利用最有效的檢驗項目預測老年住院患者的急性腎損傷

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳怡先 Chen, Yi-Shian
論文名稱：	利用最有效的檢驗項目預測老年住院患者的急性腎損傷 Early Prediction of Acquiring Acute Kidney Injury for Older Inpatients Using Most Effective Laboratory Test Results
指導教授：	陳良弼 Chen, Arbee L.P.
口試委員:	李官陵柯佳伶郭錦輯
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊工程學系 Computer Science
論文出版年：	2019
畢業學年度：	107
語文別：	英文
論文頁數：	38
中文關鍵詞：	急性腎損傷、預測、住院老年人、相似度測量
外文關鍵詞：	Acute kidney injury (AKI), Prediction, Older inpatient, Similarity measure
相關次數：	點閱：2 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

急性腎損傷（AKI）是住院患者中常見的臨床事件，影響了5-7％的住院患者和22-57％的加護病房患者，嚴重的AKI甚至會對重症病患造成相當高的死亡率（40-70％）。特別是老年患者隨著年齡的增長，腎臟功能會逐漸退化，因此增加了罹患AKI的風險。此外，老年人容易罹患高血壓、糖尿病等慢性疾病，這些慢性疾病在治療過程中經常需要同時使用多種藥物，其中包括具有腎毒性的藥物，這也使得老年患者罹患AKI的機率較年輕人高，因此，早期預測老年患者是否會罹患AKI是至關重要的。本研究透過相似度測量方法找出檢驗結果相似的住院病患，當這些有著相似檢驗結果的病患大部分都罹患AKI，則該病患也會有很高的機率罹患AKI，該相似度測量方法是根據檢驗數值的變化趨勢或是差值算出相似程度，並且我們會選出最具有影響力的檢驗項目，利用這些最具有影響力的檢驗項目進行最終的評估，我們會藉由病患間的相似程度預測出高風險的病患，並且預測病患是否會在之後的0到5天內罹患AKI。我們的研究目的是早期預測出高風險的患者使得醫生能夠提早預防，讓病患免於罹患AKI後所造成的後續問題。最後，我們會將該相似性度量方法與三種常見的機器學習方法（Logistic Regression, Random Forest, and AdaboostM1）進行比較。我們的方法不僅能夠使用在AKI的早期預測，更能推廣到其他疾病的早期預測。

Acute Kidney Injury (AKI) is a common clinical event among inpatients, which affects 5-7% of inpatients and 22-57% of patients in the intensive care unit based on the past studies. Severe AKI can result in significant mortality (40–70 %) for critically ill patients. Incidence of AKI is highest in older patients; due to aging it may increase the risk for a decline in renal functions. In addition, older patients have an increased risk of AKI because of the increasing number of comorbidities, aggressive medical treatments, and greater use of nephrotoxic drugs. Early prediction of AKI for older inpatients is therefore crucial. In this study, we use the data of 80 different laboratory tests from the electronic health records to do the prediction. By proposing new similarity measures and employing the classification technique of the K nearest neighbors, we are able to identify the most effective laboratory tests for the prediction. Furthermore, in order to know how early and accurately can AKI be predicted to make our method clinically useful, we evaluate the prediction performance of up to 5 days prior to the AKI event. Finally, compare our method with two existing works and it shows our method outperforms the others. In addition, we implemented an existing method using our dataset, which also shows our method has a better performance. Our approach can be used not only for early prediction of AKI, but also for early prediction of other diseases. In the future, we will extend this approach and develop a system for early prediction of major diseases to help better disease management for inpatients.

Acknowledgement-------------------------------------1
摘要------------------------------------------------3
Abstract--------------------------------------------4
Table of Contents-----------------------------------5
List of Figures-------------------------------------6
List of Tables--------------------------------------7
1. Introduction-------------------------------------8
2. Related Work-------------------------------------12
2.1 Dynamic Time Warping----------------------------12
2.2 K-Nearest Neighbor Classification---------------14
2.3 Feature Selection Method------------------------14
2.4 Weka--------------------------------------------14
2.5 Related Research--------------------------------15
3. Preliminary--------------------------------------17
3.1 Description of dataset--------------------------17
3.2 Preprocessing of dataset------------------------18
4. Method-------------------------------------------23
4.1 Segmentation and Data Representation------------23
4.2 Similarity Measure------------------------------24
4.3 K-nearest neighbor Classification---------------25
5. Experiments--------------------------------------27
6. Conclusion---------------------------------------33
Reference-------------------------------------------35



                                

[1] Waikar SS, Curhan GC, Ayanian JZ, Chertow GM. Race and mortality after acute renal failure. J Am Soc Nephrol. 2007;18(10):2740–8.
[2] Chertow GM, Burdick E, Honour M, Bonventre JV, Bates DW. Acute kidney injury, mortality, length of stay, and costs in hospitalized patients. Journal of the American Society of Nephrology. 2005;16(11):3365-70.
[3] Thakar CV, Christianson A, Freyberg R, Almenoff P, Render ML. Incidence and outcomes of acute kidney injury in intensive care units: a Veterans Administration study. Critical Care Medicine. 2009;37(9):2552-8.
[4] Kes P, Jukić NB. Acute kidney injury in the intensive care unit. Bosnian journal of basic medical sciences. 2010;10(Suppl 1):S8.
[5] Ostermann M, Chang RW. Acute kidney injury in the intensive care unit according to RIFLE. Critical care medicine. 2007;35(8):1837-43.
[6] Sileanu FE, Murugan R, Lucko N, Clermont G, Kane-Gill SL, Handler SM, Kellum JA. AKI in low-risk versus high-risk patients in intensive care. Clinical Journal of the American Society of Nephrology. 2014:CJN-03200314.
[7] Hoste EA, Bagshaw SM, Bellomo R, Cely CM, Colman R, Cruz DN, Edipidis K, Forni LG, Gomersall CD, Govil D, Honoré PM. Epidemiology of acute kidney injury in critically ill patients: the multinational AKI-EPI study. Intensive care medicine. 2015;41(8):1411-23.
[8] Palevsky PM, Liu KD, Brophy PD, et al. KDOQI US commentary on the 2012 KDIGO clinical practice guideline for acute kidney injury. Am J Kidney Dis. 2013;61(5):649–72.
[9] Coca SG. Acute kidney injury in elderly persons. American Journal of Kidney Diseases. 2010;56(1):122-31.
[10] Anderson S, Eldadah B, Halter JB, Hazzard WR, Himmelfarb J, Horne FM, Kimmel PL, Molitoris BA, Murthy M, O'Hare AM, Schmader KE. Acute kidney injury in older adults. Journal of the American Society of Nephrology. 2011;22(1):28-38.
[11] Glassock RJ, Rule AD. Aging and the kidneys: anatomy, physiology and consequences for defining chronic kidney disease. Nephron. 2016;134:25–9.
[12] Musso CG, Oreopoulos DG. Aging and physiological changes of the kidneys including changes in glomerular filtration rate. Nephron Physiol. 2011;119(Suppl 1):p1–5.
[13] Gong Y, Zhang F, Ding F, Gu Y. Elderly patients with acute kidney injury (AKI): clinical features and risk factors for mortality. Arch Gerontol Geriatr. 2012;54:e47–51.
[14] Turgutalp K, Bardak S, Horoz M, Helvaci I, Demir S, Kiykim AA. Clinical outcomes of acute kidney injury developing outside the hospital in elderly. Int Urol Nephrol. 2017;49:113–21.
[15] Ge S, Nie S, Liu Z, Chen C, Zha Y, Qian J, et al. Epidemiology and outcomes of acute kidney injury in elderly chinese patients: a subgroup analysis from the EACH study. BMC Nephrol. 2016;17:136.
[16] Himmelfarb J. Acute kidney injury in the elderly: problems and prospects. Semin Nephrol. 2009;29:658–64.
[17] Resar RK, Rozich JD, Simmonds T, Haraden CR. A trigger tool to identify adverse events in the intensive care unit. Joint Commission journal on quality and patient safety / Joint Commission Resources. 2006 Oct;32(10):585-90.
[18] Selby NM, Crowley L, Fluck RJ, et al. Use of electronic results reporting to diagnose and monitor AKI in hospitalized patients. Clinical journal of the American Society of Nephrology : CJASN. 2012 Apr;7(4):533-40.
[19] McCullough PA, Adam A, Becker CR, et al. Risk prediction of contrast-induced nephropathy. The American journal of cardiology. 2006 Sep 18;98(6A):27K-36K.
[20] Fortescue EB, Bates DW, Chertow GM. Predicting acute renal failure after coronary bypass surgery: cross-validation of two risk-stratification algorithms. Kidney international. 2000 Jun;57(6):2594-602.
[21] Wijeysundera DN, Karkouti K, Dupuis JY, et al. Derivation and validation of a simplified predictive index for renal replacement therapy after cardiac surgery. JAMA. 2007 Apr 25;297(16):1801-9.
[22] Chertow GM, Lazarus JM, Christiansen CL, et al. Preoperative renal risk stratification. Circulation. 1997 Feb 18;95(4):878-84.
[23] Aronson S, Fontes ML, Miao Y, et al. Risk index for perioperative renal dysfunction/failure: critical dependence on pulse pressure hypertension. Circulation. 2007 Feb 13;115(6):733-42.
[24] Kate RJ, Perez RM, Mazumdar D, Pasupathy KS, Nilakantan V. Prediction and detection models for acute kidney injury in hospitalized older adults. BMC medical informatics and decision making. 2016 Mar 29;16:39
[25] Cheng P, Waitman LR, Hu Y, et al. Predicting inpatient acute kidney injury over different time horizons: how early and accurate? AMIA Annu Symp Proc 2017; 2017: 565–74.
[26] D. J. Berndt and J. Clifford, "Using Dynamic Time Warping to Find Patterns in Time Series," in Working Notes of the Knowledge Discovery in Databases Workshop, 1994, pp. 359-370.
[27] Sutherland SM, Chawla LS, Kane-Gill SL, et al. Utilizing electronic health records to predict acute kidney injury risk and outcomes: workgroup statements from the 15(th) ADQI Consensus Conference. Canadian journal of kidney health and disease. 2016;3:11.
[28] Altman, N. S. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician. 1992, 46 (3): 175–185.
[29] Le Cessie S, Van Houwelingen JC. Ridge Estimators in Logistic Regression Journal of the Royal Statistical Society Series C (Applied Statistics). 1992;41(1):191-201.
[30] Breiman L. Random Forests. Machine Learning. 2001;45(1):5-32.
[31] Freund Y, Schapire RE. Experiments with a new boosting algorithm. Thirteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann; 1996. p. 148-56.
[32] Hall M, Frank E, Holmes G, Pfahringer B, Reitemann P, Witten I. The WEKA data mining software: an update. SIGKDD Explorations. 2009;11(1).
[33] Whitney A-W. A direct method of nonparametric measurement selection. IEEE Trans Computer 1971;20(9):1100–3.
[34] Marill T, Green D. On the effectiveness of receptors in recognition systems. IEEE Trans Inf Theory 1963;9(1):11–7.
[35] Rohit J. Kate, Noah Pearce, Debesh Mazumdar, Vani Nilakantand. Continual Prediction from EHR Data for Inpatient Acute Kidney Injury. arxiv.org 2019.

簡易檢索 / 詳目顯示

相關論文