Assisted Knowledge Discovery for the Maintenance of Clinical Guidelines

Abstract

BackgroundImproving antibiotic prescribing practices is an important public-health priority given the widespread antimicrobial resistance. Establishing clinical practice guidelines is crucial to this effort, but their development is a complex task and their quality is directly related to the methodology and source of knowledge used.ObjectiveWe present the design and the evaluation of a tool (KART) that aims to facilitate the creation and maintenance of clinical practice guidelines based on information retrieval techniques.MethodsKART consists of three main modules 1) a literature-based medical knowledge extraction module, which is built upon a specialized question-answering engine; 2) a module to normalize clinical recommendations based on automatic text categorizers; and 3) a module to manage clinical knowledge, which formalizes and stores clinical recommendations for further use. The evaluation of the usability and utility of KART followed the methodology of the cognitive walkthrough.ResultsKART was designed and implemented as a standalone web application. The quantitative evaluation of the medical knowledge extraction module showed that 53% of the clinical recommendations generated by KART are consistent with existing clinical guidelines. The user-based evaluation confirmed this result by showing that KART was able to find a relevant antibiotic for half of the clinical scenarios tested. The automatic normalization of the recommendation produced mixed results among end-users.ConclusionsWe have developed an innovative approach for the process of clinical guidelines development and maintenance in a context where available knowledge is increasing at a rate that cannot be sustained by humans. In contrast to existing knowledge authoring tools, KART not only provides assistance to normalize, formalize and store clinical recommendations, but also aims to facilitate knowledge building.

UPCLASS: a Deep Learning-based Classifier for UniProtKB Entry Publications

“…The analyses of the classification precision according to the size (or type) of the document shows that there is no correlation between these two dimensions. While it might be counter-intuitive, several works have demonstrated that for classification tasks, the performance of abstracts are at least equivalent to full texts, when not better [29]. Yet, it could be relevant to explore the use of different classifiers for abstracts and for full texts.…”

American Association of Clinical Endocrinologists and American College of Endocrinology Protocol for Standardized Production of Clinical Practice Guidelines, Algorithms, and Checklists – 2017 Update

“…environment will also need to change, with an infrastructure that supports CPG use (72), facilitates the development of consistent G4GAC, and accesses more electronic and computerized vehicles. Several innovations have been designed to automate continuous CPG frameworks, composed of decision support systems, a central patient database (e.g., EHR), a central medical knowledge base (e.g., peer-reviewed published literature), and an engine applying the knowledge base to the database (83)(84)(85)(86)(87). Diagnostic errors can result from a variety of cognitive issues and though managed superficially with CC, have been addressed with more advanced computational methods such as a semantic web framework composed of case-based fuzzy cognitive maps and Bayesian belief networks (88).…”

“…Computer-interpretable algorithm (96,97) Mobile device (98,99) Patient health records (83)(84)(85)(86)(87) Web-based (100)…”

What Do Doctors Need for Effective Adoption and Integration of Clinical Guidelines into Daily Practice?

“…Some other software tools focus on capturing the knowledge required to create CG recommendations [18]. Most of such approaches are markup-based tools such as GMT [19], DELT/A [ [20], Tallis [21], Stepper [22], GEM Cutter [23], and Uruz [24], [25].…”

“…Basically, medical processes are modeled using Business Process Management implementation (jBPM) and, given clinical data, a RETE-based rule engine is used for alerts and auditing. Still, some of the last trends in CG is the collaborative encoding [30], and the definition of a methodology and tools for the maintenance of CG [18].…”