JMIR Publications

ABSTRACT

Background:

To address fall underestimation by the International Classification of Diseases (ICD) in clinical settings, incorporating information from clinical notes via Natural Language Processing (NLP) has emerged as a solution. However, its application to inpatient notes has not been fully investigated.

Objective:

This study developed and validated a rule-based NLP algorithm to identify falls based on inpatient admission notes from older patients.

Methods:

This retrospective study used 12-year electronic inpatient records of patients aged ≥65 from public hospitals in Hong Kong. A random sample of 1,000 patients was drawn to develop the NLP algorithm. Manual review was the gold standard for assessing the algorithm's performance, with sensitivity, specificity, precision, and F-measure calculated at the record, episode, and patient levels. Additionally, the study compared the number of falls identified by ICD codes and clinical notes independently and combined.

Results:

Our NLP algorithm showed excellent performance, with a sensitivity, specificity, precision, and F-measure of 93.3%, 99.0%, 87.5%, and 0.903 at the record and episode level, and 92.9%, 98.3%, 89.7%, and 0.912 at the patient level. The combined identification strategy using ICD codes and the NLP method provided the most comprehensive capture of fall-related episodes and fallers.

Conclusions:

The rule-based NLP method proved efficient and accurate in detecting falls from clinical notes in inpatient episodes. For comprehensive capture of fall episodes and fallers, we recommend the combined use of ICD codes and the NLP algorithm, which should be applied in future fall epidemiology studies and clinical practice for identifying high-risk groups of fall interventions.