Introduction
The past 30 years has registered a major increase in the number of lifestyles diseases affecting the community. Many are life-threatening making it important to generate data and present findings to the community, government and stake holders so as to curb the problem. Cancer has been on the rise in the US during the past 3 decades and is today classified as among the main causes of death in the USA (Skyler, 2012). This makes it important to perform in-depth research on which data shall be collected and evaluated for determining important trends which may not be detectable to the naked eye while viewing numeric data. Different data mining and statistical tools can be employed to generate visuals related to the diabetes datasets which can then be used to build an action plan on how the medical condition can be prevented or managed and help reduce the number of fatalities and people being diagnosed with the disease in future (Zanasi, Ebecken, & Brebbia, 2009). To perform this analysis the diabetes dataset available on US diabetes dataset available at the UCI machine learning Repository has been used.
Description of the proposed pilot program
The proposed program would involve the mining of patient data to determine important areas and trends which will need to be reported and interventions developed (Sussman, 2001). This would require the proposed project to undergo a two-stage evaluation in which the raw data shall first be analyzed and studied to determine important trends on the statistics related to cancer in the USA. Once identified the research shall move on to stage two in which the government, healthcare department, NGO’s and the affected communities shall be approached regarding the findings and a proposal presented to the stakeholders on ways in which intervention, assistance, and support can be delivered to the affected communities.
Scale of problem
The dataset used to prepare this proposal consists of 101766 patients from 130 hospitals from across the USA. It is a fraction of the scale of the concern considering the USA has a total population of 326.5 million as of 2017.
Program Size
The proposed program will begin at a micro level in which only the data analyst shall involved and will evaluate the data using different data mining tools to determine correlating aspects linked to diabetes in the community (Kerzner, 2009). A wide verity of tools shall be used to secure a wider perspective linked to the situation before further proposals can be drafted regarding the medical concern.
Number of participants involved
Once data has been mined a proposal shall be drafted and presented to the concerned government departments and officials as well as NGO’s and other stakeholders who will be integrated to the projects implementation. The objective of the proposed project will be to create awareness among the community regarding venerable groups who will require additional support to help them understand how to avoid diabetes in future generations. The proposed awareness project will begin at community levels whereby social workers shall be educated regarding the finding and be provided with training to educate the community (Thomas, Kern, Hughes, & Chen, 2016). Gradually the concern and finding will gradually be spread to the community and especially to children, teenagers and the youth using volunteers, teachers, and government officials thus helping create awareness on ways in which the medical conduction can be prevented on future generations
Description of the proposed evaluation – Data Analyses and Findings
Data for the project has been processed using data mining tools and excel which has allowed for important statistics to be identified regarding the patient statics. Each tool has helped determine a different aspect of the data which will then be used to develop surveys and awareness programs in relation to educating the public. We have used a data mining to run simulations of the data and produced different results which shall be used to identify any correlation between the data set (Klass, 2012). In addition to the data mining tools excel has also been used to plot certain values of the data which shall also be used to determine important trends found on the dataset which may not be easily noticeable when the data is presented to the individuals in bulk.
Rapid Miner Analysis
To mine the data effectively on Rapid miner and secure understandable data, we have used the Churn data mining feature which has separated the data which allows for the results to then be converted into visual outputs using different data elements resent on the data mining tool (Miner, et al., 2014). The results for the data mining were restricted to age, gender, race, and prevalence within the documented population. The following are the results of different simulations run using the Churn data feature.
By studying the results from the data mining simulations it clear there is a major concern related to the prevalence of diabetes with relation to race and age. All simulation has reported the Caucasian and African American races are at highest risk of being affected by cancer. Other influencing factors linked to the prevalence of diabetes among all communities are linked to the age group cancer affect, thus allowing for a clearly defined survey to be developed to address this concern.
MS Office Excel Analysis
Once again, reviewing the results generated by the MS Excel program which is a simple and more direct tool used for data analysis shows a clear prevalence of cancer among two communities (Winston, 2009). This directly indicates that the results generated by the Data mining tools are accurate thus allowing for further action can be taken with regard to developing a proposal on curbing the medical concern.
The Community Survey
Before proceeding to develop an intervention plan it’s also important to collect physically data from the public. This will require being done through online forums, social media and by approaching volunteers on the streets. The surveys questioner will focus on asking the public simple questions regarding their understanding of cancer, its caused and prevalence in the community (Wurzbach, 2002). A total of between 3000 and 5000 surveys will require being filled so as for the data to be run once more to determine public awareness regarding the medical concern. Questioners shall be kept simple and restricted to Yes; No options so as to reduce the number of time volunteers spend filling the survey as well as secure the most accurate result. Only 10 questions shall be used on the questionnaire to encourage volunteer participation and accurate result.
Government, NGO, and Private Sector Intervention
With the data having been mined and analyses and public knowledge collected the project can move to the next step which is government, NGO and private sector international. This will deliver important backing towards addressing the identified medical concern among the affected communities and public in general which will allow for better education among the younger generations which will help reduce the prevalence of diabetes among the high-risk communities in future (Merson, Black, & Mills, 2006). This is important since diabetes is a medical condition which cannot be cured thus affected populations can only receive treatment which will help manage the medical condition. With no cure available for affected populations, the proposed project would focus its attention towards educating the younger generations which will create awareness and help reduce the risk of them developing diabetes when they grow older.
Conclusion
Reporting medical problems being experienced by the community today is an important aspect towards reducing the prevalence of the medical conditions among future generations. To achieve the best results its necessary for public concerns to be identified among the community in general which can then be investigated and proper reports developed regarding the concern. It’s important to accumulate evidence and demonstrate a vivid understanding of the public concern so as to develop a strong proposal that can be presented to the public and authorities for further analyzing and implementation.
References
Kerzner, H. (2009). Project Management: A Systems Approach to Planning, Scheduling, and Controlling. New York: John Wiley & Sons,.
Klass, G. M. (2012). Just Plain Data Analysis: Finding, Presenting, and Interpreting Social Science Data. Maryland: Rowman & Little field Publishers.
Merson, M., Black, R. E., & Mills, A. (2006). International Public Health: Diseases, Programs, Systems and Policies. Jones & Bartlett Learning.
Miner, L., Bolding, P., Hilbe, J., Goldstein, M., Hill, T., Nisbet, R., et al. (2014). Practical Predictive Analytics and Decisioning Systems for Medicine: Informatics Accuracy and Cost-Effectiveness for Healthcare Administration and Delivery Including Medical Research. Oxford: Academic Press.
Pal, N. (2007). Advanced Techniques in Knowledge Discovery and Data Mining. Springer Science & Business Media,.
Skyler, J. (2012). Atlas of Diabetes. Miami: Springer Science & Business Media.
Sussman, S. Y. (2001). Handbook of Program Development for Health Behavior Research and Practice. New Delhi: SAGE.
Thomas, P. A., Kern, D. E., Hughes, M. T., & Chen, B. Y. (2016). Curriculum Development for Medical Education: A Six-Step Approach. JHU Press.
Winston, W. L. (2009). Microsoft® Excel Data Analysis and Business Modeling. Microsoft Press.
Wurzbach, M. E. (2002). Community Health Education and Promotion: A Guide to Program Design and Evaluation. Jones & Bartlett Learning.
Zanasi, A., Ebecken, N. F., & Brebbia, C. A. (2009). Data Mining X: Data Mining, Protection, Detection and Other Security Technologies. Boston: WIT Press.
