Optimising the paradigms of human AI collaborative clinical coding

Automated clinical coding (ACC) has emerged as a promising alternative to manual coding. This study proposes a novel human-in-the-loop (HITL) framework, CliniCoCo. Using deep learning capacities, CliniCoCo focuses on how such ACC systems and human coders can work effectively and efficiently together in real-world settings. Specifically, it implements a series of collaborative strategies at annotation, training and user interaction stages. Extensive experiments are conducted using real-world EMR datasets from Chinese hospitals. With automatically optimised annotation workloads, the model can achieve F1 scores around 0.80-0.84. For an EMR with 30% mistaken codes, CliniCoCo can suggest halving the annotations from 3000 admissions with an ignorable 0.01 F1 decrease. In human evaluations, compared to manual coding, CliniCoCo reduces coding time by 40% on average and significantly improves the correction rates on EMR mistakes (e.g., three times better on missing codes). Senior professional coders' performances can be boosted to more than 0.93 F1 score from 0.72.

Authors

Institutions

Publication Details

Journal
npj Digital Medicine
Published
2024-12-19
DOI
https://doi.org/10.1038/s41746-024-01363-7
Citations
3
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
1.04

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Optimising the paradigms of human AI collaborative clinical coding

Xiangling Fu, Ji Wu, Xien Liu, Kaiyin Zhou et al.
3 citations
npj Digital Medicine
Machine Learning in Healthcare
1.04
article

Optimising the paradigms of human AI collaborative clinical coding

Xiangling Fu, Ji Wu, Xien Liu, Kaiyin Zhou, Honghan Wu, Jinge Wu, Yunsoo Kim, Yue Gao, Yuepeng Chen, Minghao Wang, Miao Li
article en
3 citations

Abstract

Automated clinical coding (ACC) has emerged as a promising alternative to manual coding. This study proposes a novel human-in-the-loop (HITL) framework, CliniCoCo. Using deep learning capacities, CliniCoCo focuses on how such ACC systems and human coders can work effectively and efficiently together in real-world settings. Specifically, it implements a series of collaborative strategies at annotation, training and user interaction stages. Extensive experiments are conducted using real-world EMR datasets from Chinese hospitals. With automatically optimised annotation workloads, the model can achieve F1 scores around 0.80-0.84. For an EMR with 30% mistaken codes, CliniCoCo can suggest halving the annotations from 3000 admissions with an ignorable 0.01 F1 decrease. In human evaluations, compared to manual coding, CliniCoCo reduces coding time by 40% on average and significantly improves the correction rates on EMR mistakes (e.g., three times better on missing codes). Senior professional coders' performances can be boosted to more than 0.93 F1 score from 0.72.

npj Digital MedicineVol. 7(1)
Beijing University of Posts and Telecommunications (CN), Shanghai Key Laboratory of Trustworthy Computing (CN), Health Data Research UK (GB), University College London (GB), University of Glasgow (GB), Tsinghua University (CN)
Canadian Institute of Steel Construction, National Institute for Health and Care Research, Department of Health and Social Care, National Natural Science Foundation of China, Tsinghua University, Shanghai Jiao Tong University, National Science and Technology Major Project, Medical Research Council, School of Medicine, Shanghai Jiao Tong University, Medical Research Foundation
Openalex Percentile: Top 18%
Machine Learning in Healthcare
1.04
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.