Application of counterfactual explanation framework in predictive models for treatment outcomes in acute exacerbation of chronic obstractive pulmonary disease patients

YUAN Yiwei; HE Hangzhi; HU Xiaojuan; DONG Tao; JIN Jie; ZHAO Hui; ZHANG Yanbo

doi:10.16462/j.cnki.zhjbkz.2025.04.014

Volume 29 Issue 4

Apr. 2025

Turn off MathJax

Article Contents

Article Navigation > CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION > 2025 > 29(4): 461-467

YUAN Yiwei, HE Hangzhi, HU Xiaojuan, DONG Tao, JIN Jie, ZHAO Hui, ZHANG Yanbo. Application of counterfactual explanation framework in predictive models for treatment outcomes in acute exacerbation of chronic obstractive pulmonary disease patients[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(4): 461-467. doi: 10.16462/j.cnki.zhjbkz.2025.04.014

Citation:

YUAN Yiwei, HE Hangzhi, HU Xiaojuan, DONG Tao, JIN Jie, ZHAO Hui, ZHANG Yanbo. Application of counterfactual explanation framework in predictive models for treatment outcomes in acute exacerbation of chronic obstractive pulmonary disease patients[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(4): 461-467. doi: 10.16462/j.cnki.zhjbkz.2025.04.014

Citation:

YUAN Yiwei, HE Hangzhi, HU Xiaojuan, DONG Tao, JIN Jie, ZHAO Hui, ZHANG Yanbo. Application of counterfactual explanation framework in predictive models for treatment outcomes in acute exacerbation of chronic obstractive pulmonary disease patients[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(4): 461-467. doi: 10.16462/j.cnki.zhjbkz.2025.04.014

PDF( 7331 KB)

Application of counterfactual explanation framework in predictive models for treatment outcomes in acute exacerbation of chronic obstractive pulmonary disease patients

doi: 10.16462/j.cnki.zhjbkz.2025.04.014

YUAN Yiwei¹,
HE Hangzhi¹,
HU Xiaojuan³,
DONG Tao¹,
JIN Jie¹,
ZHAO Hui^{2
,
,},
ZHANG Yanbo^{1
,
,}

1.
Department of Biostatistics, School of Public Health, Shanxi Medical University, Shanxi Provincial Key Laboratory of Major Diseases Risk Assessment, Taiyuan 030001, China
2.
Department of Cardiology, Pulmonary and Critical Care Medicine, Second Hospital, Shanxi Medical University, Taiyuan 030001, China
3.
Department of Medical Information Technology, Shanxi Medical University, Taiyuan 030001, China

Funds:

National Natural Science Foundation of China 82173631

Special Project of Science and Technology Cooperation and Exchange of Shanxi Province 202204041101031

More Information

Corresponding author: ZHAO Hui E-mail: hui_zhao@sxmu.edu.cn; ZHANG Yanbo E-mail: sxmuzyb@126.com
Received Date: 2024-06-25
Rev Recd Date: 2024-09-23
Publish Date: 2025-04-10

Abstract

Abstract

Objective For inpatients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD), a machine learning (ML) model combined with Counterfactual Explanation Framework was developed to accurately predict treatment outcomes and provide clinical decision support. Methods A total of 3 046 patients hospitalized for AECOPD at the Second Hospital of Shanxi Medical University from 2012 to 2020 were selected. The outcome variable was defined as whether the patient recovered and was discharged within the median length of hospitalization. Five ML models were constructed and compared for performance. The optimal model was then explained using counterfactual framework, which provided actionable intervention plans. Results The categorical boosting (CatBoost) model exhibited the best overall performance, with area under the receiver operating characteristic curve (AUC) of 0.748, accuracy of 68.4%, precision of 70.6%, recall of 69.1%, F1 score of 69.8%, and Brier score of 20.4%. The calibration curve was close to the diagonal. The counterfactual explanation framework visually elucidated the prognostic mechanisms in patients, with the generated actionable intervention strategies providing clinicians with decision support to optimize hospitalization efficacy for AECOPD cases. Conclusions Using only routine electronic medical record data, the CatBoost-based prediction model predicts hospitalization outcomes for AECOPD patients. By incorporating the counterfactual explanation framework, personalized intervention plans can be provided for clinicians, offering reliable support for clinical decision-making.
- Acute exacerbation of chronic obstructive pulmonary disease,
- Machine learning,
- Predictive model,
- Model interpretability,
- Counterfactual explanation,

FullText(HTML)

References(15)

References

[1]	中华医学会, 中华医学会杂志社, 中华医学会全科医学分会, 等. 中国慢性阻塞性肺疾病基层诊疗与管理指南(2024年)[J]. 中华全科医师杂志, 2024, 23(6): 600-624. DOI: 10.3760/cma.j.cn114798-20240326-00174. Chinese Medical Association, Chinese Medical Association Publishing House, Chinese Society of General Practice, et al. Chinese guideline for management of chronic obstructive pulmonary disease in primary care (2024)[J]. Chin J Gen Pract, 2024, 23(6): 600-624. DOI: 10.3760/cma.j.cn114798-20240326-00174.
[2]	Venkatesan P. GOLD COPD report: 2024 update[J]. Lancet Respir Med, 2024, 12(1): 15-16. DOI: 10.1016/s2213-2600(23)00461-7.
[3]	Kundu S. AI in medicine must be explainable[J]. Nat Med, 2021, 27(8): 1328. DOI: 10.1038/s41591-021-01461-z.
[4]	Stiglic G, Kocbek P, Fijacko N, et al. Interpretability of machine learning-based prediction models in healthcare[J]. Data Mining And Knowledge Discover, 2020, 10(5): e1379. DOI: 10.1002/widm.1379.
[5]	Ushida K, Shimizu A, Hori S, et al. Hospital frailty risk score predicts outcomes in chronic obstructive pulmonary disease exacerbations[J]. Arch Gerontol Geriatr, 2022, 100: 104658. DOI: 10.1016/j.archger.2022.104658.
[6]	Hilton CB, Milinovich A, Felix C, et al. Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence[J]. NPJ Digital Medicine, 2020, 3: 51. DOI: 10.1038/s41746-020-0249-z.
[7]	李少凡, 李莉芳, 何航帜, 等. 慢性阻塞性肺疾病急性加重住院患者出院状态预测研究[J]. 中华疾病控制杂志, 2024, 28(6): 685-690. DOI: 10.16462/j.cnki.zhjbkz.2024.06.011. Li SF, Li LF, He HZ, et al. Predictive study on discharge status of hospitalized patients with acute exacerbation of chronic obstructive pulmonary disease[J]. Chin J Dis Control Prev, 2024, 28(6): 685-690. DOI: 10.16462/j.cnki.zhjbkz.2024.06.011.
[8]	Bloom CI, Ricciardi F, Smeeth L, et al. Predicting COPD 1-year mortality using prognostic predictors routinely measured in primary care[J]. BMC Med, 2021, 17(1): 73. DOI: 10.3310/pgfar09130.
[9]	Bonomo M, Hermsen MG, Kaskovich S, et al. Using machine learning to predict likelihood and cause of readmission after hospitalization for chronic obstructive pulmonary disease exacerbation[J]. Int J Chron Obstruc Pulmon Dis, 2022, 17: 2701-2709. DOI: 10.2147/COPD.S379700.
[10]	Kor CT, Li YR, Lin PR, et al. Explainable machine learning model for predicting first-time acute exacerbation in patients with chronic obstructive pulmonary disease[J]. J Pers Med, 2022, 12(2): 228. DOI: 10.3390/jpm12020228.
[11]	Charlson ME, Carrozzino D, Guidi J, et al. Charlson comorbidity index: a critical review of clinimetric properties[J]. Psychother Psychosom, 2022, 91(1): 8-35. DOI: 10.1159/000521288.
[12]	慢性阻塞性肺疾病急性加重诊治专家组. 慢性阻塞性肺疾病急性加重诊治中国专家共识(2023年修订版)[J]. 国际呼吸杂志, 2023, 43(2): 132-149. DOI: 10.3760/cma.j.cn131368-20221123-01066. Expert Group for the Diagnosis and Treatment of Acute Exacerbations of Chronic Obstructive Pulmonary Disease. Chinese expert consensus on the diagnosis and treatment of acute exacerbations of chronic obstructive pulmonary disease(revised version 2023)[J]. Int J Respir, 2023, 43(2): 132-149. DOI: 10.3760/cma.j.cn131368-20221123-01066.
[13]	Marcinkevičs R, Vogt JE. Interpretable and explainable machine learning: a methods-centric overview with concrete examples[J]. Data Mining And Knowledge Discover, 2023, 13(3): e1493. DOI: 10.1002/widm.1493.
[14]	Zeng SY, Arjomandi M, Luo G. Automatically explaining machine learning predictions on severe chronic obstructive pulmonary disease exacerbations: retrospective cohort study[J]. JMIR Med Inform, 2022, 10(2): e33043. DOI: 10.2196/33043.
[15]	Mothilal KR, Sharma A, Tan C. Explaining machine learning classifiers through diverse counterfactual explanations[C]. Microsoft Research India; Microsoft Research India; University of Colorado Boulder, 2020.