Originally published in: Indian J Physiol Pharmacol 2004; 48 (4): 395 – 408;
Republished with Author’s permission
Medical Informatics is the science and art of processing medical information. In this age of “Information Explosion” choosing the useful one is rather difficult, and there lies the scope of electronic database management. However, still many outstanding personnel related to the healthcare sector take pride in being “computer illiterate”. The onus of the best use lies on the end-user health care providers only. Another term tele-health encompasses all the e-health and telemedicine services. Computer aided or assisted learning (CAL) is a computer based tutorial method that uses the computer to pose questions, provide remedial information and chart a student through a course. Now the emphasis in medical education, is on problem based learning (PBL) and there CAL could be of utmost help if used judiciously. Basic Medical Education and Research lays the foundation for advancing and applying proper healthcare delivery systems. There is no doubt that deep knowledge of anatomy is mandatory for successful surgery. Also, comprehensive knowledge of physiology is essential for grasping the principles of pathology and pharmacology adequately, to avoid incorrect and inadequate practice of medicine. Similarly, medical informatics is not just a subject to be learnt and forgotten after the first professional MBBS examination. The final aim of every student should not only be to become a good user but also an expert for advancing medical knowledge base through medical informatics. In view of the fast changing world of medical informatics, it is of utmost necessity to formulate a flexible syllabus rather than a rigid one.
Key words: medical informatics medical education and research flexible syllabus
Medical Informatics, a novel academic discipline, bridging Medicine and Information Sciences, has already made its presence felt. It may be defined as the art and science of processing medical information, where ‘information’ is the processed ‘data’1-5. The modern age is called the “age of information” and we are becoming apprehensive of “informationexplosion”. Improper access to excessiveinformation leads to nothing but confusion. This is truer in conditions of life and death – which the medical profession has to handle regularly.
Bioinformatics broadly relates to proteomics (informatics of protein structure banks), genomics (informatics of genomes and gene banks) and various newer drug synthesis methods. However, clinical or medical informatics also is a subset of it. Information is derived from the assembly, analysis or summarizing of data into a meaningful form. Data mean any group of operands or factors consisting of numbers (numerical), alphabetic characters or symbols (linguistic), which denote any condition, value or state. Knowledge comprises generalized truths formed from the analysis of available information. Medical or health informatics (dealing with medical information), is a necessary discipline in the tropical countries like India. With the development of excellent satellite telecommunications here, its prospects are brightening. However, this requires essentially a multidisciplinary interaction.
To cite an example, an elderly lady who presents with a fractured forearm due to fall, may have other problems leading to the fall. She might be having increased frequency of urination because of diabetes or urinary tract infection (or benign enlargement of the prostate, in case of a male). While going to the toilet, in the night, due to failing eyesight (which again may have been caused by cataract or drugs), she may overlook an obstacle and fall. The fall may also be due to increased or decreased blood pressure or blood sugar. Moreover, staying alone in the house also could be responsible as there is no one to take her to the toilet. The psychological condition might well be depressed or demented, leading to confusion and unmindfulness. Therefore, the forearm fracture, in an aged lady, has a greater amount of ‘history’ than the same in a young lady. An overburdened human doctor (not a medical student though!) may not be entirely unjustified if he or she fails to ask or register some of thesepredisposing factors in the particular example.
The scopes are immense as Medical informatics forms the interface between the subject domain of medicine, and the science and technology of computing. It requires essential inputs from cognitive sciences (including Psychology), information and communication sciences (library and documentation), computer sciences (hardware and software), logic, statistics (including biostatistics and epidemiology), decision sciences, clinical and basic (pre- and para-clinical) medical sciences, health economics and policy making as well as from medical ethics.
Health or Hospital information System (HIS) is an integrated system encompassing the departmental systems (like radiology, pathology and pharmacy), as well as the clinical systems (like Intensive Care Unit or ICU). However, a proper definition6, 7is yet to evolve. The database includes all sorts of records for each patient, including admission, evaluation, management, transfer, and discharge information, with supporting evidence. Clinical Decision support systems (CDSS, described below) may also be incorporated8 into it. It is the integration of global needs for all the healthcare users. Finally connecting it to a tele-health (e-health or health related use of electronic information and telemedicine or remote medical consultation) system, people at far places could benefit a lot9.
It may be realized by interfacing a central system to multiple departmental (e.g., Biochemistry, Pathology, Microbiology, Pharmacy and Radiology) and clinical information systems (e.g., intensive or critical care units and nursing units). Middleware in HIS may purvey solutions which integrate data for end users at the front, while hiding the multiplicity of origins of the data at the background. There are various standards2, 3, 6, 7 that have been (and are being) developed for medical messages communication format. Some of the notable ones include: ASTM (American society for testing and materials), ASC XI2N, DICOM (Digital Image and communication in Medicine, USA), HL7 (Health Level Seven, Inc. USA), IEEE PI 157 (from Institute of Electrical and Electronics Engineers, Inc. USA) MEDIX (Medical data interchange standard), IEEE PI073 MIB (Medical information bus), and NCPDP (National Council for Prescription Drug Programs, USA).
Computer based patient records (CBPR or CPR) involves digitizing all data related to a patient being treated in a hospital (along with modifications and updates) and storing in an easily retrievable or searchable form. The database may include patient admission, transfer, discharge, evaluation and management, as well as, hospital and ambulatory care systems, and at times also CDSS1, 4, 8. A plethora of nomenclature abounds in literature like EMR/EPR (Electronic medical or patient record) /PMR (Patient medical record) for similar entities.
However, present day stress is on EHR (Electronic Health Record) i.e., the whole data record of a person in health and disease both.
Reaching a foolproof diagnosis is never an easy job for a clinician. Often, a simple diagnostic procedure or test is overlooked and the disease eludes diagnosis. Clinical reasoning and decision making are phased. Initially there is a clinical evaluation (history taking and physical examination), followed by precise laboratory investigations. Then integration of clinical findings and test results is done. After that, comparative benefits and risks are weighed among the alternative courses of actions, like drug interactions. Finally, the patient’s preferences are taken into account, along with ethical and other considerations like cost of therapy, compliance expectations and a therapeutic plan is developed. Right from the first step (history taking) to the final one, computers can be of immense help to the clinician.
While taking history from a patient, an experienced doctor does an ‘iterative hypothesis testing’, while a medical student or a fresh graduate learns to do ‘comprehensive history taking’. The first method is known as the ‘rule of the thumb’ or heuristics, which comes from experience and is therefore bound to cause more errors despite saving time. As human brains (and neural networks) work in milliseconds, computers can actually do a comprehensive history taking in a much shorter time.
I have the pleasure of developing some diagnostic decision support systems for medical education and research. A simple example (using the iterative dichotomizer or ID3 decision tree) is provided in www.geocities.com/drsupten. Nevertheless, for computer-assisted diagnostic systems, a human clinician (“man in the loop” for “Intelligence Amplification”) must be a necessary component. Moreover, the clinician must understand completely the strengths and limitations of them. Computerized diagnostics and clinical acumen are not mutually exclusive; rather they should reinforce each other for the alleviation of psychosomatic suffering of mankind.