Numerous data mining models have been proposed to construct computer-aided medical expert systems. Bayesian network classifiers (BNCs) are more distinct and understandable than other models. To graphically describe the dependency relationships among clinical variables for thyroid disease diagnosis and ensure the rationality of the diagnosis results, the proposed k-dependence causal forest (KCF) model generates a series of submodels in the framework of maximum spanning tree (MST) and demonstrates stronger dependence representation. Friedman test on 12 UCI datasets shows that KCF has classification accuracy advantage over the other state-of-the-art BNCs, such as Naive Bayes, tree augmented Naive Bayes, and k-dependence Bayesian classifier. Our extensive experimental comparison on 4 medical datasets also proves the feasibility and effectiveness of KCF in terms of sensitivity and specificity.
Gait retraining to reduce knee loading has been proposed as a conservative treatment option for early-stage knee osteoarthritis. Mounting evidence suggests that a subject-specific approach may be most effective for ensuring consistent knee loading reductions across all individuals within a population. However, it is currently unclear how to determine the required gait modification dosage selection type and amount to both reduce knee loading and satisfy individual preferences. To overcome this challenge, we introduce a novel, mapping-based dosage selection approach to systematically determine multi-parameter gait modifications to reduce knee loading while maintaining individual user preference. In this approach, individuals first explore different dosages of multi-parameter gait modifications, and then a resulting visual map is displayed with a subject-specific dosage selection zone for the target knee loading reduction. Subjects then self-select a preferred gait within their dosage selection zone. To evaluate the feasibility of this approach, fifteen healthy subjects and one knee OA patient performed walking trials on a treadmill involving various dosages of gait modifications to foot progression angle and step width. Subjects quickly selected the subject-specific gait modifications via mapping-based dosage selection during a single 6 min trial, which reduced the knee adduction moment by an average of 14.2%. Resulting subject-specific gait modifications varied, with 6 subjects selecting only toe-in, 5 subjects selecting both toe-in and increased step width, 2 subjects selecting only toe-out, 1 subject selecting both toe-out and increased step width and 1 subject selecting only increased step width. Average perceived exertion was "fairly light" (index was 10.5±2.2). The knee OA patient selected only toe-in and reduced the knee adduction moment by 12.8%. The presented mapping-based dosage selection approach could provide a systematic and practical means to determine subject-specific gait modifications while maintaining individual preferences.
In the past few decades, a large number of data mining algorithms have been proposed to assist in the practical medical diagnosis. This paper proposes a novel algorithm, k-dependence causal forest (KCF) based on Bayesian network. The experiments conducted on the thyroid disease data set suggest the KCF model always has lower 0-1 loss and contains more conditional mutual information, which means the KCF model is suitable to assist in thyroid disease diagnosis and treatment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.