Lecture - 13 : Artificial Intelligence

Artificial intelligence (AI)

is a branch of science that enables a computer to tackle complex tasks and adapt to new situations. It makes the computer perform tasks that are normally done by humans. Artificial intelligence allows the computer to think like humans. It helps machines to make complex judgmental calls, solve complex problems in a more human like fashion Problems that require intelligence and reasoning can now be effectively accomplished by using computers Artificial intelligence programs are based on human knowledge to recognize patterns in complex data, learn from experience and take decisions that are normally taken by humans

TheraSim CS

(Clinical Simulator) is clinical simulation technology to support the training of physicians, nurses, medical students and pharmacists in the diagnosis and treatment of chronic and infectious diseases

There are two main streams in developing AI systems:

1. Quantitive approaches 2. Qualitative approaches. Quantitive approaches sometimes referred to as numerical approaches, because they use quantities in analysing the problems. Qualitative approaches sometimes referred to as symbolic approaches, because they use qualities of the problem to solve the problem. Logic, rules, lists based systems are examples of qualitative AI systems.

APPLICATIONS OF EXPERT SYSTEMS

1.Alerts and reminders. 2. Diagnostic assistance. 3. Therapy critiquing and planning. 4. Prescribing decision support systems. 5. Information retrieval. 6. Image recognition and interpretation.

Artificial Intelligence

the field of computing that attempts at providing computational models of some human activities, which researchers consider intelligent activities, such as learning, acting, decision making, evolving and so on. AI, therefore, relates strongly to fields such as psychology, biology and sociology. In some cases new disciplines emerged such as bio-informatics and cybernetics. is a branch of science that enables a computer to tackle complex tasks and adapt to new situations. It makes the computer perform tasks that are normally done by humans.

HELP

the first hospital information system to collect patient data needed for clinical decision-making and at the same time incorporate a medical knowledge base and inference engine to assist the clinician in making decisions

AIM systems

AIM are by and large intended to support healthcare workers in the normal course of their duties, assisting with tasks that rely on the handling of data and knowledge. An AI system could be running within an electronic medical record system, for example, and alert a clinician when it detects a contraindication to a planned treatment. It could also alert the clinician when it detected patterns in clinical data that suggested significant changes in a patient's condition.

EXPERT OR KNOWLEDGE-BASED SYSTEMS

Are the commonest type of AIM system in routine clinical use. This type of system seeks to exploit the specialized skills or information held by of a group of people on specific areas. It can be thought of as a computerized consulting service. It can also be called an information guidance system. Such systems are used for prospecting medical diagnosis or as educational aids

3. Therapy critiquing and planning.

Critiquing systems can look for inconsistencies, errors omissions in an existing treatment plan. Critiquing systems can applied to physician order entry.

PUFF

Expert System for Interpretation of Pulmonary Function Data) - Developed by Stanford University and Pacific Medical Center

Problem with Mycin

If a computer can diagnose patients with a better rate of success than an average family doctor, why not implement it on a large scale? There are many problems associated with the implementation of an clinical expert system like MYCIN. The greatest of which is that it has never actually been used in a non-experimental way, i.e. it has never been actually used to diagnose and prescribe treatment for a patient. If MYCIN gives an incorrect diagnosis and/or prescription (or, rather, a physician follows MYCIN's orders in giving such diagnosis and/or prescription), who would be responsible?

1.Alerts and reminders.

In real-time situations, an expert system attached to a patient monitoring device like an ECG or pulse oximeter can warn of changes in a patient's condition. In less acute circumstances, it might scan laboratory test results, drug or test order, or the EMR and then send reminders or warnings

How It Works

MYCIN is an expert system comprised of two major components: 1. A knowledge base which stores the information the expert system "knows", much of which is derived from other information in the knowledge base. 2. An inference engine to derive knowledge from the presently known knowledge in the knowledge base. Knowledge represented by MYCIN's knowledge base is represented as a set of IF-THEN rules with particular certainty factors. For example: IF the infection is primary-bacteria AND the site of the culture is one of the sterile sites AND the suspected portal of entry is the gastrointestinal tract THEN there is suggestive evidence (0.7) that the infection is bacterial. Researchers at Stanford found MYCIN to have an approximate correctness rate of 65%, which is better than the majority of physicians who are not specialists in diagnosing infections. MYCIN's knowledge base is small relative to those used by most rules-based systems today; it is on the order of ~500 rules. The science of the generation of these rules is known as "knowledge engineering". Let us illustrate the action of an expert system by considering the behaviour of an actual one MYCIN a medical expert system. Mycin has been informed that a patient has contracted meningitis while in hospital. Doctors wish to interrogate Mycin to check this diagnosis. Mycin then asks the doctors this question Mycin: Is Meningitis a hospital acquired illness? Doctor: why? Mycin: [2.0] this will aid in determining the organisms that might be causing the infection It has already established [2.1] the infection that requires therapy is meningitis [2.2] organisms were not seen on the stain of this pending csf culture [2.3] the type of infection is bacterial [2.4] neurosurgery is not one of the relevant items of patient 100 [2.5] the age of patient 100 is greater than 25 therefore if [2.6] the infection was acquired while the patient was in hospital then there is evidence that the organisms that might be causing the infection are E coli(0.75) staphylococcus-(0.3) pseudomonas-aeruginosa(0.3) klebsiella-pneumoniae(0.5)

6. Image recognition and interpretation.

Many clinical images can now be automatically interpreted, from plane X-rays through to more complex images like angiograms, CT and MRI scans.

Medical AI

Medical artificial intelligence is primarily concerned with the construction of AI programs that perform diagnosis and make therapy recommendations. Unlike medical applications based on other programming methods, such as purely statistical and probabilistic methods, medical AI programs are based on symbolic models of disease entities and their relationship to patient factors and clinical manifestations.

Advantages of AI (vs Human Brain)

More design freedom, including ease of modification and duplication; the capability to debug, reboot, backup and attempt numerous designs. The ability to perform complex tasks without making human-type mistakes, such as mistakes caused by lack of focus, energy, attention or memory. The ability to perform extended tasks at greater serial speeds than conscious human thought or neurons, which perform approx. 200 calculations per second. Computing chips (~2 GHz) presently have a 10 million to one speed advantage over our neurons. The main principle capacity to function 24 hours a day, seven days a week, 365 days a year.

MYCIN

Mycin is the name of a decision support system developed by Stanford University in the early- to mid-seventies, built to assist physicians in the diagnosis of infectious diseases The system would ask a series of questions designed to emulate the thinking of an expert in the field of infectious disease From the responses to these questions give a list of possible diagnoses, with probability, as well as recommend treatment ("decision support-"). The name "MYCIN" actually comes from antibiotics, many of which have the suffix "-mycin". MYCIN was originally developed by Edward Shortliffe for Stanford Medical School in the early- and mid-1970's. Written in Lisp, a computer language geared towards artificial intelligence. MYCIN was one of the pioneering expert systems, and was the first such system implemented for the medical field. The Goal of MYCIN was to compete in an experiment conducted at Stanford Medical. The case histories of ten patients with different types of meningitis were submitted to MYCIN as well as to eight human physicians. Both MYCIN and the human physicians were given the same information. Both MYCIN's and the human physician's recommendations were sent to eight non-Stanford specialists. The outside specialists gave MYCIN the highest score as far as accuracy of diagnosis and effectiveness of treatment

ONCOCIN

ONCOCIN is an expert system, a clinical decision support system that was developed in 1979 at Stanford by Shortliffe's group and used primarily from 1981 to 1987 at the Stanford Oncology Clinic as well as various other locations. ONCOCIN uses artificial intelligence techniques to offer advice to the physician on medicines, dosages, and testing. It integrates medical record keeping with decision support. It was designed to aid the physician in decision-making by combining clinical data with chemotherapy protocol guidelines and knowledge provided by expert oncologists. Oncology is the branch of medicine dealing with the physical, chemical, and biological properties of tumors, including study of their development, diagnosis, treatment, and prevention; and a protocol in the sense used here is a plan for a course of medical treatment The typical users of ONCOCIN were residents and clinical assistants rather than certified physicians. The advice provided by ONCOCIN was approved by experts in only 79% of the cases. ONCOCIN used the same rule-based approach as MYCIN. Physicians were hesitant to trust the systems advice, and moreover the advice was still only approved by experts in about 80% of the cases. For these reasons, physicians used ONCOCIN as a critique to their own work. Soon new systems such as Protege and Eon made the use of ONCOCIN obsolete.

4. Prescribing decision support systems.

PDSS can assist by checking for drug-drug interactions, dosage errors, and if connected to an EMR, for other prescribing contraindications such as allergy.

Example of some AI

PUFF HELP APACHE TheraSim CS

Disadvantages (vs Human Brain)

Present AIs lack human general intelligence and multiple years of real-world experience

Simple AI systems

The simplest view of AI systems is as a search problem solver. It is almost impossible to develop an expert system without implementing some search technique or another to navigate through the problem domain for the solution. Search techniques provide the base for the inference engine, which is an essential component of any expert system. There are two main types of searches: Conventional searches and heuristic searches. Conventional searches cover the entire domain and eventually find the solution, what is the problem with that? Heuristic searches aim at reducing the domain or covering a selected portion of the problem domain.

5. Information retrieval.

They can act as information filters, by reducing the number of documents found in response to a query to a Web search engine, and they can assist in identifying the most appropriate sources of evidence appropriate to a clinical question.

2. Diagnostic assistance.

When a patient's case is complex, rare or inexperienced professional , an expert system can help in the formulation of likely diagnoses based on patient data presented to it

APACHE

one of the first medical decision support systems to be commercialised - in 1988 by Apache Medical Systems