The “unclear problem” category: an analysis of its patient and dispatch characteristics and its trend over time

Artificial intelligence in emergency medicine. A systematic literature review

Motivation and objective: Emergency medicine is becoming a popular application area for artificial intelligence methods but remains less investigated than other healthcare branches. The need for time-sensitive decision-making on the basis of high data volumes makes the use of quantitative technologies inevitable. However, the specifics of healthcare regulations impose strict requirements for such applications. Published contributions cover separate parts of emergency medicine and use disparate data and algorithms. This study aims to systematize the relevant contributions, investigate the main obstacles to artificial intelligence applications in emergency medicine, and propose directions for further studies.

METHODS

The contributions selection process was conducted with systematic electronic databases querying and filtering with respect to established exclusion criteria. Among the 380 papers gathered from IEEE Xplore, ACM Digital Library, Springer Library, ScienceDirect, and Nature databases 116 were considered to be a part of the survey. The main features of the selected papers are the focus on emergency medicine and the use of machine learning or deep learning algorithms.

FINDINGS AND DISCUSSION

The selected papers were classified into two branches: diagnostics-specific and triage-specific. The former ones are focused on either diagnosis prediction or decision support. The latter covers such applications as mortality, outcome, admission prediction, condition severity estimation, and urgent care prediction. The observed contributions are highly specialized within a single disease or medical operation and often use privately collected retrospective data, making them incomparable. These and other issues can be addressed by creating an end-to-end solution based on human-machine interaction.

CONCLUSION

Artificial intelligence applications are finding their place in emergency medicine, while most of the corresponding studies remain isolated and lack higher generalization and more sophisticated methodology, which can be a matter of forthcoming improvements.

Registered prodromal symptoms of out-of-hospital cardiac arrest among patients calling the medical helpline services

Background Early identification of warning symptoms among out-of-hospital cardiac arrest (OHCA) patients remains challenging. Thus, we examined the registered prodromal symptoms of patients who called medical helpline services within 30-days before OHCA. Methods Patients unwitnessed by emergency medical services (EMS) aged ≥18 years during their OHCA were identified from the Danish Cardiac Arrest Registry (2014-2018) and linked to phone records from the 24-h emergency helpline (1-1-2) and out-of-hours medical helpline (1813-Medical Helpline) in Copenhagen before the arrest. The registered symptoms were categorized into chest pain; breathing problems; central nervous system (CNS)-related/unconsciousness; abdominal/back/urinary; psychiatric/addiction; infection/fever; trauma/exposure; and unspecified (diverse from the beforementioned categories). Analyses were divided by the time-period of calls (0-7 days/8-30 days preceding OHCA) and call type (1-1-2/1813-Medical Helpline). Results Of all OHCA patients, 18% (974/5442) called helpline services (males 56%, median age 76 years[Q1-Q3:65-84]). Among these, 816 had 1145 calls with registered symptoms. The most common symptom categories (except for unspecified, 33%) were breathing problems (17%), trauma/exposure (17%), CNS/unconsciousness (15%), abdominal/back/urinary (12%), and chest pain (9%). Most patients (61%) called 1813-Medical Helpline, especially for abdominal/back/urinary (17%). Patients calling 1-1-2 had breathing problems (24%) and CNS/unconsciousness (23%). Nearly half of the patients called within 7 days before their OHCA, and CNS/unconsciousness (19%) was the most registered. The unspecified category remained the most common during both time periods (32%;33%) and call type (24%;39%). Conclusions Among patients who called medical helplines services up to 30-days before their OHCA, besides symptoms being highly varied (unspecified (33%)), breathing problems (17%) were the most registered symptom-specific category.

Diagnoses and mortality among prehospital emergency patients calling 112 with unclear problems: a population-based cohort study from Denmark

BACKGROUND

Patients calling for an emergency ambulance and assessed as presenting with 'unclear problem' account for a considerable part of all emergency calls. Previous studies have demonstrated that these patients are at increased risk for unfavourable outcomes. A deeper insight into the underlying diagnoses and outcomes is essential to improve prehospital treatment. We aimed to investigate which of these diagnoses contributed most to the total burden of diseases in terms of numbers of deaths together with 1- and 30-day mortality.

METHODS

A historic regional population-based observational cohort study from the years 2016 to 2018. Diagnoses were classified according to the World Health Organisation ICD-10 System (International Statistical Classification of Diseases and Related Health Problems, 10th edition). The ICD-10 chapters, R ('symptoms, signs and abnormal clinical and laboratory findings, not elsewhere classified)' and Z ('factors influencing health status and contact with health services") were combined and designated "non-specific diagnoses". Poisson regression with robust variance estimation was used to estimate proportions of mortality in percentages with 95% confidence intervals, crude and adjusted for age, sex and comorbidities.

RESULTS

Diagnoses were widespread among the ICD-10 chapters, and the most were 'non-specific diagnoses' (40.4%), 'circulatory diseases' (9.6%), 'injuries and poisonings' (9.4%) and 'respiratory diseases' (6.9%). The diagnoses contributing most to the total burden of deaths (n = 554) within 30 days were 'circulatory diseases' (n = 148, 26%) followed by 'non-specific diagnoses' (n = 88, 16%) 'respiratory diseases' (n = 85, 15%), 'infections' (n = 54, 10%) and 'digestive disease' (n = 39, 7%). Overall mortality was 2.3% (1-day) and 7.1% (30-days). The risk of mortality was highly associated with age.

CONCLUSION

This study found that almost half of the patients brought to the hospital after calling 112 with an 'unclear problem' were discharged with a 'non-specific diagnosis' which might seem trivial but should be explored more as these contributed the second-highest to the total number of deaths after 30 days only exceeded by 'circulatory diseases'.

Zwei Jahre Pilotphase Gemeindenotfallsanitäter in der Region Oldenburg (Niedersachsen)

Hintergrund

Steigende Einsatzzahlen im Rettungsdienst, demografischer Wandel sowie Veränderungen bei der Morbidität und in den Strukturen der Akutversorgung erfordern eine Weiterentwicklung der Versorgungsoptionen an den Sektorengrenzen zwischen ambulanter und stationärer Versorgung. Zur Erprobung von Gemeindenotfallsanitätern (G-NFS) als eine unterstützende Ressource des Rettungsdienstes wird in der Region Oldenburg seit 2019 ein Modellprojekt mit wissenschaftlicher Begleitung durchgeführt.

Methodik

Im Rahmen einer Mixed-Methods-Studie wurden Fokusgruppeninterviews mit den vier regionalen G‑NFS-Gruppen (Stadt Oldenburg und die Kreise Vechta, Cloppenburg und Ammerland) durchgeführt. Die Interviews (Teilnahme ca. 56,7 % aller G‑NFS) wurden jeweils durch eine kurze anonyme Online-Umfrage (Teilnahme ca. 53,3 % aller G‑NFS) mit denselben Teilnehmern ergänzt. Interviews und Online-Befragung zielten auf die persönlichen Einsatzerfahrungen vor und während der Coronapandemie ab. Die Interviewergebnisse wurden anhand thematischen Codierens analysiert und ausgewertet.

Ergebnisse

An den Interviews und der anschließenden Umfrage nahmen 17 bzw. 16 G-NFS teil. Aus Sicht der G‑NFS ergänzt die Ressource das bisherige Reaktionsspektrum des Rettungsdienstes in Form von Rettungswagen (RTW) oder Krankentransportwagen (KTW) um eine sinnvolle und fachgerechte Komponente, die insbesondere zur erforderlichen Entlastung der Einsatzmittel der Notfallversorgung beiträgt. Die notwendige sektorenübergreifende Zusammenarbeit mit anderen Diensten verläuft in Abhängigkeit von den jeweiligen lokalen Gegebenheiten unterschiedlich, aber insgesamt zielgerichtet und effizient; Gleiches gilt für die Zusammenarbeit mit den zuständigen Rettungsleitstellen. G‑NFS wurden in den Hochphasen der Pandemie in die Triagierung von COVID-Verdachtsfällen einbezogen und haben zur dringend gebotenen Entlastung des Rettungssystems in der Region beigetragen.

Diskussion

Das G‑NFS-Konzept hat sich aus Sicht der Mitarbeiter in der bisherigen Projektlaufzeit bewährt. Die vorliegenden Erfahrungen bieten eine gute Grundlage für die konzeptionelle Weiterentwicklung des G‑NFS.