Exploring data quality for machine learning-based disease risk predictions with electronic medical records_Chinese Journal of Evidence-Based Medicine

Authors：

DUAN Yifan , TANG Mingkun , SUN Haixia , HAO Jie , WANG Jiayang , ZHOU Jiayin , LI Jiao ,  QIAN Qing

Institute of Medical Information, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100020, P. R. China;

Corresponding?author：

QIAN Qing, Email: qian.qing@imicams.ac.cn

Keywords：

Disease risk prediction; Data quality; Demand models; Electronic medical records

DOI：

10.7507/1672-2531.202301076

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To construct a demand model for electronic medical record (EMR) data quality in regards to the lifecycle in machine learning (ML)-based disease risk prediction, to guide the implementation of EMR data quality assessment. Methods Referring to the lifecycle in ML-based predictive model, we explored the demand for EMR data quality. First, we summarized the key data activities involved in each task on predicting disease risk with ML through a literature review. Second, we mapped the data activities in each task to the associated requirements. Finally, we clustered those requirements into four dimensions. Results We constructed a three-layer structured ring to represent the demand model for EMR data quality in ML-based disease risk prediction research. The inner layer shows the seven main tasks in ML-based predictive models: data collection, data preprocessing, feature representation, feature selection and extraction, model training, model evaluation and optimization, and model deployment. The middle layer is the key data activities in each task; and the outer layer represents four dimensions of data quality requirements: operability, completeness, accuracy, and timeliness. Conclusion The proposed model can guide real-world EMR data governance, improve its quality management, and promote the generation of real-world evidence.

Citation： DUAN Yifan, TANG Mingkun, SUN Haixia, HAO Jie, WANG Jiayang, ZHOU Jiayin, LI Jiao, QIAN Qing. Exploring data quality for machine learning-based disease risk predictions with electronic medical records. Chinese Journal of Evidence-Based Medicine, 2023, 23(9): 1072-1080. doi: 10.7507/1672-2531.202301076 Copy

1.	Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol, 2017, 2(4): 230-243.
2.	谷鴻秋, 王俊峰, 章仲恒, 等. 臨床預測模型: 模型的建立. 中國循證心血管醫學雜志, 2019, 11(1): 14-16, 23.
3.	王士泉, 蘇明亮, 高東平. 基于大數據的青光眼眼壓實時預警監測系統研究. 中國數字醫學, 2018, 13(5): 5-7, 15.
4.	徐怡. 復雜疾病的風險預測模型研究及遺傳變異數據庫挖掘. 杭州: 浙江大學, 2019.
5.	李言生, 龔后武, 栗翊超, 等. 基于真實世界數據的疾病風險預測研究. 醫學信息, 2020, 33(23): 17-19.
6.	Rudrapatna VA, Butte AJ. Opportunities and challenges in using real-world data for health care. J Clin Invest, 2020, 130(2): 565-574.
7.	Johnson SG, Speedie S, Simon G, et al. A data quality ontology for the secondary use of EHR data. AMIA Annu Symp Proc, 2015, 5: 1937-1946.
8.	余煒倫. 電子病歷中的數據質量與病人群組可視分析. 杭州: 浙江大學, 2020.
9.	楊鑫禹, 牟冬梅, 彭浩, 等. 基于數據特征的電子病歷數據驅動臨床決策模型研究. 情報理論與實踐, 2022, 45(5): 181-188.
10.	Ni K, Chu H, Zeng L, et al. Barriers and facilitators to data quality of electronic health records used for clinical research in China: a qualitative study. BMJ Open, 2019, 9(7): e029314.
11.	田琪, 陳雅妮, 韓喆僖, 等. 臨床數據質量評估指標研究. 醫學信息學雜志, 2020, 41(10): 9-17.
12.	Weiskopf NG, Bakken S, Hripcsak G, et al. A data quality assessment guideline for electronic health record data reuse. EGEMS (Wash DC), 2017, 5(1): 14.
13.	熊興江. 醫療大數據質量評價指標體系構建研究. 武漢: 華中科技大學, 2019.
14.	Spjuth O, Frid J, Hellander A. The machine learning life cycle and the cloud: implications for drug discovery. Expert Opin Drug Discov, 2021, 16(9): 1071-1079.
15.	Eric H. Machine learning life cycle. 2021.
16.	Srcmini. 機器學習開發的生命周期. 2021.
17.	國家藥品監督管理局醫療器械技術審評中心. 人工智能醫療器械注冊審查指導原則. 2022.
18.	國家藥品監督管理局. 深度學習輔助決策醫療器械軟件審評要點. 2022.
19.	昝松亭. 移動醫療大數據的數據質量評估模型研究. 北京: 北京郵電大學, 2019.
20.	江心怡, 陳敏. 電子病歷數據治理方法的研究. 中國醫院管理, 2020, 40(8): 68-70.
21.	Sun Y, Lu T, Gu N. A method of electronic health data quality assessment: enabling data provenance. Wellington: 2017 IEEE 21st international conference on computer supported cooperative work in design (CSCWD), 2017: 233-238.
22.	Weiskopf NG, Weng C. Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research. J Am Med Inform Assoc, 2013, 20(1): 144-151.
23.	Kahn MG, Callahan TJ, Barnard J, et al. A harmonized data quality assessment terminology and framework for the secondary use of electronic health record data. EGEMS (Wash DC), 2016, 4(1): 1244.
24.	胡丹青. 基于電子病歷的急性冠脈綜合征患者主要不良心血管事件預測. 杭州: 浙江大學, 2017.
25.	Le S, Allen A, Calvert J, et al. Convolutional neural network model for intensive care unit acute kidney injury prediction. Kidney Int Rep, 2021, 6(5): 1289-1298.
26.	李冬冬. 腦卒中電子病歷文本數據結構化方法研究及應用. 上海: 中國人民解放軍海軍軍醫大學, 2021.
27.	Dinh A, Miertschin S, Young A, et al. A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC Med Inform Decis Mak, 2019, 19(1): 211.
28.	Tseng PY, Chen YT, Wang CH, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care, 2020, 24(1): 478.
29.	He J, Hu Y, Zhang X, et al. Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records. JAMIA Open, 2019, 2(1): 115-122.
30.	杜珍珍. 基于電子病歷的機器學習算法在心血管疾病預測方面的應用. 武漢: 武漢郵電科學研究院, 2020.
31.	Li Y, Chen X, Shen Z, et al. Prediction models for acute kidney injury in patients with gastrointestinal cancers: a real-world study based on Bayesian networks. Ren Fail, 2020, 42(1): 869-876.
32.	肖文翔. 基于電子病歷分析的糖尿病患病風險數據挖掘方法研究. 青島: 青島大學, 2016.
33.	吳風浪, 周銘, 耿鵬. 醫院電子病歷的多維數據分析研究. 中國醫學裝備, 2019, 16(9): 132-135.
34.	Wang H, Tan X, Huang Z, et al. Mining incomplete clinical data for the early assessment of Kawasaki disease based on feature clustering and convolutional neural networks. Artif Intell Med, 2020, 105: 101859.
35.	王萍. 基于電子病歷數據的疾病預測模型構建研究. 長春: 吉林大學, 2017.
36.	楊玉潔. 基于醫學大數據的心血管慢病風險精準建模. 深圳: 中國科學院大學(中國科學院深圳先進技術研究院), 2021.
37.	Chan L, Nadkarni GN, Fleming F, et al. Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease. Diabetologia, 2021, 64(7): 1504-1515.
38.	陳德華, 周東陽, 樂嘉錦. 基于深度學習的甲狀腺結節良惡性預測方法研究. 微型機與應用, 2017, 36(12): 13-15.
39.	李星彥. 基于電子病歷的輔助問診系統的設計與實現. 北京: 北京郵電大學, 2020.
40.	袁莎, 沈麗寧. 醫療數據質量評價指標體系研究. 衛生軟科學, 2020, 34(12): 12-16.

1. Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol, 2017, 2(4): 230-243.
2. 谷鴻秋, 王俊峰, 章仲恒, 等. 臨床預測模型: 模型的建立. 中國循證心血管醫學雜志, 2019, 11(1): 14-16, 23.
3. 王士泉, 蘇明亮, 高東平. 基于大數據的青光眼眼壓實時預警監測系統研究. 中國數字醫學, 2018, 13(5): 5-7, 15.
4. 徐怡. 復雜疾病的風險預測模型研究及遺傳變異數據庫挖掘. 杭州: 浙江大學, 2019.
5. 李言生, 龔后武, 栗翊超, 等. 基于真實世界數據的疾病風險預測研究. 醫學信息, 2020, 33(23): 17-19.
6. Rudrapatna VA, Butte AJ. Opportunities and challenges in using real-world data for health care. J Clin Invest, 2020, 130(2): 565-574.
7. Johnson SG, Speedie S, Simon G, et al. A data quality ontology for the secondary use of EHR data. AMIA Annu Symp Proc, 2015, 5: 1937-1946.
8. 余煒倫. 電子病歷中的數據質量與病人群組可視分析. 杭州: 浙江大學, 2020.
9. 楊鑫禹, 牟冬梅, 彭浩, 等. 基于數據特征的電子病歷數據驅動臨床決策模型研究. 情報理論與實踐, 2022, 45(5): 181-188.
10. Ni K, Chu H, Zeng L, et al. Barriers and facilitators to data quality of electronic health records used for clinical research in China: a qualitative study. BMJ Open, 2019, 9(7): e029314.
11. 田琪, 陳雅妮, 韓喆僖, 等. 臨床數據質量評估指標研究. 醫學信息學雜志, 2020, 41(10): 9-17.
12. Weiskopf NG, Bakken S, Hripcsak G, et al. A data quality assessment guideline for electronic health record data reuse. EGEMS (Wash DC), 2017, 5(1): 14.
13. 熊興江. 醫療大數據質量評價指標體系構建研究. 武漢: 華中科技大學, 2019.
14. Spjuth O, Frid J, Hellander A. The machine learning life cycle and the cloud: implications for drug discovery. Expert Opin Drug Discov, 2021, 16(9): 1071-1079.
15. Eric H. Machine learning life cycle. 2021.
16. Srcmini. 機器學習開發的生命周期. 2021.
17. 國家藥品監督管理局醫療器械技術審評中心. 人工智能醫療器械注冊審查指導原則. 2022.
18. 國家藥品監督管理局. 深度學習輔助決策醫療器械軟件審評要點. 2022.
19. 昝松亭. 移動醫療大數據的數據質量評估模型研究. 北京: 北京郵電大學, 2019.
20. 江心怡, 陳敏. 電子病歷數據治理方法的研究. 中國醫院管理, 2020, 40(8): 68-70.
21. Sun Y, Lu T, Gu N. A method of electronic health data quality assessment: enabling data provenance. Wellington: 2017 IEEE 21st international conference on computer supported cooperative work in design (CSCWD), 2017: 233-238.
22. Weiskopf NG, Weng C. Methods and dimensions of electronic health record data quality assessment: enabling reuse for clinical research. J Am Med Inform Assoc, 2013, 20(1): 144-151.
23. Kahn MG, Callahan TJ, Barnard J, et al. A harmonized data quality assessment terminology and framework for the secondary use of electronic health record data. EGEMS (Wash DC), 2016, 4(1): 1244.
24. 胡丹青. 基于電子病歷的急性冠脈綜合征患者主要不良心血管事件預測. 杭州: 浙江大學, 2017.
25. Le S, Allen A, Calvert J, et al. Convolutional neural network model for intensive care unit acute kidney injury prediction. Kidney Int Rep, 2021, 6(5): 1289-1298.
26. 李冬冬. 腦卒中電子病歷文本數據結構化方法研究及應用. 上海: 中國人民解放軍海軍軍醫大學, 2021.
27. Dinh A, Miertschin S, Young A, et al. A data-driven approach to predicting diabetes and cardiovascular disease with machine learning. BMC Med Inform Decis Mak, 2019, 19(1): 211.
28. Tseng PY, Chen YT, Wang CH, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning. Crit Care, 2020, 24(1): 478.
29. He J, Hu Y, Zhang X, et al. Multi-perspective predictive modeling for acute kidney injury in general hospital populations using electronic medical records. JAMIA Open, 2019, 2(1): 115-122.
30. 杜珍珍. 基于電子病歷的機器學習算法在心血管疾病預測方面的應用. 武漢: 武漢郵電科學研究院, 2020.
31. Li Y, Chen X, Shen Z, et al. Prediction models for acute kidney injury in patients with gastrointestinal cancers: a real-world study based on Bayesian networks. Ren Fail, 2020, 42(1): 869-876.
32. 肖文翔. 基于電子病歷分析的糖尿病患病風險數據挖掘方法研究. 青島: 青島大學, 2016.
33. 吳風浪, 周銘, 耿鵬. 醫院電子病歷的多維數據分析研究. 中國醫學裝備, 2019, 16(9): 132-135.
34. Wang H, Tan X, Huang Z, et al. Mining incomplete clinical data for the early assessment of Kawasaki disease based on feature clustering and convolutional neural networks. Artif Intell Med, 2020, 105: 101859.
35. 王萍. 基于電子病歷數據的疾病預測模型構建研究. 長春: 吉林大學, 2017.
36. 楊玉潔. 基于醫學大數據的心血管慢病風險精準建模. 深圳: 中國科學院大學(中國科學院深圳先進技術研究院), 2021.
37. Chan L, Nadkarni GN, Fleming F, et al. Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease. Diabetologia, 2021, 64(7): 1504-1515.
38. 陳德華, 周東陽, 樂嘉錦. 基于深度學習的甲狀腺結節良惡性預測方法研究. 微型機與應用, 2017, 36(12): 13-15.
39. 李星彥. 基于電子病歷的輔助問診系統的設計與實現. 北京: 北京郵電大學, 2020.
40. 袁莎, 沈麗寧. 醫療數據質量評價指標體系研究. 衛生軟科學, 2020, 34(12): 12-16.

Previous Article
Evidence-based construction of transparency evaluation tool 2.0 of clinical practice guidelines
Next Article
Data transformation method of real world study on traditional Chinese medicine

Chinese Journal of Evidence-Based Medicine

Exploring data quality for machine learning-based disease risk predictions with electronic medical records

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content