Trans AMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance using Antibiotic Administration Data

Simple item page
dc.contributor.authorMukunthan, T.
dc.contributor.authorWenwu, W.
dc.contributor.authorMichael, K.
dc.contributor.authorRoberto Lo, R.
dc.contributor.authorAnil, F.
dc.date.accessioned2023-12-28T06:31:12Z
dc.date.available2023-12-28T06:31:12Z
dc.date.issued2023
dc.description.abstractAntimicrobialResistance(AMR)isagrowingpublicandveterinaryhealthconcern,andthe abilitytoaccuratelypredictAMRfromantibioticsadministrationdataiscrucialforeffectivelytreatingand managinginfections.Whilegenomics-basedapproachescanprovidebetterresults,sequencing,assembling, andapplyingMachineLearning(ML)methodscantakeseveralhours.Therefore,alternativeapproachesare required.ThisstudyfocusedonusingMLforantimicrobialstewardshipbyutilisingdataextractedfrom hospitalelectronichealthrecords,whichcanbedoneinreal-time,anddevelopinganinterpretable1DTransformermodelforpredictingAMR.Amulti-baselineIntegratedGradientpipelinewasalsoincorporated tointerpretthemodel,andquantitativevalidationmetricswereintroducedtovalidatethemodel.The performanceoftheproposed1D-Transformermodelwasevaluatedusingadatasetofurinarytractinfection (UTI)patientswithfourantibiotics.Theproposed1D-Transformermodelachieved10%higherareaunder curve(AUC)inpredictingAMRandoutperformedtraditionalMLmodels.TheExplainableArtificial Intelligence(XAI)pipelinealsoprovidedinterpretableresults,identifyingthesignaturescontributingto thepredictions.Thiscouldbeusedasadecisionsupporttoolforpersonalisedtreatment,introducing AMR-awarefoodandmanagementofAMR,anditcouldalsobeusedtoidentifysignaturesfortargeted interventions.en_US
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/10004
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectTransformeren_US
dc.subjectMulti-drug AMRen_US
dc.subjectAntimicrobial stewardshipen_US
dc.subjectMissing labelsen_US
dc.subjectXAIen_US
dc.subjectMulti-label predictionen_US
dc.titleTrans AMR: An Interpretable Transformer Model for Accurate Prediction of Antimicrobial Resistance using Antibiotic Administration Dataen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
TransAMR_An_Interpretable_Transformer_Model_for_Accurate_Prediction_of_Antimicrobial_Resistance_Using_Antibiotic_Administration_Data.pdf
Size:
1.53 MB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Electrical & Electronic Engineering