By Dr Bhupinder Chaudhary, Baljit Saini and Rishu Gupta
In the health sector, there is a need for a computer based system, which not only asks relevant questions to the patients but also aids the physician by giving a set of possible diseases from the symptoms obtained using logic at inference. Expert systems or knowledge-based systems use computer programs that contain some of the subject-specific knowledge of one or more experts
Expert systems are a branch of Artificial Intelligence or ‘AI’, which also includes robotics, natural language processing, and other applications. Such systems can be defined as a collection of hardware, software, data, and embedded knowledge that demonstrates characteristics of intelligence. Although, the medical profession and healthcare management have historically lagged behind industry in the use of expert systems and decision support, yet, theses applications can save countless lives, not to mention hundreds of billions of unnecessary expense Although, expert decision-support systems in medical diagnosis and treatment have been around since the 1960’s, they have remained until recently an academic exercise, waiting desperately, for the medical and health professions to reach out and apply them.There are three main relevant classes of information to be accessed by physicians when trying to reach a decision concerning a medical case namely expert’s opinion, colleague’s opinion and medical literature. The expert opinion is necessary in medical decision making, since there are wide variations in clinical practices. Moreover, the growing need to assess and improve quality of healthcare has brought to light the possibility of developing and implementing clinical practice guidelines based on expert opinions. Even though a colleague’s opinion helps in accessing information about real cases, which is another important source of information, an important goal to reach when dealing with real medical cases is to have simultaneous access to an expert’s opinion about the same indications of the real case being treated. The increase of the information volume in each medical field, due to the emergence of new discoveries, treatments, medicines and technologies, leads to a frequent need of consulting medical literature and in particular specialised journals. Certainly, due to the huge volume of this information, a classified, targetted, access is necessary.
The application of IT research and development to support health and medicine is an emerging research area with significant potential. Major initiatives to improve the quality, accuracy and timeliness of healthcare data and information delivery are emerging all over the world. The Agency for Healthcare Research and Quality (AHRQ), of the US Department of Health Services (HHS), awarded grants and contracts to promote the use of health information technology.
Computerised systems including expert systems have been used to carry out efficient and effective data processing on complex problems to support various problem domains since the 1970’s. Since the advent of artificial intelligence in the 1970’s that saw the birth of expert systems, various domains have taken advantage of this technology. The most popular application has been in the area of health and medicine. MYCIN developed in 1970 at the Stanford University, is one of the most popular medical expert system used to assist to diagnose and treat blood diseases. MYCIN was the pioneer in demonstrating how a system can be used to successfully perform medical diagnosis. Another early expert system is the PACE (Patient Care Expert System), which was conceived in 1977 with the purpose to make ‘intelligent selections’ from the overwhelming and ever changing information related to health in order to facilitate patient care. The system started off as an educational system for the nursing profession. Throughout the years, the system evolved and went through many development generations to a point where it became an advanced clinical management system capable of supporting the entire health care field to diagnose and care for patients with pulmonary diseases. Another expert system called, MITIS system, was developed in 2004 at the National Technical University of Athens.
The MITIS system was developed to assist in the management and processing of obstetrical, gynaecological, and radiological medical data. The concept behind this system is to record and store information from experts in medical departments of gynaecology, radiology and obstetrics to provide a centralised mechanism for managing patient information within and outside a hospital.
Systems are computer programs that are meant to solve real world problems. In normal routine, these problems are solved by domain experts. Thus, the knowledge has to be extracted from the domain expert in order to develop an expert system. Extracting the knowledge from a domain expert and to convert it into a computer program is a difficult task. This task of extracting the knowledge from a domain expert is performed by a knowledge engineer. The knowledge engineer provides useful assistance to domain experts in determining the representation of knowledge. If the knowledge is represented in the form of rules then such systems are called rule-based expert systems. Different techniques have been developed for knowledge acquisition. The interaction with the expert system is made through user interface. The interaction is performed through an interactive dialog.
The knowledge base is the heart of an expert system. Typically the knowledge base is in the form of if-then rules. The inference engine finds a sequence in which inferences are made. The inference engine is used to reason with the knowledge base. In forward chaining rule-based systems case specific data is also called working memory. The working memory contains the result of inference process. Expert systems also facilitate the users by providing explanation subsystem. The explanation subsystem explains its reasoning to the users. Knowledge base editor is provided in some systems for writing and updating the knowledge base. Expert systems have the ability to separate problem specific knowledge from general purpose reasoning.
This general purpose block without any domain specific knowledge is called skeletal systems, or expert system shells. Many commercial shells are available these days. Thus expert systems are a combination of expert system shell and domain specific knowledge.
Expert system software programs consist of large databases of information with various components integrated into a software package. Software programs include partitioned and cataloged information for user access. Databases in the software contain health care information by separating data into knowledge-based components.
User Interface: Description of a problem is entered through user interface.
Inference Engine: Inference engine is a generic control mechanism that applies the axiomatic knowledge in the knowledge base to the task-specific data to arrive at some solution or conclusion. Knowledge Base: The knowledge base constitutes the problem-solving rules, facts, or intuition that a human expert might use in solving problems in a given problem domain. The knowledge base is usually stored in terms of if – then rules.
Constructing medical expert systems
Medical expert systems can be constructed either through AI languages or from expert systems shells. Expert system shells provide more general facilities and an easy way to enter necessary knowledge about the problem domain. ESTA, EXSYS, XpertRule, ACQUIRE, FLEX etc. are some of the popular Software packages used in the construction of medical expert systems. LISP and PROLOG are two famous AI languages used to develop medical expert systems.
The International Classification of Diseases is published by the World Health Organisation (WHO). The International Statistical Classification of Diseases and Related Health Problems (most commonly known by the abbreviation ICD) provides codes to classify diseases and a wide variety of signs, symptoms, abnormal findings, complaints, social circumstances and external causes of injury or disease.
One of the main benefits of upgrading to ICD-10 codes is that it will finally allow the United State’s healthcare data to be compatible with the rest of the developed world. In addition, implementing ICD-10 diagnosis codes will allow for more accurate and complete documentation of patient diagnosis and care. The thirty year old ICD-9 diagnosis codes have reached the limits of their effectiveness and are no longer capable of taking into account the advancements in patient care, advent of new technology and manifestations of new diseases and their treatment. ICD-10 codes will have the ability to take on the latest advancements in modern medicine and have the room and flexibility needed to allow for future healthcare advancements.
The ICD is used world-wide for morbidity and mortality statistics, reimbursement systems and automated decision support in medicine. This system has been designed to promote international compatibility in the collection, processing, classification, and presentation of these statistics. The ICD is a core classification of the WHO. The ICD is revised periodically by WHO and is currently in its tenth edition. The ICD is a core classification of the WHO-FIC. The ICD-10, as it is therefore known, was developed in 1992 to track mortality statistics. ICD-11 is planned for 2011 and has become the most widely used statistical classification system in the world.