Methods Inf Med 2021; 60(05/06): 147-161
DOI: 10.1055/s-0041-1735620
Original Article

Developing an Analytical Pipeline to Classify Patient Safety Event Reports Using Optimized Predictive Algorithms

Asa Adadey
1   Partnership for Health IT Patient Safety, ECRI, Plymouth Meeting, Pennsylvania, United States
,
Robert Giannini
1   Partnership for Health IT Patient Safety, ECRI, Plymouth Meeting, Pennsylvania, United States
,
Lorraine B. Possanza
1   Partnership for Health IT Patient Safety, ECRI, Plymouth Meeting, Pennsylvania, United States
› Author Affiliations

Abstract

Background Patient safety event reports provide valuable insight into systemic safety issues but deriving insights from these reports requires computational tools to efficiently parse through large volumes of qualitative data. Natural language processing (NLP) combined with predictive learning provides an automated approach to evaluating these data and supporting the work of patient safety analysts.

Objectives The objective of this study was to use NLP and machine learning techniques to develop a generalizable, scalable, and reliable approach to classifying event reports for the purpose of driving improvements in the safety and quality of patient care.

Methods Datasets for 14 different labels (themes) were vectorized using a bag-of-words, tf-idf, or document embeddings approach and then applied to a series of classification algorithms via a hyperparameter grid search to derive an optimized model. Reports were also analyzed for terms strongly associated with each theme using an adjusted F-score calculation.

Results F1 score for each optimized model ranged from 0.951 (“Fall”) to 0.544 (“Environment”). The bag-of-words approach proved optimal for 12 of 14 labels, and the naïve Bayes algorithm performed best for nine labels. Linear support vector machine was demonstrated as optimal for three labels and XGBoost for four of the 14 labels. Labels with more distinctly associated terms performed better than less distinct themes, as shown by a Pearson's correlation coefficient of 0.634.

Conclusions We were able to demonstrate an analytical pipeline that broadly applies NLP and predictive modeling to categorize patient safety reports from multiple facilities. This pipeline allows analysts to more rapidly identify and structure information contained in patient safety data, which can enhance the evaluation and the use of this information over time.

Ethical Approval

No human and/or animal subjects were involved in this research.


Supplementary Material



Publication History

Received: 12 November 2020

Accepted: 05 August 2021

Article published online:
31 October 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 
  • References

  • 1 Hwang C-Y, Wu C-H, Cheng F-C, Yen Y-L, Wu K-H. A 12-year analysis of closed medical malpractice claims of the Taiwan civil court: a retrospective study. Medicine (Baltimore) 2018; 97 (13) e0237
  • 2 Santuzzi NR, Brodnik MS, Rinehart-Thompson L, Klatt M. Patient satisfaction: how do qualitative comments relate to quantitative scores on a satisfaction survey?. Qual Manag Health Care 2009; 18 (01) 3-18
  • 3 Boussat B, Kamalanavin K, François P. The contribution of open comments to understanding the results from the Hospital Survey on Patient Safety Culture (HSOPS): a qualitative study. PLoS One 2018; 13 (04) e0196089
  • 4 James JTA. A new, evidence-based estimate of patient harms associated with hospital care. J Patient Saf 2013; 9 (03) 122-128
  • 5 Makary MA, Daniel M. Medical error-the third leading cause of death in the US. BMJ 2016; 353: i2139
  • 6 Lawton R, McEachan RRC, Giles SJ, Sirriyeh R, Watt IS, Wright J. Development of an evidence-based framework of factors contributing to patient safety incidents in hospital settings: a systematic review. BMJ Qual Saf 2012; 21 (05) 369-380
  • 7 Pronovost PJ, Morlock LL, Sexton JB. et al. Improving the value of patient safety reporting systems. In: Henriksen K, Battles JB, Keyes MA, Grady ML. eds. Advances in Patient Safety: New Directions and Alternative Approaches (Vol. 1: Assessment). Advances in Patient Safety.. Rockville, MD: Agency for Healthcare Research and Quality; 2008
  • 8 Mitchell I, Schuster A, Smith K, Pronovost P, Wu A. Patient safety incident reporting: a qualitative study of thoughts and perceptions of experts 15 years after 'To Err is Human'. BMJ Qual Saf 2016; 25 (02) 92-99
  • 9 Pronovost PJ, Thompson DA, Holzmueller CG. et al. Toward learning from patient safety reporting systems. J Crit Care 2006; 21 (04) 305-315
  • 10 Piotrowski MM, Saint S, Hinshaw DB. The Safety Case Management Committee. The Safety Case Management Committee: expanding the avenues for addressing patient safety. Jt Comm J Qual Improv 2002; 28 (06) 296-305
  • 11 Joshi MS, Anderson JF, Marwaha S. A systems approach to improving error reporting. J Healthc Inf Manag 2002; 16 (01) 40-45
  • 12 Benn J, Koutantji M, Wallace L. et al. Feedback from incident reporting: information and action to improve patient safety. Qual Saf Health Care 2009; 18 (01) 11-21
  • 13 Wang Y, Coiera E, Runciman W, Magrabi F. Using multiclass classification to automate the identification of patient safety incident reports by type and severity. BMC Med Inform Decis Mak 2017; 17 (01) 84
  • 14 Throop C, Stockmeier C. SEC & SSER Patient Safety Measurement System for Healthcare (2nd revision). Virginia Beach, VA: Healthcare Performance Improvement, LLC; 2011: 34
  • 15 Patterson ES, Anders S, Moffatt-Bruce S. Clustering and prioritizing patient safety issues during EHR implementation and upgrades in hospital settings. Proc Int Symp Hum Factors Ergon Healthc 2017; 6 (01) 125-131
  • 16 Chang A, Schyve PM, Croteau RJ, O'Leary DS, Loeb JM. The JCAHO patient safety event taxonomy: a standardized terminology and classification schema for near misses and adverse events. Int J Qual Health Care 2005; 17 (02) 95-105
  • 17 Zhang Y, Jin R, Zhou Z-H. Understanding bag-of-words model: a statistical framework. Int J Mach Learn Cybern 2010; 1 (1–4): 43-52
  • 18 Leskovec J, Rajaraman A, Ullman JD. eds. Data mining. In: Mining of Massive Datasets. 3rd ed.. Cambridge: Cambridge University Press; 2020: 1-19
  • 19 Le QV, Mikolov T. Distributed representations of sentences and documents. In: Proceedings of the 31st International Conference on Machine Learning Vol 32. JMLR: W&CP; 2014. Accessed May 20, 2021 at: http://arxiv.org/abs/1405.4053
  • 20 Govindan M, Van Citters AD, Nelson EC, Kelly-Cummings J, Suresh G. Automated detection of harm in healthcare with information technology: a systematic review. Qual Saf Health Care 2010; 19 (05) e11
  • 21 Melton GB, Hripcsak G. Automated detection of adverse events using natural language processing of discharge summaries. J Am Med Inform Assoc 2005; 12 (04) 448-457
  • 22 Penz JFE, Wilcox AB, Hurdle JF. Automated identification of adverse events related to central venous catheters. J Biomed Inform 2007; 40 (02) 174-182
  • 23 Gerdes LU, Hardahl C. Text mining electronic health records to identify hospital adverse events. Stud Health Technol Inform 2013; 192: 1145
  • 24 Weller GB, Lovely J, Larson DW, Earnshaw BA, Huebner M. Leveraging electronic health records for predictive modeling of post-surgical complications. Stat Methods Med Res 2018; 27 (11) 3271-3285
  • 25 Zhou S, Kang H, Yao B, Gong Y. An automated pipeline for analyzing medication event reports in clinical settings. BMC Med Inform Decis Mak 2018; 18 (Suppl. 05) 113
  • 26 Fong A, Adams KT, Gaunt MJ, Howe JL, Kellogg KM, Ratwani RM. Identifying health information technology related safety event reports from patient safety event report databases. J Biomed Inform 2018; 86: 135-142
  • 27 Fong A, Komolafe T, Adams KT, Cohen A, Howe JL, Ratwani RM. Exploration and initial development of text classification models to identify health information technology usability-related patient safety event reports. Appl Clin Inform 2019; 10 (03) 521-527
  • 28 AHRQ Patient Safety Organization Program. Common formats. Agency for Healthcare Research and Quality (AHRQ). Accessed September 15, 2020 at: https://pso.ahrq.gov/common-formats
  • 29 Benin AL, Fodeh SJ, Lee K, Koss M, Miller P, Brandt C. Electronic approaches to making sense of the text in the adverse event reporting system. J Healthc Risk Manag 2016; 36 (02) 10-20
  • 30 Ong M-S, Magrabi F, Coiera E. Automated categorisation of clinical incident reports using statistical text classification. Qual Saf Health Care 2010; 19 (06) e55
  • 31 Perkins J. ed. Calculating high information words. In: Python 3 Text Processing with NLTK 3 Cookbook. 2 ed. Packt open source.. Birmingham: Packt Publishing; 2014: 214-219
  • 32 Zhang H. The optimality of naive Bayes. In: Proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference. Menlo Park, CA: AAAI Press; 2004: 1-6
  • 33 Lau JH, Baldwin T. An empirical evaluation of doc2vec with practical insights into document embedding generation. In: Proceedings of the 1st Workshop on Representation Learning for NLP, Berlin, Germany. Stroudsburg, PA: ACL; 2016: 78-86
  • 34 Chai KEK, Anthony S, Coiera E, Magrabi F. Using statistical text classification to identify health information technology incidents. J Am Med Inform Assoc 2013; 20 (05) 980-985
  • 35 Kowsari JM, Heidarysafa M, Barnes B. Text classification algorithms: a survey. Information (Basel) 2019; 10 (04) 150
  • 36 Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY: ACM; 2016: 785-794
  • 37 Pedregosa F, Varoquaux G, Gramfort A. et al. Scikit-learn: machine learning in Python. J Mach Learn Res 2011; (12) 2825-2830
  • 38 Řehůřek R, Sojka P. Software framework for topic modelling with large Corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. Paris: ELRA; 2010: 45-50
  • 39 Kessler J. Scattertext: a browser-based tool for visualizing how Corpora differ. In: Proceedings of ACL 2017, System Demonstrations. Stroudsburg, PA: ACL; 2017: 85-90
  • 40 Man Kwon Y, Hee Jun S, Mo Gal W, Jae Lim M. The performance comparison of the classifiers according to binary bow, count bow and Tf-Idf feature vectors for malware detection. Int J Eng Technol. 2018; 7 (3.33): 15-22
  • 41 Unified Medical Language System® (UMLS®): RxNorm. National Library of Medicine (NLM). Accessed September 15, 2020 at: https://www.nlm.nih.gov/research/umls/rxnorm/index.html
  • 42 LOINC®(Logical Observation Identifiers Names and Codes) - home page. Regenstrief Institute, Inc. Accessed September 15, 2020 at: https://loinc.org/
  • 43 SNOMED - Home | SNOMED International. SNOMED International. Accessed September 15, 2020 at: https://www.snomed.org/