JMIR Publications

ABSTRACT

Background:

Falls are common adverse events in hospitals, frequently leading to additional health costs due to prolonged stays and extra care. Therefore, reliable fall detection is vital to develop and test prevention strategies. However, conventional methods – voluntary incident reports and manual chart reviews – are respectively error-prone and time-consuming. Using a search algorithm to examine patients’ electronic health record (EHR) data and flag fall indicators offers an inexpensive, sensitive, cost-effective alternative.

Objective:

This study’s purpose was to develop a fall detection algorithm for use with EHR data, then to evaluate it alongside the Global Trigger Tool (GTT), incident reports, a manual chart review and patient-reported falls.

Methods:

Conducted on two campuses of a large hospital system in Switzerland, this retrospective diagnostic accuracy study consisted of two sub-studies: the first, targeting 240 patients, for algorithm development, the second, targeting 298, for validation. In the development study, we compared the new algorithm’s in-hospital fall rates with those indicated by the GTT and incident reports; in the validation study, we compared them with patient-reported falls and a manual chart review. We compared the various methods by calculating their sensitivity, specificity, and predictive values.

Results:

Twenty in-hospital falls were discovered in the development study sample. Of these, the algorithm discovered 19 (sensitivity 95%), the GTT 18 (90%) and incident reports 14 (67%). Of the 15 falls found in the validation sample, the algorithm identified all 15 (100%), the manual chart review 14 (93%) and the patient-reported fall measure 5 (33%). Owing to relatively high number of false positives (FP) before the hospital stay, the algorithm’s positive predictive values (PPVs) were 50% (development sample) and 47% (validation sample).

Conclusions:

The newly developed EHR algorithm demonstrated very high sensitivity for fall detection. Applied in near-real time, the algorithm can record in-hospital falls events effectively and help to develop and test fall prevention measures.