DESIGN AND IMPLEMENTATION OF A MEDICAL DIAGNOSTIC SYSTEM

Background of the Study
According to Frost et al. (2009) medical diagnosis, (often simply termed diagnosis) refers both to the process of attempting to determine or identifying a possible disease or disorder to the opinion reached by this process. A diagnosis in the sense of diagnostic procedure can be regarded as an attempt at classifying an individual’s health condition into separate and distinct categories that allow medical decisions about treatment and prognosis to be made. Subsequently, a diagnostic opinion is often described in terms of a disease or other conditions. In the medical diagnostic system procedures, elucidation of the etiology of the disease or conditions of interest, that is, what caused the disease or condition and its origin is not entirely necessary. Such elucidation can be useful to optimize treatment, further specify the prognosis or prevent recurrence of the disease or condition in the future (Frost et al. 2009).
Clinical decision support systems (CDSS) are interactive computer programs designed to assist healthcare professionals such as physicians, physical therapists, optometrists, healthcare scientists, dentists, pediatrists, nurse practitioners or physical assistants with decision making skills. The clinician interacts with the software utilizing both the clinician’s knowledge and the software to make a better analysis of the patient’s data than neither humans nor software could make on their own (Coulter et al. 2010).

Typically, the system makes suggestions for the clinician to look through and picks useful information that removes erroneous suggestions. To diagnose a disease, a physician is usually based on the clinical history and physical examination of the patient, visual inspection of medical images, as well as the results of laboratory tests. In some cases, confirmation of the diagnosis is particularly difficult because it requires specialization and experience, or even the application of interventional methodologies (e.g., biopsy). Interpretation of medical images (e.g., Computed Tomography, Magnetic Resonance Imaging, Ultrasound, etc.) usually performed by radiologists, is often limited due to the non-systematic search patterns of humans, the presence of structure noise (camouflaging normal anatomical background) in the image, and the presentation of complex disease states requiring the integration of vast amounts of image data and clinical information. Computer-Aided Diagnosis (CAD), defined as a diagnosis made by a physician who uses the output from a computerized analysis of medical data as a second opinion‖ in detecting lesions, assessing disease severity, and making diagnostic decisions, is expected to enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. With CAD, the final diagnosis is made by the physician (Negnevitsky, 2005).

The first CAD systems were developed in the early 1950s and were based on production rules and decision frames. More complex systems were later developed, including blackboard systems to extract a decision, Bayes models and artificial neural networks (ANNs) (Smith, 2009). Recently, a number of CAD systems have been implemented to address a number of diagnostic problems. CAD systems are usually based on biosignals, including the electrocardiogram (ECG), electroencephalogram (EEG), and so on or medical images from a number of modalities, including radiography, computed tomography, magnetic resonance imaging, ultrasound imaging, and so on. In therapy, the selection of the optimal therapeutic scheme for a specific patient is a complex procedure that requires sound judgement based on clinical expertise, and knowledge of patient values and preferences, in addition to evidence from research. Usually, the procedure for the selection of the therapeutic scheme is enhanced by the use of simple statistical tools applied to empirical data. In general, decision making about therapy is typically based on recent and older information about the patient and the disease, whereas information or prediction about the potential evolution of the specific patient disease or response to therapy is not available. Recent advances in hardware and software allow the development of modern Therapeutic Decision Support (TDS) systems, which make use of advanced simulation techniques and available patient data to optimize and individualize patient treatment, including diet, drug treatment, or radiotherapy treatment (Smith, 2009).

In addition to this, CDS systems may be used to generate warning messages in unsafe situations, provide information about abnormal values of laboratory tests, present complex research results, and predict morbidity and mortality based on epidemiological data.