YANG Qingsheng, YOU Xibin, ZHANG Hongxian, Kevin MWENDA, WANG Yuandong, HUANG Ying. A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China[J]. Chinese Geographical Science, 2020, 30(1): 157-169. doi: 10.1007/s11769-020-1102-7
Citation: YANG Qingsheng, YOU Xibin, ZHANG Hongxian, Kevin MWENDA, WANG Yuandong, HUANG Ying. A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China[J]. Chinese Geographical Science, 2020, 30(1): 157-169. doi: 10.1007/s11769-020-1102-7

A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China

doi: 10.1007/s11769-020-1102-7
Funds:

Under the auspices of National Natural Science Foundation of China (No. 40971060)

  • Received Date: 2018-12-06
  • Rev Recd Date: 2019-02-22
  • Reference values of erythrocyte sedimentation rate (ESR) are the key to interpret ESR blood test in clinic. The common local reference ESR values are more accuracy in blood test that are established with natural geographical factors by using the multiple linear regression (MLR) model and the artificial neural network (ANN). These knowledge-based methods have limitations since the knowledge domains of ESR and natural geographical factors are limited. This paper presents a new cases-depended model to establish reference ESR values with natural geographical factors and location using case-based reasoning (CBR) since knowledge domain of ESR and geographical factors is weak. Overall 224 local normal ESR values of China that calculated from 13 623 samples were obtained, and the corresponding natural geographical factors and location that include altitude, sunshine hours, relative humidity, temperature, precipitation, annual temperature range and annual average wind speed were obtained from the National Geomatics Center of China. CBR was used to predict the unseen local reference ESR values with cases. The average absolute deviation (AAD), mean square error (MSE), prediction accuracy (PA), and Pearson correlation coefficient (r) between the observed and estimated data of proposed model is 33.07%, 9.02, 66.93% and 0.78, which are better than those of ANN and MLR model. The results show that the proposed model provides higher prediction accuracy than those of the artificial neural network and multiple linear regression models. The predicted values are very close to the observed values. Model results show significant agreement of cases data. Consequently, the model is used to predict the unseen local reference ESR with natural geographical factors and location. In spatial, the highest ESR reference areas are distributed in the southern-western district of China that includes Sichuan, Chongqing, Guangxi and Guizhou provinces, and the reference ESR values are greater than 23 mm/60 min. The higher ESR reference values are distributed in the middle part and northern-eastern of China which include Hubei, Henan, Shaanxi, Shanxi, Jilin and Heilongjiang provinces, and the reference ESR values are greater than 18 mm/60 min. The lowest ESR reference values are distributed in the northern-western of China that includes Tibet and Xinjiang, and the reference ESR values are lower than 5 mm/60 min.
  • [1] A Aamodt A, Plaza E, 1994. Case-based reasoning:foundational issues, methodological variations, and system approaches. AI Communications, 7(1):39-59. doi: 10.3233/AIC-1994-7104
    [2] Aha D W, Kibler D, Albert M K, 1991. Instance-based learning algorithms. Machine Learning, 6(1):37-66. doi: 10.1007/BF00153759
    [3] Ansell B, Bywaters E G L, 1958. The ‘Unexplained’ high erythrocyte sedimentation rate. British Medical Journal, 1(5067):372-374. doi: 10.1136/bmj.1.5067.372
    [4] Cui J H, Zhang X Z, Zhang F et al., 2001. Change of erythropoietin on high altitude hypoxia adaptation mechanism. Clinical Journal of Medical Officer, 29(3):45-47. (in Chinese)
    [5] da C Sousa J V, dos Santos M N N, Magna L A et al., 2018. Validation of a fractional model for erythrocyte sedimentation rate. Computational and Applied Mathematics, 37(5):6903-6919. doi: 10.1007/s40314-018-0717-0
    [6] Dasarathy B V, 1991. Nearest Neighbor (NN) Norms:NN Pattern Classification Techniques. Los Alamitos:IEEE Computer Society Press.
    [7] Fahraeus R, 1929. The Suspension stability of the blood. Physiological Reviews, 9(2):241-274. doi:10.1152/physrev. 1929.9.2.241
    [8] Ge M, Yan Y, Ren Z Y et al., 1999. The relationship between normal erythrocyte sedimentation rate of Chinese young people and geographical factors. Clinical Hemorheology and Microcirculation, 20(3):151-157.
    [9] Ge M, Ren Z Y, Yang Q S et al., 2001. The relationship between reference value of old people's erythrocyte sedimentation rate and altitude. Clinical Hemorheology and Microcirculation, 24(3):155-159.
    [10] Ge M, 2004. Reference value of younger people's erythrocyte sedimentation rate and altitude. Journal of Laboratory and Clinical Medicine, 143(6):367-368. doi:10.1016/j.lab.2004. 03.006
    [11] Gierl L, Steffen D, Ihracky D et al., 2003. Methods, architecture, evaluation and usability of a case-based antibiotics advisor. Computer Methods and Programs in Biomedicine, 72(2):139-154. doi: 10.1016/S0169-2607(02)00121-9
    [12] Greisheimer E M, Warwick M, Walton M, 1929. The relationship between fibrin content and sedimentation index in orthopedic cases. American Journal of Diseases of Children, 37(5):953-956. doi: 10.1001/archpedi.1929.01930050063007
    [13] Hale A J, Ricotta D N, Freed J A. 2019. Evaluating the erythrocyte sedimentation rate. JAMA, 321(14):1404-1405. doi: 10.1001/jama.2019.1178
    [14] Hoiland R L, Smith K J, Carter H H et al., 2017. Shear-mediated dilation of the internal carotid artery occurs independent of hypercapnia. American Journal of Physiology Heart and Circulatory Physiology, 313(1):H24-H31. doi: 10.1152/ajpheart.00119.2017
    [15] Holt A, 1999. Applying case-based reasoning techniques in GIS. International Journal of Geographical Information Science, 13(1):9-25. doi: 10.1080/136588199241436
    [16] Houben I, Wehenkel L, Pavella M, 1995. Coupling of K-NN with decision trees for power system transient stability assessment. In:Proceedings of International Conference on Control Applications. Albany, NY, USA:IEEE. doi:10.1109/CCA. 1995.555856
    [17] Isiksacan Z, Erel O, Elbuken C, 2016. A portable microfluidic system for rapid measurement of the erythrocyte sedimentation rate. Lab on A Chip, 16(24):4682-4690. doi: 10.1039/c6lc01036a
    [18] Jalali V, Leake D, 2016. Enhancing case-based regression with automatically-generated ensembles of adaptations. Journal of Intelligent Information Systems, 46(2):237-258. doi: 10.1007/s10844-015-0377-0
    [19] Jou J M, Lewis S M, Briggs C et al., 2011. ICSH review of the measurement of the erythocyte sedimentation rate. International Journal of Laboratory Hematology, 33(2):125-132. doi: 10.1111/j.1751-553X.2011.01302.x
    [20] Kawashiri S Y, Kawakami A, Iwamoto N et al., 2011. Disease activity score 28 may overestimate the remission induction of rheumatoid arthritis patients treated with tocilizumab:comparison with the remission by the clinical disease activity index. Modern Rheumatology, 21(4):365-369. doi: 10.3109/s10165-010-0402-7
    [21] Kibler D, Aha D W, Albert M K, 1989. Instance-based prediction of real-valued attributes. Computational Intelligence, 5(2):51-57. doi:10.1111/j.1467-8640.1989. tb00315.x
    [22] Kolodner J, 1993. Case-based Reasoning. San Mateo:Morgan Kaufmann.
    [23] Kolodner J L, 1992. An introduction to case-based reasoning. Artificial Intelligence Review, 6(1):3-34. doi: 10.1007/bf00155578
    [24] Kratz A, Plebani M, Peng M et al., 2017. ICSH recommendations for modified and alternate methods measuring the erythrocyte sedimentation rate. International Journal of Laboratory Hematology, 39(5):448-457. doi: 10.1111/ijlh.12693
    [25] Kuznetsova D A, Sizova E N, Tuliakova O V, 2013. Influence of high altitude on the functional status and morbidity of teenagers. Gigiena I Sanitariia, (3):77-80.
    [26] Li X, Yeh A G O, 2002. Neural-network-based cellular automata for simulating multiple land use changes using GIS. International Journal of Geographical Information Science, 16(4):323-343. doi: 10.1080/13658810210137004
    [27] Miller A, Green M, Robinson D, 1983. Simple rule for calculating normal erythrocyte sedimentation rate. British Medical Journal, 286(6361):266. doi: 10.1136/bmj.286.6361.266
    [28] Moen J K, Reimann H A, 1933. Plasma protein changes and suspension stability of the blood in lobar pneumonia. The Journal of Clinical Investigation, 12(3):589-598. doi: 10.1172/JCI100522
    [29] Montani S, Jain L C, 2010. Successful Case-Based Reasoning Applications. Berlin:Springer Verlag.
    [30] Näyhä S, 1987. Normal variation in erythrocyte sedimentation rate in males over 50 years old. Scandinavian Journal of Primary Health Care, 5(1):5-8. doi: 10.3109/02813438709024179
    [31] Olshaker J S, Jerrard D A, 1997. The erythrocyte sedimentation rate. The Journal of Emergency Medicine, 15(6):869-874. doi: 10.1016/S0736-4679(97)00197-2
    [32] Pincherle G, Shanks J, 1967. Value of the erythrocyte sedimentation rate as a screening test. British Journal of Preventive & Social Medicine, 21(3):133-136. doi: 10.1136/jech.21.3.133
    [33] Ropes M W, Rossmeisl E, Bauer W, 1939. The relationship between the erythrocyte sedimentation rate and the plasma proteins. The Journal of Clinical Investigation, 18(6):791-798. doi: 10.1172/JCI101096
    [34] Schäfer V S, Weiß K, Krause A et al., 2018. Does erythrocyte sedimentation rate reflect and discriminate flare from infection in systemic lupus erythematosus? Correlation with clinical and laboratory parameters of disease activity. Clinical Rheumatology, 37(7):1835-1844. doi: 10.1007/s10067-018-4093-3
    [35] Sharland D E, 1980. Erythrocyte sedimentation rate:the normal range in the elderly. Journal of the American Geriatrics Society, 28(8):346-348. doi:10.1111/j.1532-5415.1980. tb01096.x
    [36] Siemons L, ten Klooster P M, Vonkeman H E et al., 2014. How age and sex affect the erythrocyte sedimentation rate and C-reactive protein in early rheumatoid arthritis. BMC Musculoskeletal Disorders, 15(1):368. doi: 10.1186/1471-2474-15-368
    [37] Sönmez Ç, Guntas G, Kaymak A Ö et al., 2014. Comparison of erythrocyte sedimentation rate results of test-1 and automatic westergren device with reference westergren method. Gazi Medical Journal, 25(2):52-54. doi: 10.12996/gmj.2014.15
    [38] Suckling P V, 1957. The erythrocyte sedimentation rate in kwashiorkor in Cape coloured children. South African Journal Of Laboratory And Clinical Medicine. Suid-Afrikaanse Tydskrif vir Laboratorium-en Kliniekwerk, 3(4):308-315.
    [39] Theil H, 1967. Economics and Information Theory. Chicago:North-Holland Pub. Co.
    [40] van Atteveld V A, van Ancum J M, Reijnierse E M et al., 2019. Erythrocyte sedimentation rate and albumin as markers of inflammation are associated with measures of sarcopenia:a cross-sectional study. BMC Geriatrics, 19:233. doi: 10.1186/s12877-019-1253-5
    [41] Wetteland P, Røger M, Solberg H E et al., 1996. Population-based erythrocyte sedimentation rates in 3910 subjectively healthy Norwegian adults. A statistical study based on men and women from the Oslo area. Journal of Internal Medicine, 240(3):125-131. doi: 10.1046/j.1365-2796.1996.30295851000.x
    [42] Wyler D J, 1977. Diagnostic implications of markedly elevated erythrocyte sedimentation rate:a reevaluation. Southern Medical Journal, 70(12):1428-1430. doi: 10.1097/00007611-197712000-00015
    [43] Yang Q S, Mwenda K M, Ge M, 2013. Incorporating geographical factors with artificial neural networks to predict reference values of erythrocyte sedimentation rate. International Journal of Health Geographics, 12(1):11. doi: 10.1186/1476-072x-12-11
    [44] Zacharski L R, Kyle R A, 1967. Significance of extreme elevation of erythrocyte sedimentation rate. JAMA, 202(4):264-266. doi: 10.1001/jama.1967.03130170064008
    [45] Zouboules S M, Lafave H C, O'Halloran K D et al., 2018. Renal reactivity:acid-base compensation during incremental ascent to high altitude. The Journal of Physiology, 596(24):6191-6203. doi: 10.1113/JP276973
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(326) PDF downloads(52) Cited by()

Proportional views
Related

A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China

doi: 10.1007/s11769-020-1102-7
Funds:

Under the auspices of National Natural Science Foundation of China (No. 40971060)

Abstract: Reference values of erythrocyte sedimentation rate (ESR) are the key to interpret ESR blood test in clinic. The common local reference ESR values are more accuracy in blood test that are established with natural geographical factors by using the multiple linear regression (MLR) model and the artificial neural network (ANN). These knowledge-based methods have limitations since the knowledge domains of ESR and natural geographical factors are limited. This paper presents a new cases-depended model to establish reference ESR values with natural geographical factors and location using case-based reasoning (CBR) since knowledge domain of ESR and geographical factors is weak. Overall 224 local normal ESR values of China that calculated from 13 623 samples were obtained, and the corresponding natural geographical factors and location that include altitude, sunshine hours, relative humidity, temperature, precipitation, annual temperature range and annual average wind speed were obtained from the National Geomatics Center of China. CBR was used to predict the unseen local reference ESR values with cases. The average absolute deviation (AAD), mean square error (MSE), prediction accuracy (PA), and Pearson correlation coefficient (r) between the observed and estimated data of proposed model is 33.07%, 9.02, 66.93% and 0.78, which are better than those of ANN and MLR model. The results show that the proposed model provides higher prediction accuracy than those of the artificial neural network and multiple linear regression models. The predicted values are very close to the observed values. Model results show significant agreement of cases data. Consequently, the model is used to predict the unseen local reference ESR with natural geographical factors and location. In spatial, the highest ESR reference areas are distributed in the southern-western district of China that includes Sichuan, Chongqing, Guangxi and Guizhou provinces, and the reference ESR values are greater than 23 mm/60 min. The higher ESR reference values are distributed in the middle part and northern-eastern of China which include Hubei, Henan, Shaanxi, Shanxi, Jilin and Heilongjiang provinces, and the reference ESR values are greater than 18 mm/60 min. The lowest ESR reference values are distributed in the northern-western of China that includes Tibet and Xinjiang, and the reference ESR values are lower than 5 mm/60 min.

YANG Qingsheng, YOU Xibin, ZHANG Hongxian, Kevin MWENDA, WANG Yuandong, HUANG Ying. A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China[J]. Chinese Geographical Science, 2020, 30(1): 157-169. doi: 10.1007/s11769-020-1102-7
Citation: YANG Qingsheng, YOU Xibin, ZHANG Hongxian, Kevin MWENDA, WANG Yuandong, HUANG Ying. A New Method to Predict Erythrocyte Sedimentation Rate with Natural Geographical Factors and Location by Case-based Reasoning: A Case Study of China[J]. Chinese Geographical Science, 2020, 30(1): 157-169. doi: 10.1007/s11769-020-1102-7
Reference (45)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return