Using machine learning to predict subsequent events after EMS non-conveyance decisions
Abstract Background Predictors of subsequent events after Emergency Medical Services (EMS) non-conveyance decisions are still unclear, though patient safety is the priority in prehospital emergency care. The aim of this study was to find out whether machine learning can be used in this context and t...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-06-01
|
Series: | BMC Medical Informatics and Decision Making |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12911-022-01901-x |
_version_ | 1811334357409857536 |
---|---|
author | Jani Paulin Akseli Reunamo Jouni Kurola Hans Moen Sanna Salanterä Heikki Riihimäki Tero Vesanen Mari Koivisto Timo Iirola |
author_facet | Jani Paulin Akseli Reunamo Jouni Kurola Hans Moen Sanna Salanterä Heikki Riihimäki Tero Vesanen Mari Koivisto Timo Iirola |
author_sort | Jani Paulin |
collection | DOAJ |
description | Abstract Background Predictors of subsequent events after Emergency Medical Services (EMS) non-conveyance decisions are still unclear, though patient safety is the priority in prehospital emergency care. The aim of this study was to find out whether machine learning can be used in this context and to identify the predictors of subsequent events based on narrative texts of electronic patient care records (ePCR). Methods This was a prospective cohort study of EMS patients in Finland. The data was collected from three different regions between June 1 and November 30, 2018. Machine learning, in form of text classification, and manual evaluation were used to predict subsequent events from the clinical notes after a non-conveyance mission. Results FastText-model (AUC 0.654) performed best in prediction of subsequent events after EMS non-conveyance missions (n = 11,846). The model and manual analyses showed that many of the subsequent events were planned before, EMS guided the patients to visit primary health care facilities or ED next or following days after non-conveyance. The most frequent signs and symptoms as subsequent event predictors were musculoskeletal-, infection-related and non-specific complaints. 1 in 5 the EMS documentation was inadequate and many of these led to a subsequent event. Conclusion Machine learning can be used to predict subsequent events after EMS non-conveyance missions. From the patient safety perspective, it is notable that subsequent event does not necessarily mean that patient safety is compromised. There were a number of subsequent visits to primary health care or EDs, which were planned before by EMS. This demonstrates the appropriate use of limited resources to avoid unnecessary conveyance to the ED. However, further studies are needed without planned subsequent events to find out the harmful subsequent events, where EMS non-conveyance puts patient safety at risk. |
first_indexed | 2024-04-13T17:06:43Z |
format | Article |
id | doaj.art-ff90fc514ca441bfb566c39704cfd5f0 |
institution | Directory Open Access Journal |
issn | 1472-6947 |
language | English |
last_indexed | 2024-04-13T17:06:43Z |
publishDate | 2022-06-01 |
publisher | BMC |
record_format | Article |
series | BMC Medical Informatics and Decision Making |
spelling | doaj.art-ff90fc514ca441bfb566c39704cfd5f02022-12-22T02:38:27ZengBMCBMC Medical Informatics and Decision Making1472-69472022-06-0122111210.1186/s12911-022-01901-xUsing machine learning to predict subsequent events after EMS non-conveyance decisionsJani Paulin0Akseli Reunamo1Jouni Kurola2Hans Moen3Sanna Salanterä4Heikki Riihimäki5Tero Vesanen6Mari Koivisto7Timo Iirola8Department of Clinical Medicine, University of Turku and Turku University of Applied SciencesDepartment of Biology, University of TurkuCentre for Prehospital Emergency Care, Kuopio University Hospital and University of Eastern FinlandDepartment of Computing, University of TurkuDepartment of Nursing Science, University of Turku and Turku University HospitalDepartment of Nursing Science, University of TurkuDepartment of Nursing Science, University of TurkuDepartment of Biostatistics, University of TurkuEmergency Medical Services, Turku University Hospital and University of TurkuAbstract Background Predictors of subsequent events after Emergency Medical Services (EMS) non-conveyance decisions are still unclear, though patient safety is the priority in prehospital emergency care. The aim of this study was to find out whether machine learning can be used in this context and to identify the predictors of subsequent events based on narrative texts of electronic patient care records (ePCR). Methods This was a prospective cohort study of EMS patients in Finland. The data was collected from three different regions between June 1 and November 30, 2018. Machine learning, in form of text classification, and manual evaluation were used to predict subsequent events from the clinical notes after a non-conveyance mission. Results FastText-model (AUC 0.654) performed best in prediction of subsequent events after EMS non-conveyance missions (n = 11,846). The model and manual analyses showed that many of the subsequent events were planned before, EMS guided the patients to visit primary health care facilities or ED next or following days after non-conveyance. The most frequent signs and symptoms as subsequent event predictors were musculoskeletal-, infection-related and non-specific complaints. 1 in 5 the EMS documentation was inadequate and many of these led to a subsequent event. Conclusion Machine learning can be used to predict subsequent events after EMS non-conveyance missions. From the patient safety perspective, it is notable that subsequent event does not necessarily mean that patient safety is compromised. There were a number of subsequent visits to primary health care or EDs, which were planned before by EMS. This demonstrates the appropriate use of limited resources to avoid unnecessary conveyance to the ED. However, further studies are needed without planned subsequent events to find out the harmful subsequent events, where EMS non-conveyance puts patient safety at risk.https://doi.org/10.1186/s12911-022-01901-xEmergency medical serviceNon-conveyanceSubsequent eventPatient safetyMachine learningText classification |
spellingShingle | Jani Paulin Akseli Reunamo Jouni Kurola Hans Moen Sanna Salanterä Heikki Riihimäki Tero Vesanen Mari Koivisto Timo Iirola Using machine learning to predict subsequent events after EMS non-conveyance decisions BMC Medical Informatics and Decision Making Emergency medical service Non-conveyance Subsequent event Patient safety Machine learning Text classification |
title | Using machine learning to predict subsequent events after EMS non-conveyance decisions |
title_full | Using machine learning to predict subsequent events after EMS non-conveyance decisions |
title_fullStr | Using machine learning to predict subsequent events after EMS non-conveyance decisions |
title_full_unstemmed | Using machine learning to predict subsequent events after EMS non-conveyance decisions |
title_short | Using machine learning to predict subsequent events after EMS non-conveyance decisions |
title_sort | using machine learning to predict subsequent events after ems non conveyance decisions |
topic | Emergency medical service Non-conveyance Subsequent event Patient safety Machine learning Text classification |
url | https://doi.org/10.1186/s12911-022-01901-x |
work_keys_str_mv | AT janipaulin usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT akselireunamo usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT jounikurola usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT hansmoen usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT sannasalantera usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT heikkiriihimaki usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT terovesanen usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT marikoivisto usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions AT timoiirola usingmachinelearningtopredictsubsequenteventsafteremsnonconveyancedecisions |