Te Whatu Ora exploring AI for clinical coding

NEWS - eHealthNews.nz editor Rebecca McBeth

Te Whatu Ora is planning to pilot the use of Artificial Intelligence (AI) for clinical coding of hospital admissions.

A Registration of Interest (ROI) says AI could help improve the speed and accuracy of coding, which is largely done manually.

The clinical notes from all inpatient and same day patients discharged from public hospitals are clinically coded and recorded in each hospital’s patient management system (PMS).

Clinically coded summaries of these discharges are forwarded to National Collections where the information is loaded into the National Minimum Data Set (NMDS).

This work supports service planning, research and policy development.

The ROI says clinical codes are currently identified and entered manually by individual teams nationwide, who work independently with no common worklist.

You’ve read this article for free, but good journalism takes time and resource to produce. Please consider supporting eHealthNews by becoming a member of HiNZ, for just $17 a month.

Most hospitals code from paper or scanned records as well as some digital systems.

Te Whatu Ora wants to pilot an AI assisted solution to “understand the current state of using AI and digital solutions to support the model of clinical coding and understand how this affects a potential future state so that AI assisted coding can be enabled”, the ROI says.

It says an AI assisted solution could improve the efficiency, accuracy and quality of clinical coding. By using large volumes of clinical data, AI could identify new patterns or anomalies that may not be easily detectable by humans.

It would also create a single worklist, in order to share and allocate work across different locations, and allow more robust benchmarking between areas, the ROI says.

To comment on or discuss this news story, go to the eHealthNews category on the HiNZ eHealth Forum

Read more Analytics news

Return to eHealthNews.nz home page