• 沒有找到結果。

Interactive data exploration system to examine the application of medical insurance benefits

N/A
N/A
Protected

Academic year: 2021

Share "Interactive data exploration system to examine the application of medical insurance benefits"

Copied!
7
0
0

加載中.... (立即查看全文)

全文

(1)

Interactive data exploration system to examine the application of medical insurance benefits

An Interactive Data Exploration System for Auditing Health Insurance Reimbursement Claim

Pei-Lan Hsu a, I-Jen Chiang ab

a Institute of Medical Informatics, Taipei Medical University, b National Taiwan University, Institute of Biomedical Engineering

Abstract

Reporting process in medical payments, some abuse of error, such as: coding error (Miscoding) or encoding of high reported (Up-Cording), primary and secondary diagnosis of inverted (Diagnosis Sequencing), improper cutting (Unbundling of Services), the file does not complete (Missing Documentation), non-essential medical services (Medical Necessity), examination and radiological procedures and coding errors, often tricky to get a higher medical benefit, and seriously affected the fairness of the overall payment of medical expenses.

Although there are thousands of standards to regulate medical care steps, such as drug use and so on. However lacking in an automated decision system can be applied to health insurance to pay assignment.

In dealing with a large number of medical information operations, to full and fair dealing with a lot of medical information, an automated insurance, please pay check and review system is very important. An automated system can reduce the economical and rapid manual operation when the bias and error. In

particular, the computer system can simplify the review of operating procedures and audit time, the medical institutions and clinics is quite effective. By fast

operating speed, medical institutions and clinics may also reduce the waiting time of payment.

This article is hope that by visual classification of the information technology and skills to set up this type of automated insurance claims auditing system.

Keywords: visualization, medical decision support, health insurance review, data exploration

Prodrome

(2)

We often provide medical care to patients facing a higher quality of health care issues. Here, we must first understand what is meant by "higher quality"? And

the relative criteria? And there really assess the standards of medical service quality? If only the volume and patient disease status, we may be very difficult to answer these questions. However, if the combination of information

technology for medical decision support system, can be used to assist clinical professionals in providing patients with high-quality health care.

In Taiwan, the health insurance after the implementation of national health insurance emerged one after another. Medical insurance reimbursement and medical diagnosis, treatment, between the existence of inappropriate and unfair.

The most serious, medical institutions or clinics, to use illegal means to deceive the Central Health Insurance Agency to obtain improper benefits. For example, repeated examinations and medication or necessary, modify the medical records, open over medicine. The fact that many illegal work not only damage the

reputation of the medical staff, but also undermines the relationship between physician and patient.

National Health Insurance policy key to success is whether the balance of National Health Insurance organization. Therefore, the central health insurance institutions to efficiently review the medical centers or hospitals and clinics, health insurance assessment of the application referred to. If the unlawful situation had not improved, the government budget will experience financial difficulties.

All the people of Taiwan have the obligation to participate in the health insurance system. So far, more than Erqian San Bai people (99% of Taiwan's population) to apply. National Health Insurance Bureau played a supervisory role to review and review of payment requests made by the hospital information for errors, such as:

coding error (Miscoding) or encoding of high reported (Up-Cording), primary and secondary diagnosis of inverted (Diagnosis Sequencing), improper Cutting (Unbundling of Services), documents are incomplete (Missing Documentation), non-essential medical services (Medical Necessity), inspection and radiation processes error coding. This information contains medical details (diagnosis, examination, treatment and disposal of items) list of medications and medical care received by patients related to disposal of electronic records.

Literature

(3)

We often refer to medical decision support system, usually only focus on clinical professionals in assisting, through computer programs, clinical decision support system. Clinical decision support system through the computer software

technology to handle the patients medical records and knowledge to provide such information. Their medical staff according to patient conditions in the

development of a diagnosis, treatment plan to provide adequate information.

Shortliffe [20] by dividing them into three types: information management, focusing attention, and patient-specific consultation. Trends of these systems is based on data collection, interpretation, and effective integration, important and applicable patient report and clinician observation, and study the evidence obtained to improve the quality of clinical judgments. This type of system may also be used as an evidence based medicine, academics, David Sackett [8]

defined EBM as "the best evidence of the current cautious, clear and prudent use of independent decision-making related to patient care . it means for the

systematic study by the combination of external clinical evidence can be used better integration of the individual clinical professional. " Artificial intelligence is often used in such systems. For example, natural language processing are also included in the information management systems, document database can be to extract health-related information, including MEDLINE, TOXLINE and AIDSLINE [7]

[9] [12], DXplain [1] [2] [3 ] RECONSIDER [5] and so on.

In addition, in order to improve the quality of health care services, there are other in order to monitor the diagnosis, treatment, surgery and other clinical decision support system for medical procedures, Risk adjustment [14] [15] that is representative of such systems, in order to set the budget and measuring the effectiveness of primary care-critical systems. Often medical insurance payment system are such systems.

Introduction

Automated review system established in this study, using data to explore (Data Exploratory) approach to the form of (Table List) and visualization

(VISUALIZATION) is showing a tendency, to help determine the "health insurance medical orders to declare", "disease classification and coding" and "medical report costs "correlation between the abnormal, to find out the hidden rules among the large amounts of data (rules) and the reconstruction of the hospital clinical course.

(4)

Figure 1: System flow chart 1. Visualization technology

Visualization technology is based on hospital reporting of data put forward to rebuild the hospital clinical course. Visualization is the graphical user interface display application data. According to use visualization techniques can be divided into three categories: 1. Exploratory analysis Explorative analysis [4] [6] [10]

[13] [16] [17] [21]: According to the assumption that there is no information, to provide for the structure and trends in the exchange-type and do not specify a query to display data. 2. Recognized type of Confirmative analysis:to provide for the assumption that the data confirm that type of analysis will be taken after the data visualization for data confirm the hypothesis or not the results. 3.

Showcase of Presentation: the use of appropriate display technology to produce high-quality data visualization.

2. Data Show

In order to show the N dimensional data, how to "reduce the dimension of"

technology is recommended. Also said that a group of d dimensional data can be converted into a k dimensional data sets, and k is less than d. How to

multidimensional data, the lower the dimension of the question, the following are some commonly used in data processing methods: 1. Principal component

analysis (Principal component analysi): specify the basic elements of the original specifications to become independent of linear combination to explain the main differences in the data. 2. Factor analysis (Factor analysis [11]): find out the basic structure, simplify the observations, solve a complex combination of various factors between checking the hypothesized relationships between certain factors and to identify potential characteristics. 3. Multidimensional scaling analysis (Multidimensional scaling [19]): the definition of neighboring (similar) matrix of information in the multi-dimensional space coordinates.

To do more in the description, we first explore the definition for the information.

Data to explore the database can be defined as a subset of D S and found the hypothesis Hu (S, C), the user through the program to select some method (option) to find out some information sets and association rules, the association

(5)

rules can be expert verification, multi-dimensional 2D or 3D application framework, to present data and association rules.

Medical records, including non-drug treatment, contains basic information on patients and physicians, medical treatment, prescription, treatment and quantity of information such as individual costs.

For professionals, audit information is very tedious work. If no computer assistance, professional audit documentation format is very difficult. The data

visualization for accurate assessment of the medical experts and the disposal of prescription of great help. In order to perform high-dimensional exploratory data analysis, data processing must be applied to organize the information. This

article is the use of exploratory analysis to search the database, and analysis, to find out the hospital medical claims paid data, useful but hidden information.

Discuss

National Health Insurance payment audit system for health insurance benefits is a duplication of work. A lot of manpower and time must be put in claims paid, the work day. A sum of the data one by one manually is a tedious audit work, the whole audit work is manual or semi-automated. Some standards are set to do audit basis. National Health Insurance Bureau based on established standards of experts to review each section a health insurance information please. The audit

of the project includes the amount of the quantity and quality of medicines for patients with symptoms of the implementation of the reasonableness of such treatment. Even the audit staff to spend more time and energy can not be identified drawbacks of each. And the demand for the number of audit staff is great, but these professionals must undergo professional training. The audit

work is not only an enormous task and the limited benefits.

To reduce the serious waste of medical resources, we need a fair review system.

There is no doubt that the integration of automated computer systems is the best solution. Joint entire medical records, a computer system to verify the claims of any information.

Consult a health care decision-making system is to provide medical professionals the necessary insurance claims auditing system. The amount of medical claims each month, so not too much to manually audit. The small number of audit sampling methods for health care institutions is not fair, for example, a hospital

(6)

prescription errors were detected, face a fine of several times, sampling methods can only find a few mistakes. So set up a consultation system can not only assist in making insurance claims audit and the collation of information can be made by the more reasonable audit rules, inhibit inappropriate medical expense benefits, in order to save medical costs, make health care resources fairly and wisely. On

the other hand also on patient care, clinical research, medical education,

epidemiology, health resource planning and other purposes ... to provide a more accurate and reliable information on the disease. So not only an effective audit system architecture, the design should also be considered a fair way to find the problem in the data, making assessment system can be set up correctly.

References

1. BO Barnett, KT Famiglietti, RJ Kim, EP Hoffer, and MJ Feldman. Dxplain on the internet. In Proceedings of the 1998 AMIA Annual Fall symposium, page 607-611, Orland, 1998.

2. GO Barnett, JJ Cimino, JA Hupp, and EP Hoffer. Dxplain-an evolving diagnostic decision-support system. , 258:67-74, 1987.

3. ES Berner, JR Jackson, and J. Algina. Relationships among performance scores of four diagnostic decision support systems. Journal of the American Medical Information

Association, 3 (3) :208-215, 1996.

4. RF Berry and JL Hellerstein. An flexible and scalable approach to navigating measurement data in performance management applications. In Proceedings of the Second IEEE

International Conference on Systems Management, 1996.

5. MS Blois, MS Tuttle, and DD Sheretz. Reconsider: A program for generating differential diagnoses. In Proceedings of the Fifth Symposium on Computer Applications in Medical Care, pages 263-268, Washington, DC, 1981.

6. RJ Brachman, PG Selfridge,LG Terveen, B. Altman, A. Borgida, F. Halper, T.

Kirk, A. Lazar, DL McGuinness, and LA Resnick. Integrated support for data archaeology. International Journal of Intelligent and Cooperative Information System ,

2:159-185, 1993.

7. MF Collen. Full-text medical literature retrieval by computer: a pilot test. Journal of the American Medical Association, 254:2768-2774, 1985.

8. GD Webster ES Berner and et al AA Shugermann. Performance of four computer-based diagnostic systems. New England Journal of Medicine, 330:1792-1796, 1994.

9. B. Humphrey et al. The unified medical language system: an informatics research

collaboration. Journal of the American Medical Informatics Associati, on, 5:1-11, 1998.

(7)

10. J. Goldstein, SF Roth, J. Kolojejchick, and J. Mattis. A framework for knowledge-based, interactive data exploration. Journal of Visual Languages and Computing, 5:399-363,1994.

11. HH Harman. Modern Factor Analysis. University of Chicago Press, Chicago, 1967.

12. R. Haynes, N. Wilczynski, K. McKibbon, C. Walker, and J. Sinclair. Medline for health professionals: how to search pubmed on the internet. Journal of the American Medical Informatics Association, Volume 130 Issue 6 PAGES = 540), 1999.

13. DA Keim and H. Kriegel. Visdb: Database exploration using multidimensional visualization. Computer Graphics and Applications, pages 40-49, 1994.

14. A. Majeed, A. B Bindman, and J. P Weiner. Use of risk adjustment in setting budgets and measuring performance in primary care i: How it works. BMJ, 323, 2001.

15. A. Majeed, AB Bindman, and J. P Weiner. Use of risk adjustment in setting budgets and measuring performance in primary care ii: Advantages, disadvantages, and practicalities. BMJ, 323, 2001.

16. DA Rabenhorst. Interactive exploration of multi-dimensional data. In Proceedings of the SPIE Symposium on Electronic Imaging, pages 277-286, 1994.

17. RJ Resnick, MO Ward, and EA Rundensteiner. Fed-a framework for iterative data selection in exploratory visualization. In Proceedings of the Tenth International Conference on Scientific and Statistical Database Management, 1998.

18. DL Sackett, S. Straus, S. Richardson, W. Rosenberg, and RB Haynes. Evidence- Based Medicine: How to Practice and Teach EBM. Churchill Livingstone,London, 2000.

19. RN Shepard, AK Romney, and SB Nerlove. Multidimensional Scaling. Seminar Press, New York, 1972.

20. EH Shortliffe. Computer programs to support clinical decision making. Journal of the American Medical Association, 258:61-66,1987.

21. MO Ward. Xmdvtool: Integrating multiple methods for visualizing multivariate data. In Proceedings of Visualization, pages 326-336, Washington, DC, 1994.

22. MO Ward, J. LeBlanc, and R. Tipnis. N-land: A graphical tool for exploring n- dimensional data, 1994.

參考文獻

相關文件

This kind of algorithm has also been a powerful tool for solving many other optimization problems, including symmetric cone complementarity problems [15, 16, 20–22], symmetric

In order to solve the problems mentioned above, the following chapters intend to make a study of the structure and system of The Significance of Kuangyin Sūtra, then to have

The increasing charges of medical services, rising prices in jewellery and air tickets pushed the indices of Health; Other goods and services; and Transport and communications up

• focused on using CEHRT to improve health outcomes by implementing protected health information, e-prescribing, clinical decision support, computerized provider order entry,

In order to solve the problem of the tough recruitment of students in the future, universities and colleges, in addition to passing the relevant assessment conducted by the

In order to improve the aforementioned problems, this research proposes a conceptual cost estimation method that integrates a neuro-fuzzy system with the Principal Items

In order to use the solar rays more efficient and improve the conversion efficiency of solar cell, it is necessary to use antireflection layer to reduce the losses of

In order to ensure a sufficient quality and quantity of city water, the engineering quality of relevant works must be controlled so as to comply with the designed