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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

From medical charts to national census, healthcare has traditionally operatedunder a paper-based paradigm. However, the past decade has marked a long andarduous transformation bringing healthcare into the digital age. Ranging fromelectronic health records, to digitized imaging and laboratory reports, topublic health datasets, today, healthcare now generates an incredible amount ofdigital information. Such a wealth of data presents an exciting opportunity forintegrated machine learning solutions to address problems across multiplefacets of healthcare practice and administration. Unfortunately, the ability toderive accurate and informative insights requires more than the ability toexecute machine learning models. Rather, a deeper understanding of the data onwhich the models are run is imperative for their success. While a significanteffort has been undertaken to develop models able to process the volume of dataobtained during the analysis of millions of digitalized patient records, it isimportant to remember that volume represents only one aspect of the data. Infact, drawing on data from an increasingly diverse set of sources, healthcaredata presents an incredibly complex set of attributes that must be accountedfor throughout the machine learning pipeline. This chapter focuses onhighlighting such challenges, and is broken down into three distinctcomponents, each representing a phase of the pipeline. We begin with attributesof the data accounted for during preprocessing, then move to considerationsduring model building, and end with challenges to the interpretation of modeloutput. For each component, we present a discussion around data as it relatesto the healthcare domain and offer insight into the challenges each may imposeon the efficiency of machine learning techniques.

Beyond Volume: The Impact of Complex Healthcare Data on the Machine Learning Pipeline