Search

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.

Abstract Background The safety of the Emergency Medical Service’s (EMS’s) non-conveyance decision was evaluated by EMS re-contacts, primary health care or emergency department (ED) visits, and hospitalization within 48 h. The secondary outcome was 28-day mortality. Methods This cohort study used prospectively collected data on non-conveyed EMS patients from three different regions in Finland between June 1 and November 30, 2018. The Adjusted International Classification of Primary Care (ICPC2) as the reason for care was compared to hospital discharge diagnoses (ICD10). Multivariable logistic regressions were used to determine factors that were independently associated with adverse outcomes. Results are presented with adjusted odds ratios (aORs) together with 95% confidence intervals (CIs). Data regarding deceased patients were reviewed by the study group. Results Of the non-conveyed EMS patients (n = 11,861), 6.3% re-contacted the EMS, 8.3% attended a primary health care facility, 4.2% went to the ED, 1.6% were hospitalized, and 0.1% died 0–24 h after the EMS mission. The 0–24 h adverse event rate was higher than 24–48 h. After non-conveyance, 32 (0.3%) patients were admitted to an intensive care unit within 24 h. Primary non-urgent EMS mission (aOR 1.49; 95% CI 1.25 to 1.77), EMS arrival at night (aOR 1.82; 95% CI 1.58 to 2.09), ALS unit type vs BLS (aOR 1.43; 95% CI 1.16 to 1.77), rural area (aOR 1.74; 95% CI 1.51 to 1.99), and older patient age (aOR 1.41; 95% CI 1.20 to 1.66) were associated with subsequent primary health care visits (0–24 h). Conclusions Four in five non-conveyed patients did not have any re-contact in follow-up period. EMS non-conveyance seems to be a relatively safe method of focusing ED resources and avoiding ED crowding.