Natural language interactions enhanced by data visualization to explore insurance claims and manage risk

This paper reports and describes VINCENT, a visual analytics system that is designed to help public health stakeholders (i.e., users) make sense of data from websites involved in the online debate about vaccines. VINCENT allows users to explore visualizations of data from a group of 37 vaccine-focused websites. These websites differ in their position on vaccines, topics of focus about vaccines, geographic location, and sentiment towards the efficacy and morality of vaccines, specific and general ones. By integrating webometrics, natural language processing of website text, data visualization, and human-data interaction, VINCENT helps users explore complex data that would be difficult to understand, and, if at all possible, to analyze without the aid of computational tools.The objectives of this paper are to explore A) the feasibility of developing a visual analytics system that integrates webometrics, natural language processing of website text, data visualization, and human-data interaction in a seamless manner; B) how a visual analytics system can help with the investigation of the online vaccine debate; and C) what needs to be taken into consideration when developing such a system. This paper demonstrates that visual analytics systems can integrate different computational techniques; that such systems can help with the exploration of public health online debates that are distributed across a set of websites; and that care should go into the design of the different components of such systems.

Download Full-text

Interactive data visualization based on conventional statistical findings for antihypertensive prescriptions using National Health Insurance claims data

International Journal of Medical Informatics ◽

10.1016/j.ijmedinf.2018.05.003 ◽

2018 ◽

Vol 116 ◽

pp. 1-8 ◽

Cited By ~ 6

Author(s):

Inseok Ko ◽

Hyejung Chang

Keyword(s):

Health Insurance ◽

Data Visualization ◽

National Health Insurance ◽

National Health ◽

Claims Data ◽

Insurance Claims ◽

Insurance Claims Data ◽

Health Insurance Claims Data ◽

Health Insurance Claims ◽

Interactive Data

Download Full-text

AUDiaL: A Natural Language Interface to Make Statistical Charts Accessible to Blind Persons

Lecture Notes in Computer Science - Computers Helping People with Special Needs ◽

10.1007/978-3-030-58796-3_44 ◽

2020 ◽

pp. 373-384

Author(s):

Tomas Murillo-Morales ◽

Klaus Miesenberger

Keyword(s):

Natural Language ◽

Data Visualization ◽

Initial Evaluation ◽

Natural Manner ◽

Web Based ◽

User Training ◽

Natural Language Interface ◽

Blind Persons ◽

Visualization Techniques ◽

Traditional Approaches

AbstractThis paper discusses the design and evaluation of AUDiaL (Accessible Universal Diagrams through Language). AUDiaL is a web-based, accessible natural language interface (NLI) prototype that allows blind persons to access statistical charts, such as bar and line charts, by means of free-formed analytical and navigational queries expressed in natural language. Initial evaluation shows that NLIs are an innovative, promising approach to accessibility of knowledge representation graphics, since, as opposed to traditional approaches, they do not require of additional software/hardware nor user training while allowing users to carry out most tasks commonly supported by data visualization techniques in an efficient, natural manner.

Download Full-text

PND83 IDENTIFYING NEUROMYELITIS OPTICA PATIENTS FROM INSURANCE CLAIMS DATA USING NFERX, A NATURAL LANGUAGE PROCESSING-BASED PLATFORM

Value in Health ◽

10.1016/j.jval.2020.04.975 ◽

2020 ◽

Vol 23 ◽

pp. S275

Author(s):

E. Garcia-Rivera ◽

J. Park ◽

Z. Doctor ◽

A. Lopez-Marquez ◽

D. Sheinson ◽

...

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Language Processing ◽

Neuromyelitis Optica ◽

Claims Data ◽

Insurance Claims ◽

Insurance Claims Data

Download Full-text

NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries

IEEE Transactions on Visualization and Computer Graphics ◽

10.1109/tvcg.2020.3030378 ◽

2020 ◽

pp. 1-1

Author(s):

Arpit Narechania ◽

Arjun Srinivasan ◽

John Stasko

Keyword(s):

Natural Language ◽

Data Visualization

Download Full-text

A Decision Support System with Artificial Intelligence and Natural Language Processing to Mitigate the Deduction Rate of Health Insurance Claims

Applied Sciences ◽

10.3390/app112411623 ◽

2021 ◽

Vol 11 (24) ◽

pp. 11623

Author(s):

Shey-Chiang Su ◽

Chun-Che Huang ◽

Roger R. Gung ◽

Li-Kai Hsiung ◽

Zhi-Wei Gao ◽

...

Keyword(s):

Health Insurance ◽

Natural Language ◽

Language Processing ◽

Latent Dirichlet Allocation ◽

Big Data Analytics ◽

Insurance Claims ◽

Medical Resources ◽

Health Insurance Claims ◽

Based Medicine ◽

Medical Examinations

Globally, 20% to 40% of medical resources are wasted, which could be avoided through professional audit of health insurance claims. The professional audit can pinpoint excessive use of unnecessary medicines and medical examinations. Taiwan’s National Health Insurance Bureau (TNHIB) deducts the weight that medical resources carry if regarded as unnecessary or abused when examining health insurance claims. The ratio of the deducted weight to the total weight claimed by a hospital is defined as the health insurance claim deduction rate (HICDR). A high HICDR increases the operating expenses of the hospital. In addition, it takes the hospital many resources to prepare and file appeals for the deduction. This study aims to: (1) minimize the weight deducted by the TNHIB for a hospital; and (2) facilitate efficient appeals to claim denials. It is expected that HICDR will be reduced through big data analytics. In this study, evidence-based medicine (EBM) is involved to clarify the debate, dilemmas, conflicts of interests in examining health insurance claims. A natural language method—latent Dirichlet allocation (LDA), was used to analyze patients’ medical records. The topics derived from the LDA are used as factors in the logistic regression model to estimate the probability of each claim to be deducted. The experimental results on various medical departments show that the proposed predictive model can produce accurate results, and lead to more than 41.7% reduction to the deduction of the health insurance claims. It is equivalent to more than a 750 thousand NT dollars saving per year. The efficiency of application is validated compared to the manual process that is time-consuming and labor intensive. Moreover, it is expected that this study will supplement the insufficiency of traditional methods and propose a new and effective solution to reduce the deduction rate.

Download Full-text