臺灣博碩士論文加值系統

遠距照護為醫療及健康照護上的重要議題，各種相關研究及技術亦蓬勃發展中。雖然先前研究已開發出各種遠距照護系統，但仍有以下不足之處: (1) 先前系統普遍缺乏量測自動化，因此照護人員進行例行性量測後，須以手動方式紀錄量測結果。此過程不僅過於繁瑣，並且容易造成人為記錄錯誤。(2) 儀器間缺乏互通性與連接性，導致量測資訊不易整合。(3) 系統缺乏可攜性，使得照護人員不便攜帶並無法提供行動照護。本研究提出了一套以Continua規範為基礎並建置於行動平台上之遠距照護架構，提供即時照護指引推薦並應用於慢性病患照護。本架構主要功能乃藉由行動平台的可攜性及無線行動網路，提供照護人員更便利以及有效率的照護環境。本研究實作一套以Continua規範為基礎的即時照護指引推薦系統。資料在量測完畢後會自動傳輸並儲存至系統，縮短了原本的量測流程，也減少了人為紀錄發生疏失的機會。此外，系統與儀器間具有互通性以及連接性，可輕易地在符合CHA規範的儀器間傳輸資料，而不需要額外的操作與設定，資訊可更容易被整合。本研究亦利用情節探勘技術，監測病患生理數值並即時推薦照護指引，讓照護人員可以盡早實施相關預防照護行為。實驗結果顯示，本研究所提出之系統確實能在臨床資料中找到具生理意義的規則，且這些規則可作為輔助照護人員照護病患的參考。

Telehealth is an important issue in medical and healthcare domains. Although many telehealth systems have been developed, they incur the following deficiencies: (1) The previous systems lack the function of automatic vital signs data transmission. Consequently, the task of measuring vital signs of patients becomes a repetitive process. (2) The previous systems lack interoperability and connectivity between devices. Thus, the information of vital signs is hard to be integrated. (3) The previous systems lack portability. In view of these, we propose a framework for Continua-based care guideline recommendation system, which utilizes mobile device platforms to provide chronic patients with care guideline recommendation in real-time and allows vital signs data to be transferred between different devices automatically without unnecessary operations and setup. In the proposed framework, the processes of vital signs data measurement are streamlined and the probability of inputting incorrect data is decreased. Moreover, the proposed system adopts the episode mining techniques to monitor vital signs of patients and recommend care guidelines to caregivers as references for taking preventive care actions in real-time manner. The experimental results show that the proposed system can discover representative rules from clinical data with physiological meaning and thus provide useful insights to caregivers.

摘要 I
ABSTRACT II
誌謝 III
Content IV
List of Tables VI
List of Figures VII
1. Introduction 1
1.1. Background 1
1.2. Motivation 4
1.3. Problem Statement 5
1.4. Contribution 6
1.5. Thesis Organization 7
2. Related Work 8
2.1. Continua Health Alliance 8
2.2. ISO/IEEE 11073 9
2.3. Health Device Profile (HDP) 10
2.4. Mobile Device in Patient Care 12
2.5. Data Mining 13
2.6. Episode Mining 13
2.7. Data Stream on Episode Mining 14
2.8. Overview of Current Literatures 15
3. Proposed Methods 17
3.1. Framework 17
3.2. Implementation Design 18
3.2.1. Vital Signs Measurement 19
3.2.2. Data Visualization 21
3.2.3. Guidelines Query 23
3.2.4. Scales of Symptoms 24
3.2.5. Task Handover 25
3.2.6. Anomaly List 25
3.3. Care Guideline Recommendation 26
3.3.1. Episode Mining 27
3.3.2. Vital Signs States Prediction 30
3.3.3. Guideline Recommendation 31
3.3.4. Dynamic Updating VSP 31
4. Experiments and Evaluation 34
4.1. Practical Evaluation of System 34
4.2. Experiments on Real Data 36
4.2.1. Experiment Environment Setting 36
4.2.2. Dataset Description 37
4.2.3. Distribution of Vital Signs States 37
4.2.4. The Number of Rules 41
4.2.5. Evaluation Metrics 41
4.2.6. Experimental Results 44
4.3. Summarization and Discussion 51
5. Conclusions and Future Work 52
5.1. Conclusions 52
5.2. Future Work 54
References 55

[1]A. P. Abernethy, J. E. 2nd Herndon, J. L. Wheeler, M. Patwardhan, H. Shaw, H. K. Lyerly, and K. Weinfurt, Improving health care efficiency and quality using tablet personal computers to collect research-quality, patient-reported data, Health Serv Res, Volume 43, Issue 6, pp. 1975-1991, 2008.
[2]M. J. Atallah, W. Szpankowski, and R. Gwadera, Detection of significant sets of episodes in event sequences, in Proceedings of the 4th IEEE International Conference on Data Mining, pp. 3-10, 2004.
[3]M. Blount, C. McGregor, A. James, D. Sow, R. Kamaleswaran, S. Tuuha, J. Percival, and N. Percival, On the integration of an artifact system and a real-time healthcare analytics system, in Proceedings of the 1st ACM International Health Informatics Symposium, pp. 647-655, 2010.
[4]Bluetooth SIG, Health Device Profile Implementation Guidance Whitepaper, 2009.
[5]M. J. Chen, K. Y. Chen, S. J. Chiang, and P. Chang, Taipei Smart Medical Package, in Proceedings of the 14th IEEE International Conference on e-Health Networking, Applications and Services, pp. 439-442, 2012.
[6]C. W. Cho, Y. H. Wu, S. J. Yen, Y. Zheng, and Arbee L. P. Chen, On-line rule matching for event prediction, The International Journal on Very Large Data Bases, Volume 20, Issue 3, pp. 303-334, 2011.
[7]M. Clarke, ISO/IEEE 11073 personal health data tutorial, 2008.
[8]A. Dattasharma, P. K. Tripathi, and G. Sridhar, Identifying stock similarity based on multi-event episodes, in Proceedings of the 7th Australasian Data Mining Conference, Volume 87, pp. 153-162, 2008.
[9]A. Farmer, O. Gibson, P. Hayton, K. Bryden, C. Dudley, A. Neil, and L. Tarassenko, A real-time, mobile phone-based telemedicine system to support young adults with type 1 diabetes, Inform Prim Care, Volume 13, Issue 3, pp. 171-177, 2005.
[10]R. Gwadera, M. J. Atallah, and W. Szpankowski, Reliable detection of episodes in event sequences, Knowledge and Information Systems, Volume 7, Issue 4, pp. 415-437, 2005.
[11]D. Goyal, J. Bhaskar, and P. Singh, Designing the low cost patient monitoring device (LCPMD) ＆ Ubiquitous based Remote Health Monitoring and Health Management System using Tablet PC, in Proceedings of the 2nd IEEE International Conference on Parallel Distributed and Grid Computing, pp. 7-11, 2012.
[12]M. Galarraga, I. Martinez, L. Serrano, P. De Toledo, J. Escayolan, J. Fernandez, S. Jimenez-Fernandez, S. Led, M. Martinez-Espronceda, E. Viruete, and J. Garcia, Proposal of an ISO/IEEE11073 Platform for Healthcare Telemonitoring: Plug-and-Play Solution with new Use Cases, in Proceedings of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6709-6712, 2007.
[13]K. Y. Huang, and C. H Chang, Efficient mining of frequent episodes from complex sequences, Information Systems, Volume 33, Issue 1, pp. 96-114, 2008.
[14]Health Informatics-Personal Health Device Communication Part 20601: Application Profile-Optimized Exchange Protocol, IEEE Std 11073-20601-2008, pp. c1-198, 2008.
[15]L. Jin, D. J. Chai1, Y. K. Lee, and K. H. Ryu, Mining Frequent Itemsets over Data Streams with Multiple Time-Sensitive Sliding Windows, in Proceedings of the 6th International Conference on Advanced Language Processing and Web Information Technology, pp. 486-491, 2007.
[16]H. C. Koh, and G. Tan, Data mining applications in healthcare, Journal of Healthcare Information Management, Volume 19, Issue 2, pp. 64-72, 2005.
[17]J. H. Lim, C. Park, and S. J. Park, Home healthcare settop-box for senior chronic care using ISO/IEEE 11073 PHD standard, in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 216-219, 2010.
[18]R. Latuske, Bluetooth health device profile and the IEEE 11073 medical device framework.
[19]T. Matsumoto, S. Ogata, and S. Kawaji, Designing and implementation of mobile terminal for telehealth care life support system, in Proceedings of the 7th International Conference on Computer Supported Cooperative Work in Design, pp. 479-485, 2002.
[20]X. Ma, H. H. Pang, and K. L. Tan, Finding constrained frequent episodes using minimal occurrences, in Proceedings of the 4th IEEE International Conference on Data Mining, pp. 471-474, 2004.
[21]H. Mannila, H. Toivonen, and A. I. Verkamo, Discovering frequent episodes in sequences, in Proceedings of the 1st Conference on Knowledge Discovery and Data Mining, pp. 210-215, 1995.
[22]H. Mannila, H. Toivonen, and A. I. Verkamo, Discovery of Frequent Episodes in Event Sequences, Data Mining and Knowledge Discovery, Volume 1, Issue 3, pp. 259-289, 1997.
[23]A. Ng, and Ada W.C. Fu, Mining frequent episodes for relating financial events and stock trends, in Proceedings of the 7th Pacific-Asia conference on Advances in Knowledge Discovery and Data mining, pp. 27-39, 2003.
[24]N. Nawka, A. K. Maguliri, D. Sharma, and P. Saluja, SESGARH: A scalable extensible smart-phone based mobile gateway and application for remote health monitoring, in Proceedings of the 5th International Conference on IEEE Internet Multimedia Systems Architecture and Application, pp. 1-6, 2011.
[25]J. A. Osheroff, D. E. Forsythe, B. G. Buchanan, R. A. Bankowitz, B. H. Blumenfeld, and R. A. Miller, Physicians' information needs: analysis of questions posed during clinical teaching, Annals of International Medicine, Volume 114, Issue 7, pp. 576-81, 1991.
[26]A. Özgür, L. Özgür, and T. Güngör, Text categorization with class-based and corpus-based keyword selection, in Proceedings of the 20th International Conference on Computer and Information Sciences, pp. 606-615, 2005.
[27]B. K. Patel, C. G. Chapman, N. Luo, J. N. Woodruff, and V. M. Arora, Impact of mobile tablet computers on internal medicine resident efficiency, Archives of Internal Medicine, Volume 172, Issue 5, pp. 436-8, 2012.
[28]J. Pei, J. Han, B. Mortazavi-Asl, H. Pinto, Q. Chen, U. Dayal, and M. C. Hsu, PrefixSpan: Mining Sequential Patterns Efficiently by Prefix-Projected Pattern Growth, in Proceedings of the 17th International Conference on Data Engineering, pp. 215, 2001.
[29]D. Patnaik, S. Laxman, B. Chandramouli, and N. Ramakrishnan, Efficient Episode Mining of Dynamic Event Streams, in Proceedings of the 12th IEEE International Conference on Data Mining, pp. 605-614, 2012.
[30]C. Y. Park, J. H. Lim, and S. Park, ISO/IEEE 11073 PHD standardization of legacy healthcare devices for home healthcare services, in Proceedings of the IEEE International Conference on Consumer Electronics, pp. 547-548, 2011.
[31]D. Patnaik, B. Patrick, N. Ramakrishnan, L. Parida, Benjamin J. Keller, David Hanauer, David A. Hanauer, and MD, Experiences with Mining Temporal Event Sequences from Electronic Medical Records: Initial Successes and Some Challenges, in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data mining, pp. 360-368, 2011.
[32]K. H. Park and J. G. Pak, Implementation of a Handheld Compute Engine for Personal Health Devices, International Journal of Smart Home, Volume 6, Issue 2, pp. 59-64, 2012.
[33]P. Phoungphol, Y. Zhang, Y. Zhao, Robust Multiclass Classification for Learning from Imbalanced Biomedical Data, Tsinghua Science and Technology, Volume 17, Issue 6, pp. 619-628, 2012.
[34]L. Schmitt, T. Falck, F. Wartena, and D. Simons, Towards Plug-and-Play Interoperability for Wireless Personal Telehealth Systems, in Proceedings of the 4th International Workshop on Wearable and Implantable Body Sensor Networks, pp. 247-263, 2007.
[35]M. H. Tseng, H. C. Hsu, C. C. Chang, H. Ting, H. C. Wu, and P. H. Tang, Development of an Intelligent App for Obstructive Sleep Apnea Prediction on Android Smartphone Using Data Mining Approach, in Proceedings of the 9th Ubiquitous Intelligence ＆ Computing and 9th International Conference on Autonomic ＆ Trusted Computing (UIC/ATC), pp. 774-779, 2012.
[36]I. H. Tsai, Y. F. Lin, Y. C. Yang, and V. S. Tseng, A Mobile Framework for Personalized Diabetes Telecare, in Proceedings of the Conference on Technologies and Applications of Artificial Intelligence, pp. 97-102, 2012.
[37]Y. L. Wang , Z. X. Hou, and X. S. Zhou, An Incremental and Hash-based Algorithm for Mining Frequent Episodes, in Proceedings of the International Conference on Computational Intelligence and Security, Volume 1, pp. 832-835, 2006.
[38]J. R. Wu, and Y. S. Tsai, Building a Home Care System with the ISO/IEEE 11073 Standard, in Proceedings of the International Federation for Medical and Biological Engineering, Volume 25, Issue 5, pp. 326-329, 2009.
[39]S. Warren, J. Yao, R. Schmitz, and J. Lebak, Reconfigurable Point-of-Care Systems Designed with Interoperability Standards, in Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3270-3273, 2004.
[40]Y. Yang, and X. Liu, A re-examination of text categorization methods, in Proceedings of the 22th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 42-49, 1999.
[41]Q. Zeng, J. J. Cimino, and K. H. Zou, Providing concept-oriented views for clinical data using a knowledge-based system: an evaluation, Journal of the American Medical Informatics Association, Volume 9, Issue 3, pp. 294-305, 2002.
[42]BluetoothHealth, http://developer.android.com/reference/android/bluetooth/BluetoothHealth.html
[43]Continua Health Alliance,
http://www.continuaalliance.org/about-the-alliance
[44]Council for Economic Planning and Development,
http://www.cepd.gov.tw/encontent/
[45]Department of Health, Executive Yuan, R.O.C. (Taiwan), http://www.doh.gov.tw/CHT2006/index_populace.aspx.
[46]DICOM-Digital Imaging and Communications in Medicine,
http://medical.nema.org/
[47]Google Inc. Android Developers,
http://www.android.com/.
[48]HL7 Health Level 7,
http://www.hl7.org/
[49]IEEE Standards Association page,
http://standards.ieee.org/
[50]MioCare,
http://miocare.mio.com/index_enGBR.asp.