A Review on Medical Diagnostic Systems Using Artificial Intelligence Algorithms
- Pages: 9
- Word count: 2099
- Category: Artificial Intelligence
A limited time offer! Get a custom sample essay written according to your requirements urgent 3h delivery guaranteedOrder Now
The disease is an abnormal condition, a disorder that affects a part or full body. Diagnosis is the identification of a disease, disorder, or other condition that a person may have. Diagnoses are sometimes very easy to come by, while others may be a bit trickier. The medical field is very rich in information but “Poor in knowledge”. There is a huge amount of data available within the healthcare systems. However, there is a lack of effective analysis tools to discover hidden relationships and trends in data. The traditional methods which are used to diagnose a disease are manual and error-prone. Usage of AI predictive techniques enables auto diagnosis and reduces the errors of detection comparatively a human expert. In this paper, we have reviewed research papers of the last 10 years (2009 to 2019) in which various diseases have been discussed along with corresponding Techniques of AI including Fuzzy Logic, Machine Learning, and Deep Learning. This research paper aims to provide a survey of current and previous different techniques of AI in the medical field that are used in today’s medical research particularly in heart disease Prediction, brain disease, prostate, liver disease, kidney disease, etc.
The study of any disease is one of the key concepts in medical sciences. In humans, a disease usually refers to any condition that causes pain, dysfunction, or death to the person. Diseases can affect people not only physically, but also mentally, as living with a disease can alter the affected person’s perspective on life. The causal study of disease is called the pathological process. Moreover, Diseases are generally understood to be medical conditions that involve a pathological process related to a selected set of symptoms. The disease is a set of observable signs and symptoms that ought to be interpreted by physicians. This interpretation process needs to be done by the diagnosis process. Diagnosis has been defined as the art of identifying a disease from its signs and symptoms and concluded. In other words, diagnosis is the method of determining which disease or condition explains a person’s symptoms and signs. It is most often referred to as a diagnosis with the medical context being implicit. The knowledge required for diagnosis is usually collected from a history and physical examination of the person seeking medical aid. Often, one or more diagnostic procedures, like medical tests, are also done during the process. To form an honest diagnosis your doctor will undergo a process that involves several steps, allowing them to collect the maximum amount of information as possible.
Diagnosis is recognized as a complex and difficult process for healthcare professionals because the physicians have to simultaneously consider the various factors and circumstances concerning medical evidence. Due to the complexity of the clinical diagnostic process as one of the main tasks of physicians, all health professionals try to reduce uncertainty in diagnosis by collecting empirical data to manage a patient’s problems. Mistakes in judgment
Made at this point can serve to derail the entire diagnostic process and unless a disciplined redirection occurs down the line, the correct diagnosis may be delayed or missed with serious consequences to the patient’s outcome and safety. Unfortunately, all doctors don’t possess expertise in every subject specialty and there is a shortage of resource persons at certain places. Therefore, an automatic diagnosis system would probably be beneficial by bringing all of them together. Appropriate computer-based information or decision support systems can aid in achieving clinical tests at a reduced cost. The efficient and accurate implementation of the automated system needs a comparative study of various techniques available. Artificial intelligence (AI) has the potential to revolutionize disease diagnosis and management by performing classification difficult for human experts. Now a day’s various AI techniques have been used in the field of medicine to accurately diagnosis a disease.
AI is an integral part of computer science by which computers become more intelligent. The vital need for any intelligent system is learning. There are various techniques in AI that are based on Learning like deep learning, machine learning, etc. Some particular AI technologies of value to healthcare are defined and described as a Rule-based intelligent system are collections of ‘if-then’ rules were the dominant technology for AI. In healthcare, they were widely employed for ‘clinical decision support”.Many electronic health record providers furnish a set of rules with their systems today. Intelligent systems require human experts and knowledge engineers to construct a series of rules in a particular knowledge domain. They are slowly being replaced in healthcare by more approaches based on data and machine learning algorithms. Neural Networks are a computational approach which is based on a large collection of neural units loosely modeling the way the brain solves problems with large clusters of biological neurons connected by axons. Each neural unit is connected with many others.These systems are self-learning and trained.
ANNs help to provide the predictions in healthcare that doctors and surgeons simply couldn’t address alone. They work in moments wherein we can collect data, but we don’t understand which pieces of that data are vitally important yet. Machine learning computational and statistical tools are used to develop a personalized treatment system based on patients’ symptoms and genetic information. To develop the personalized treatment system, a supervised machine learning algorithm is used. This system is developed using patient medical information. Deep learning, a subset of machine learning and also based on algorithms, Deep learning in healthcare provides doctors the analysis of any disease accurately and helps them treat them better, thus resulting in better medical decisions. Deep learning helps in drug discovery, medical imaging, Genome, detecting Alzheimer’s disease.
2. Literature Review
In this study, a literature review of the peer-reviewed literature was performed to identify what evidence exists about factors that influence earlier detection of disease outbreaks. The focus was placed to identify to what extent AI techniques have been changed to early detection of diseases. The goals of this review were to synthesize what is currently known and to identify gaps and limitations that can be addressed by future research efforts. Understanding the evidence-base of influencing factors could guide approaches to achieve earlier detection
2.1 Nature of disease and diagnosis process
The diagnostic process as follows: First, a patient experiences a health problem. The patient is likely the first person to consider his symptoms and may choose a health care system. Once a patient seeks health care, there is an iterative process of information gathering, information integration and interpretation and determining a diagnosis. Performing a clinical history and interview, conducting a physical exam, performing diagnostic testing, and referring or consulting with other clinicians are all ways of acquiring information that may be relevant to understanding a patient’s health problem. The continuous process of information gathering, integration, and interpretation involves hypothesis generation and updating prior probabilities as more information is learned. Instead of emerging various diagnostic methods and tools, not only the inherent ambiguity was not decreased but also the complexity and uncertainty of final diagnosis is enhancing because of the high volume of data. Hence, physicians often have to decide based on this collected information as soon as possible in the iterative hypothetic deductive process.
Insufficient time for gathering information might be the greatest obstacle to make accurate decisions. Besides that, diagnostic errors are inevitable. Several methods in the context of artificial intelligence have been utilized to minimize the complexity of the diagnosis process and to improve diagnostic accuracy. Dealing with uncertainty and errors in disease diagnosis is very important which can help to control diseases by healthcare professionals. Artificial intelligence (AI) is simply nearly as good at diagnosing a disease based on a medical image as healthcare professionals, in spite of it more quality studies are necessary. Artificial intelligence in healthcare use of complex algorithms and software to imitate human knowledge within the analysis of complex medical data. In fact, AI is the ability of computer algorithms to approximate conclusions without direct human input. There are already lots of research studies suggesting that AI can perform equal or better than humans in healthcare tasks, such as diagnosing disease. Algorithms are outperforming radiologists at spotting malignant tumors, and guiding researchers in how to construct cohorts for costly clinical trials. In this paper, we describe both the potential that AI offers to automate aspects of care and some of the barriers to the rapid implementation of AI in healthcare. Artificial intelligence is not one technology, instead of a collection of different tools and techniques. Most of these technologies have immediate relevance to the healthcare field, but the specific processes and tasks they support vary widely.
2.2 Applied Ai Methods In Multiple Disease
Artificial intelligence (AI) aims to act like human cognitive functions. We review the current status of AI applications in healthcare and discuss its future. AI is often applied to numerous types of healthcare data (structured and unstructured). Famous AI techniques include machine learning methods for structured data, like the classical support vector machine and neural network, and the modern deep learning, as well as natural language processing for unstructured data. Major disease areas that use AI tools include cancer, prostate, liver, kidney, neurology, and cardiology. We then review in more detail the AI applications in multiple diseases, in the three major areas of early detection and diagnosis, treatment, also as outcome prediction and prognosis evaluation.
The diagnostic decisions that medical experts take to rely on similarity, experience, knowledge, capability, and understanding of the scientist. It is tough to diagnose a problem without making any mistake, especially when the complexity of the system increases. Dynamic techniques are provided by fuzzy logic which will handle complex problems. Fuzzy logic has proved to be a strong tool for decision-making systems, like expert systems and pattern classification systems. Fuzzy set theory has already been used in some medical expert systems [16,17,18,19]. Fuzzy logic used in the medical examination is of great importance, providing an exact evaluation report. These types of systems provide an instant and simple method of medical examination. And this is also helpful where professional or medical experts are not present. These systems give a result based on the knowledge base built into it and acquire from experts and authorities in the field. Numerous medical diagnoses
Systems have already been developed based on the fuzzy set model and have already been applied in treatments and diagnosis. The term fuzzy refers to things that are not clear or are vague. In the real world many times we encounter a situation when we can’t determine whether the state is true or false, their fuzzy logic provides very valuable flexibility for reasoning. It is a rule-based technique. Fuzzy Rule-Based System (FRBS) is one of the most common fuzzy set methods applied in medicine which belongs to Fuzzy Inference Systems (FIS) in general . FRBS refers to fuzzy systems that apply “IF-Then “rules for knowledge representation. Fuzzy clustering and classifying are the most interesting methods used in the medical domain too. In addition to fuzzy sets and fuzzy clusters, the following FIS and FDSS are also described as the most common methods in the field of medicine. The main feature of fuzzy logic is we can consider the inaccuracies and uncertainties of any situation, in the fuzzy system; there is no logic for the absolute truth and absolute false value. But in fuzzy logic, there is intermediate value too present which is partially true and partially false. Let’s take the following example to show how fuzzy logic works
Fuzzy Logic becomes more and more popular for diagnosing diseases based on different parameters during recent years. We will discuss some of them. HEART DISEASE is a type of disease caused due to damage or blockage of blood vessels in the heart affecting fewer nutrients and oxygen supply to heart organs. Different types of heart diseases are very common like artery problems, cardiac arrest, heart failure, arrhythmia, stroke, etc. Fuzzy logic is constantly growing to detect heart patients throughout the world with the help of developing new software based on different parameters. Several papers have been published in the diagnosis of heart disease using a fuzzy expert system, Ansari and Gupta (2011) discuss coronary heart disease detection using a neuro-fuzzy integrated system, results reached with a similar level of doctor’s opinion in case of high/low cardiac risk. Junior at el (2013). Introduces a cardiac arrhythmia classification system using fuzzy classifiers to detect specific points of the electroencephalogram using network-based fuzzy interferences. This system offers a time reduction on electrocardiogram – ECG signal processing by reducing the number of data samples, without any significant loss. The ECG signals are applied into the system that performs initial filtering, and then uses a Gustafson–Kessel fuzzy.