Fill This Form To Receive Instant Help

Help in Homework
trustpilot ratings
google ratings


Homework answers / question archive / IT in Biomedicine Lab (COMP5424) 1

IT in Biomedicine Lab (COMP5424) 1

Health Science

IT in Biomedicine Lab (COMP5424) 1. ITB Research Report 1.1 Key Information • This assignment is worth 13% of your final assessment. • The mark of "COMP5424 Assignment 1: ITB Research Report" will be given depends on the file submitted on Canvas: – Canvas Submission [Due Date] 23:59 Sunday of Week 12 (2021-05-30). • Submission Deliverable: – You are asked to submit the report written in pdf format to Canvas. – Your copy should include an Assignment Coversheet, which can be downloaded from HERE. 1.2 General Marking Policy • Late Submission Policy: For the late submission cases, penalties will be assigned according to the university wide late penalties for assignment Clause 7A of the Assessment Procedures. • Special Consideration and Arrangements: While you are studying, there may be circumstances or essential commitments that impact your academic performance. Our special consideration and special arrangements process is there to support you in these situations. More information on how to lodge the special consideration application, can be found from this webpage. 1.3 1.3.1 COMP5424 Assignment 1: ITB Research Report Introduction This individual assignment aims to develop your skills to survey recent advances in information technology in biomedicine (ITB), and extend your ability in summarizing and understanding new methodologies in a systematic manner. 1.3 COMP5424 Assignment 1: ITB Research Report 1.3.2 3 Specification You are required to write a scientific research report on a selected ITB topic below. Your research report should be presented audience-friendly, i.e, it should be written for audiences not familiar with your chosen topic and would like to learn more in the area by reading your report. You are required not only to report the developed methods in recent years, but also to summarize and discuss these methods based on your own understanding and interpretation. 1.3.3 Report Topics ID 1 2 3 4 5 6 7 8 9 10 11 R 1.3.4 Topic Biomedical Data Mining Computer-Aided Interventional Systems and Robotics Computer Graphics in Biomedicine Medical Computer Vision Enhanced or Augmented Reality in Medicine Image Guided Therapy Longitudinal Analysis in Personalized Medicine Medical Image Database Systems Sensor Networks in Biomedicine Software Development in e-Health Telemedicine and Telepresentations The above topics are provided for your reference. You should have your own report title based on your selected topic. Report Structure The report must contain, but not limited to the following structure: 1. Abstract – A concise single paragraph summary of your completed work. The summary should be 200 words or less. 2. Introduction – Definition of the topic, background and overview of the topic, description of the importance (significance) of the study and what is to be covered in the report. 3. Main body with your own section title(s) – Explanation and investigated results of the topic. Graphics and drawing can be included. There is no restriction on the style of the body however the structure and flow of the report should be clearly presented in a logical order. The body can be presented in multiple sections. 4. Discussion – Interpretation of your results in appropriate depth, e.g. advantage and shortcoming, possible direction for advance. 5. Conclusions – Summary of the essay and any conclusion made. 6. References and Appendix – All material used for the report including books, magazines, publications, internet resources, etc. must be listed in the reference. Reference examples: • Reference format 1 – Book: Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Second Edition, Prentice Hall, New Jersey, 2002. Assignment 1. ITB Research Report 4 • Reference format 2 – Journal & Magazine Publication: D. Feng, "Information Technology Applications In Biomedical Functional Imaging", IEEE Transactions on Information Technology in Biomedicine, vol. 3, no. 3, pp. 221-230, 1999. • Reference format 3 – Internet resource: Health Level-7 Standards [Online]. http://www.hl7.org [Last accessed 10/04/2021] 1.3.5 1.4 Report Formatting • Reference - The minimum number of references is 10. • Number of Pages - At least 10 pages, at most 20 pages. • Captions - Captions are required for any figures or tables presented in the report. • Page Formatting: – page size: A4; – line space: 1.5 lines; – font size: 12; – font name: Times New Roman – margin: 2.5cm in all direction Resources • For literature search, please refer to the online tutorial: http://libguides.library.usyd. edu.au/infotech • Recommend databases: Science Citation Index (SCI), Engineering Index (EI), and Association for Computer Machinery (ACM) library from the university library link. • The online tutorial offers links to key databases used in IT research: http://libguides. library.usyd.edu.au/content.php?pid=27815&sid=202340 • For research publications, the University of Sydney has digital subscription as well as printed publication available in the library. The electronic journals in the library can be found in: http://www.library.usyd.edu.au Running Head: HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE 1 How Data Mining has Revolutionized Biomedicine Student’s Name Course Name and Number Assignment Due Date HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE Abstract Data mining refers to the process of finding patterns, anomalies and correlations within large data sets using various analytical techniques to predict possible outcomes. In simpler terms, data mining refers to the process used by most organizations of turning raw data into useful information. Biomedical data mining is defined as the analysis of data generated with the sole purpose of addressing a biomedical problem. Due to the rapid advancement of medical devices and data management systems, there are many databases in the biomedicine world. Establishing a method of discovering knowledge and managing vast amounts of data has become a priority for most healthcare settings. This paper is geared towards introducing basic data mining concepts such as data mining techniques: unsupervised and supervised learning. It also discusses the use of data mining in biomedicine. Data mining is a field of study that is evolving rapidly. As a result, it is imperative to highlight some future developments expected in the area. Introduction Technological advancements have immensely impacted the world. Computers are more than two times faster than they were earlier. The rapid increase in computer speed and the rapid decrease in the cost of data storage has resulted in organizations having vast amounts of data at their disposal. However, raw data little to no value in today's world. Only if raw data is transformed into information does it become of importance (TING et al., 2009). The process of converting raw data to essential information brought forth the existence of data mining. The field of data mining is more than two decades old. Early pioneers realized that traditional statistical techniques were not adequate to handle the growing volumes of data. Without more efficient methods, organizations and individuals would not leverage information found in large amounts of data. There was an urgent need to come up with techniques that were not only better and faster but also cheaper. Data, especially biomedicine data, is no longer restricted to numeric or characters only in today's world. Due to the increase in the number of medical devices and database management systems, hospital systems have data that cuts across image, video, text and audio. As a result, coming up with efficiently gathering knowledge and managing diversified data has become a priority for most organization in the health care industry. This paper will briefly describe what data mining is and what it primarily entails and robust data mining techniques used in biomedicine (Dong, 2014). 2 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE What is Data Mining (DM), and What does it Entail? Data mining primarily identifies patterns and relationships in data by using various analytical techniques to derive useful information or knowledge. Data mining can also be defined as the process of analyzing data from different angles and summarizing it into essential information that can be used to improve processes within an organization. Data mining is one of the most recent developments in computer science that uses several statistical methods, databases and artificial intelligence (Ferreira et al., 2012). Data mining is possible to identify hidden patterns that are not easily recognized from raw data. By identifying new patterns, physicians can get a new perspective on various diseases and handle them. In many areas of medicine today, data mining has proven to be quite significant by shedding light on new information and improving results obtained. Data mining mainly entails pattern identification and database systems through mathematic and statistical concepts, artificial intelligence and machine learning communities. Although data mining has a lot in common with the statists discipline, they are not the same. Unlike statistics, data mining can deal with diverse data fields. Usually, knowledge management and data mining go hand in hand. Knowledge discovery refers to the process of seeking new information through the synthesis of prior knowledge. Prior knowledge and data are reconfigured and recategorized to develop new explicit knowledge. Data mining is one of the essential steps in knowledge discovery. The first step of understanding a problem that has arisen in the biomedical domain is to work closely with other domain experts to efficiently define the problem and establish goals meant to solve the problem. The next step involves collecting sample data and deciding the data that will be required based on format and size. At this juncture, the data is carefully examined for completeness, missing values and redundancy. Once the sample data is collected, the next step involves preparing the data meant for input for data mining methods in the successive stages. Mainly, it requires sampling, determining correlation, running significance tests and conducting data cleaning. Eventually, the data miner uses data mining techniques to acquire knowledge from the unprocessed data (TING et al., 2009). 3 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE Knowledge Discovery Database Model Data Mining Techniques Data mining techniques are classified into two supervised and unsupervised. Supervised data mining is also known as predictive or directed data mining. On the other hand, unsupervised data mining is referred to as undirected or descriptive mining. Both categories are equipped with functions that facilitate different hidden patterns in large data sets (TING et al., 2009). Supervised Data Mining Techniques Supervised data mining techniques should primarily be used when individuals or organizations have a specific target value they would like to predict about their data. Typically, the targets can have more than one possible outcome. To effectively use supervised data mining methods, it is imperative to have a subset of data points whose target value is already determined. This data is used to develop a model that depicts a typical data point with 4 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE different target values. Some examples of supervised data mining include classification, regression and association rule (Roiger, 2017). Unsupervised Data Mining Techniques Unlike supervised data mining, which has a predetermined objective function, unsupervised data mining does not possess a predetermined objective function. It also doesn't predict a target value. In unsupervised data mining techniques, there is absolutely no outcome variable to predict. The algorithm used in unsupervised methods requires the data miner to specify the number of data points to be included in intervals. Unsupervised data mining techniques are used primarily when a specific goal is nonexistent or when the data miner is focused on identifying hidden relationships in data. Unsupervised data techniques include classification, statistical regression and artificial neural networks. Association The association technique is used to find the link or relationship between different objects in a database. This technique mainly focuses on observing regularly occurring patterns and relationships from datasets found in other databases. Clustering Clustering is an unsupervised data mining technique used in scenarios where there are no easily identifiable natural groupings. Its algorithm can readily find realistic set occurring in data. A cluster refers to a collection of data objects that share some similar characteristics. Usually, a satisfactory clustering method results in high-quality groups to confirm that intercluster similarity is relatively low and inter-cluster similarity is high. In simpler terms, members of a cluster should share similar characteristics with each other than members of a different group. Clustering is one of the most open-ended data mining techniques. Classification Classification is one of the most popular supervised data mining techniques because it mainly involves learning the structure of a group through an example data set. The classification technique is used primarily to learn the datasets system that has already been portioned in groups known as categories. The ultimate objective of the classification technique is to develop a model for each type. Classification techniques are classified into three: decision tree, probability models and nearest neighbour (Besimi et al., 2017). 5 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE Artificial Neural Networks (ANN) Artificial neural networks refer to a computing system designed to simulate the behaviour of a human brain in analyzing and processing information. It primarily learns through examples and solves problems that would be difficult or impossible to solve through human statistical standards. As more data becomes readily available, ANN uses its selflearning features to develop better results (Gerven & Bohte, 2018). In this techniques, no prior information is required. The method features many elements connected together. These elements are called neuron nodes and have numerous artificial neurons known as processing units. These processing units usually have input and output units. The input units receive diverse information determined by an internal weighting system. Eventually, the neural networks attempt to learn as much as they can about the information presented with the sole purpose of producing an output. One of the significant advantages of ANNs is that it has adaptive learning ability. However, this is also a disadvantage because it relies heavily on training data. Therefore, it does not explain the decisions made (TING et al., 2009). Data mining in biomedicine has taken a notch higher due to advancements in technology. It is the detailed process of statistical identification of patterns, associations, and data relationships using advanced analytical techniques (Littl3field, 2017). The creation of data models in biomedicine is vital for using information and knowledge for informed decision-making. The healthcare industry has witnessed the advancement of new database management systems necessary for informed decision-making. There is an application of the image, text, and web mining techniques that help the technicians and the clinicians accord patients the best evidence-based care (Littl3field, 2017). There is no doubt that raw biomedical data is a challenging task. Therefore, data mining is the proper technique used to clean data and ensure that the final product is promising and can be used to make the right decisions in the medical world. Drawing credible conclusions from raw data require sophisticated computational analysis techniques for the correct interpretation of data. Data mining is vital for understanding the structure of the protein and the structure prediction, classification of the gene, analyzing the causes of gene mutations in cancer and ensuring that the gene expressions are done in the best way possible(Littl3field, 2017). In the past years, the clinical world witnessed rapid growth in studies concerning genomics, proteomics, and other biological 6 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE researches. Indeed this requires extensive application of the biological data that has well been analyzed, relationships created, and the associations established. Data mining is embraced in biomedicine and bioinformatics for solving complex biological problems (Littl3field, 2017). This is a clear indicator that data mining is a detailed process of extracting information to establish models, patterns from extensive datasets. In this case, biomedicine relies on artificial intelligence systems, pattern recognition and visualization, and database sets, among other techniques. This is critical in Knowledge Discovery in Databases or Intelligent Data analysis. Therefore, it can be easily deduced that data mining is limited to biomedicine and used in other industries to provide data intelligence. The application of data mining and the advanced machine learning language makes it easy for the professionals in biomedicine to carry out extensive research and come up with historic scientific findings such as the invention of the polio vaccine and the COVID-19 vaccine to reduce the ravaging effects that the pandemic has caused. There are immeasurable advantages associated with the continuous use of data mining techniques in biomedicine (Harrison et al., 2018). For example, knowledge discovery provides critical insights such as diagnosis, validation, simulations, and forecasting, among other essential activities. The whole process of knowledge search and discovery is very complex since it involves storage and the processing of data, correct application of the algorithms, proper visualization, and the statistical presentation of the key findings (Harrison et al., 2018). Data mining as used in healthcare entails many steps that are supposed to be repeated and refined to develop accurate solutions after correct data analysis has been done. Generally, there is no standard framework for data mining in biomedicine as the process depends on the prevailing conditions. Main tasks of Biomedicine Data Mining As opined in the above section, data mining is a complex process anchored on several steps. For example, classification is the primary process that arranges data into the class of under analysis items. Estimation is the second process of data mining that involves ascertaining the value and worth of the continuous variables that have not been correctly determined. Once estimation has been done, the second process is prediction, where the records are classified as per the estimated value of the future use. Association is another task of data mining that entails the proper definition of the items that are together. Clustering is the classification of the population into groups or clusters so that scientific data analysis is done 7 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE in the best way possible. The last task of data mining is description and visualization, where the extracted knowledge and the information are presented using the best graphical and pictorial models (Harrison et al., 2018). Integration of machine learning techniques such as classification, regression, clustering, learning of associations, and the adoption of logical equations and relations makes data mining an essential concept in the noble field of biomedicine (Llovet, 2016). Unsupervised machine learning involves using the data mining logarithms where the patterns and the structures in a given data set are identified. Bioinformatics is one of the required fields that make biomedicine a complete profession. The field deals with the storage, gathering, simulation, and analysis of biological data. Some of the applications under this field are not limited to studying gene expressions, pathways, and molecules, among other vital aspects (Llovet, 2016). The latest advancement in technology has made it easy for the computation of biological data to be developed and stored and accumulated in massive amounts. The interpretation of such information is vital, and it is growing daily. For example, understanding the DNA sequence is one of the most researched areas in biomedicine. Understanding the DNA sequence of the viruses, bacteria and other microorganisms lays the concrete foundation for medical researchers to develop drugs and vaccines to curb the widespread of the diseases (Llovet, 2016). Therefore, the use of sequence, functional, and structural data is of great value in biomedicine. Data mining is essential because it provides and proposes proactive research within the noble field of biomedicine (Llovet, 2016). The researchers have been enabled to develop an advanced understanding of the biological mechanisms to discover new treatments for complicated diseases is made possible. Definition of the research hypothesis during biomedical research studies is highly aided by using the data mining techniques (Llovet, 2016). "Gene finding, protein function domain detection, function motif detection and protein function inference" are but some of the discoveries made possible underuse of data mining techniques (Littl3field, 2017). Protein Data Bank and other biological databases provide great insights into predicting the sequence of the outputs to create a scientific hypothesis as per the results. Proper application of the data mining techniques creates an enabling ground for faster generation of the products to test the reliability and validity of the results (Llovet, 2016). 8 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE Discussion Data mining is associated with multiple values and benefits in the field of research. The manufacture of new drugs and testing the research hypothesis cannot be accomplished without integrating the above data mining techniques (Llovet, 2016). Biomedicine is an extensive area of research whose success relies on a vast amount of biological data. Continuous research and development programs in bioinformatics and biomedicine rely on data mining techniques and strategies. Therefore, the key findings indicate that the biomedical databases provide the factual background for making tremendous and informed-decision decisions such as the development of vaccines promptly. Biomedicine and the related sciences are some of the intensive data fields that require the application of data-driven approaches (Llovet, 2016). It is necessary to appreciate the fact that sophisticated data analysis under the guidance of data mining techniques. It is giving the correct statistics for effective decision-making to support clinical practices requiring a wellguided data analysis process. Therefore, data mining continues to be an essential aspect in the field of biomedicine and bioinformatics. Conclusion Biomedical informatics refers to the natural and scientific process of applying data analysis and data mining techniques to make informed decisions. The current era is considered the golden age of using data mining techniques in making relevant decisions. Data mining has matured to being considered an integral part of biomedicine and the whole healthcare industry. There is no doubt that healthcare institutions are leveraging advanced systems and the success of such systems depends on the use of health informatics and sophisticated data mining strategies. Having a close look at biomedical research indicates that advanced data analysis and data mining techniques have become integral components of day-to-day activities. Researchers, medical experts, and scientists cannot make the right decisions without embracing data mining techniques and the methods as discussed in the above sections. Stakeholders must be aware that the continuous use of data mining approaches has raised controversies (Bellazzi et al., 2011). However, the validity of the medical experiments and the 9 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE generation of the new unbiased knowledge is substantive evidence to inform the world about the values and the benefits of using data mining approaches in biomedicine. 10 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE References Bellazzi, R., Diomidous, M., Sarkar, I. N., Takabayashi, K., Ziegler, A., & McCray, A. T. (2011). Data analysis and data mining: current issues in biomedical informatics. Methods of information in medicine, 50(6), 536–544. https://doi.org/10.3414/ME1106-0002 Besimi, N., Cico, B., & Besimi, A. (2017). Overview of data mining classification techniques: Traditional vs. parallel/distributed programming models. 2017 6th Mediterranean Conference on Embedded Computing (MECO). https://doi.org/10.1109/meco.2017.7977126 Dong, G. (2014). Editorial for International Journal of biomedical data mining. International Journal of Biomedical Data Mining, 03(01). https://doi.org/10.4172/20904924.1000e101 Ferreira, D., Oliveira, A., & Freitas, A. (2012). Applying data mining techniques to improve diagnosis in neonatal jaundice. BMC Medical Informatics and Decision Making, 12(1). https://doi.org/10.1186/1472-6947-12-143 Gerven M., & Bohte, S. (2018). Artificial neural networks as models of neural information processing. Frontiers Media SA. Harrison, E., Dreisbach, C., Basit, N., & Keim-Malpass, J. (2018). An Application of Data Mining Techniques to Explore Congressional Lobbying Records for Patterns in Pediatric Special Interest Expenditures Prior to the Affordable Care Act. Frontiers in big data, 1, 3. https://doi.org/10.3389/fdata.2018.00003 Littl3field. (2017). An Introduction into Data Mining in Bioinformatics. Llovet, J. (2016). Handbook of translational medicine. 1st ed. Edicions Universitat Barcelona. 11 HOW DATA MINING HAS REVOLUTIONIZED BIOMEDICINE Roiger, R. J. (2017). Supervised statistical techniques. Data Mining, 317356. https://doi.org/10.1201/9781315382586-11 TING, S. L., SHUM, C. C., KWOK, S. K., TSANG, A. H., & LEE, W. B. (2009). Data mining in biomedicine: Current applications and further directions for research. Journal of Software Engineering and Applications, 02(03), 150159. https://doi.org/10.4236/jsea.2009.23022 12

Option 1

Low Cost Option
Download this past answer in few clicks

16.89 USD

PURCHASE SOLUTION

Already member?


Option 2

Custom new solution created by our subject matter experts

GET A QUOTE

Related Questions