PDF herunterladen
Methods Inf Med 2014; 53(01): 47-53
DOI: 10.3414/ME13-01-0027
Original Articles
Schattauer GmbH

Improvement of Adequate Use of Warfarin for the Elderly Using Decision Tree-based Approaches[*]

K. E. Liu
1   Department of Economics, National Chung Cheng University, Chia-Yi, Taiwan
,
C.-L. Lo
2   Department of Information Management and Graduate Institute of Healthcare Information Management, National Chung Cheng University, Chia-Yi, Taiwan
,
Y.-H. Hu
2   Department of Information Management and Graduate Institute of Healthcare Information Management, National Chung Cheng University, Chia-Yi, Taiwan
› Institutsangaben
Weitere Informationen

Publikationsverlauf

received: 06. März 2013

accepted: 16. September 2013

Publikationsdatum:
20. Januar 2018 (online)

    Lizenzen und Reprints

Summary

Objectives: Due to the narrow therapeutic range and high drug-to-drug interactions (DDIs), improving the adequate use of warfarin for the elderly is crucial in clinical practice. This study examines whether the effectiveness of using warfarin among elderly inpatients can be improved when machine learning techniques and data from the laboratory information system are incorporated.

Methods: Having employed 288 validated clinical cases in the DDI group and 89 cases in the non-DDI group, we evaluate the prediction performance of seven classification techniques, with and without an Adaptive Boosting (AdaBoost) algorithm. Measures including accuracy, sensitivity, specificity and area under the curve are used to evaluate model performance.

Results: Decision tree-based classifiers outperform other investigated classifiers in all evaluation measures. The classifiers supplemented with AdaBoost can generally improve the performance. In addition, weight, congestive heart failure, and gender are among the top three critical variables affecting prediction accuracy for the non-DDI group, while age, ALT, and warfarin doses are the most influential factors for the DDI group.

Conclusion: Medical decision support systems incorporating decision tree-based approaches improve predicting performance and thus may serve as a supplementary tool in clinical practice. Information from laboratory tests and inpatients’ history should not be ignored because related variables are shown to be decisive in our prediction models, especially when the DDIs exist.

Keywords

Warfarin - anticoagulant - decision support techniques - decision trees - health services for the elderly

* Supplementary material published on our website http://www.methods-online.com


 

  • References

  • 1 ASHP. ASHP statement on the pharmacist’s role in clinical pharmacokinetic monitoring. American journal of health-system pharmacy. AJHP: official journal of the American Society of Health-System Pharmacists. 1998; 55 (016) 1726-1727.
    PubMedGoogle Scholar
  • 2 Dunn AS, Wisnivesky J, Ho W, Moore C, McGinn T, Sacks HS. Perioperative management of patients on oral anticoagulants: a decision analysis. Med Decis Making 2005; 25 (04) 387-397.
    CrossrefPubMedGoogle Scholar
  • 3 Horton JD, Bushwick BM. Warfarin therapy: evolving strategies in anticoagulation. Am Fam Physician 1999; 59 (03) 635-646.
    PubMedGoogle Scholar
  • 4 Setiabudi E, Alwi I, Setiati S. Oral anticoagulant treatment in management of elderly patients with atrial fibrillation [corrected]: is it beneficial or detrimental?. Acta medica Indonesiana 2008; 40 (01) 40-47.
    PubMedGoogle Scholar
  • 5 Colombet I, Bura-Riviere A, Chatila R, Chatellier G, Durieux P. for the P-OATsg. Personalized versus non-personalized computerized decision support system to increase therapeutic quality control of oral anticoagulant therapy: an alternating time series analysis. BMC Health Services Research 2004; 4 (01) 27.
    CrossrefPubMedGoogle Scholar
  • 6 Tadros R, Shakib S. Warfarin--indications, risks and drug interactions. Aust Fam Physician 2010; 39 (06) 476-479.
    PubMedGoogle Scholar
  • 7 Lutz W, Sanderson W, Scherbov S. The coming acceleration of global population ageing. Nature 2008; 451 07179 716-719.
    CrossrefPubMedGoogle Scholar
  • 8 Schelleman H, Chen J, Chen Z, Christie J, Newcomb CW, Brensinger CM. et al Dosing Algorithms to Predict Warfarin Maintenance Dose in Caucasians and African Americans. Clin Pharmacol Ther 2008; 84 (03) 332-339.
    CrossrefPubMedGoogle Scholar
  • 9 The International Warfarin Pharmacogenetics Consortium. Estimation of the Warfarin Dose with Clinical and Pharmacogenetic Data. N Engl J Med 2009; 360 (08) 753-764.
    CrossrefPubMedGoogle Scholar
  • 10 Byrne SCP, Barry A, Graham I, Delaney T, Corrigan OI. editor. Using neural nets for decision support in prescription and outcome prediction in anticoagulation drug therapy. Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP-2000). Berlin, Germany: CVAST; 2000
    Google Scholar
  • 11 Solomon I, Maharshak N, Chechik G, Leibovici L, Lubetsky A, Halkin H. et al Applying an artificial neural network to warfarin maintenance dose prediction. Isr Med Assoc J 2004; 6 (012) 732-735.
    PubMedGoogle Scholar
  • 12 D’Andrea G, D’Ambrosio RL, Di Perna P, Chetta M, Santacroce R, Brancaccio V. et al A polymorphism in the VKORC1 gene is associated with an interindividual variability in the dose-anticoagulant effect of warfarin. Blood 2005; 105 (02) 645-649.
    CrossrefPubMedGoogle Scholar
  • 13 Miao L, Yang J, Huang C, Shen Z. Contribution of age, body weight, and CYP2C9 and VKORC1 genotype to the anticoagulant response to warfarin: proposal for a new dosing regimen in Chinese patients. Eur J Clin Pharmacol. 2007; 63 (012) 1135-1141.
    CrossrefPubMedGoogle Scholar
  • 14 Wang TL, Li HL, Tjong WY, Chen QS, Wu GS, Zhu HT. et al Genetic factors contribute to patient-specific warfarin dose for Han Chinese. Clinica chimica acta; international journal of clinical chemistry 2008; 396 (01) (02) 76-79.
    CrossrefPubMedGoogle Scholar
  • 15 Ferder NS, Eby CS, Deych E, Harris JK, Ridker PM, Milligan PE. et al Ability of VKORC1 and CYP2C9 to predict therapeutic warfarin dose during the initial weeks of therapy. Journal of thrombosis and haemostasis : JTH 2010; 8 (01) 95-100.
    CrossrefPubMedGoogle Scholar
  • 16 Wadelius M, Chen LY, Lindh JD, Eriksson N, Ghori MJ, Bumpstead S. et al The largest prospective warfarin-treated cohort supports genetic forecasting. Blood 2009; 113 (04) 784-792.
    CrossrefPubMedGoogle Scholar
  • 17 Harada T, Ariyoshi N, Shimura H, Sato Y, Yokoyama I, Takahashi K. et al Application of Akaike information criterion to evaluate warfarin dosing algorithm. Thromb Res 2010; 126 (03) 183-190.
    CrossrefPubMedGoogle Scholar
  • 18 Le Gal G, Carrier M, Tierney S, Majeed H, Rodger M, Wells PS. Prediction of the warfarin maintenance dose after completion of the 10 mg initiation nomogram: do we really need genotyping?. J Thromb Haemost 2010; 8 (01) 90-94.
    CrossrefPubMedGoogle Scholar
  • 19 Martin B, Filipovic M, Rennie L, Shaw D. Using Machine Learning to Prescribe Warfarin. 2010; 151: 60
    PubMedGoogle Scholar
  • 20 Wells PS, Majeed H, Kassem S, Langlois N, Gin B, Clermont J. et al A regression model to predict warfarin dose from clinical variables and polymorphisms in CYP2C9, CYP4F2, and VKORC1: Derivation in a sample with predominantly a history of venous thromboembolism. Thromb Res 2010; 125 (06) e259-264.
    CrossrefPubMedGoogle Scholar
  • 21 Cosgun E, Limdi NA, Duarte CW. High-dimensional pharmacogenetic prediction of a continuous trait using machine learning techniques with application to warfarin dose prediction in African Americans. Bioinformatics 2011; 27 (010) 1384-1389.
    CrossrefPubMedGoogle Scholar
  • 22 Wadelius M, Chen LY, Downes K, Ghori J, Hunt S, Eriksson N. et al Common VKORC1 and GGCX polymorphisms associated with warfarin dose. The pharmacogenomics journal 2005; 5 (04) 262-270.
    CrossrefPubMedGoogle Scholar
  • 23 Riley K. FDA approves updated warfarin (Coumadin) prescribing information. 2007 (updated 06/18/2009 cited 2012 March, 20). Available from http://www.fda.gov/NewsEvents/Newsroom/PressAnnouncements/2007/ucm108967.htm
    PubMedGoogle Scholar
  • 24 Conti R, Veenstra DL, Armstrong K, Lesko LJ, Grosse SD. Personalized medicine and genomics: challenges and opportunities in assessing effectiveness, cost-effectiveness, and future research priorities. Med Decis Making 2010; 30 (03) 328-340.
    CrossrefPubMedGoogle Scholar
  • 25 Bussey HI, Wittkowsky AK, Hylek EM, Walker MB. Genetic testing for warfarin dosing? Not yet ready for prime time. Pharmacotherapy 2008; 28 (02) 141-143.
    CrossrefPubMedGoogle Scholar
  • 26 Gage BF, Eby C, Milligan PE, Banet GA, Duncan JR, McLeod HL. Use of pharmacogenetics and clinical factors to predict the maintenance dose of warfarin. Thromb Haemost 2004; 91 (01) 87-94.
    Artikel in Thieme ConnectPubMedGoogle Scholar
  • 27 Bertola JP, Mazoyer E, Bergmann JF, Drouet L, Simoneau G, Mahe I. Early prediction of the sensitivity of warfarin in elderly patients by the fall in factor VIIc and protein C at the induction of treatment. Thromb Res 2003; 109 (05) (06) 287-291.
    CrossrefPubMedGoogle Scholar
  • 28 Chatap G, Chaibi P, Giraud K, Sadji F, Vincent JP. Oral anticoagulation in older patients. (Establishment and validation of a new posologic warfarin regimen. Anticoagulation orale du sujet age. Etablissement et validation d’une grille d’adaptation posologique de la warfarine. ) Presse Med 2001; 30 (010) 475-480.
    PubMedGoogle Scholar
  • 29 Franko J, Kish KJ, O’Connell BG, Subramanian S, Yuschak JV. Advanced age and preinjury warfarin anticoagulation increase the risk of mortality after head trauma. J Trauma 2006; 61 (01) 107-110.
    CrossrefPubMedGoogle Scholar
  • 30 Oates A, Jackson PR, Austin CA, Channer KS. A new regimen for starting warfarin therapy in out-patients. Br J Clin Pharmacol 1998; 46 (02) 157-161.
    PubMedGoogle Scholar
  • 31 Lebovitz HE, Kreider M, Freed MI. Evaluation of Liver Function in Type 2 Diabetic Patients During Clinical Trials: Evidence that rosiglitazone does not cause hepatic dysfunction. Diabetes Care 2002; 25 (05) 815-821.
    CrossrefPubMedGoogle Scholar
  • 32 Ishida K, Ishida H, Narita M, Sairenchi T, Saito Y, Fukutomi H. et al Factors affecting renal function in 119985 adults over three years. QJM 2001; 94 (010) 541-550.
    CrossrefPubMedGoogle Scholar
  • 33 You J, Chan F, Wong R, Cheng G. Is INR between 2.0 and 3.0 the optimal level for Chinese patients on warfarin therapy for moderate intensity anticoagulation?. Br J Clin Pharmacol 2005; 59 (05) 582-587.
    CrossrefPubMedGoogle Scholar
  • 34 Hu Y-H, Wu F, Lo C-L, Tai C-T. Predicting warfarin dosage from clinical data: A supervised learning approach. Artif Intell Med 2012; 56 (01) 27-34.
    CrossrefPubMedGoogle Scholar
  • 35 Quinlan JR. C4.5: Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann; 1993
    Google Scholar
  • 36 Andrew F, Shorr DMarya, Zilberberg TScott, Micek HMarin. Kollef. Prediction of Infection Due to Antibiotic-Resistant Bacteria by Select Risk Factors for Health Care-Associated Pneumonia. Arch Intern Med 2008; 168 (020) 2205-2210.
    CrossrefPubMedGoogle Scholar
  • 37 Hasan O, Meltzer DO, Shaykevich SA, Bell CM, Kaboli PJ, Auerbach AD. et al Hospital readmission in general medicine patients: a prediction model. J Gen Intern Med 2010; 25 (03) 211-219.
    CrossrefPubMedGoogle Scholar
  • 38 Lee TH, Marcantonio ER, Mangione CM, Thomas EJ, Polanczyk CA, Cook EF. et al Derivation and prospective validation of a simple index for prediction of cardiac risk of major noncardiac surgery. Circulation 1999; 100 (010) 1043-1049.
    CrossrefPubMedGoogle Scholar
  • 39 Prompers L, Schaper N, Apelqvist J, Edmonds M, Jude E, Mauricio D. et al Prediction of outcome in individuals with diabetic foot ulcers: focus on the differences between individuals with and without peripheral arterial disease. The EURODIALE Study. Diabetologia 2008; 51 (05) 747-755.
    CrossrefPubMedGoogle Scholar
  • 40 Tu JV, Austin PC, Walld R, Roos L, Agras J, McDonald KM. Development and validation of the Ontario acute myocardial infarction mortality prediction rules. J Am Coll Cardiol 2001; 37 (04) 992-997.
    CrossrefPubMedGoogle Scholar
  • 41 Freund Y, Schapire R. A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 1997; 55 (01) 119-139.
    CrossrefPubMedGoogle Scholar
  • 42 Iftekharuddin KM, Ahmed S, Hossen J. Multiresolution texture models for brain tumor segmentation in MRI. Conf Proc IEEE Eng Med Biol Soc 2011; pp 6985-6988.
    PubMedGoogle Scholar
  • 43 Niu B, Cai YD, Lu WC, Li GZ, Chou KC. Predicting protein structural class with AdaBoost Learner. Protein and peptide letters 2006; 13 (05) 489-492.
    CrossrefPubMedGoogle Scholar
  • 44 Stollhoff R, Sauerbrei W, Schumacher M. An Experimental Evaluation of Boosting Methods for Classification. Methods Inf Med 2010; 49 (03) 219-229.
    Artikel in Thieme ConnectPubMedGoogle Scholar
  • 45 Scalzo F, Hamilton R, Asgari S, Kim S, Hu X. Intracranial hypertension prediction using extremely randomized decision trees. Med Eng Phys 2012
    PubMedGoogle Scholar
  • 46 Tan P-N, Steinbach M, Kumar V. Introduction to Data Mining. Boston: Addison Wesley; 2006. p 769
    Google Scholar
  • 47 Hosmer DW, Lemeshow S. Applied Logistic Regression. New York: John Wiley & Sons; 1989
    Google Scholar
  • 48 Bellazzi R, Diomidous M, Sarkar IN, Takabayashi K, Ziegler A, McCray AT. Data Analysis and Data Mining: Current Issues in Biomedical Informatics. Methods Inf Med 2011; 50 (06) 536-544.
    Artikel in Thieme ConnectPubMedGoogle Scholar
  • 49 Winkelmayer WC, Charytan DM, Brookhart MA, Levin R, Solomon DH, Avorn J. Kidney function and use of recommended medications after myocardial infarction in elderly patients. Clin J Am Soc Nephrol 2006; 1 (04) 796-801.
    CrossrefPubMedGoogle Scholar
  • 50 Schmucker DL. Liver function and phase I drug metabolism in the elderly: a paradox. Drugs Aging 2001; 18 (011) 837-851.
    CrossrefPubMedGoogle Scholar
  • 51 Stiglic G, Kokol P. Discovering Subgroups Using Descriptive Models of Adverse Outcomes in Medical Care. Methods Inf Med 2012; 51 (04) 348-352.
    Artikel in Thieme ConnectPubMedGoogle Scholar
  • 52 Tatro D. Drug interaction facts. St. Louis, MO: Wolters Kluwer Health; 2004
    Google Scholar
  • 53 Micromedex Gateway. Truven Health Analytics Inc. (internet) (cited May 1, 2012 ). Avaliable from http://www.micromedexsolutions.com/micromedex2/librarian
    PubMedGoogle Scholar
  • 54 MIMS USA Drug information System. UBM Medica Inc. (internet) (cited May 1, 2012). Available from http://www.mims.com/
    PubMedGoogle Scholar