JMIR Publications

ABSTRACT

Background:

Overcrowding of hospitals and emergency departments (ED’s) is a growing problem. However, not all ED consultations are necessary. For example, 80% of ED patients with chest pain do not suffer from an acute coronary syndrome (ACS). Artificial Intelligence (AI) is useful in analysing (medical) data, and might aid healthcare workers in prehospital clinical decision making before patients are presented to the hospital.

Objective:

The aim of the study was to develop an AI model which would be able to predict ACS before patients visit the ED. The model retrospectively analysed prehospital data acquired by emergency medical services (EMS) nurse paramedics.

Methods:

Patients presenting to the EMS with symptoms suggestive of acute coronary syndrome between September 2018 and September 2020 were included. An AI model using a supervised text classification algorithm was developed to analyze data. Data were analyzed for all 7458 patients (68±15 years, 54% male). Specificity, sensitivity, positive predictive value, and negative predictive value were calculated for control – and intervention groups.

Results:

The AI model had a specificity of 11% and a sensitivity of 99.5% whereas usual care had a specificity of 1% and a sensitivity of 99.5%. The PPV of the AI model was 15% and the NPV was 99%. The PPV of usual care was 13% and the NPV was 94%.

Conclusions:

The AI model was able to predict an ACS in the prehospital setting with an 1100% increase in specificity when compared to usual care, with a similar sensitivity. If applied in daily practice, this could mean an enormous increase in patients who could safely stay at home after EMS consultation.