need a presentation in mins

Data science is an essential aspect of the health care and medical field. Data science enhances drug development and discovery by analyzing genomic information; therefore, helping medics and researchers understand critical issues related to certain drugs and diseases. With data science tools, it is now easier to evaluate raw data and develop meaningful insights. Data science allows medics to use deep learning methods to conduct various laboratory reports. The testing of patients and the provision of results is now easier and efficient with data analytics. The data science concept can be used in Vietnam to improve the health care system and ensure that people can access health care services easily. In this report, the researcher will provide the analysis of the given data and talk about the discoveries of the identified visualization data.

The standards of living in Vietnam have implications on medical and healthcare expenses. Low standards of living experienced by the poor people increases their probability to pay high charges for treatment. Most health and medical services available for poor human beings in Vietnam requires them to pay before or after receiving the healthcare services. Another challenge that poor people face in this country is their low capacity of paying for the healthcare and medical services (Trivedi, 2002). Also, people living at low standards rarely have access to prepayment programs as well as medical insurance which makes them have trouble in payment of the high medical costs out of the pocket. The substantial medical expenditures force the living standards of such households to remain low because consumption of essential supplies is reduced to meet medical expenditures. This reduction of consumption of crucial items for healthy living and welfare in the long run denies the poor the opportunity of leading healthy and economically firm lives. Economic stress and poor consumption of essential goods exposes them to higher risk of health problems hence making payment of such high costs for treatment a routine.

Makers of health-related policies in Vietnam have apprehension with protection of poor households from prospect that poor health would result to catastrophic fiscal expenses and succeeding destitution (Sepehri & Vu, 2019). This study is therefore conducted to find out more implications of living standards on healthcare and medical costs in Vietnam and come up with recommendations on appropriate ways of mitigating the negative impacts. The study investigates the magnitude of catastrophic medical costs as the initial step towards the development of appropriate responses to this problem via construction of relevant policies. Some relevant policies include reduction of medical systems that heavily rely on out of the pocket cash payments and provision of insurance programs that provide protection of fiscal risk.

The study is conducted within a period of twelve months by the World Bank in the year 1997 (Trivedi, 2002). The analysis uses a survey design to the study to make 5999 observations on household consumption and living standards. The survey uses variables such as age, location (urban or rural), gender, and consumption on food, expenditures on medical services among others. Regression analysis is used in identification of factors related to catastrophic medical costs with an aim of assessing the magnitude of living standards’ implications on medical costs. This assessment is accomplished through comparison of percentage of income utilized in medical costs to percentage used on other items and total income.

The research paper will fall into the category of analysis done on the pre-existing data, where it is pulled from the survey conducted by world bank in Vietnam (Living Standards Survey 1997-1998, 2020). So, the step of collecting data can be skipped, as the next step is to work with data (Kirk, 2016), these includes the steps of plan the analysis steps. The process of planning the analysis need to perform based on the questions need to be answered or expected to find from the survey data. In the data analysis, process, it is very important to describe the dataset before you start performing the analysis and present it (Simpson, 2015). Before analyzing the quantitative study, it is important to understand the numerical information from the dataset.

In this paper the data analysis is performed on the dataset file names “dataset_VietNamH” to understand medical expenditure of the household based on the standard of living they fall into. Figure 1 describes about the details of the field belong to the dataset chosen. The dataset includes of the information such as Sex of the household, household styles, size, log value of total expenditure, medical expenditure, and total expenditure. The interesting information from the dataset is the total medical expenditure and total 12-month medical expenditure are the same, this can be inferred from the Figure 4. Correlation of the dataset, where the correlation is 1. Other interesting point is due to the Vietnamese dong uses very high value, which is why the survey expenditure data is converted into logarithm value, to represent in the small number.

Table 1. Dataset field description

On clear understanding of the dataset fields, the next step is to understand the simple analysis to find any useful information (Simpson, 2015). The simple analysis starts off with understanding the summary of the dataset executed in R. From the summary refer to the figure2, it is clear that the mean average age of the household head is 48.01, median of the household head is 46 and maximum value is 98.In terms of the education attained by the household head, it is clear that the mean of the education earned is 7 years and the median falls on 7, any household head who has 10 plus years of experience will fall above the 3rd quartile of the whisker plot. Considering the household size, the size is the mean size is 5, as the fraction really can’t applicable here and median falls under the same size of 5 and the maximum size of the household from the survey conducted is 19.By looking at the maximum value of the 2 different data field lnmed and lnexp12m, it is confirmed the two different data set is same, but the name refers it differently.

Figure 1. Summary of the survey dataset

On finishing the understanding in terms of the mean, median value, the next step is to determine the correlation between the various data fields exisits. It is clear from the figure 4, that the correlation between the various factors to determine the impact of one data over the other. From the correleation diagram the following key points can be inferred:

· Urban household has the highest intotal expenditure when compared to farm household

· In terms of the size of the housemates, the size of farm household is higher than the urban household

· Food expenditure increase along with the number of households increase in any type of household.

· Medical expenditure is high on the urban, the size of the house also affects the medical expenditure in urban household.

Figure 2. Correlation of household type, size, total, medical and food expenditure

Figure 3. Correlation of entire dataset

The following various pie charts represent the visual form of the female household head percentage versus the male household head percentage, this is much different then the household head survey confirmed from United states which states only 10 percent of the national households were holding women as their house head (Dymski & Isenberg, 2018).

Figure 4. Gender household head chart

Below pie chart represents the different ratio of farm household versus the urban household, the difference in percentage of the both the pie chart represents that there are some household head had a household in both urban and farm household.

1

THE IMPACT OF LIVING STANDARDS ON MEDICAL EXPENSES IN VIETNAM

5

THE IMPACT OF LIVING STANDARDS ON MEDICAL EXPENSES IN VIETNAM

Figure 5. Farm and Urban household chart

Comparison for sex of a head in farm household represented in figure 7. This comparison is to help understand the percentage of female vs male leading a house in Vietnam. This shows more male leading the house in farm category.

Figure 6.Farm Householders based on sex

Comparison for sex of a head in Urban household are represented in figure 8. This comparison is to help understand the percentage of female vs male leading a house in Vietnam. This shows more male leading the house in Urban category.

Figure 7. Urban householders based on sex

The figure 9 plot shows the comparison of expenditure in 3 different categories (Total, Medical and Food) between farm and urban households. The values shown in the graph denotes average expenditures and this will help us to understand what category of household have more expenditure which implicitly tells us if the farm households are well developed in Vietnam or not. The comparison implies that Urban household have more expenditure on all 3 categories which also shows that Urban people are well off compared to farm households. Total Expenditure is way higher in Urban households

Figure 8. Farm and Urban expenditure

The below figure 10 bar chart shows the percentage of farming people in Urban households. The reason for the comparison is to know the demography of farming people in Vietnam.

Figure 9. Comparison of farm with urban household

The below figure 11 bar chart is the comparison of expenses in all the categories based on number of people in a household (christinelly, n.d.). The comparison is pretty much intuitive, but there is some exception according to the data. This shows the average of total expenditure, medical and food expenditure by households.

Figure 10.Average expenditure with household size

Comparison of total average expenditure based on number of household members. Figure 12 shows the people with less household members spend less and vice versa.

Figure 11.Total expenditure based on number of household members

This is the exponential average value of Comparisons for expenses of households with total, medical and food expenditure. This is the graphical plot of average expenses.

Figure 12.Graphical view of expenditures with household members

Figure 13 Number. Of people in each household size

Figure is a clustered bar chart that depicts the number of people in each household size. The x-axis represents Household size and y –axis represents Gender. The maximum number of males and females are in hhsize 4 and minimum number of males are in household size 19 and minimum number of females are in hhsize 16.

The data set on the impact of living standards on the medical expenditure in Vietnam has varying findings. The analysis of the data shows that urban households have a higher expense in medical and other sectors such as the food and generally in total expenditure. This may be because urban households are comprised of more educated people who earn reasonably higher than those in farm households and hence spends higher. Another notable finding is that food expenditure is more elevated than medical expenditure. This points to the conclusion that the general health of Vietnamese is stable, hence reducing the need for medical expenditure. Food is a vital need, thus takes a higher portion of the earnings, which is very reasonable. A majority of the household heads are male in both urban and farm households. The size of the households also affects the expenditure in totality. All forms of expenditure seem to increase with the increase in the number of household members. Interestingly, a large household has a high spike in food expenditure compared to a small household. The setting of the household, size as well as the composition of the household affect medical expenditure directly with an increase in one leading to a rise in the other.

References christinelly. (n.d.). How do I compare two categorical values in a graph by ratio? From Community.Rstudio: https://community.rstudio.com/t/how-do-i-compare-two-categorical-values-in-a-graph-by-ratio/1870 Dymski, G., & Isenberg, D. (2018). Seeking Shelter on the Pacific Rim: Financial Globalization, Social Change, and the Housing Market: Financial Globalization, Social Change, and the Housing Market. Routledge, 2018. Kirk, A. (2016). Data Visualisation - A Hanbook for Data Driven Design. SAGE Publications. Living Standards Survey 1997-1998. (2020, Jan 30). From Microdata Worldbank: https://microdata.worldbank.org/index.php/catalog/2694 Simpson, S. H. (2015, Jul-Aug). Creating a Data Analysis Plan: What to Consider When Choosing Statistics for a Study. Can J Hosp Pharm, 68(4), 311–317. doi:10.4212/cjhp.v68i4.1471 Sepehri, A., & Vu, P. H. (2019). Severe injuries and household catastrophic health expenditure in Vietnam: findings from the Household Living Standard Survey 2014. Public health, 174, 145-153. Trivedi, P. K. (2002). Patterns of health care utilization in Vietnam: analysis of 1997–98 Vietnam living standards survey data. The World Bank. Fröhlich, H., Balling, R., Beerenwinkel, N., Kohlbacher, O., Kumar, S., Lengauer, T., ... & Rebhan, M. (2018). From hype to reality: data science enabling personalized medicine. BMC medicine, 16(1), 150.