Optimising the paradigms of human AI collaborative clinical coding. Gao, Y., Chen, Y., Wang, M., Wu, J., Kim, Y., Zhou, K., Li, M., Liu, X., Fu, X., Wu, J., & Wu, H. npj Digital Medicine, 7(1):1–15, December, 2024. Publisher: Nature Publishing Group
Optimising the paradigms of human AI collaborative clinical coding [link]Paper  doi  abstract   bibtex   
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.
@article{gao_optimising_2024,
	title = {Optimising the paradigms of human {AI} collaborative clinical coding},
	volume = {7},
	copyright = {2024 The Author(s)},
	issn = {2398-6352},
	url = {https://www.nature.com/articles/s41746-024-01363-7},
	doi = {10.1038/s41746-024-01363-7},
	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.},
	language = {en},
	number = {1},
	urldate = {2025-02-12},
	journal = {npj Digital Medicine},
	author = {Gao, Yue and Chen, Yuepeng and Wang, Minghao and Wu, Jinge and Kim, Yunsoo and Zhou, Kaiyin and Li, Miao and Liu, Xien and Fu, Xiangling and Wu, Ji and Wu, Honghan},
	month = dec,
	year = {2024},
	note = {Publisher: Nature Publishing Group},
	keywords = {Health services, Information technology},
	pages = {1--15},
}

Downloads: 0