English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Each year there are nearly 57 million deaths around the world, with over 2.7million in the United States. Timely, accurate and complete death reporting iscritical in public health, as institutions and government agencies rely ondeath reports to analyze vital statistics and to formulate responses tocommunicable diseases. Inaccurate death reporting may result in potentialmisdirection of public health policies. Determining the causes of death is,nevertheless, challenging even for experienced physicians. To facilitatephysicians in accurately reporting causes of death, we present an advanced AIapproach to determine a chronically ordered sequence of clinical conditionsthat lead to death, based on decedent's last hospital discharge record. Thesequence of clinical codes on the death report is named as causal chain ofdeath, coded in the tenth revision of International Statistical Classificationof Diseases (ICD-10); in line with the ICD-9-CM Official Guidelines for Codingand Reporting, the priority-ordered clinical conditions on the discharge recordare coded in ICD-9. We identify three challenges in proposing the causal chainof death: two versions of coding system in clinical codes, medical domainknowledge conflict, and data interoperability. To overcome the first challengein this sequence-to-sequence problem, we apply neural machine translationmodels to generate target sequence. Along with three accuracy metrics, weevaluate the quality of generated sequences with the BLEU (BiLingual EvaluationUnderstudy) score and achieve 16.04 out of 100. To address the secondchallenge, we incorporate expert-verified medical domain knowledge asconstraint in generating output sequence to exclude infeasible causal chains.Lastly, we demonstrate the usability of our work in a Fast HealthcareInteroperability Resources (FHIR) interface to address the third challenge.

Public Health Informatics: Proposing Causal Sequence of Death Using Neural Machine Translation