藉由海量資料視覺化疾病軌跡

Visualizing Disease Trajectories Using Big Data

黃芝瑋(Chih-Wei Huang)

指導教授 ： 李友專

臺北醫學大學/醫學科技學院/醫學資訊研究所/博士(2016年)

摘要

現今的電子病歷中包含大量、豐富且重要的病人資訊，對於臨床醫師、研究人員及政策制定者來說，從龐大且複雜的病歷資料中萃取出有意義的資訊之能力變得日益重要，故本研究之目的即為發展出一套巨量疾病資料視覺化分析方法，找出某一慢性疾病與其共病及共病群組在時間軸上呈現之關聯，並觀察疾病演化與發展軌跡。本研究利用健保資料庫百萬歸人檔作為資料來源，發展出一套標準化的疾病資料篩選、分析及視覺化分析方法、流程、系統工具及應用程式介面，最終的視覺化透過桑基圖(Sankey diagram)與時間軸結合之形式呈現，展示出某一特定慢性疾病與其共病因子及各階段疾病狀態隨著時間演化的情形。在研究結果中，我們呈現了1998-2011年之14,567位慢性腎臟病病人族群與1997-2012年之24,221位臺灣十大癌症病人族群之疾病演化，並透過系統易用性量表評估不同使用者族群對於系統使用之學習性與易用性程度，研究結果顯示，研究人員與學生較臨床醫師在學習性方面更具正面態度，而使用者在易用性與系統整合方面皆表示滿意。此研究展示了一個創新的疾病軌跡視覺化的方法學與應用工具，不僅能協助研究人員探索複雜的疾病及其多樣共病因子與預後之時序性特徵與關聯；對於臨床醫師而言可協助診斷病情，並藉由互動式視覺化系統與病人共同進行治療決策，提升醫療照護品質；在臨床醫學教育方面則能利用多維視角將疾病多元化、立體化，並透過視覺化呈現不同疾病的演進與複雜的共病問題；政策制訂者可以巨量資料視覺化之成果為基礎，制訂出對醫療環境有實質效益之法規，並能有效監測及改善疾病的預後。

關鍵字

視覺化分析 ； 資料視覺化 ； 桑基圖 ； 慢性腎臟病 ； 臺灣十大癌症 ； 系統易用性量表

並列摘要

Background
Electronic medical records (EMRs) contain vast amounts of data that is of great interest to physicians, clinical researchers, and medial policy makers. As the size, complexity, and accessibility of EMRs grow, the ability to extract meaningful information from them has become an increasingly important problem to solve.
Objective
The aim of this study is to analyze and visualize the comorbidity associated with chronic diseases. The study demonstrate diseases and their associations before and after a specific diagnosis in a time-evolutionary type visualization.
Methods
We develop a standardized data analysis and visual analysis process to support cohort study with a focus on a specific disease. We use an interactive divide-and-conquer approach to classify patients into relatively uniform within each group. It is a repetitive process enabling the user to divide the data into homogeneous subsets that can be visually examined, compared, and refined. The final visualization was driven by the transformed data, and user feedback direct to the corresponding operators which completed the repetitive process. The output results are shown in a Sankey diagram–style timeline, which is a particular kind of flow diagram for showing factors’ states and transitions over time.
Results
This study presents a visually rich, interactive web-based application that enables anyone to easily generate and study patient cohorts over time using EMR data. The resulting visualizations help uncover hidden structures in the data, compare differences between patient groups, determine critical factors that influence a particular disease, and help direct further analyses. We introduce and demonstrate our design with case studies using EMRs of 14,567 Chronic Kidney Disease (CKD) patients and 24,221 ten leading cancers patients. The system usability scale (SUS) is implemented to evaluate usability and learnability of different groups of user. The user study shows that researchers and students have more positive attitude than physicians in learnability; however, the users all are satisfying with system integration and system usability.
Discussion
This study represents a novel visualization approach for temporal patterns of polymorbidities associated with any complex disease and its outcomes. We proposed this Sankey-style diagram as a promising method for visualizing complex diseases and exploring the effect of comorbidities on outcomes in a time-evolution style. This type of visualization may help clinicians foresee possible outcomes of complex diseases by considering comorbidities that the patients have developed. The visualization methods in this study can reveal useful knowledge about the particular disease cohort and the trajectories of the disease over time.
Conclusion
We developed a visualization tool based on a Sankey-style diagram that can represent the comorbidity and progression of a specific disease over time. This tool has the potential to help clinicians when deciding on the management of treatment or procedure. We believe that the disease visualization of comorbidities and outcomes can lead us to a better understanding of underlying pathogenesis. Efforts in this direction will eventually aid in prediction and prevention of the disease, personalization of diagnosis and treatment, as well as the participation of patients in our healthcare system.

並列關鍵字

Visualize Analytics ； Data Visualization ； Chronic Kidney Disease ； Ten Leading Cancers in Taiwan ； Sankey-style Diagram ； System Usability Scale

參考文獻

Bade, R., Schlechtweg, S., & Miksch, S. (2004). Connecting time-oriented data and information to a coherent interactive visualization. Paper presented at the Proceedings of the SIGCHI conference on Human factors in computing systems.

Bangor, A., Kortum, P., & Miller, J. (2009). Determining what individual SUS scores mean: Adding an adjective rating scale. Journal of usability studies, 4(3), 114-123.

Basole, R. C., Braunstein, M. L., Kumar, V., Park, H., Kahng, M., Chau, D. H., . . . Thompson, M. (2015). Understanding variations in pediatric asthma care processes in the emergency department using visual analytics (Vol. 22).

Beyer, M. A., & Laney, D. (2012). The importance of ‘big data’: a definition. Stamford, CT: Gartner.

Brooke, J. (1996). SUS-A quick and dirty usability scale. Usability evaluation in industry, 189(194), 4-7.