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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Clinicians may rely on medical coding systems such as InternationalClassification of Diseases (ICD) to identify patients with diseases fromElectronic Health Records (EHRs). However, due to the lack of detail andspecificity as well as a probability of miscoding, recent studies suggest theICD codes often cannot characterise patients accurately for specific diseasesin real clinical practice, and as a result, using them to find patients forstudies or trials can result in high failure rates and missing out on uncodedpatients. Manual inspection of all patients at scale is not feasible as it ishighly costly and slow.  This paper proposes a scalable workflow which leverages both structured dataand unstructured textual notes from EHRs with techniques including NLP, AutoMLand Clinician-in-the-Loop mechanism to build machine learning classifiers toidentify patients at scale with given diseases, especially those who mightcurrently be miscoded or missed by ICD codes.  Case studies in the MIMIC-III dataset were conducted where the proposedworkflow demonstrates a higher classification performance in terms of F1 scorescompared to simply using ICD codes on gold testing subset to identify patientswith Ovarian Cancer (0.901 vs 0.814), Lung Cancer (0.859 vs 0.828), CancerCachexia (0.862 vs 0.650), and Lupus Nephritis (0.959 vs 0.855). Also, theproposed workflow that leverages unstructured notes consistently outperformsthe baseline that uses structured data only with an increase of F1 (OvarianCancer 0.901 vs 0.719, Lung Cancer 0.859 vs 0.787, Cancer Cachexia 0.862 vs0.838 and Lupus Nephritis 0.959 vs 0.785). Experiments on the large testing setalso demonstrate the proposed workflow can find more patients who are miscodedor missed by ICD codes. Moreover, interpretability studies are also conductedto clinically validate the top impact features of the classifiers.

A Scalable Workflow to Build Machine Learning Classifiers with Clinician-in-the-Loop to Identify Patients in Specific Diseases