Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Advertisement

Accepted for/Published in: JMIR Medical Informatics

Date Submitted: Nov 7, 2019
Open Peer Review Period: Nov 7, 2019 - Nov 14, 2019
Date Accepted: Jan 22, 2020
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Predicting Inpatient Falls Using Natural Language Processing of Nursing Records Obtained From Japanese Electronic Medical Records: Case-Control Study

Nakatani H, Nakao M, Uchiyama H, Toyoshiba H, Ochiai C

Predicting Inpatient Falls Using Natural Language Processing of Nursing Records Obtained From Japanese Electronic Medical Records: Case-Control Study

JMIR Med Inform 2020;8(4):e16970

DOI: 10.2196/16970

PMID: 32319959

PMCID: 7203618

Predicting Inpatient Falls using Natural Language Processing of Nursing Records Obtained from Japanese Electronic Medical Records: A Case-Control Study

  • Hayao Nakatani; 
  • Masatoshi Nakao; 
  • Hidefumi Uchiyama; 
  • Hiroyoshi Toyoshiba; 
  • Chikayuki Ochiai; 

ABSTRACT

Background:

Falls in hospitals are the most common risk factor that affects the safety of inpatients and can result in severe harm. Therefore, preventing falls is one of the most important areas of risk management for healthcare organizations. However, existing methods for predicting falls are laborious and costly.

Objective:

The objective of the study is to verify that hospital inpatient falls can be predicted through the analysis of a single input, that is, unstructured nursing records (NRs) obtained from Japanese electronic medical records (EMRs), using a natural language processing (NLP) algorithm and machine learning.

Methods:

The NRs of 335 fallers and 408 non-fallers for a 12-month period were extracted from the EMRs of an acute care hospital and randomly divided into a learning dataset and test dataset. The former dataset was subjected to NLP and machine learning to extract morphemes that contributed to separating fallers from non-fallers to construct a model for predicting falls. Then the latter dataset was used to determine the predictive value of the model using receiver operating characteristic (ROC) analysis.

Results:

The prediction of falls using the test dataset was good and showed high accuracy, with the area under the ROC curve, sensitivity, specificity, and odds ratio of 0.834 + 0.005, 0.769 + 0.013, 0.785 + 0.020, and 12.27 + 1.11 (mean + standard deviation of five independent experiments), respectively. The morphemes incorporated into the final model included many words closely related to known risk factors for falls, such as the use of psychotropic drugs, state of consciousness, and mobility, thereby demonstrating that an NLP algorithm combined with machine learning can effectively extract risk factors for falls from NRs.

Conclusions:

We successfully established that falls among hospital inpatients can be predicted by analyzing NRs using an NLP algorithm and machine learning. Hence, it may be possible to develop a fall risk monitoring system that analyzes NRs on a daily basis that alerts healthcare professionals when the fall risk of an inpatient is increased.


 Citation

Please cite as:

Nakatani H, Nakao M, Uchiyama H, Toyoshiba H, Ochiai C

Predicting Inpatient Falls using Natural Language Processing of Nursing Records Obtained from Japanese Electronic Medical Records: A Case-Control Study

JMIR Medical Informatics. 22/01/2020:16970 (forthcoming/in press)

DOI: 10.2196/16970

URL: https://preprints.jmir.org/preprint/16970

PMID: 32319959

PMCID: 7203618

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.