Skip to main content
SpringerLink
Log in

Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction

  • Original Research Article
  • Published:
Drug Safety Aims and scope Submit manuscript

Abstract

Introduction

Recently, automated detection has been a new approach to address the risks posed by prescribing errors. This study focused on prescription errors and utilized real medical data to supplement the Drug Utilization Review (DUR)-based rules, the current prescription error detection method. We developed a new hybrid method through artificial intelligence for prescription error prediction by utilizing actual detection accuracy improvement to reduce ‘warning fatigue’ for doctors and improve medical care quality.

Object

This study was conducted in the Department of Pediatrics, targeting children sensitive to drugs to develop a prescription error detection system. Based on the DUR prescription history, 15,281 patient-level observations of children from Konyang University Hospital (KYUH)’s common data model (CDM) and DUR were collected and analyzed retrospectively.

Method

Among the CDM data, inspection information was interlocked with DUR and reflected as standard information for model development; this included outpatient prescriptions from January 1 to December 31, 2018. Through consultation with pediatric clinicians, rule definitions and model development were conducted for 35 drugs, with 137,802 normal and 1609 prescription errors.

Results

We developed a novel hybrid method of error detection in the form of an advanced rule-based deep neural network (ARDNN), which showed the expected performance (precision: 72.86, recall: 81.01, F1 score: 76.72) and reduced alarm pop-up alert fatigue to below 10%. We also created an ARDNN-based comprehensive dashboard that allows doctors to monitor prescription errors with alarm pop-ups when prescribing medications.

Conclusion

These results can advance the existing rule-based model by developing a prescription error detection model using deep learning. This method can improve overall medical efficiency and service quality by reducing doctors’ fatigue.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Donaldson MS, Corrigan JM, Kohn LT, editors. To err is human: building a safer health system. National Academies Press; 2000.

    Google Scholar 

  2. Andel C, Davidow SL, Hollander M, Moreno DA. The economics of health care quality and medical errors. J Health Care Fin. 2012;39(1):39–50.

    Google Scholar 

  3. Leviatan I, Oberman B, Zimlichman E, Stein GY. Associations of physicians’ prescribing experience, work hours, and workload with prescription errors. J Am Med Inform Assoc. 2020. https://doi.org/10.1093/jamia/ocaa219.

    Article  PubMed Central  Google Scholar 

  4. Osheroff J, et al. Improving Outcomes with Clinical Decision Support: An Implementer’s Guide. HIMSS Publishing; 2012.

    Book  Google Scholar 

  5. Berner ES, La Lande TJ. Overview of clinical decision support systems. In: Clinical decision support systems. New York: Springer; 2007. p. 3–22.

    Chapter  Google Scholar 

  6. Anooj PK. Clinical decision support system: risk level prediction of heart disease using weighted fuzzy rules. J King Saud Univ Comput Inf Sci. 2012;24(1):27–40.

    Google Scholar 

  7. Segal G, Segev A, Brom A, Lifshitz Y, Wasserstrum Y, Zimlichman E. Reducing drug prescription errors and adverse drug events by application of a probabilistic, machine-learning-based clinical decision support system in an inpatient setting. J Am Med Inform Assoc. 2019;26(12):1560–5. https://doi.org/10.1093/jamia/ocz135.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Medaware: Transforming Patient Safety. MedAware. Available: https://www.medaware.com/. Accessed December 3, 2020.

  9. Prada SI, Loaiza JS. Comparing the medicaid prospective drug utilization review program cost-savings methods used by state agencies in 2015 and 2016. Am Health Drug Benefits. 2019;12(1):7–12.

    PubMed  PubMed Central  Google Scholar 

  10. Lipton HL, Bird JA. Drug utilization review in ambulatory settings: state of the science and directions for outcomes research. Med Care. 1993;31:1069–82. https://doi.org/10.1097/00005650-199312000-00001.

    Article  CAS  PubMed  Google Scholar 

  11. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intel Res. 2002;16:321–57. https://doi.org/10.1613/jair.953.

    Article  Google Scholar 

  12. Kubat M, et al. Addressing the curse of imbalanced training sets: one-sided selection. ICML; 1997. p. 179–86.

    Google Scholar 

  13. Liang Z, et al. Deep learning for healthcare decision making with EMRs. 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2014. Doi: https://doi.org/10.1109/BIBM.2014.6999219.

  14. Rozenblum R, Rodriguez-Monguio R, Volk LA, Forsythe KJ, McGurrin WDH, et al. Using a machine learning system to identify and prevent medication prescribing errors: a clinical and cost analysis evaluation. J Qual Patient Saf. 2020;46(1):3–10. https://doi.org/10.1016/j.jcjq.2019.09.008.

    Article  Google Scholar 

  15. Fulda TR, Lyles A, Pugh MC, Christensen DB. Current status of prospective drug utilization review. J Manag Care Pharm. 2004;10(5):433–41. https://doi.org/10.18553/jmcp.2004.10.5.433.

    Article  PubMed  Google Scholar 

  16. Lee S-M, Lee S-O, Kim D-S. Physicians’ and pharmacists’ perceptions on real-time drug utilization review system: a nationwide survey. Int J Qual Health Care. 2017;29(5):634–41. https://doi.org/10.1093/intqhc/mzx085.

    Article  PubMed  Google Scholar 

  17. Wilson DG, McArtney RG, Newcombe RG, McArtney RJ, Gracie J, Kirk CR, et al. Medication errors in pediatric practice: insights from a continuous quality improvement approach. Eur J Pediatr. 1998;157(9):769–74. https://doi.org/10.1007/s004310050932.

    Article  CAS  PubMed  Google Scholar 

  18. Cohen MR, Senders J, Davis NM. Failure mode and effects analysis: a novel approach to avoiding dangerous medication errors and accidents. Hosp Pharm. 1994;29(4):319–30.

    CAS  PubMed  Google Scholar 

  19. Christopoulou F, et al. Adverse drug events and medication relation extraction in electronic health records with ensemble deep learning methods. J Am Med Inf Assoc. 2020;27:39–46. https://doi.org/10.1093/jamia/ocz101.

    Article  Google Scholar 

  20. Ting H-W, Chung SL, Chen CF, Chiu HY, Hsieh YW. A drug identification model developed using deep learning technologies: experience of a medical center in Taiwan. BMC Health Serv Res. 2020;20:312. https://doi.org/10.1186/s12913-020-05166-w.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Corny J, Rajkumar A, Martin O, Dode X, Lajonchère JP, Billuart O, et al. 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. https://doi.org/10.1093/jamia/ocaa154.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Health Care Data Science Center, Konyang University Hospital, Daejeon, Republic of Korea

    Seunghee Lee, Jong-Yeup Kim & Suehyun Lee

  2. Departments of Biomedical Informatics, College of Medicine, Konyang University, 158 Gwanjeodong‐ro, Seo‐gu, Daejeon, 35365, Republic of Korea

    Jong-Yeup Kim & Suehyun Lee

  3. Department of Pediatrics, Konyang University Hospital, Daejeon, Republic of Korea

    Jung Min Yoon

  4. Department of Biomedical Engineering, Konyang University, Daejeon, Republic of Korea

    Sohee Lee

  5. Department of Medical Artificial Intelligence, Konyang University, Daejeon, Republic of Korea

    Yongsuk Kim

  6. Infinigru, Seoul, Republic of Korea

    Jeongwon Shin, Hyeon Seong Kim & Min Je Lee

Authors
  1. Seunghee Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jeongwon Shin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hyeon Seong Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Min Je Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jung Min Yoon
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sohee Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yongsuk Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jong-Yeup Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Suehyun Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jong-Yeup Kim or Suehyun Lee.

Ethics declarations

Author contributions

All authors contributed to the manuscript conception and design. All authors read and approved the final manuscript. Conceptualization, JS, JY, YK, SL and J-YK; Funding acquisition, J-YK; Data curation, Formal analysis and Methodology, JS, HSK and MJL; Project administration, SL and SL; Resources, JMY; Supervision, J-YK; Investigation, Writing—original draft, review & editing, SL, SL, SL and J-YK.

Funding

This research was supported by the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (Grant number: HI17C2412) and by the National IT Industry Promotion Agency (NIPA) Grant funded by the Korean government (MSIT) (No. A0105-20-1008, Development of AI-based detection service for prescription errors).

Data availability

The dataset used and analyzed during this study are not publicly available due to privacy or ethical restrictions.

Conflicts of interest

The authors declare no conflict of interest.

Ethics approval

This study was approved by the Institutional Review Board (IRB) of KYUH (IRB number : 2019-06-013-009).

Consent to participate

Not applicable.

Consent for publication

Not applicable.

Code availability

Not applicable.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 261 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, S., Shin, J., Kim, H.S. et al. Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction. Drug Saf 45, 27–35 (2022). https://doi.org/10.1007/s40264-021-01123-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40264-021-01123-6

Search

Navigation