Wannisa Wongkamchan

[Wannisa Wongkamchan]

I considered two interventions for the HIV prediction model: increasing antiretroviral therapy (ART) coverage and expanding referral networks.
1. ART is a highly effective treatment for reducing viral load, mortality, and complications, including co-infections, which reduces the need for complex treatment.
2. Expanding referral networks, particularly from high-incidence provinces, will increase the number of patients receiving continuous care.

These can be added to the model by specifying parameters such as the proportion of current and new patients receiving ART, the duration of ART, and the proportion of new patients referred to hospitals from high-incidence areas.

References:
What is Antiretroviral Therapy (ART)? Benefits, Side Effects, and Treatment. https://lovefoundation.or.th/antiretroviral-therapy/Rapid ART Initiation. https://www.hivguidelines.org/guideline/hiv-art-rapid/

[Wannisa Wongkamchan]

From Discussion Week 1, my topic is about forecasting the number of HIV patients in a super tertiary hospital. This is not mainly focused on community transmission. I plan to use a disease transmission dynamic model to simulate the number of HIV patients over 3–5 years, as well as the peak load, in order to support hospital resource planning and policy decisions.

HIV patients require continuous healthcare utilization, including regular hospital visits, laboratory monitoring, and occasional hospitalization. Control measures focus mainly on antiretroviral therapy (ART), which reduces viral load, improves survival, and decreases the risk of transmission. In terms of referral patterns, super tertiary hospitals often receive severe or complicated HIV cases, particularly from provinces with high incidence rates.

The main variables are those related to patient numbers. From Meachok (2019), which shows the top five provinces with the highest HIV incidence rates in Thailand, some of these provinces are also among those referring patients to my hospital. Therefore, I included province as an additional variable.

Number of existing patients = Existing HIV patients under follow-up
Frequency of hospital visits = Frequency of HIV patients’ hospital visits
Number of new patients = New HIV diagnoses
Mortality rate = Deaths among HIV patients
Clinic visit frequency = Average number of HIV patients per month
Co-infections = Number of HIV patients with comorbidities (e.g., TB, hepatitis). This increases the complexity of resource needs and mortality rates.
ART Therapy = Number of HIV patients receiving antiretroviral therapy for HIV infection
Number of Referral patients = Referral HIV patients
Referral province = Referral pathways (province to hospital)
Province incidence rate = For example Meachok (2019), Top 5 provinces with highest HIV incidence in Thailand.

Source of data from HIS and Meachok (2019)

Reference:
WHO. (2025). HIV and AIDS. https://www.who.int/news-room/fact-sheets/detail/hiv-aids
Meachok, P., Viwatwongkasem, C., Satitvipawee, P., Sillabutra, J., & Srihera, R. (2019). Estimation of HIV Incidence Rate in Thailand Using the Bayesian Hierarchical Approach. Journal of Public Health, 49(2), 171-182. https://he02.tci-thaijo.org/index.php/jph/article/view/188605

[Wannisa Wongkamchan]

Normally, in my work, I report patient statistics only as counts and percentages of each disease over time. I also use simple predictions of ER patients during long holidays, such as New Year and Songkran, by using Excel.

From the latest presentation to hospital executive committee, I present that the top ten outpatient diseases decreased after March, following a major earthquake. However, two diseases did not decrease, HIV and breast cancer. This made me think that basic statistical reporting might not be enough to monitor diseases.

So, I am interested in using mathematical model to forecast the number of HIV patients in a super tertiary hospital more accurately and in a way that is useful for policy decisions. This would especially help in preparing hospital resources and reducing costs.

Research questions that modeling could help answer are:
1. If there is a crisis or emergency, how will it affect the number of HIV patients in hospitals in the short, medium, and long term?
2. How accurately can a model estimate the short, medium, and long-term resource needs for HIV patient care during such periods?

Also, since my hospital is a referral center for severe and complex cases, another question is “If there were a policy to allow HIV treatment everywhere, like cancer treatment, how would this affect the number of HIV patients at the hospital, and what would be the rate of patient referrals back to their original hospitals?”

[Wannisa Wongkamchan]

1. The author is interested in studying the suicide problem in Thailand due to the increasing trend of suicide, the high suicide rate of more than 6 people per 100,000 population, and the lack of quantitative research at the macro-level.

2. Population over 60 years of age (AGE60) is one of the risk factors that significantly increases the suicide rate (p < 0.01 for both models). Many older adults in Thailand lack effective financial and social support. Many live without family support, without regular income or adequate living allowances, which may lead to depression and suicidal ideation.

3. Statistical modeling helps in studying the epidemiological and spatial studies of suicide problems in Thailand in the following ways:

– Identifying risk factors that influence suicide. For example, using multiple regression models allows for the identification of the level of the relationship between factors and the ability to distinguish which factors have a positive or negative relationship with suicide rates. This helps to decide which factor should be controlled first if we want to reduce suicide rates.

– Interpreting spatial data. For example, a model using data by province can compare differences between regions and show which regions have higher suicide rates. It can also help find local causes, such as being an agricultural or industrial area, which may relate to income and cost of living.

– Statistical models help control confounders and check if the model fits the data. This makes the results more reliable.

[Wannisa Wongkamchan]

I’m having trouble installing the INLA package, whether I’m using the R code from the Introduction to R-INLA Activities, friends comments in the Course Forum, or the website https://www.r-inla.org/download-install.
I’m still getting an error message:

cp: unknown option — )
ERROR: installing binary package failed

So I asked ChatGPT and used this code to successfully install it on my Windows.

install.packages(“INLA”, repos = c(INLA = “https://inla.r-inla-download.org/R/stable&#8221;), type = “binary”)

I hope this INLA installed will be useful for course learning and class projects.

[Wannisa Wongkamchan]

1. Descriptive epidemiology focuses on the triad of people, place, and time. However, in the past, most epidemiology research focused more on individual factors like age, gender, genetics, and behavior, or on how diseases changed over time, rather than historically focusing on place or location. A significant reason for this lack of interest in place was the limitations of suitable databases and insufficient software for effectively managing and analyzing spatial data in the past. But now, with advance technology, spatial epidemiology has many more chances in epidemiological research. Because of this, spatial epidemiology is an interdisciplinary field. It requires knowledge and skills in epidemiology, statistics, geography, and computer science to understand how people, places, and environments are connected, and how they affect health.

2. The place where an individual lives or works should be considered a potential disease determinant because it can indicate the risk of health problems and the onset of diseases. This is because “place” encompasses environmental, social, and economic factors. For example, individuals living or working near nuclear power plants or coal-fired power plants may be exposed to radiation or various toxins, increasing their risk of developing diseases such as cancer. In remote rural areas, individuals may experience malnutrition or nutrient deficiencies due to limited access to diverse and healthy food sources. In urban areas, living in densely populated environments, the social and environmental at the workplace, can contribute to conditions like stress and office syndrome.

[Wannisa Wongkamchan]

I would like to share the COVID–19 Pandemic Surveillance Dashboard. This dashboard helps decision makers, as well as medical and public health personnel and researchers, by showing clear and updated COVID-19 data such as confirmed, recovered, and death cases by date, country, and continent. It includes filters for selecting a country, year, and date range, which makes it easier to focus on specific time periods or regions. This helps users quickly understand the situation and compares.
Go to the interactive dashboard –> https://lookerstudio.google.com/s/oaIk3f9r7Hw

[Wannisa Wongkamchan]

Hello, everyone. Here is my assignment for this week. However, from working on the Week 3–4 assignments, I found that customizing graphs in Looker has limitations when it comes to sorting data in chronological order, such as when dividing the dimensions into years.

Looker Studio link: https://lookerstudio.google.com/s/lXjQf29F26o

[Wannisa Wongkamchan]

Hello, everyone. I would like to share my data visualizations for week3 assignment, which are in the PDF below.
https://drive.google.com/file/d/1uELdMFcXQ4ckYpiXU-Ag0TEQibfUcmCs/view
<iframe src=”https://drive.google.com/file/d/1uELdMFcXQ4ckYpiXU-Ag0TEQibfUcmCs/preview&#8221; width=”640″ height=”480″ allow=”autoplay”></iframe>

The interactive version is available via this Looker Studio link: https://lookerstudio.google.com/reporting/b14f5a4e-b120-4b10-bee3-cdb7be86541f

[Wannisa Wongkamchan]

I would like to present the Tuberculosis Epidemiological Profile Dashboard by WHO https://data.who.int/dashboards/tuberculosis?m49=764 Overall, this dashboard is well-designed and covers all important aspects related to TB.

What I like:
• The dashboard is placed on one single webpage. The information is well organized in steps. I can scroll down and follow the order smoothly. The menu on the left side helps me navigate easily.
• The website uses soft colors like light grey, white, and blue. The font and text size are easy to read.
• The dashboard uses many types of charts. The colors are simple but help show trends and differences between groups clearly. However, I feel the orange and red colors in the same chart are too similar.
• Some charts show estimated values with upper and lower bounds. This helps users understand the data is not exact.
• There are links to download raw data and data sources, which is helpful for analysts.
• The dashboard includes metadata and a glossary of definitions.

What I do not like:
• Some charts use colors that are too close (like orange and red), which makes them hard to tell apart.
• To help policymakers or non-clinical users understand the data more quickly and clearly, the dashboard should add a one-page summary report (Mini Dashboard Summary) at the top of the page, before Section 1 (Tuberculosis Epidemiological Profile). This will highlight the key insights first.

[Wannisa Wongkamchan]

I have Learned about the law, health professions and telemedicine – including the pros, cons and ethical and legal issues.

[Wannisa Wongkamchan]

I have learned that GDPR and PDPA share similar approaches in safeguarding health data in research and healthcare institutions. Organizations must follow legal principles, implement strict security measures, and ensure compliance through policies and protocols.

My Infographic Wrap-Up! https://snipboard.io/6lCZis.jpg

[Wannisa Wongkamchan]

The Code of Ethics for Health Informatics ensures patient data is handled with privacy, security, and fairness. Ethical rules guide data use, management, and research to protect individuals. Violating rules, like sharing user login, risks data breaches and legal consequences. Reporting data breaches is important to maintain accountability.

This is my infographic

[Wannisa Wongkamchan]

I have learned about the limitations and precautions of using AI in Healthcare. AI will help and support the work to be efficient, not replace personnel. Because medical and health decisions that involve human life are important. AI decisions will not instill confidence in patients and medical personnel. In addition, there are concerns about ethics, legal, technology, data quality, public health issues.

My Wrap up infographic –> https://snipboard.io/NR3ZoB.jpg

[Wannisa Wongkamchan]

Thailand has a Primary Care System that is available nationwide, as I mentioned in Topic discussion 1. The Universal Coverage Scheme (Gold Card) is a fundamental right that helps people access medical treatment without high financial burdens. The primary care system in Thailand is divided into three levels as follows:
1. Primary Care Services: Focuses on health promotion, disease prevention, basic medical treatment, and rehabilitation. It is managed by doctors, nurses, public health officers, and village health volunteers (VHV). Service units at this level include Subdistrict Health Promoting Hospitals (SHPH) and Community Health Centers.
2. Secondary Care Services: Provides outpatient and inpatient services and can offer basic specialized treatment. It supports patient referrals from primary care services and is staffed with doctors, nurses, pharmacists, and public health personnel. Service units at this level include Community Hospitals or District Hospitals.
3. Tertiary Care Services: Offers highly specialized care and treats complex diseases. It provides specialized medical services and supports referrals from community hospitals. Service units at this level include Provincial Hospitals, General Hospitals, or Regional Hospitals.

Case Study of a Successful Primary Health Intervention
The Village Health Volunteer (VHV) System is one of Thailand’s globally recognized projects. The World Health Organization (WHO) has praised it as an effective model for public health promotion. For example, during the COVID-19 pandemic, VHVs played a crucial role in distributing health information about disease prevention and facilitating access to vaccines. The success of the VHV system is attributed to the following factors:
• Extensive network: There are currently over 1,500,000 VHVs nationwide, with each volunteer responsible for about 20 households.
• Community involvement: VHVs are local residents who understand community culture and people’s behavior.
• Government support: VHVs receive allowances and training from the Ministry of Public Health.
• Use of innovation and technology: Digital applications are used for health data collection.

Case Study of an Unsuccessful Primary Health Intervention
The Health Information Exchange (HIE) System in Thailand has faced several challenges, despite efforts to develop a system for data sharing between hospitals and public health units. The main issues include:
• Incompatibility of Health Information Systems (HIS): Different hospitals use various HIS platforms, causing difficulties in data exchange.
• Scattered and duplicate patient health records.
• Despite the Ministry of Public Health’s standardized data structure (43 files), the system may not be efficient enough for seamless data exchange.
• Concerns about health data security, patient privacy, and system safety.
• Limited IT skills among public health personnel, along with communication and coordination challenges between multidisciplinary teams working on HIE implementation.

In conclusion
Thailand has a Primary Care System that covers all levels – primary, secondary, and tertiary care. The VHV system plays a key role in public health promotion and has been recognized by WHO. However, the Health Information Exchange (HIE) System still faces limitations in system compatibility, data duplication, Interdisciplinary Collaboration in Health Information Technology, and health data security.

Reference: https://www.bangkokbiznews.com/social/877773

[Wannisa Wongkamchan]

The Universal Health Coverage (UHC) scheme in Thailand is based on three main state health insurance schemes, which provide coverage to almost 100% of the Thai population.
1. Civil Servant Medical Benefit Scheme (CSMBS) implemented since 1980, covering civil servants and their families (7.2%).
2. Social Security Scheme (SSS) covering private sector employees who are insured (17.3%).
3. Universal Coverage Scheme (UCS) scheme, also known as the 30-baht gold card, which was launched in 2002, covers the general public who are not covered by the first two schemes, making up the largest number (72.3%). It provides comprehensive healthcare services free of charge at the point of care, including inpatient and outpatient services, essential medicines, and preventive care. The UCS has been recognized by many leaders as an example of a country that has achieved universal health coverage while at a moderate-income level, enabling all Thais to access essential healthcare services.

Outcomes and strengths of the UHC in Thailand
– People, especially low-income groups, have access to healthcare services universally. Receive comprehensive services
– Reduce the burden of health expenses, prevent problems with medical expenses that make households bankrupt, no copayment at the service point
– Reduce the rate of premature death from serious diseases such as AIDS, cancer and kidney failure that in the past the poor could not access
– Efficient management using the structure of sub-district hospitals, community hospitals, provincial hospitals, providing services according to the level of ability
– Emphasize preventive care such as free vaccination, maternity care and disease screening, resulting in better health outcomes

Weaknesses and challenges
– The budget for UHC comes mainly from government taxes, which may not be sustainable in the long term, especially as Thailand enters a full-fledged aging society, resulting in an increase in the demand for public health services, which requires an increased budget.
– Thailand faces a shortage of doctors and nurses, especially in remote areas. Rural hospitals often face a shortage of staff and equipment.
– Ineffective patient referral systems may delay treatment.
– The increase in non-communicable diseases (NCDs) such as diabetes, hypertension and cancer result in higher treatment costs. Lifestyle-related diseases require better preventive strategies.

Although Thailand’s UHC program has been successful in increasing access to health services, reducing the burden on people’s expenses and developing a more efficient service system, However, there is a point to discuss about the inequality between the 3 systems. Civil servants (CSMBS) receive treatment through the fee-for-service system, which has no budget ceiling, while the SSS and UCS use a capitation system that sets a limited budget. This has led to debates about the quality of service between different rights, including the issue of co-payment. Because UCS currently provides free treatment for all illnesses, there is an increased incentive to use the service. There may be unnecessary use of services. In addition, people lack awareness of taking care of their own health problems. The proposal to have a co-payment system to ease the budget burden still lacks a clear policy. And I think it may be resisted by the public.

What needs to be done to make UHC more effective and sustainable
I think of the phrase “Prevention is better than cure” by promoting primary care to be stronger. Support sub-district health promotion hospitals (sub-district health promotion hospitals) and family doctor clinics to be the front line of the health system. Reduce the burden on large hospitals. It may use technology and AI in activities to provide knowledge and promote health for all age groups.

I also agree that the co-payment system should be implemented in cases where a person’s behavior is the cause of disease or accidents. This is especially true for high-risk behaviors that directly lead to a burden on the public health system and society. Examples include liver cirrhosis from alcohol consumption, accidents caused by drunk driving, lung cancer from smoking, accidents from drug use, and accidents resulting from negligence or illegal actions. In these cases, individuals should take responsibility for their own medical costs or contribute to the expenses.

Conclusion
Thailand’s UHC is one of the successful models in the world, helping to increase access to medical care. However, there are still challenges in terms of budget, service quality, and management that need to be continuously developed, especially in increasing the efficiency of the primary care system, preparing to cope with the aging society, and considering appropriate Co-payment approaches.

Reference:
Thailand Health Profile 2016-2017 Chapter 8: Integration of the Universal Health Coverage System in Thailand
https://spd.moph.go.th/wp-content/uploads/2022/08/%E0%B8%81%E0%B8%B2%E0%B8%A3%E0%B8%AA%E0%B8%B2%E0%B8%A3%E0%B8%93%E0%B8%AA%E0%B8%B8%E0%B8%82%E0%B9%84%E0%B8%97%E0%B8%A2.pdf

[Wannisa Wongkamchan]

The gaps of healthcare inequality between rural and urban areas in Thailand has been a long-standing issue, with significant differences in both access and quality of medical services.

I think that geographical factors and infrastructure are the main causes of this gap. Thailand has a diverse landscape—mountainous regions in the north make travel to medical facilities difficult, the northeastern region is remote and far from large hospitals, and the southern region has mountains, coastlines, and islands, leading to a shortage of medical personnel and healthcare infrastructure. These factors affect access to medical services, causing delays in treatment for rural patients due to the distance of hospitals, lack of medical staff, limited equipment, and difficulties in patient referrals. These challenges lead to further differences in several areas:
1. Access to medical care and treatment – Urban areas have specialists, medical staff, and modern equipment such as MRI and CT scans, allowing patients to receive fast and effective treatment. In contrast, rural areas face a shortage of specialists, with one doctor often having to care for many patients, resulting in long waiting times, delayed diagnoses, and lower quality of treatment.
2. Emergency response and patient referrals – Cities have highly efficient emergency systems, with ambulances reaching patients quickly and referrals to specialized hospitals being straightforward. However, in rural areas, patients must travel long distances for treatment, ambulances are limited, and some areas lack accessible roads, leading to delayed treatment and increased risks of fatality.
3. Health awareness and disease prevention – Urban residents benefit from better education and access to health information, awareness campaigns, and regular disease screenings. In rural areas, health knowledge is often limited, leading to lower disease prevention efforts and late-stage diagnoses.

Thailand has been working to reduce this gap for decades. The Princess Mother’s Medical Volunteer Foundation, established in 1969, is one of the projects aimed at providing medical services to remote communities, promoting health, preventing diseases, and allowing medical professionals to help underserved populations. Today, Thailand has improved infrastructure and developed a regional healthcare management system to address these issues. Additionally, the country is integrating technology and innovation, such as:
• Primary Care Cluster (PCC) – A system that connects community health centers with larger hospitals, improving patient referrals.
• Telemedicine – Many hospitals now offer telemedicine services, allowing rural patients to consult specialists via video calls, reducing waiting times and travel costs.
• Medication refill and home delivery services – A system that helps chronic disease patients receive medications without frequent hospital visits.
• Mobile health units – Medical professionals and diagnostic tools are brought to remote areas to provide care for underserved populations.
• Mobile X-ray units – These allow rural residents to access diagnostic services more conveniently.
• Medical drones – Thailand has tested drone deliveries for medicine in remote areas, such as in Satun province, similar to the project mentioned by Ari Isman.

Proposals to Reduce the Urban-Rural Healthcare Gap
1. AI for health data analysis – AI and big data can predict disease trends, such as diabetes and dengue fever, assessing risks in different regions to help public health authorities prepare better.
2. Expanding medical drone services – Besides delivering medicine, drones could be used to transport blood samples for testing or send emergency medical supplies faster than ambulances.
3. Developing Mobile Health Units – Equipping mobile clinics with basic life-saving equipment to provide easier access to healthcare.
4. Advancing digital health technology – Creating platforms for health education, nutrition, and hygiene to empower communities to take better care of their health.
5. Incentives for medical professionals in rural areas – Providing scholarships, financial support, and special benefits to attract and retain doctors and healthcare workers in remote areas.
6. Enhancing government efficiency and transparency – Ensuring fair and sufficient distribution of medical resources and equipment across regions.

Conclusion
The healthcare disparity between urban and rural areas in Thailand is primarily due to geographical, infrastructural, and resource distribution challenges, resulting in differences in access and quality of medical care. Addressing this issue requires continuous efforts. Utilizing digital technology, such as telemedicine, AI, and mobile health units, alongside better support for rural medical personnel, can help ensure equal access to quality healthcare for all citizens.

[Wannisa Wongkamchan]

From news and my work experience, I recognize Thailand’s long-standing challenges in the healthcare workforce. Recent reports also highlight a rising trend of doctors resigning due to those issues.

1. Workload and Burnout
Public hospitals often experience severe overcrowding due to an imbalanced patient-to-doctor ratio, particularly in tertiary care centers. This results in excessive workloads for healthcare professionals, leading to burnout, decreased job satisfaction, and high stress levels. Long working hours further exacerbate the issue, contributing to fatigue and even tragic losses, such as news of a doctor having a car accident while driving home after extended shifts.

2. Shortage of Healthcare Professionals
Many healthcare professionals in public hospitals, face heavy workloads due to high patient volume and staff shortages, leading to a high resignation rate. While rural areas face a shortage of doctors, nurses, and specialists, as most professionals prefer to work in urban centers or private hospitals. Additionally, experienced healthcare workers are approaching retirement, creating concerns about workforce sustainability.

3. Inadequate Compensation and Delayed Payments
The low salaries and delayed payments are a significant problem in public hospitals. Many healthcare workers receive low wages compared to those in private hospitals. In addition, salary payments are often delayed, many staffs experience year-long payment backlogs.

4. Limited Career Growth and training
Healthcare workers often experience slow career progression. Additionally, some medical specialties lack sufficient training programs, limiting opportunities for skill development and career advancement.

To Improve the Health Workforce Situation:

1. Reduce Workload and Prevent Burnout
– Analyze the workload and calculate the patient-to-healthcare worker ratio to determine the appropriate increase in public hospital staff.
– Enhance work-life balance by implementing regulated work hours to ensure fair working hours.
– Promote a positive work environment and collaboration between different healthcare professions.
– Providing mental health support
– Use technology and AI to help with administrative tasks and patient management.

2. Address the Shortage of Healthcare Professionals
– Provide benefits and incentives, such as housing or financial support, for specialists working in rural areas or high-demand areas.
– Develop a plan to train and recruit more healthcare workers, including replacing those who retire.
– Expanding medical school enrollments and offering scholarships for students who commit to working in underserved areas.

3. Inadequate Compensation and Delayed Payments
– Adjust the salary base of doctors, nurses, and other shortage positions in public hospitals to align with the current cost of living.
– Improving the efficiency of payroll systems to ensure timely salary payments.

4. Improve Career Growth and Incentives
– Create clearer career paths and faster promotions for public healthcare workers.
– Expand training programs for specialized fields to provide more learning opportunities.

Reference: https://www.hfocus.org/content/2023/06/27776

[Wannisa Wongkamchan]

In my setting, EMR has been used for over 10 years, and currently some inpatient wards also use CPOE (Computerized Physician Order Entry). From my experience, there are both advantages and disadvantages to replacing traditional paper-based medical records with EMR.

One of the biggest advantages is the reduction in paperwork. This helps decrease the need for physical document storage, making the hospital environment more organized. With fewer paper records, there is also a lower risk of document loss. Another important benefit is that hospitals can use the freed-up space for other medical services.

Moreover, EMR helps improve patient safety, can reduce medical errors by minimizes misinterpretations due to illegible handwriting. EMR also speeds up the process of managing and submitting medical billing claims. This improves hospital cash flow and reduces delays in reimbursement. Additionally, EMR makes it easier to review and ensure the quality of medical record documentation.

Another key advantage is improved accessibility and efficiency. Healthcare providers can quickly retrieve patient records from anywhere within the hospital system, leading to faster decision-making and better patient care. EMR also allows for integration with other health information systems, such as laboratory results, imaging, and prescriptions, which helps healthcare teams work together more effectively. It also makes it easier to use data for different purposes, such as creating reports, statistics report, and conducting research.

However, there are also disadvantages. Some staffs members were resistant to using EMR, making the transition difficult. Some departments still need to use both paper records and EMR, which creates extra work and makes document management more complicated. This hybrid system can cause inefficiencies in medical record audits.

Another issue is the performance of the computers used. If the system is slow or unreliable, it can affect the workflow of healthcare providers, leading to frustration and delays in patient care. Technical problems, such as system crashes or network downtime, can also disrupt hospital operations.

Additionally, while EMR enhances data accessibility, it also raises concerns about data security and privacy. Hospitals must invest in cybersecurity measures to protect sensitive patient information from unauthorized access, data breaches, or cyberattacks.

In conclusion
Overall, EMR offers many benefits, especially in reducing paperwork, improving efficiency, enhancing data accessibility, and improving patient safety. However, successful implementation requires staff cooperation, proper training, a reliable IT system, and strong data security.

[Wannisa Wongkamchan]

Big health data has great potential to improve cardiovascular research, but there are many challenges that need to be addressed. Here are ways to address them:

1. Missing Data
Missing data is a common problem in big health datasets and can lead to biased results. To handle missing data, we can use imputation techniques, such as mean imputation, regression imputation, or multiple imputation, to estimate missing values based on available data. In cases where missing data is too high (over 60%), researchers should consider collecting additional data or using sensitivity analysis to check how missing values affect results. Improving data entry practices and integrating multiple data sources may help reduce missing data problems. It is also important to improve data collection by training healthcare workers to record information more consistently.

2. Selection Bias
Selection bias happens when the data does not represent the entire population, leading to incorrect conclusions. One way to fix this is to collect data from many hospitals, regions, and patient demographics, to make the dataset more representative. Another way is using statistical methods, like propensity score matching, to balance the differences between patient groups. While big data allows for large sample sizes, it does not always mean better accuracy, so careful validation with randomized controlled trials (RCTs) is necessary before applying findings to clinical practice.

3. Data Analysis and Training
Analyzing big health data requires advanced statistical and programing skills, which many researchers and clinicians are not trained to use. To improve this, more training programs on biostatistics, statistical methods, AI, and programing should be provided to healthcare professionals. Using simple AI/ data analytics tools can help doctors and researchers use data more easily without needing advanced technical skills. However, collaboration between clinicians, data scientists, and engineers is also important to ensure accurate data analysis and interpreted correctly.

4. Interpretation and Translational Applicability of Results
Since big data analyses are complex and not always easy to apply in real-world medicine, the interpretation and translational applicability of results can be difficult. To improve this, research findings should be presented in a simple and clear format for doctors and policymakers. AI models should be tested in real clinical settings before being widely used. It is also important to standardize data collection and ensure that studies use high-quality, well-documented datasets to avoid incorrect interpretations.

5. Privacy and Ethical Issues
Handling patient data requires strict privacy protection to prevent misuse and ensure ethical research practices. Strong security measures, like encryption, secure storage and access controls, can help keep data safe from cyberattacks. Additionally, following legal regulations such as PDPA, GDPR and HIPAA ensures that data is used ethically. Most importantly, patients should be informed consent about how their data is used and should have the right to give or refuse consent.

In conclusion, big health data offers many opportunities for cardiovascular research, but it also faces challenges. By addressing missing data, reducing selection bias, improving training, making results easier to use, and protecting privacy, these steps will help utilize big data more effectively and safely, ultimately improving healthcare outcomes.

[Wannisa Wongkamchan]

Thank you for your detailed and clearly explained how IRS affects adult mosquitoes and the other compartments. I think the model may adding variables for season and weather, which can affect the mosquito population too.

[Wannisa Wongkamchan]

Thank you for your comment. I don’t have a flow diagram yet. I plan to include ART therapy and co-infections, because they can affect patient numbers and hospital resources.

[Wannisa Wongkamchan]

Hello Thinzar , thanks for sharing. Using the COVID-19 case with vaccination is a good example, because the model can show how vaccines change the number of people who get sick. I think we may also add one more variable for disease severity, which will reflect the vaccine effectiveness more clearly.

[Wannisa Wongkamchan]

Thank you for your advice ka Arjan. I will research the structure of the HIV model and its parameters to better understand them.

[Wannisa Wongkamchan]

Thank you Aung, regarding the parameter values, I mainly focused on using data collected from the hospital’s HIS, to identify parameters that are both practical to obtain and not overly complex, while still enabling accurate predictions.

[Wannisa Wongkamchan]

Hello Aung, thanks for sharing the overview of the model. I have a question about the biting rate, how is this data measured and collected?

[Wannisa Wongkamchan]

Hello Tanaphum, thank you for sharing. Your work on the malaria model sounds interesting. I think if synthetic data can give results similar to real data, it will be very useful for developing disease models.

[Wannisa Wongkamchan]

Hello Alex, thank you for sharing. I am also interested in the effects of public health interventions. However, I think that getting reliable data on medication adherence and lifestyle changes is challenging and may not always be accurate, since these measures often depend on self-reporting (unless people use wearable devices). Mathematical modeling may help address this problem and estimate the real impact of interventions.

[Wannisa Wongkamchan]

Thank you for your discussion, Your point about the study’s limitation in spatial analysis is very insightful. While the regression model identifies risk factors well, it doesn’t fully explore geographical patterns. Adding GIS or spatial clustering methods in future research would help better understand why northern provinces have such high suicide rates compared to other regions.

[Wannisa Wongkamchan]

Thank you for these insights. I agree that alcohol significantly increases suicide risk because it impairs judgment and decision-making. I’m surprised that economic hardship doesn’t increase suicide rates as expected. This shows how important statistical analysis is for understanding complex social issues properly.

[Wannisa Wongkamchan]

Hi Thinzar, Have you updated your R program to the latest version? If not, try updating first.

[Wannisa Wongkamchan]

Hello Than Soe Oo, thank you for sharing, I agree that It is essential to comprehend that a health issue is concentrated in specific areas for allocating resources for prevention, treatment, or enhancing health results. I think that as new geographic tools get better, spatial epidemiology will become even more vital for health care system.

[Wannisa Wongkamchan]

Hello Aung, thank you for sharing, I agree that location really shapes people health. It’s clear that environmental factors, like pollution in workplaces, or natural surroundings play a big role in disease risk.

[Wannisa Wongkamchan]

Hi, Thinzar. Your dashboard shows a clear summary of total patients, with numbers for male and female. This helps users understand the data easily. It uses bar charts and pivot tables to show patient numbers by month, township, and clinic. This makes it easy to compare the data. I think it would be good to add an option to choose a date range for the report.

[Wannisa Wongkamchan]

Yes, teacher. I completed getting the API training data from the first connection (2 years of Malaria data and the Provincial Thailand population dataset) for the VDO course using the API. But, for the Week 2 assignment, I can’t connect to the API data sources for the COVID-19 Surveillance data and the Population by country due to the KPIBees limit.

So, can I use the 2 years Malaria data for the Week 2 assignment instead of the COVID-19 Surveillance data?

[Wannisa Wongkamchan]

Data quality is very important in AI healthcare because bad data can lead to wrong decisions. Your infographic explains this well!

[Wannisa Wongkamchan]

It’s great that you highlighted responsibility in AI use! I think both AI creators and users must share responsibility, with clear laws in place.

[Wannisa Wongkamchan]

Your wrap-up was clear, and the infographic was well-designed!
AI cannot not complete replace, human decision-making in healthcare.

[Wannisa Wongkamchan]

besides increasing special taxes on alcohol and tobacco, controlling salt and sugar levels in the food industry can help reduce chronic diseases. This can lower medical costs and improve public health in the long run.

[Wannisa Wongkamchan]

Thankyou for your explains Myanmar’s progress toward UHC very well. It shows both the achievements and challenges.

[Wannisa Wongkamchan]

Community support and international assistance played an important role in maintaining basic health services. As a neighboring country, we hope for stability and better healthcare access for all people in Myanmar.

[Wannisa Wongkamchan]

Heavy paperwork is one issue in healthcare system. Doctors and nurses spend too much time on documents instead of treating patients. Reducing paperwork with digital systems can help improve patient care.

[Wannisa Wongkamchan]

It’s really sad to hear that hospitals are often targeted in conflicts. In the past, wars avoided attacking hospitals, but now it’s different. Even in Thailand no war, but we still news about violence in emergency rooms or recently man setting hospitals on fire due to stress. I think mental health monitoring is also very important.

[Wannisa Wongkamchan]

I agree that, we need to think about activities and workforce performance. Effective workforce planning helps support and develop each type of healthcare worker properly. This makes sure there are enough skilled people to provide good healthcare services.

[Wannisa Wongkamchan]

It’s really sad to hear about the healthcare crisis in Myanmar. Helping people in conflict zones is difficult. Humanitarian aid should be given in a way that helps without putting too much burden on the countries providing support. I hope we can overcome this.

[Wannisa Wongkamchan]

Implementation costs and dependence on technology are important challenges when using EMR. The hospital needs a good budget plan and staff training to make sure the system works well. Also, hospitals must prepare backup plans for system failures, such as manual record-keeping or alternative IT support, to ensure patient care continues smoothly.

[Wannisa Wongkamchan]

Thank you for sharing, I agree that quality of data should be one of the major challenges, while anonymization helps protect patient identities, obtaining informed consent should be a standard practice in big data research. However, in practice, obtaining explicit consent from every patient can be challenging, especially in retrospective studies where data has already been collected. Balancing ethical considerations with research feasibility remains a key challenge.

[Wannisa Wongkamchan]

Thank you for sharing these valuable suggestions! I agree that addressing missing data, Data Quality Improvement, and privacy concerns is crucial for making big health data more reliable in cardiovascular research. Collaboration between experts and institutions, along with clear guidelines and ethical frameworks, will help ensure accurate analysis and real-world applicability.

[Wannisa Wongkamchan]

Thank you for sharing. I agree that EMR improves efficiency and patient care by making information easily accessible and reducing errors. However, technical issues and data security are big concerns. Hospitals need to balance the benefits with proper training and strong security measures to protect patient data.

[Wannisa Wongkamchan]

Thank you for your insightful discussion. It reminds me of the word “goodness,” which, like corruption, can vary in meaning depending on their values and individual perspectives. Defining corruption carefully to avoid misinterpretation is crucial and ensure appropriate action in each unique context., especially in complex contexts like health systems.

[Author]

Posts