偏頭痛一直以來都是國內不可忽視病痛之一，根據研究顯示，國內患有頭痛疾病的人也佔有一定比例，雖然偏頭痛經過一段時間可以被緩解，但是由於偏頭痛的病患大多正值青壯年，而且頭痛病患沒辦法預知何時會再次復發，發作時可能會造成病患嚴重失能的狀態，因此偏頭痛對日常生活、工作及社交影響很大，因此患者求醫的比例越來越高。
    在本次研究中，將病人本身填寫的紙本初診問卷，轉換為智慧型的初診問卷，藉此來幫助臨床醫師在初診判斷時有更準確的數據參考以及自動計算各項測驗分數來協助做診斷，並且大幅改善臨床醫師在看初診病人的時間，解決護理人員需要檢查初診問卷以及計算分數的問題，降低病人填寫時可能會出現的錯誤，另外並提供完善的資料保存，確保資料不會因人為因素導致流失，以供後續醫院可以藉此大量數據來深入研究，找出偏頭痛可能會有的隱藏因子來提供給臨床醫師協助診斷用，讓偏頭痛可以被提早診斷出，並且能夠在早期治療及提升治療成效。
    最後，希望能利用本研究之研究成果為案例，提供各醫院對於神經內科醫師看診時有所幫助，有效的提升臨床醫師看診的效率，改善整體就診環境，大幅降低護理人員耗費在初診病患身上的時間，而收集的所有初診問卷在系統化之後所產生的相關資料，更可以作為臨床醫學上巨量數據(Big Data)研究的基礎資料。

Migraine has always been the one of the serious illness in Taiwan. According to the studies, a large amount of people suffer from headache. In this study, most migraine patients are young adults, although migraine can get remission after a period of times, patient can’t predict the frequency of migraine attacks. People with migraine may be in serious disability status. Therefore, migraine impacts our daily life, work and social. The seeking treatment patient's proportion are getting increase. 
    In this study, we use a newly diagnosed patient questionnaire and patient's electronic records to analysis and help doctor make the diagnosis. We improve the diagnosed efficiency and reduce the time when the doctor make a diagnosis. In addition, we also expect to identify migraine which may have a hidden factor available to assist clinicians with diagnosis. If migraine can be diagnosed early, the way of treatment can be improved much efficiently.

Table of Contents
Chapter 1 Introduction	1
1.1. Background	1
1.2. Motivation	2
1.3. Purpose	3
Chapter 2 Literature Review	5
2.1. Big Data	5
2.2. Database	7
2.3. Agile Software Development	8
2.4. Taiwan Food and Drug Administration	10
2.5. Migraine and Measuring Tools	12
2.5.1. Headache Questionnaire	13
2.5.2. Beck Depression Inventory	14
2.5.3. Pittsburgh Sleep Quality Index	14
2.5.4. Restless Leg Syndrome	15
2.5.5. Migraine Disability Assessment	16
2.5.6. Anxiety and Depression Scale	16
Chapter 3	Method	18
3.1. Interview and Clinical Observation	20
3.2. Questionnaire Requirements Analysis	21
3.3. Preliminary System Design	22
3.4. System Implementation	24
3.5. System Application	25
3.6. Advanced System Design	25
3.7. System Maintenance	29
3.8. Discussion	29
Chapter 4	Results	30
4.1. User Application Management	30
4.2. Questionnaire Application Management	32
4.3. Clinical Effectiveness Evaluation	48
Chapter 5	Conclusion and Future Prospects	51
5.1. Conclusion	51
5.2. Prospects	53
Reference	55
Appendix	57

List of Figures
Figure 1. Study Flowchart	20
Figure 2. System Analysis Flowchart	23
Figure 3. System requirement list	26
Figure 4. System modifications	27
Figure 5. System modifications	27
Figure 6. The number of users	28
Figure 7. The number of migraine users	28
Figure 8. Clinicians sign-in page	31
Figure 9. Patients sign-in page	31
Figure 10. User sign out	31
Figure 11. Main function page	32
Figure 12. Patients list page	32
Figure 13. Score statistics page	33
Figure 14. Score statistics page	33
Figure 15. RLS scale	34
Figure 16. MIDAS scale	35
Figure 17. HIT-6 Score	36
Figure 18. The Hospital Anxiety and Depression Scale	37
Figure 19. BDI scale	38
Figure 20. WPI scale	38
Figure 21. SympS score	39
Figure 22. FIQR scale	40
Figure 23. Sleep scale	41
Figure 24. First-visit patient basic information	42
Figure 25. First-visit patient headache status	42
Figure 26. Headache omen	42
Figure 27. Visual status	43
Figure 28. NRS	43
Figure 29. Pulse	43
Figure 30. N.V.S.L.O	44
Figure 31. Family History	45
Figure 32. PA	45
Figure 33. Yawning	45
Figure 34. Headache position	46
Figure 35. Headache position	46
Figure 36. Women issue	47
Figure 37. Medicine	47
Figure 38. Clinical Impression	48
Figure 39. Clinical Impression	48
Figure 40. Patient’s Time Comparison  49
Figure 41. Patient’s Time Comparison  50


List of Table
Table 1. Different data analysis between traditional business and big data	6
Table 2. Medical Device Document  11

Reference
[1]	Wei-Ta, Chen, Shuu-Jiun, Wang. Alteration of visual cortical excitabilities in migraine 2009, pp. 44-48.
[2]	Juang KD, Wang SJ, Fuh JL, Lu SR, Su TP. Comorbidity of depressive and anxiety disorders in chronic daily headache and its subtypes. 2000, pp. 818-823.
[3]	Hung-Jung Lin, The Study on Risk Factors of Patient Safety -- An Empirical Study of the Emergency Departments of Large-Scaled Hospitals in Taiwan. 2003.
[4]	Hsien-Ming Lin, The Implications and Reflections of Applying Big Data to Social Science Research, 2016.
[5]	Formosan J Med, Big Data Analysis in Medical Care. pp. 652-661.
[6]	D.A. Adjeroh and K.C. Nwosu, Multimedia Database Management Requirements and Issues, IEEE Multimedia, July-September.
[7]	Martin, Robert C., Agile Software Development, Principles, Patterns, and Practices, 1st edition, Prentice Hall, 2002.
[8]	Hui-Lan Tsai, The Study of Agile Methodology for Information Service Industry in Taiwan, 2014.
[9]	Medical Devices; Medical Device Data System, Federal Register, Vol.76, No.31, 2011.
[10] What is Migraine, http://www.tph.mohw.gov.tw/?aid=509&pid=75&page name=detail&iid=514.
[11] Migraine, http://www.taiwanheadache.com.tw.
[12] Migraine and Sleep, http://www.taiwanheadache.com.tw.
[13]	Aigmond AS, Snaith RP: The Hospital Anxiety and Depression Scale. 1983, pp.67-70.