Data Mining Applied To Health Industry And Looking For Classification
Introduction-Data Mining Applied To Health Industry And Looking For Classification
Want the Best Assignment Help in the UK? Look to Native Assignment Help for unparalleled expertise and support. Our dedicated team of professionals goes above and beyond to ensure you receive top-quality assignments that exceed your expectations.
Data mining (DM) uses a pattern for dataset
DM is a subfield of AI (Kolling et al. 2021)
Bibliometric use of DM in healthcare will be discussed
Case study and support will be provided
Hi everyone, good morning and welcome to this presentation session regarding the importance of DM in healthcare. Today I will provide details about the healthcare industry, details of DM and its importance along with a supportive case study. Data mining (DM) has a great influence on the improvement of data management of a large dataset in the healthcare industry. DM uses specific patterns for different cases for analysation of such a large amount of data. DM is an important part of AI that uses different subfields of AI in detection of databases in healthcare. Bibliometric use of DM in healthcare along with the different strategies of using AI will be discussed here. A complete case study with supportive details will be discussed in their study.
Healthcare industry
Healthcare industry offer medical service
Includes hospitals, medical shops and so many
Important for achieving sustainable goals (Forbes.com, 2018)
UK spends 9.6% GBP from GDP in healthcare (Ons.gov.uk, 2019)
I am starting this part with the offerings of healthcare services along with its part and recent statistics of UK. The Healthcare industry is an important sector that offers different medical services in case of any medical emergency. Healthcare industries are associated with different sectors such as hospitals, medical shops, and different medical services in any type of medical emergency. Healthcare service needs to be improved and data needs to be managed effectively as it influences in achieving sustainable goals. I have collected recent data that indicates spending by UK in healthcare is almost 9.6% of GBP from the GDP value.
Contd.
This part will consist of the challenges that are associated with healthcare will be the key aspect of the discussion. I have understood that mainly four challenges create issues in healthcare such as affordability of service, awareness, quality of the healthcare service and accessibility by everyone. Challenges regarding affordability of proper help service are a factor that causes issues for various persons in UK. Further, lack of awareness and accessibility are two factors that create barriers to availing effective treatment. Quality service is important in healthcare emergencies that will improve the overall industrial growth of healthcare in UK. If you have any questions or suggestions on this, u all can easily express them without any hesitation before going to the new part.
Issues with data handling in healthcare
Quality of data, interoperability, security and policy setting are issues
Data includes health record to medical images (Palanisamy and Thirunavukarasu, 2019)
Lack of patient-centric ecosystem management
Reduces operational efficiency
In this part, I will explain different issues in data handling, especially for healthcare services. Four issues are associated with data handling such as management of quality, interoperability of data, security issues and set of policies in service. We all know that those data include healthcare services and different medical images that help in providing services to patients. Lack of data handling reduces service quality and operational efficiency in the healthcare industries of UK. I hope all of you have understood from this part about how important data handling is in healthcare.
Contd.
I am starting this part with the influence of data mismanagement in healthcare. Mismanagement of data causes frustration for the patients that try to receive quality treatment. You will identify that these frustration issues cause a decrease in efficiency in providing healthcare services. Poor decision-making is another important issue to lack of data management that causes barriers to providing sufficient service. The last issue that I have identified is distrust of staff over new technology that can improve healthcare service quality and patient satisfaction rate. Is there any question on this part?
Details of data mining
Advanced technology in data handling
Discover information from a large dataset
DM helps in intrusion and fraud detection (Salo et al. 2018)
Use mathematical analysis
Now, I will provide information about DM in this part with its importance in the modern-day. DM is nothing but an advanced technology that helps in handling large data that are present within a specific dataset. DM has a significant usage especially in maintaining the security of data by detecting fraud issues or intrusion problems. Another important asset that DM contains is mathematical analysis through which it can easily detect fraud issues within a dataset. In the next part, I will discuss more on the DM and its techniques.
Contd.
I will provide advantages of DM in this part that can be beneficial in the health industry. DM helps in gathering information that is knowledge-based and helps in profitable production. DM has the potential in discovering hidden patterns that cause a cost-effective fraud detection strategy. Easy analysis, profitable decision-making ability, and perfect production providing ability create advantages in using DM, especially for health industry growth.
Techniques of data mining
Association, clustering, classification, prediction and sequence in the pattern
Modern techniques are cluster analysis, ANN and decision trees (Qiao and Jiao, 2018)
Supports regression and prediction
Used in warehouse management
This part is important as I am going to inform you about the techniques of DM here. Five important techniques are associated with DM such as association that helps in data association, clustering, classification of data, prediction, and maintaining sequence in the data pattern. However, other modern technologies are analysis of clusters, ANN, and the use of decision trees for data handling. The advantage of using DM is that it supports regression along with prediction patterns and uses of technology in warehouse management. You can ask any question about this topic easily.
Methodology
Use of statistical techniques (Forbes.com, 2018)
Discover relationships in a database
An interactive process that requires specific objectives
Use software for data sorting
I have identified the methodology using which DM works in data handling. DM uses different statistical techniques to discover relationships between different datasets. The interactive process in DM requires some specific objectives for data handling that uses software-based techniques. Do you have further questions on the methodology of DM?
Importance of DM in health industries
Helps in predicting disease diagnosis (Chandrakala et al. 2021)
Supports decision for customer relationship
Detects fraud in medical history
Supports medicine prediction for health issues
I will provide details about the main part of DM in health industries in this part. The DM helps in the effective diagnosis of any disease through which medical services can be provided to patients at an early stage. DM supports a proper decision-making ability through which health industries can maintain relationships with customers. Further, fraud detection and effective medicine prediction are the other two uses of DM in health care. I am going to further explain this topic in the next slide.
Contd.
Continuing with the previous analysis, other advantages of DM for using it in the health industry includes personalised service in medicine. Availability of any unprecedented treatment along with cost-reduced services is another advantage for using DM by health industries in UK. Further, management of patient history by managing data helps healthcare sectors effectively to provide service. I think all of you have understood the importance of DM in the health industry.
Strategies of using DM in healthcare
Improvement of system functionalities
Works on assumptions from data history (Roper, 2021)
Understanding objectives are essential
Selection of mathematical tracking pattern
Now, I will provide information about how health industries can easily use DM in service. The first thing that I have understood is an improvement of systems before implementing DM. DM works on assumptions for which historical data availability is necessary to track the data pattern. Understanding objectives are crucial, through which the health industry can select a mathematical tracking process. I will provide further details in the next slide and until now are there any question?
Contd.
Based on the discussion in the previous slide, I will provide other strategies using which DM generally functions. Maintenance of unsupervised clustering, supervised learnings and analysis of the market for health services in specific areas such as in UK are essential. Learning depends on three factors such as classification of DM, estimation and prediction that helps in the improvement of health services for health industries in UK. I think I am successful in clearing all the strategies of DM associated with health industries.
Challenges of using DM in healthcare
Reliability in management of medical data (Pubmed.ncbi.nlm.nih.gov, 2017)
Continuous performance management and tracking
Sometimes noisy data
Data distribution error
I am providing details of challenges that health industries face in using DM in this part. The reliability of different medical data is a challenge here. Management of continuous performance and racking fraudulent activities are not possible all-time for DM. The presence of noise in data and error in distribution are other hazards associated with DM.
Contd.
Data complexity
Erroneous algorithm in software
Influence in patient care (Pubmed.ncbi.nlm.nih.gov, 2017)
Management of data security
Continuation of the discussion in the previous slide, other challenges that I have identified is data complexity and the presence of erroneous algorithms in DM techniques. The error in DM strongly influences patient care service in health industries. Security of data is another key issue that causes challenges in using DM in health care as data leakage dampens data safety.
Case studies
Expenditure in health care is 214.4 billion GBP (Ons.gov.uk, 2020)
Covid-19 issue and confirm case in UK is 10189059 (Statista.com, 2021)
Effective DM usage in testing of health issues
Training to staffs based on data of symptoms
A case study of Covid-19 in UK and expenditure of UK government in health services are mentioned in this slide. I have collected data that UK government has spent 214.4 billion GBP on health services. The data of Covid indicates that almost 10189059 people have experienced the deadly virus in UK and all of their data is maintained using data mining for future use. Staff gets training based on the history of disease that is collected through data mining.
Contd.
Health issue
Symptoms
High temperature
High temperature in chest or back in maximum patients
Caught
Coughing continuously and have more than three coughing episodes within 24 hours (Nhs.uk, 2021)
Loss in smelling power
Loss in smelling power in various patients are other issues
I will continue the case study about Covid-19 systems in UK. Three major symptoms those are present such as excessive temperature, caught and loss of smell. All of them are identified based on DM through which improvement of medical services is possible.
Future perspective
Helps in improving data management of patients
Improves service in diagnosis of deadly disease (Sohail et al. 2018)
Broad aspect in personalised medicine delivery
Helps doctors to get additional information
This slide is based on the future perspective of DM in the health industries of UK. I have found that DM supports improvement in the management of chunk data in health industries that are related to a patient's history. Further, improvement in service in the diagnosis of deadly diseases in future can be a broader aspect of DM. Personalised delivery of medicines and availability of additional data for doctors about different patients can be a great advantage of using DM in healthcare in near future.
Contd.
Further affordability of healthcare
Better patient satisfaction
Will reduce data dimensionality issues (Ali et al. 2021)
Will bring perfection in diagnosis
Based on the future advantages mentioned in the previous slide, another advantage that can improve the health industry in future by using DM is affordability in service. Improvement of patient satisfaction and reduction of data dimension problems will be key future aspects. DM will bring more perfection in diagnosis and data analysis in the health industry of UK.
Clustering and correlation
Figure of cluster analysis between UK and Australia indicates that number of new cases in Australia is higher compared to number of new cases of COVID-19 in UK from 2020 to 2021. Further, correlation table of UK and Australia indicates Pearson correlation value is 0.265 and 0.69 respectively. In correlation when Pearson value is close to +1 it indicates positive association between two variables. In this regard, positive relation identified between COVID cases and death rates in UK and Australia
Regression
Null hypothesis (H0): New cases of COVID-19 do not increase number of death in UK due to COVID-19 (p<0.05)
Alternative Hypothesis (H1): New cases of COVID-19 increase number of death in UK due to COVID-19 (p>0.05)
In this regression model, dependent variable is new cases of COVID 19 and independent variable is number of death due to COVID 19. In this regression model R square value is 0.072, which indicates predictor variable may able to predict 7% of variances in independent variables in this dataset. Above regression model indicates p- value is 7.3E-13, which is less than level of significance (0.05). Here, regression model consider alternative hypothesis. Here, it can be stated that number of COVID-19 cases increases number of death in UK due to COVID 19. Therefore, these data mining may apply in health industry to predict number of death rate and new cases.
Conclusion
DM is an critical solution (Moreira et al. 2019)
Details of DM in health industries are mentioned
Advantages include accuracy, cost reduction and other
Challenges include security and maintenance
In this last slide, I will conclude that DM is critical in health industries for maintaining accuracy. All advantages and challenges are mentioned in detail in this study. I hope this is a good session and all of you have enjoyed the presentation. Thank you for providing an important time for listening to the presentation.
References
Journals
Ali, F., El-Sappagh, S., Islam, S.R., Ali, A., Attique, M., Imran, M. and Kwak, K.S., 2021. An intelligent healthcare monitoring framework using wearable sensors and social networking data. Future Generation Computer Systems, 114, pp.23-43.
Chandrakala, P., Sumithra, A., Saranya, A. and Lakshmi, R.B., 2021. Influence of Data Mining Techniques in Healthcare Research. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(14), pp.1303-1311.
Kolling, M.L., Furstenau, L.B., Sott, M.K., Rabaioli, B., Ulmi, P.H., Bragazzi, N.L. and Tedesco, L.P.C., 2021. Data mining in healthcare: Applying strategic intelligence techniques to depict 25 years of research development. International Journal of Environmental Research and Public Health, 18(6), p.3099.
Moreira, M.W., Rodrigues, J.J., Korotaev, V., Al-Muhtadi, J. and Kumar, N., 2019. A comprehensive review on smart decision support systems for health care. IEEE Systems Journal, 13(3), pp.3536-3545.
Palanisamy, V. and Thirunavukarasu, R., 2019. Implications of big data analytics in developing healthcare frameworks–A review. Journal of King Saud University-Computer and Information Sciences, 31(4), pp.415-425.
Qiao, X. and Jiao, H., 2018. Data mining techniques in analyzing process data: a didactic. Frontiers in psychology, 9, p.2231.
Roper, S., 2021. Ethicality of Data Mining and Predictive Analytics. Undergraduate Research, 1(2), p.8.
Salo, F., Injadat, M., Nassif, A.B., Shami, A. and Essex, A., 2018. Data mining techniques in intrusion detection systems: A systematic literature review. IEEE Access, 6, pp.56046-56058.
Sohail, M.N., Jiadong, R., Irshad, M., Uba, M.M. and Abir, S.I., 2018. Data mining techniques for Medical Growth: A Contribution of Researcher reviews. Int. J. Comput. Sci. Netw. Secur, 18, pp.5-10.
Websites
Forbes.com, 2018. Data Mining Concepts That Business People Should Know, Available at: [Accessed on: 06/12/2021]
Forbes.com, 2018. The Importance Of The Healthcare Sector To The Sustainable Development Goals, Available at: [Accessed on: 06/12/2021]
Nhs.uk, 2021. Main symptoms of coronavirus (COVID-19), Available at: https://www.nhs.uk/conditions/coronavirus-covid-19/symptoms/main-symptoms/ [Accessed on: 06/12/2021]
Ons.gov.uk, 2019. How does UK healthcare spending compare with other countries?, Available at: https://www.ons.gov.uk/peoplepopulationandcommunity/healthandsocialcare/healthcaresystem/articles/howdoesukhealthcarespendingcomparewithothercountries/2019-08-29 [Accessed on: 06/12/2021]
Ons.gov.uk, 2020. Healthcare expenditure, UK Health Accounts: 2018, Available at: https://www.ons.gov.uk/peoplepopulationandcommunity/healthandsocialcare/healthcaresystem/bulletins/ukhealthaccounts/2018 [Accessed on: 06/12/2021]
Pubmed.ncbi.nlm.nih.gov, 2017. The Hazards of Data Mining in Healthcare, Available at: https://pubmed.ncbi.nlm.nih.gov/28679892/ [Accessed on: 06/12/2021]
Statista.com, 2021. Cumulative number of coronavirus (COVID-19) cases in the United Kingdom (UK) since January 2020, Available at: https://www.statista.com/statistics/1101958/cumulative-coronavirus-cases-in-the-uk/ [Accessed on: 06/12/2021]
