+ Translate
+ Most Popular
Investigations on the organic drift in North Swedish streams
Limitations of Using Microsoft Excel Version 2016 (MS Excel 2016) for Statistical Analysis for Medical Research
Phloem necrosis of coffee in Surinam
Anatomy of Mystus seenghala IV Nervous system
Integrated farming system for gardenland conditions of Coimbatore district - an over view
Tetrapleure (Tetrapleura tetraptera), an unknown African medicinal and spice plant
The origin and phylogenetic significance of the trochophoran larvae 2. evolutionary significance of the larvae of coelomate worms and mollusks
Comparison of rice bran and maize bran as feeds for growing and fattening pigs
Enterobacter amnigenus. An unusual human pathogen
Influence of Seriboost foliar application on leaf yield and leaf protein content in mulberry (Morus spp.), in relation to silkworm cocoon production
The identity of the lipstick mold of cultivated mushrooms agaricus bisporus
Advantages and disadvantages of bordeaux mixture and of lime-sulphur used on apples in the growing season
'Pan-sukh' disease of Rice in the Central Provinces
Geological age of the Ptilophyllum flora; a critical reassessment
Study of vitellogenesis in birds; physiological phases & role of folliculin in vitellogenesis
Evaluation of WCT coconut and Komadan coconut
Therapy for acne with saccharomyces boulardii
Evidence for Late Cretaceous N-S dextral shear in the west-central crystalline core, North Cascades, Washington
'Rajeshwari' - a high-yielding white seeded variety of sesame for Andhra Pradesh
Manufacture of Ricotta cheese from whey fortified with skim milk powder using different acidulants
Occurrence of Eutrichophilus mexicanus (Rudow, 1866) and Eutrichophilus lobatus (Ewing, 1936) (Phthiraptera: Trichodectidae) on Sphiggurus villosus (Cuvier, 1825) (Rodentia: Erethizontidae) in Rio de
Factors affecting fruitfulness in durian (Durio zibethinus Murr.). I. Flowering and pollination
Bronchial cuff pressure change caused by left-sided double-lumen endobronchial tube displacement
Some Biological Applications of Organometallic Compounds
The composition of pampas-grass (Cortaderia argentea.)

Usefulness of a decision tree model for the analysis of adverse drug reactions: Evaluation of a risk prediction model of vancomycin-associated nephrotoxicity constructed using a data mining procedure

Usefulness of a decision tree model for the analysis of adverse drug reactions: Evaluation of a risk prediction model of vancomycin-associated nephrotoxicity constructed using a data mining procedure

Journal of Evaluation in Clinical Practice 23(6): 1240-1246

ISSN/ISBN: 1356-1294

PMID: 28544476

DOI: 10.1111/jep.12767

Several publications concerning decision tree (DT) analysis in medical fields have recently demonstrated its usefulness for defining prognostic factors in various diseases. However, there are minimal reports on the predictors of adverse drug reactions. We attempted to use DT analysis to discover combinations of multiple risk factors that would increase the risk of nephrotoxicity associated with vancomycin (VCM). To demonstrate the usefulness of DT analysis, we compared its predictive performance with that of multiple logistic regression analysis. A single-centre, retrospective study was conducted at Hokkaido University Hospital. A total of 592 patients, who received intravenous administrations of VCM between November 2011 and April 2016, were enrolled. Nephrotoxicity was defined as an increase in serum creatinine of ≥0.5 mg/dL or a ≥50% increase in serum creatinine from the baseline. Risk factors for VCM nephrotoxicity were extracted from previous reports. In the DT analysis, a chi-squared automatic interaction detection algorithm was constructed. For evaluating the established algorithms, a 10-fold cross validation method was adopted to calculate the misclassification risk of the model. Moreover, to compare the accuracy of the DT analysis, multiple logistic regression analysis was conducted. Eighty-seven (14.7%) patients developed nephrotoxicity. A VCM trough concentration of ≥15.0 mg/L, concomitant medication (vasopressor drugs and furosemide), and a duration of therapy ≥14 days were extracted to build the DT model, in which the patients were divided into 6 subgroups based on variable rates of nephrotoxicity, ranging from 4.6 to 69.6%. The predictive accuracies of the DT and logistic regression models were similar (87.3%, respectively), indicating that they were accurate. This study suggests the usefulness of DT models for the evaluation of adverse drug reactions.

Please choose payment method:

(PDF emailed within 0-6 h: $19.90)

Accession: 060447285

Download citation: RISBibTeXText

Related references

Construction of a risk prediction model of vancomycin-associated nephrotoxicity to be used at the time of initial therapeutic drug monitoring: A data mining analysis using a decision tree model. Journal of Evaluation in Clinical Practice 25(1): 163-170, 2019

Data-Mining-Based Coronary Heart Disease Risk Prediction Model Using Fuzzy Logic and Decision Tree. Healthcare Informatics Research 21(3): 167-174, 2015

Construction of a flow chart-like risk prediction model of ganciclovir-induced neutropaenia including severity grade: A data mining approach using decision tree. References 44(5): 726-734, 2019

Development and validation of a risk model for predicting adverse drug reactions in older people during hospital stay: Brighton Adverse Drug Reactions Risk (BADRI) model. Plos one 9(10): E111254, 2014

Prediction of adverse drug reactions using decision tree modeling. Clinical Pharmacology and Therapeutics 88(1): 52-59, 2010

Comparison of the Prediction Model of Adolescents' Suicide Attempt Using Logistic Regression and Decision Tree: Secondary Data Analysis of the 2019 Youth Health Risk Behavior Web-Based Survey. Journal of Korean Academy of Nursing 51(1): 40-53, 2021

Development and Validation of a Risk Prediction Model of Vancomycin-Associated Nephrotoxicity in Elderly Patients: A Pilot Study. Clinical and Translational Science 13(3): 491-497, 2020

Incidence of teicoplanin adverse drug reactions among patients with vancomycin-associated adverse drug reactions and its risk factors. Korean Journal of Internal Medicine 35(3): 714-722, 2020

Study on the Increased Probability of Detecting Adverse Drug Reactions Based on Bayes' Theorem: Evaluation of the Usefulness of Information on the Onset Timing of Adverse Drug Reactions. Biological and Pharmaceutical Bulletin 40(9): 1389-1398, 2017

Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice. Plos one 15(7): E0236789, 2020

Analysis of antiseizure drug-related adverse reactions from the electronic health record using the common data model. References 61(4): 610-616, 2020

Geospatial analysis and model development for specific degradation in South Korea using model tree data mining. Catena 200: 105142, 2021

The application of an institutional clinical data warehouse to the assessment of adverse drug reactions (ADRs). Evaluation of aminoglycoside and cephalosporin associated nephrotoxicity. Methods of Information in Medicine 46(5): 516-522, 2007

Mining adverse drug reactions from online healthcare forums using hidden Markov model. Bmc Medical Informatics and Decision Making 14: 91, 2014

Propensity score-adjusted three-component mixture model for drug-drug interaction data mining in FDA Adverse Event Reporting System. References 39(7): 996-1010, 2020