Diagnosis of Poisoning Using Probabilistic Logic Networks

dc.contributor.author Chary, Michael
dc.contributor.author Boyer, Edward
dc.contributor.author Burns, Michele
dc.date.accessioned 2020-12-24T19:44:14Z
dc.date.available 2020-12-24T19:44:14Z
dc.date.issued 2021-01-05
dc.description.abstract Medical toxicology is the clinical specialty that treats the toxic effects of substances, be it an overdose, a medication error, or a scorpion sting. The volume of toxicological knowledge has, as with other medical specialties, outstripped the ability of the individual clinician to master and stay current with it. The application of machine learning techniques to medical toxicology is challenging because initial treatment decisions are often based on a few pieces of textual data and rely heavily on prior knowledge. Moreover, ML techniques often do not represent knowledge in a way that is transparent for the physician, raising barriers to usability. Rule-based systems and decision tree learning are more transparent approaches, but often generalize poorly and require expert curation to implement and maintain. Here, we construct a probabilistic logic network to represent a portion of the knowledge base of a medical toxicologist. Our approach transparently mimics the knowledge representation and clinical decision-making of practicing clinicians. The software, dubbed \emph{Tak}, performs comparably to humans on straightforward cases and intermediate difficulty cases, but is outperformed by humans on challenging clinical cases. \emph{Tak} outperforms a decision tree classifier at all levels of difficulty. Probabilistic logic provides one form of explainable artificial intelligence that may be more acceptable for use in healthcare, if it can achieve acceptable levels of performance.
dc.format.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2021.434
dc.identifier.isbn 978-0-9981331-4-0
dc.identifier.uri http://hdl.handle.net/10125/71050
dc.language.iso English
dc.relation.ispartof Proceedings of the 54th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Implementation of Body Sensor Systems in Healthcare Practice
dc.subject explainable artificial intelligence
dc.subject healthcare
dc.subject probabilistic logic networks
dc.title Diagnosis of Poisoning Using Probabilistic Logic Networks
prism.startingpage 3573
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
413.7 KB
Adobe Portable Document Format