Propensity Scoring for Comparison of Wound Care Treatments: A Case Study

propensity score methods;diabetic foot ulcers;matching methods;Applied Mathematics & Statistics

Fu, ChenqiNaiman, Daniel Q. ;

Johns Hopkins University

关键词: propensity score methods;    diabetic foot ulcers;    matching methods;    Applied Mathematics & Statistics;   

Others  :  https://jscholarship.library.jhu.edu/bitstream/handle/1774.2/58700/FU-THESIS-2017.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: JOHNS HOPKINS DSpace Repository

【 摘 要 】

Treatment effect modeling in an observational study is challenging. In an observational study, participants;; conditions in diverse treatment groups may differ from each other to a large extent, which can result in potential bias in an analysis aimed at the comparison of treatment effect. The propensity score method is a commonly employed approach to analyzing causal effects and eliminating confounding based on an observation study. In this paper, two models for modeling propensity scores are discussed and implemented. Once models have been arrived at, treated subjects and control ones are matched according to estimated propensity scores.These methods are illustrated for an important application, where the effectiveness of two possible treatments for Diabetic Foot Ulcers are compared. Here, treatment effectiveness is measured that whether the wound is closed within 12 weeks after the treatment. At last, we conclude that there is no significant difference in the effectiveness of two treatments.