Abstract—In this paper, a Bayesian Network (BN) based system is presented for providing clinical decision support to healthcare practitioners in rural or remote areas of India for young infants or children up to the age of 5 years. The government is unable to appoint child specialists in rural areas because of inadequate number of available pediatricians. It leads to a high Infant Mortality Rate (IMR). In such a scenario, Intelligent Pediatric System provides a realistic solution. The prototype of an intelligent system has been developed that involves a knowledge component called an Intelligent Pediatric Assistant (IPA); and User Agents (UA) along with their Graphical User Interfaces (GUI). The GUI of UA provides the interface to the healthcare practitioner for submitting sign-symptoms and displaying the expert opinion as suggested by IPA. Depending upon the observations, the IPA decides the diagnosis and the treatment plan. The UA and IPA form client-server architecture for knowledge sharing. Keywords—Network, Based Intelligent, Pediatric System I. INTRODUCTION NTELLIGENT systems are considered a subset or an application of the branch of computer science known as artificial intelligence. In turn, artificial intelligence is broadly defined as comprising certain techniques that allow computers to take on the characteristics of human intelligence. A medical intelligent system is a computer program that, when well- crafted, gives decision support in the form of accurate diagnostic information or, less commonly, suggests treatment or prognosis. Diagnostic, Therapeutic, or prognostic advice is given after the program receives information (input) about the patient, usually via the patient’s physician. Intelligent systems have characteristics which make them dissimilar from other kinds of medical software because it deals with uncertainty. Because clinical medicine often does not deal in certainty, intelligent systems may have the capability of expressing conclusions as a probability. It is generally agreed that intelligent software must contain a large number of facts and rules about the disease or condition in question in order to deliver accurate answers.In this paper, a Bayesian Network based system is presented to help healthcare professionals to diagnose the disease of young infant/child, classify it and identify the treatment plan. The Intelligent Pediatric Assistant (IPA) has been developed for deciding the diagnosis as per the sign-symptoms provided by the healthcare professional. It also keeps track of the number of diseases diagnosed from a particular rural/remote site. Jagmohan Mago is with Rayat Bahra institution of Engineering, India, (e- mail:parvinder.sandhu@gmail.com) The GUI of User Agent (UA) provides the practitioner a user interface to feed in the measured values and observations. The UA and IPA use the disease ontology that specifies the vocabulary and semantics for understanding the child related diseases. The GUI of IPA is used to display the activity of PHC practitioners. The system works without the direct involvement of a pediatrician as IPA is responsible to emulate a child specialist in dealing with some childhood diseases. The system has been designed to support even a naïve healthcare practitioner in dealing with child diseases. A. Healthcare Scenario of infants in India A majority of the Indian population is living in rural or remote areas. The healthcare practitioners in these areas are not specialized in dealing with infant or childhood diseases. They simply refer child related critical cases to specialized doctors in urban areas. There is also an acute shortage of funds and adequate trained child specialists in India. The first ever report tracking global progress against pneumonia, the leading killer of children under five years of age, finds that India is witnessing the highest number of pneumonia-related child deaths in the world. The infection is killing 16 lakh children under five every year, more than 3.7 lakh in India alone. According to the National Commission on Population (India), in 2002, approximately Rs. 643.1 million was needed for infrastructure and services of 1,774 more pediatricians were required. Hence, the government is unable to appoint child specialists in rural areas. All this leads to high Infant Mortality Rate (IMR) i.e. 68/1000 live births. The National Commission on Population observes that main contributors to high IMR in India are states having majority of population residing in rural areas as shown in Table I. TABLE I IMR WITHIN INDIAN STATES (1999) PER THOUSAND STATES Orissa Madhya Pardesh Uttar Pardesh Rajasthan IMR 98 98 85 83 B. Origin of the Research Problem The responsibility of providing treatment to young infants/children in rural India is with the general health care practitioner posted in Primary Health Center (PHC) or rural dispensaries. Because of the shortage of funds and inadequate trained specialists, the government appoints a child specialist at Community Health Care Center (CHC) only. Therefore, CHC serves as a first referral center to PHC and dispensaries. At some rural places, even less qualified health care Jagmohan Mago, Parvinder S. Sandhu, Neeru Chawla Bayesian Network Based Intelligent Pediatric System I World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering Vol:5, No:1, 2011 37 International Scholarly and Scientific Research & Innovation 5(1) 2011 scholar.waset.org/1307-6892/13463 International Science Index, Computer and Information Engineering Vol:5, No:1, 2011 waset.org/Publication/13463