Rapid triage for ischemic stroke: A machine learning-driven approach in the context of predictive, preventive and personalised medicine

Authors

Yulu Zheng, Edith Cowan UniversityFollow
Zheng Guo, Edith Cowan UniversityFollow
Yanbo Zhang
Jianjing Shang
Leilei Yu
Ping Fu
Yizhi Liu
Xingang Li, Edith Cowan UniversityFollow
Hao Wang
Ling Ren
Wei Zhang
Haifeng Hou, Edith Cowan UniversityFollow
Xuerui Tan
Wei Wang, Edith Cowan UniversityFollow
Global Health Epidemiology Reference Group (GHERG)

Author Identifier

Zheng Guo

https://orcid.org/0000-0003-2105-4537

Xingang Li

https://orcid.org/0000-0003-0252-154X

Wei Wang

https://orcid.org/0000-0002-1430-1360

Document Type

Journal Article

Publication Title

EPMA Journal

Publisher

Springer

School

School of Medical and Health Sciences / Centre for Precision Health

RAS ID

44424

Funders

Funding information : https://doi.org/10.1007/s13167-022-00283-4

Grant Number

NHMRC Number : 1112767

Grant Link

http://purl.org/au-research/grants/nhmrc/1112767

Comments

Zheng, Y., Guo, Z., Zhang, Y., Shang, J., Yu, L., Fu, P., . . . Wang, W. (2022). Rapid triage for ischemic stroke: A machine learning-driven approach in the context of predictive, preventive and personalised medicine. EPMA Journal, 14(2), 285-298. https://doi.org/10.1007/s13167-022-00283-4

Abstract

Background

Recognising the early signs of ischemic stroke (IS) in emergency settings has been challenging. Machine learning (ML), a robust tool for predictive, preventive and personalised medicine (PPPM/3PM), presents a possible solution for this issue and produces accurate predictions for real-time data processing.

Methods

This investigation evaluated 4999 IS patients among a total of 10,476 adults included in the initial dataset, and 1076 IS subjects among 3935 participants in the external validation dataset. Six ML-based models for the prediction of IS were trained on the initial dataset of 10,476 participants (split participants into a training set [80%] and an internal validation set [20%]). Selected clinical laboratory features routinely assessed at admission were used to inform the models. Model performance was mainly evaluated by the area under the receiver operating characteristic (AUC) curve. Additional techniques—permutation feature importance (PFI), local interpretable model-agnostic explanations (LIME), and SHapley Additive exPlanations (SHAP)—were applied for explaining the black-box ML models.

Results

Fifteen routine haematological and biochemical features were selected to establish ML-based models for the prediction of IS. The XGBoost-based model achieved the highest predictive performance, reaching AUCs of 0.91 (0.90–0.92) and 0.92 (0.91–0.93) in the internal and external datasets respectively. PFI globally revealed that demographic feature age, routine haematological parameters, haemoglobin and neutrophil count, and biochemical analytes total protein and high-density lipoprotein cholesterol were more influential on the model’s prediction. LIME and SHAP showed similar local feature attribution explanations.

Conclusion

In the context of PPPM/3PM, we used the selected predictors obtained from the results of common blood tests to develop and validate ML-based models for the diagnosis of IS. The XGBoost-based model offers the most accurate prediction. By incorporating the individualised patient profile, this prediction tool is simple and quick to administer. This is promising to support subjective decision making in resource-limited settings or primary care, thereby shortening the time window for the treatment, and improving outcomes after IS.

DOI

10.1007/s13167-022-00283-4

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.