Shunt efficiency plays an important role in hydrocephalus management. Artificial intelligence has been used far and wide in managing healthcare treatment such example is the use of artificial neural network for increasing shunt device efficiency as through the research done has find that there are gap in current practice. This research focus in improving artificial neural network algorithm to create a more efficient hydrocephalus shunt device that could detect any shunt malfunctions before used clinically on patient. The improved algorithm would also help to ensure a more efficient shunt management, in terms of after shunt insertion; predicting shunt infection to decrease the length of hospitals stays and mortality rate for patients especially for children. The method proposed is by improving the current algorithm that are currently being used by the shunt device to increase its efficiency and also enable advance data collection for more accurate prediction. © BEIESP.