การลดจำนวนกลุ่มในการจำแนกแบบหลายกลุ่มเป็นสองกลุ่มสำหรับการจำแนกการกลับมารักษาซ้ำในโรงพยาบาลของผู้ป่วยโรคเบาหวาน
Article Sidebar
เผยแพร่แล้ว:
ธ.ค. 29, 2019
คำสำคัญ:
การถดถอยลอจิสติก ต้นไม้การตัดสินใจ การจำแนกประเภทอเนกนาม การจำแนกประเภทหลายกลุ่ม การจำแนกประเภททวิภาค ผู้ป่วยโรคเบาหวาน
Main Article Content
บทคัดย่อ
การวิจัยครั้งนี้เป็นการวิจัยเพื่อเปรียบเทียบประสิทธิภาพการจำแนกประเภทของการกลับมารักษาซ้ำในโรงพยาบาลของผู้ป่วยโรคเบาหวานแบบหลายกลุ่ม (multiclass) หรืออเนกนาม (multinomial) และแบบสองกลุ่มหรือทวิภาค (binary) จำนวน 2 กรณี โดยใช้เทคนิคการวิเคราะห์การถดถอยลอจิสติกและต้นไม้การตัดสินใจ ข้อมูลที่ใช้ในการวิจัยเป็นข้อมูลประวัติการรักษาพยาบาลของผู้ป่วยโรคเบาหวานจาก Clinical Care at 130 US Hospitals and Integrated Delivery Networks ตัวแปรเป้าหมายในการจำแนกประกอบด้วยประเภทการนัดหมายให้กลับมารักษาซ้ำในโรงพยาบาลของผู้ป่วยโรคเบาหวาน จำนวน 3 กลุ่ม คือ ไม่กลับมารักษาซ้ำหรือไม่มีภาวะโรค กลับมารักษาซ้ำภายใน 30 วัน และกลับมารักษาซ้ำมากกว่า 30 วัน ผลการวิจัยพบว่าประสิทธิภาพของการจำแนกประเภทโดยใช้เทคนิคต้นไม้การตัดสินใจแบบทวิภาค จำนวน 2 กรณี มีประสิทธิภาพสูงสุด
Article Details
บท
Physical Sciences
References
[1] Shaw, J.E., Sicree, R.F. and Zimmet, P.Z., 2010, Global estimates of the prevalence of diabetes for 2010 and 2030, Diabetes Res. Clin. Pract. 87: 4-14.
[2] Dungan, K.M., 2012, The effect of diabetes on hospital readmissions, J. Diabetes. Sci. Technol. 6: 1045-1052.
[3] Bradley, E.H., Curry, L., Horwitz, L.I., Sipsma, H., Wang, Y., Walsh, M.N., Goldmann, D., White, N., Piña, I.L. and Krumholz, H.M., 2013, Hospital strategies associated with 30-day readmission rates for patients with heart failure, Circ. Cardiovasc. Qual. Outcomes 6: 444-450.
[4] Choowattanapakorn, T., Karuna, R., Konghan, S. and Tangmettajittakun, D., 2016, Factors predicting quality of life in older people with diabetes in Thailand, Songklanakarin J. Sci. Technol. 38: 707-714.
[5] Anitha, J. and Pethalakshmi, A., 2017, Comparison of classification algorithms in diabetic dataset, The 5th National Conference on Computational Methods, Communication Techniques and Informatics Department of Computer Science & Applications, The Gandhigram Rural Institute-Deemed University, Tamil Nadu.
[6] Chen, H., Zhang, J., Xu, Y., Chen, B. and Zhang, K., 2012, Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans, J. Med. Eng. Technol. 39: 11503-11509.
[7] Dogan, N. and Tanrikulu, Z., 2013, A comparative analysis of classification algorithms in data mining for accuracy, speed and robustness, Inf. Technol. Manage. 14: 105-124.
[8] Eftekhar, B., Mohammad, K., Ardebili, H. E., Ghodsi, M. and Ketabchi, E., 2005, Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data, BMC Med. Inform. Decis. Mak. 5: 1-8.
[9] Thangaraju, P., Deepa, B. and Karthikeyan, T., 2014, Comparison of data mining techniques for forecasting diabetes mellitus, IJARCSEE 3: 7674-7677.
[10] Srinivas, M., Bharath, R., Rajalakshmi, P. and Mohan, C.K., 2015, Multi-level classification: A generic classification method for medical datasets, The 17th International Conference on E-health Networking, Application & Services (HealthCom).
[11] Hosmer, Jr.D.W., Lemeshow, S. and Sturdivant, R.X., 2013, Applied Logistic Regression, John Wiley & Sons, New York, 398 p.
[12] James, G., Witten, D., Hastie, T. and Tibshirani, R., 2013, An Introduction to Statistical Learning with Applications in R, Springer, 426 p.
[13] Cichosz, P., 2015, Data mining algorithms: Explained using R, Chichester, West Sussex, Wiley, Chichester, West Sussex, Wiley, 683 p.
[14] Jitthavech, J., 2015, Regression Analysis, Bangkok, National Institute of Development Administration, 433 p. (in Thai)
[15] Maiprasert, D., 2013, Prediction of breast cancer stage using multinomial logistic regression and artificial neural network, Ph.D. Thesis, Rangsit University, Bangkok, 215 p. (in Thai)
[16] Pacharawongsakda, E., 2014, An Introduction to Data Mining Techniques. Bangkok, Asia Digital Press Co., Ltd., 124 p. (in Thai)
[17] Grisanti, J., Decision Trees: An Overview. Available Source: https://www.aunalytics.com/2015/01/30/decision-trees-an-overvi ew, June 9, 2015.
[18] Strack, B., DeShazo, J.P., Gennings, C., Olmo, J.L., Ventura, S., Cios, K.J. and Clore, J.N., 2014, Impact of HbA1c measurement on hospital readmission rates: Analysis of 70,000 clinical database patient records, Biomed. Res. Int. 2014: 1-11.
[19] Cotha, N.K.P. and Sokolova, M., 2015, Multi-Labeled Classification of Demographic Attributes of Patients: A Case Study of Diabetics Patients, pp. 1-16, Cornall University Library, New York.
[20] Jelinek, H., Abawajy, J., Kelarev, A., Chowdhury, M. and Stranieri, A., 2013, Decision trees and multi-level ensemble classifiers for neurological diagnostics, AIMS Med. Sc. 1: 1-12.
[21] Bihis, M. and Roychowdhury, S., 2015, A generalized flow for multi-class and binary classification tasks: An Azure ML approach, pp. 1728-1737, The 2015 IEEE International Conference on Big Data.
[22] Beleites, C., Salzer, R. and Sergo, V., 2013, Validation of soft classification models using partial class memberships: An extended concept of sensitivity & co. applied to grading of astrocytoma tissues, Chemometr. Intell. Lab. Syst. 122: 12-22.
[23] Ebrahimi, N., 2008, Simultaneous control of false positives and false negatives in multiple hypotheses testing, J. Multivar. Anal. 99: 437-450.
[24] Zhao, C., Crothers, B.A., Tabatabai, Z.L., Li, Z., Ghofrani, M., Souers, R.J., Husain, M., Fan, F., Shen, R. and Ocal, I.T., 2017, False-negative interpretation of adenocarcinoma in situ in the college of American Pathologists Gynecologic PAP Education Program, Arch. Pathol. Lab. Med. 141: 666-670.
[2] Dungan, K.M., 2012, The effect of diabetes on hospital readmissions, J. Diabetes. Sci. Technol. 6: 1045-1052.
[3] Bradley, E.H., Curry, L., Horwitz, L.I., Sipsma, H., Wang, Y., Walsh, M.N., Goldmann, D., White, N., Piña, I.L. and Krumholz, H.M., 2013, Hospital strategies associated with 30-day readmission rates for patients with heart failure, Circ. Cardiovasc. Qual. Outcomes 6: 444-450.
[4] Choowattanapakorn, T., Karuna, R., Konghan, S. and Tangmettajittakun, D., 2016, Factors predicting quality of life in older people with diabetes in Thailand, Songklanakarin J. Sci. Technol. 38: 707-714.
[5] Anitha, J. and Pethalakshmi, A., 2017, Comparison of classification algorithms in diabetic dataset, The 5th National Conference on Computational Methods, Communication Techniques and Informatics Department of Computer Science & Applications, The Gandhigram Rural Institute-Deemed University, Tamil Nadu.
[6] Chen, H., Zhang, J., Xu, Y., Chen, B. and Zhang, K., 2012, Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans, J. Med. Eng. Technol. 39: 11503-11509.
[7] Dogan, N. and Tanrikulu, Z., 2013, A comparative analysis of classification algorithms in data mining for accuracy, speed and robustness, Inf. Technol. Manage. 14: 105-124.
[8] Eftekhar, B., Mohammad, K., Ardebili, H. E., Ghodsi, M. and Ketabchi, E., 2005, Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data, BMC Med. Inform. Decis. Mak. 5: 1-8.
[9] Thangaraju, P., Deepa, B. and Karthikeyan, T., 2014, Comparison of data mining techniques for forecasting diabetes mellitus, IJARCSEE 3: 7674-7677.
[10] Srinivas, M., Bharath, R., Rajalakshmi, P. and Mohan, C.K., 2015, Multi-level classification: A generic classification method for medical datasets, The 17th International Conference on E-health Networking, Application & Services (HealthCom).
[11] Hosmer, Jr.D.W., Lemeshow, S. and Sturdivant, R.X., 2013, Applied Logistic Regression, John Wiley & Sons, New York, 398 p.
[12] James, G., Witten, D., Hastie, T. and Tibshirani, R., 2013, An Introduction to Statistical Learning with Applications in R, Springer, 426 p.
[13] Cichosz, P., 2015, Data mining algorithms: Explained using R, Chichester, West Sussex, Wiley, Chichester, West Sussex, Wiley, 683 p.
[14] Jitthavech, J., 2015, Regression Analysis, Bangkok, National Institute of Development Administration, 433 p. (in Thai)
[15] Maiprasert, D., 2013, Prediction of breast cancer stage using multinomial logistic regression and artificial neural network, Ph.D. Thesis, Rangsit University, Bangkok, 215 p. (in Thai)
[16] Pacharawongsakda, E., 2014, An Introduction to Data Mining Techniques. Bangkok, Asia Digital Press Co., Ltd., 124 p. (in Thai)
[17] Grisanti, J., Decision Trees: An Overview. Available Source: https://www.aunalytics.com/2015/01/30/decision-trees-an-overvi ew, June 9, 2015.
[18] Strack, B., DeShazo, J.P., Gennings, C., Olmo, J.L., Ventura, S., Cios, K.J. and Clore, J.N., 2014, Impact of HbA1c measurement on hospital readmission rates: Analysis of 70,000 clinical database patient records, Biomed. Res. Int. 2014: 1-11.
[19] Cotha, N.K.P. and Sokolova, M., 2015, Multi-Labeled Classification of Demographic Attributes of Patients: A Case Study of Diabetics Patients, pp. 1-16, Cornall University Library, New York.
[20] Jelinek, H., Abawajy, J., Kelarev, A., Chowdhury, M. and Stranieri, A., 2013, Decision trees and multi-level ensemble classifiers for neurological diagnostics, AIMS Med. Sc. 1: 1-12.
[21] Bihis, M. and Roychowdhury, S., 2015, A generalized flow for multi-class and binary classification tasks: An Azure ML approach, pp. 1728-1737, The 2015 IEEE International Conference on Big Data.
[22] Beleites, C., Salzer, R. and Sergo, V., 2013, Validation of soft classification models using partial class memberships: An extended concept of sensitivity & co. applied to grading of astrocytoma tissues, Chemometr. Intell. Lab. Syst. 122: 12-22.
[23] Ebrahimi, N., 2008, Simultaneous control of false positives and false negatives in multiple hypotheses testing, J. Multivar. Anal. 99: 437-450.
[24] Zhao, C., Crothers, B.A., Tabatabai, Z.L., Li, Z., Ghofrani, M., Souers, R.J., Husain, M., Fan, F., Shen, R. and Ocal, I.T., 2017, False-negative interpretation of adenocarcinoma in situ in the college of American Pathologists Gynecologic PAP Education Program, Arch. Pathol. Lab. Med. 141: 666-670.