Prevention of Epidemics in Third World Countries Using Data Mining - Coursework Example

Prevention of Epidemics in Third World Countries Using Data Mining Broadly, data mining can be described as the art of collecting data from different sources and analyzing it with the aim of obtaining a summary of useful information. This art has traditionally been used in various fields such as business and engineering. In healthcare, this is a recently adopted practice and the impact has been positive; it has been proven that if properly performed it can be used to prevent epidemics in third world countries (Mantas 46). In data mining, data is collected and looked at it through various dimensions. It is carefully analyzed, summarized and the relationship between various variables noted. This can be used to fight epidemics in third world country by closely examining medical data about the region and coming up with solutions before they occur again. This has been properly utilized by the retail companies who get to know their shoppers preferences beforehand. Likewise, the health industry can develop a database for all medical parties, such as institutions, individuals and communities. Such a data base would include a list of ailments, people who have suffered them and their treatments. Data mining Healthcare Information Systems The ultimate goal of data mining is to analyze data and come up with prediction patterns for future occurrences’. Basically, the process of data mining consists of a series of steps. These are: The initial exploration. This is the phase where all the data is amassed and cleaned to find out which is relevant to the subject matter. Only relevant variables proceed to the next stage. Model building. Various models are used to try and find the one that best fits the situation at hand. Different models are applied to the same data and their outcomes measured. Deployment. The most suitable model is applied to the rest of the data to get the desired predictions. Electronic health records can be in various forms such as measurements, free texts and images. This amount of medical data is very large and keeps on increasing on an annual basis. There are various systems of handling medical data: One of the models used is the semantic model. In this model, the knowledge is extracted from the lowest levels, where data is represented in measurements or other data that forms multidimensional feature spaces. Another model is the generalized special semantics. In this case, knowledge is represented across various multimodal data repositories. It enables a link between low and high methods, thus bridging this gap. An example is when one has to describe pathological findings, body parts and anatomies. This can applied to various data mining duties when it comes to information in the medical field. How tracking sales of over the counter drugs give us clues on disease outbreaks Over the counter drugs refer to those drugs sold on a constant basis to individuals. Most of the drugs bought in this manner rarely require a prescription. More so, most people that buy these drugs have not seen a certified healthcare provider to assess their situation. This means that data pertaining to these illnesses cannot be collected and is unknown. However, by closely monitoring the drugs that are most sought after, medical professionals can come up with ways of preventing these illnesses from recurring. If doctors find out that people in an area are buying large amounts of diarrhea treatment it can mean that something is wrong in the area. Further tests can show that there might be a looming outbreak of Typhoid or Dysentery based on other external factors such as poor sanitation and presence of dirty drinking water. Nothing should be left uncovered when trying to find the disease that afflict third world countries because even a simple ailment can prove to be a cover for something bigger that finishes off a whole community (Cerrito 18). There is an English saying that reads prevention is better than cure, this is the first step in dealing with these epidemics. Tracking epidemics through social media In recent times, social media has become an important tool that influences our lives in hundreds of ways. Part of this is in the health field. Nowadays, a person does not have to travel an entire country to know the epidemics that afflict the communities, all one has to do is plug in into the internet and that information is available to them. The following are instances of how social media is helping track epidemics in third world countries: Interactive platforms The internet offers interactive platforms where individuals get to interact with medical professionals. They can share their symptoms and the doctors can give prevention measures or even prescribe medication. This is done from the comfort of homes and saves a lot of time. Likewise, information about various ailments is available online. People carry out their research and with the help of local health providers they carry out preventive measures to guard them against diseases. Mobile applications There are millions of mobile applications being developed daily. Some cater specifically to the medical field and are very important to patients and healthcare providers. Notably, in South Africa there is an application that allows patients to order for their prescriptions from the safety of their homes and has to date helped thousands. These drugs are then delivered in a short while via a bicycle. Other notable applications let one input their symptoms and then a possible diagnosis is given. This is very important for people living in areas where affordable healthcare is a luxury they do not have access to. Web pages There are plenty of websites that abound with data relating to epidemics that are prevalent in third world countries. This information is important as it can be accessed by healthcare providers who will then come up with direct measures to tackle such problems. Identifying the problem is a step towards finding a solution (Sauter, 78). The above analysis demonstrates that social media plays a very important role when it comes to tracking epidemics in third world countries. Despite this, more can still be done to make maximum use of this very important tool. Advantages of data mining 1. Forecasting what future drug purchases will be. If carried out effectively, it is possible to determine the drugs that the majority people buy. This can be used to show if a disease is afflicting the population (Rahman 236). We can therefore come up with measures that will ensure the drug is available when it is needed. An example is Malaria. Studies show that Malaria is one of the highest killer diseases in Africa, killing millions every year. It is common knowledge that Malaria is prevalent in the rainy seasons. Using data mining, we can therefore forecast when this will be and make available the necessary equipment and medication before an epidemic occurs. This includes supplying enough mosquito nets, mosquito repellants and anti-malarial treatments. In such an instance, data mining would have helped us prevent a possible epidemic. 2. Fraud detection. When data mining is in use, all transactions are closely monitored. In this way, any irregular payment can be followed up with and halted. This helps stop misappropriation of funds (Giles 142). A lot of foreign nations donate money to be used in third world countries to fight certain ailments. More often than not, this money has been diverted and spent elsewhere or used for personal gain. When tracking information relating to such sums of money, we can ensure the money gets to its target users. Communities are able to benefit by getting free medication, healthcare and even food. Such programs are known to have an impact in the lives of hundreds of individuals. 3. Aid in decision making. Data mining enables us to know the trends in the field or the target market. This information helps us know the situation on the ground. Using this, we can predict the future and hence make informed decisions. A study showed that between HIV/ AIDS and Malaria, malaria was more prevalent in the tropics that towards the poles. As such, it made it possible to properly distribute funding and medication in a clear manner that resulted in lower wastages (Gaol 46). 4. Assistance in lowering costs The most important aspect about data mining is that it gathers past data and enables us prevent mistakes that might have been done in the daily course of business. The end result of this is that we are able to reduce costs in regard to any particular project. This can go a long way, especially so in donor projects where every shilling counts. Insurance companies also use data mining to detect medical insurance fraud. They use the data to come up with claim patterns, after this, they can easily notice the claim patterns that are unusual. Insurers can therefore use this information to ensure that they have limited losses. When this happens, they can reduce the cost of insurance therefore making insurance more affordable for majority of the population. 5. Provision of effective healthcare. Doctors can analyze data so as to find out which treatments are most effective (Berka 36). By comparing related data such as symptoms, treatments and drug effects, data mining can enable doctors know which type of medications are effective for various groups of individuals. This can further be used to develop standards of care and guidelines for best practices. Healthcare providers can further prevent hospital admissions and transmission. This is by tracking patients with chronic illnesses or those considered to be high risk. They therefore have appropriate intervention methods to be used in case anything comes up. This up close approach also guarantees the patients better healthcare. Disadvantages of data mining Despite all the benefits outlined about data mining in regards to preventing epidemics in third world countries, there are a number of disadvantages in line with this that should also be considered. 1. The amount of information available is tremendous. Data mining involves gathering data from various fields so as to analyze it. However, where there exists a lot of information in regards to a certain subject matter, analysis of each one of them becomes a difficult task (Bos 3). This is made worse by the fact that this is a digital era. Therefore data mining has to be done carefully and over a long period of time so that it is as accurate as possible. 2. User privacy When data is being collected from various sources it carries with it a lot of user information. In most cases, the users are not aware of this. Such information has the potential to reach the wrong hands and cause serious harm to the providers of the data. This mainly includes personal data such as social security numbers, personal identification numbers for electronic cards and even bank account details. As such, much care has to be taken when carrying out data mining to ensure one’s privacy. 3. Data inaccuracy Data mining involves the use of other people’s information. This type of data can be inaccurate. Most people write based on their own personal opinion. Their work is therefore biased to suit their line of thinking (Fasano 14). Other people use the freedom available on the internet to write falsehoods. This causes a lot of headache to people who will come across this information and believe it to be the gospel truth. Conclusion In conclusion we should embrace technology and let it be our friend. On a daily basis, we interact with each other and leave a lot of information lying about. Such pieces of information are very crucial since they represent a piece of us that might help us in future. Data mining is very important and despite the pros and the cons we have to agree, it is far more beneficial than harmful. Something has to be done about the perennial epidemics in third world country. Surprisingly, most of these are treatable diseases and if left at large, they kill millions of people every year. This should not be the case. Data about such diseases should be readily accessible so that all interested parties know the right approach to use when they want to assist third world countries who in particular suffer as a result of disease and epidemics. If this trend continues, epidemics in third world countries will be a thing of the past. References: 1. Cerrito, Patricia B, and John Cerrito. Clinical Data Mining for Physician Decision Making and Investigating Health Outcomes: Methods for Prediction and Analysis. Hershey, PA: Medical Information Science Reference, 2010. Internet resource. 2. Giles, Roslyn, Irwin Epstein, and Anne Vertigan. Clinical Data-Mining in an Allied Health Organisation: A Real World Experience. Sydney: Sydney University Press, 2011. Print. 3. Berka, Petr, Jan Rauch, and Djamel A. Zighed. Data Mining and Medical Knowledge Management: Cases and Applications. Hershey PA: Information Science Reference, 2009. Internet resource. 4. Fasano, Philip. Transforming Health Care: The Financial Impact of Technology, Electronic Tools, and Data Mining. , 2013. Internet resource. 5. Bos, Lodewijk. Medical and Care Compunetics 5. Amsterdam: IOS Press, 2008. Print. 6. Gaol, Ford L. Recent Progress in Data Engineering and Internet Technology: Volume 1. Berlin: Springer, 2013. Internet resource. 7. Rahman, Hakikur, and Isabel Ramos. Ethical Data Mining Applications for Socio-Economic Development. Hershey, Pa: IGI Global (701 E. Chocolate Avenue, Hershey, Pennsylvania, 17033, USA, 2013. Internet resource. 8. Cerrito, Patricia. Cases on Health Outcomes and Clinical Data Mining: Studies and Frameworks. Hershey, PA: IGI Global, 2010. Internet resource. 9. Sauter, Vicki L. Decision Support Systems for Business Intelligence. Hoboken: John Wiley & Sons, 2011. Internet resource. 10. Mantas, J, Stig K. Andersen, Maria C. Mazzoleni, Bernd Blobel, Silvana Quaglini, and Anne Moen. Quality of Life Through Quality of Information: Proceedings of Mie2012. Amsterdam: IOS Press, 2012. Internet resource. Read More