Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit
Aim: To develop models that predict the presence of medication errors (MEs) (prescription, preparation, administration, and monitoring) using machine learning in NICU patients.Design: Prospective, observational cohort study randomized with machine learning (ML) algorithms.Setting: A 22-bed capacity...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2023.1151560/full |
| _version_ | 1827967552257523712 |
|---|---|
| author | Nadir Yalçın Merve Kaşıkcı Hasan Tolga Çelik Karel Allegaert Karel Allegaert Karel Allegaert Kutay Demirkan Şule Yiğit Murat Yurdakök |
| author_facet | Nadir Yalçın Merve Kaşıkcı Hasan Tolga Çelik Karel Allegaert Karel Allegaert Karel Allegaert Kutay Demirkan Şule Yiğit Murat Yurdakök |
| author_sort | Nadir Yalçın |
| collection | DOAJ |
| description | Aim: To develop models that predict the presence of medication errors (MEs) (prescription, preparation, administration, and monitoring) using machine learning in NICU patients.Design: Prospective, observational cohort study randomized with machine learning (ML) algorithms.Setting: A 22-bed capacity NICU in Ankara, Turkey, between February 2020 and July 2021.Results: A total of 11,908 medication orders (28.9 orders/patient) for 412 NICU patients (5.53 drugs/patient/day) who received 2,280 prescriptions over 32,925 patient days were analyzed. At least one physician-related ME and nurse-related ME were found in 174 (42.2%) and 235 (57.0%) of the patients, respectively. The parameters that had the highest correlation with ME occurrence and subsequently included in the model were: total number of drugs, anti-infective drugs, nervous system drugs, 5-min APGAR score, postnatal age, alimentary tract and metabolism drugs, and respiratory system drugs as patient-related parameters, and weekly working hours of nurses, weekly working hours of physicians, and number of nurses’ monthly shifts as care provider-related parameters. The obtained model showed high performance to predict ME (AUC: 0.920; 95% CI: 0.876–0.970) presence and is accessible online (http://softmed.hacettepe.edu.tr/NEO-DEER_Medication_Error/).Conclusion: This is the first developed and validated model to predict the presence of ME using work environment and pharmacotherapy parameters with high-performance ML algorithms in NICU patients. This approach and the current model hold the promise of implementation of targeted/precision screening to prevent MEs in neonates.Clinical Trial Registration:ClinicalTrials.gov, identifier NCT04899960. |
| first_indexed | 2024-04-09T18:07:09Z |
| format | Article |
| id | doaj.art-b866cdc65fe548fc859be978c1527a06 |
| institution | Directory Open Access Journal |
| issn | 1663-9812 |
| language | English |
| last_indexed | 2024-04-09T18:07:09Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj.art-b866cdc65fe548fc859be978c1527a062023-04-14T05:38:41ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122023-04-011410.3389/fphar.2023.11515601151560Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unitNadir Yalçın0Merve Kaşıkcı1Hasan Tolga Çelik2Karel Allegaert3Karel Allegaert4Karel Allegaert5Kutay Demirkan6Şule Yiğit7Murat Yurdakök8Department of Clinical Pharmacy, Faculty of Pharmacy, Hacettepe University, Ankara, TürkiyeDepartment of Biostatistics, Faculty of Medicine, Hacettepe University, Ankara, TürkiyeDivision of Neonatology, Department of Child Health and Diseases, Faculty of Medicine, Hacettepe University, Ankara, TürkiyeDepartment of Pharmaceutical and Pharmacological Sciences, KU Leuven, BelgiumDepartment of Development and Regeneration, KU Leuven, BelgiumDepartment of Hospital Pharmacy, Erasmus Medical Center, Rotterdam, NetherlandsDepartment of Clinical Pharmacy, Faculty of Pharmacy, Hacettepe University, Ankara, TürkiyeDivision of Neonatology, Department of Child Health and Diseases, Faculty of Medicine, Hacettepe University, Ankara, TürkiyeDivision of Neonatology, Department of Child Health and Diseases, Faculty of Medicine, Hacettepe University, Ankara, TürkiyeAim: To develop models that predict the presence of medication errors (MEs) (prescription, preparation, administration, and monitoring) using machine learning in NICU patients.Design: Prospective, observational cohort study randomized with machine learning (ML) algorithms.Setting: A 22-bed capacity NICU in Ankara, Turkey, between February 2020 and July 2021.Results: A total of 11,908 medication orders (28.9 orders/patient) for 412 NICU patients (5.53 drugs/patient/day) who received 2,280 prescriptions over 32,925 patient days were analyzed. At least one physician-related ME and nurse-related ME were found in 174 (42.2%) and 235 (57.0%) of the patients, respectively. The parameters that had the highest correlation with ME occurrence and subsequently included in the model were: total number of drugs, anti-infective drugs, nervous system drugs, 5-min APGAR score, postnatal age, alimentary tract and metabolism drugs, and respiratory system drugs as patient-related parameters, and weekly working hours of nurses, weekly working hours of physicians, and number of nurses’ monthly shifts as care provider-related parameters. The obtained model showed high performance to predict ME (AUC: 0.920; 95% CI: 0.876–0.970) presence and is accessible online (http://softmed.hacettepe.edu.tr/NEO-DEER_Medication_Error/).Conclusion: This is the first developed and validated model to predict the presence of ME using work environment and pharmacotherapy parameters with high-performance ML algorithms in NICU patients. This approach and the current model hold the promise of implementation of targeted/precision screening to prevent MEs in neonates.Clinical Trial Registration:ClinicalTrials.gov, identifier NCT04899960.https://www.frontiersin.org/articles/10.3389/fphar.2023.1151560/fullnewbornmedication errormachine learningdrug safetyclinical pharmacydata collection |
| spellingShingle | Nadir Yalçın Merve Kaşıkcı Hasan Tolga Çelik Karel Allegaert Karel Allegaert Karel Allegaert Kutay Demirkan Şule Yiğit Murat Yurdakök Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit Frontiers in Pharmacology newborn medication error machine learning drug safety clinical pharmacy data collection |
| title | Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| title_full | Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| title_fullStr | Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| title_full_unstemmed | Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| title_short | Development and validation of a machine learning-based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| title_sort | development and validation of a machine learning based detection system to improve precision screening for medication errors in the neonatal intensive care unit |
| topic | newborn medication error machine learning drug safety clinical pharmacy data collection |
| url | https://www.frontiersin.org/articles/10.3389/fphar.2023.1151560/full |
| work_keys_str_mv | AT nadiryalcın developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT mervekasıkcı developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT hasantolgacelik developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT karelallegaert developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT karelallegaert developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT karelallegaert developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT kutaydemirkan developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT suleyigit developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit AT muratyurdakok developmentandvalidationofamachinelearningbaseddetectionsystemtoimproveprecisionscreeningformedicationerrorsintheneonatalintensivecareunit |