Explainable decision support through the learning and visualization of preferences from a formal ontology of antibiotic treatments.

Journal of Biomedical Informatics
Jean-Baptiste LamyRosy Tsopra

Abstract

The aim of eXplainable Artificial Intelligence (XAI) is to design intelligent systems that can explain their predictions or recommendations to humans. Such systems are particularly desirable for therapeutic decision support, because physicians need to understand rcommendations to have confidence in their application and to adapt them if required, e.g. in case of patient contraindication. We propose here an explainable and visual approach for decision support in antibiotic treatment, based on an ontology. There were three steps to our method. We first generated a tabular dataset from the ontology, containing features defined on various domains and n-ary features. A preference model was then learned from patient profiles, antibiotic features and expert recommendations found in clinical practice guidelines. This model made the implicit rationale of the expert explicit, including the way in which missing data was treated. We then visualized the preference model and its application to all antibiotics available on the market for a given clinical situation, using rainbow boxes, a recently developed technique for set visualization. The resulting preference model had an error rate of 3.5% on the learning data, and 5.2% on test data (10-...Continue Reading

References

Sep 5, 2006·International Journal of Medical Informatics·Karin A Thursky, Michael Mahemoff
Sep 25, 2007·International Journal of Antimicrobial Agents·Leonard LeiboviciSteen Andreassen
Jan 13, 2010·Journal of the American Medical Informatics Association : JAMIA·Annette MoxeySallie-Anne Pearson
Sep 14, 2011·Journal of Biomedical Informatics·Elpiniki I PapageorgiouDirk Colaert
Sep 24, 2011·BMC Family Practice·Marjolein LugtenbergGert P Westert
Oct 18, 2011·Computer Methods and Programs in Biomedicine·Elpiniki I Papageorgiou
Oct 25, 2011·Journal of Biomedical Informatics·Tiffani J BrightSuzanne Bakken
Aug 16, 2014·Journal of the American Medical Informatics Association : JAMIA·Jakob HolstiegeDawid Pieper
Jun 19, 2016·International Journal of Medical Informatics·Melissa T BaysariJohanna I Westbrook
Mar 8, 2017·Clinical Microbiology and Infection : the Official Publication of the European Society of Clinical Microbiology and Infectious Diseases·T M RawsonA H Holmes
Mar 16, 2019·Artificial Intelligence in Medicine·Jean-Baptiste LamyBrigitte Séroussi
May 10, 2019·Journal of Biomedical Informatics·Bernardo Cánovas-SeguraFrancisco Palacios
Jun 11, 2019·IEEE Transactions on Visualization and Computer Graphics·Jean-Baptiste Lamy, Rosy Tsopra
Dec 22, 2019·BMC Family Practice·Jegatha Krishnakumar, Rosy Tsopra

❮ Previous
Next ❯

Citations

Jun 12, 2021·Journal of Medical Internet Research·Ronni MadarRosy Tsopra

❮ Previous
Next ❯

Related Concepts

Related Feeds

Allergy and Asthma

Allergy and asthma are inflammatory disorders that are triggered by the activation of an allergen-specific regulatory t cell. These t cells become activated when allergens are recognized by allergen-presenting cells. Here is the latest research on allergy and asthma.