Machine Learning Analysis to Identify Data Entry Errors in Prehospital Patient Care Reports: A Case Study of a National Out-of-Hospital Cardiac Arrest Registry

References

• Adler-Milstein J, Holmgren AJ, Kralovec P, Worzala C, Searcy T, Patel V. Electronic health record adoption in US hospitals: the emergence of a digital "advanced use" divide. J Am Med Inform Assoc. 2017;24(6):1142–8. doi:10.1093/jamia/ocx080.
   PubMed Web of Science ®Google Scholar
• Mulder DS, Spicer J. Registry-based medical research: data dredging or value building to quality of care? Ann Thorac Surg. 2019;108(1):274–82. doi:10.1016/j.athoracsur.2018.12.060.
   PubMed Web of Science ®Google Scholar
• Emilsson L, Lindahl B, Koster M, Lambe M, Ludvigsson JF. Review of 103 Swedish Healthcare Quality Registries. J Intern Med. 2015;277(1):94–136. doi:10.1111/joim.12303.
   PubMed Web of Science ®Google Scholar
• Lyu H, Cooper M, Patel K, Daniel M, Makary MA. Prevalence and data transparency of National Clinical Registries in the United States. J Healthc Qual. 2016;38(4):223–34. doi:10.1097/JHQ.0000000000000001.
   PubMed Web of Science ®Google Scholar
• Hoque DME, Kumari V, Hoque M, Ruseckaite R, Romero L, Evans SM. Impact of clinical registries on quality of patient care and clinical outcomes: a systematic review. PLoS One. 2017;12(9):e0183667. doi:10.1371/journal.pone.0183667.
   PubMed Web of Science ®Google Scholar
• Venermo M, Mani K, Kolh P. The quality of a registry based study depends on the quality of the data—without validation, it is questionable. Eur J Vasc Endovasc Surg. 2017;53(5):611–2. doi:10.1016/j.ejvs.2017.03.017.
   PubMed Web of Science ®Google Scholar
• Arts DG, De Keizer NF, Scheffer GJ. Defining and improving data quality in medical registries: a literature review, case study, and generic framework. J Am Med Inform Assoc. 2002;9(6):600–11. doi:10.1197/jamia.m1087.
   PubMed Web of Science ®Google Scholar
• Hogan WR, Wagner MM. Accuracy of data in computer-based patient records. J Am Med Inform Assoc. 1997;4(5):342–55. doi:10.1136/jamia.1997.0040342.
   PubMed Web of Science ®Google Scholar
• Churova V, Vyskovsky R, Marsalova K, Kudlacek D, Schwarz D. Anomaly detection algorithm for real-world data and evidence in clinical research: implementation, evaluation, and validation study. JMIR Med Inform. 2021;9(5):e27172. doi:10.2196/27172.
   PubMed Web of Science ®Google Scholar
• Corny J, Rajkumar A, Martin O, Dode X, Lajonchere JP, Billuart O, Bezie Y, Buronfosse A. A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error. J Am Med Inform Assoc. 2020;27(11):1688–94. doi:10.1093/jamia/ocaa154.
   PubMed Web of Science ®Google Scholar
• Valko M, Cooper G, Seybert A, Visweswaran S, Saul M, Hauskrecht M. Conditional anomaly detection methods for patient-management alert systems. Proc Int Conf Mach Learn; Finland; 2008.
   Google Scholar
• Kiguchi T, Okubo M, Nishiyama C, Maconochie I, Ong MEH, Kern KB, Wyckoff MH, McNally B, Christensen EF, Tjelmeland I, et al. Out-of-hospital cardiac arrest across the world: first report from the International Liaison Committee on Resuscitation (ILCOR). Resuscitation. 2020;152:39–49. doi:10.1016/j.resuscitation.2020.02.044.
   PubMed Web of Science ®Google Scholar
• McNally B. The importance of cardiac arrest registries. Scand J Trauma Resusc Emerg Med. 2014;22(S1):A3–A. doi:10.1186/1757-7241-22-S1-A3.
   Google Scholar
• Cummins RO, Chamberlain DA, Abramson NS, Allen M, Baskett PJ, Becker L, Bossaert L, Delooz HH, Dick WF, Eisenberg MS. Recommended guidelines for uniform reporting of data from out-of-hospital cardiac arrest: the Utstein Style. A statement for health professionals from a task force of the American Heart Association, the European Resuscitation Council, the Heart and Stroke Foundation of Canada, and the Australian Resuscitation Council. Circulation. 1991;84(2):960–75. doi:10.1161/01.CIR.84.2.960.
   PubMed Web of Science ®Google Scholar
• Brice JH, Friend KD, Delbridge TR. Accuracy of EMS-recorded patient demographic data. Prehosp Emerg Care. 2008;12(2):187–91. doi:10.1080/10903120801907687.
   PubMed Web of Science ®Google Scholar
• Kim YT, Shin SD, Hong SO, Ahn KO, Ro YS, Song KJ, Hong KJ. Effect of national implementation of Utstein recommendation from the global resuscitation alliance on ten steps to improve outcomes from out-of-hospital cardiac arrest: a ten-year observational study in Korea. BMJ Open. 2017;7(8):e016925. doi:10.1136/bmjopen-2017-016925.
   PubMed Web of Science ®Google Scholar
• Choi DH, Ro YS, Kim KH, Park JH, Jeong J, Hong KJ, Song KJ, Shin SD. The association between alcohol intake shortly before arrest and survival outcomes of out-of-hospital cardiac arrest. Resuscitation. 2022;173:39–46. doi:10.1016/j.resuscitation.2022.02.006.
   PubMed Web of Science ®Google Scholar
• NHTSA. National EMS scope of practice model. DOT HS. 2007;810:657.
   Google Scholar
• Hancock JT, Khoshgoftaar TM. Survey on categorical data for neural networks. J Big Data. 2020;7(1):28. doi:10.1186/s40537-020-00305-w.
   Google Scholar
• Chen T, Guestrin C, editors. Xgboost: a scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining; USA; 2016. doi:10.1145/2939672.2939785.
   Google Scholar
• Zhao Y, Hryniewicki MK, editors. Xgbod: improving supervised outlier detection with unsupervised representation learning. 2018 International Joint Conference on Neural Networks (IJCNN); Brazil: IEEE; 2018. doi:10.1109/IJCNN.2018.8489605.
   Google Scholar
• Zhao Y, Nasrullah Z, Li Z. Pyod: a python toolbox for scalable outlier detection. arXiv preprint arXiv:190101588. 2019.
   Google Scholar
• Buderer NMF. Statistical methodology: I. Incorporating the prevalence of disease into the sample size calculation for sensitivity and specificity. Acad Emerg Med. 1996;3(9):895–900. doi:10.1111/j.1553-2712.1996.tb03538.x.
   PubMed Web of Science ®Google Scholar
• Redelmeier DA, Bloch DA, Hickam DH. Assessing predictive accuracy: how to compare Brier scores. J Clin Epidemiol. 1991;44(11):1141–6. doi:10.1016/0895-4356(91)90146-z.
   PubMed Web of Science ®Google Scholar
• Altmann A, Toloşi L, Sander O, Lengauer T. Permutation importance: a corrected feature importance measure. Bioinformatics. 2010;26(10):1340–7. doi:10.1093/bioinformatics/btq134.
   PubMed Web of Science ®Google Scholar
• Cava W, Bauer C, Moore JH, Pendergrass SA. Interpretation of machine learning predictions for patient outcomes in electronic health records. AMIA Annu Symp Proc. 2019;2019:572–81.
   PubMedGoogle Scholar
• McHugh ML. Interrater reliability: the kappa statistic. Biochem Med (Zagreb). 2012;22(3):276–82. doi:10.11613/BM.2012.031.
   PubMed Web of Science ®Google Scholar
• Lewis MM, Stubbs BA, Eisenberg MS. Determining witnessed status for out-of-hospital cardiac arrest. Resuscitation. 2016;109:133–7. doi:10.1016/j.resuscitation.2016.08.022.
   PubMed Web of Science ®Google Scholar
• Zive D, Daya M. Witness status: a new definition for out-of-hospital cardiac arrest? Resuscitation. 2016;109:A8–A9. doi:10.1016/j.resuscitation.2016.09.023.
   PubMed Web of Science ®Google Scholar
• Goldstein M, Uchida S. A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data. PLoS One. 2016;11(4):e0152173. doi:10.1371/journal.pone.0152173.
   PubMed Web of Science ®Google Scholar
• Nagata K, Tsuji T, Suetsugu K, Muraoka K, Watanabe H, Kanaya A, Egashira N, Ieiri I. Detection of overdose and underdose prescriptions—an unsupervised machine learning approach. PLoS One. 2021;16(11):e0260315. doi:10.1371/journal.pone.0260315.
   PubMed Web of Science ®Google Scholar
• Taha A, Hadi AS. Anomaly detection methods for categorical data: a review. ACM Comput Surv. 2019;52(2):1–35. doi:10.1145/3312739.
   Web of Science ®Google Scholar
• Lock P, McElroy B, Mackenzie M. The hidden cost of clinical audit: a questionnaire study of NHS staff. Health Policy. 2000;51(3):181–90. doi:10.1016/s0168-8510(00)00064-6.
   PubMed Web of Science ®Google Scholar
• Jackson D, McDonald G, Luck L, Waine M, Wilkes L. Some strategies to address the challenges of collecting observational data in a busy clinical environment. Collegian. 2016;23(1):47–52. doi:10.1016/j.colegn.2014.10.001.
   PubMed Web of Science ®Google Scholar