-MVN is a multimedia interactive consultation-based program that contains 2 major parts: the nursing diagnosis and the knowledge base on nursing care of mechanically ventilated neonates. A rule-based (Boolean frame) was chosen for the nursing diagnosis decision model. The prototype was developed on the Web server and a combination of computer applications operated in a Microsoft Windows environment. A quasi-experimental, 1-group pretest-posttest design was used to measure the efficacy of the ES-MVN in 16 neonatal intensive care unit registered nurses. Case simulations were used to test the nurses' clinical judgment performance. The results showed a significant increase in the nurses' performance scores of diagnoses and managed care after using the ES-MVN (t[15] = 17.21, P = .0001). The nurses' scores for perceptions of their information access capability and clinical judgment ability after receiving the ES-MVN were significantly higher than before installing the ES-MVN in the neonatal intensive care unit (ts[15] = 6.91 and = 17.53, Ps = .0001, respectively). The findings suggest the usefulness of the computer expert system as an effective tool to support nurses' clinical judgment in critical care situations and to provide access to information at the practice site.