When the machine is wrong. Characteristics of true and false predictions of Out-of-Hospital Cardiac arrests in emergency calls using a machine-learning model

Blomberg, Stig Nikolaj; Jensen, Theo Walther; Andersen, Mikkel Porsborg; Folke, Fredrik; Ersbøll, Annette Kjær; Torp-Petersen, Christian; Lippert, Freddy; Christensen, Helle Collatz

doi:10.1016/j.resuscitation.2023.109689

Cited by 11 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MLM did not recognize OHCA in 15.5% cases, it identified false positivity in 2.4% (ref. 18 ). A large group of callers from the unrecognized OHCA group were callers with a language barrier, therefore one of the conclusions of the authors of the study is to widen the pool of language patterns for MLM (ref.…”

Section: Artificial Intelligence and Machine Learning Modelsmentioning

confidence: 99%

“…A large group of callers from the unrecognized OHCA group were callers with a language barrier, therefore one of the conclusions of the authors of the study is to widen the pool of language patterns for MLM (ref. 18 ). That MLM is able to analyse in advance learnt patterns sufficiently quickly was also confirmed by the study of authors from Sweden.…”

Section: Artificial Intelligence and Machine Learning Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Current trends in the management of out of hospital cardiac arrest (OHCA)

Plodr,

Chalusova

2024

Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub

View full text Add to dashboard Cite

Sudden cardiac arrest remains a relevant problem with a significant number of deaths worldwide. Although survival rates have more than tripled over the last 20 years (4% in 2001 vs. 14% in 2020), survival rates with good neurological outcomes remain persistently low, representing a major socioeconomic problem. Every minute of delay from patient collapse to start cardiopulmonary resuscitation (CPR) and early defibrillation reduces the chance of survival by approximately 10-12%. Therefore, the time to treatment is a crucial factor in the prognosis of patients with out-of-hospital cardiac arrest (OHCA). Research teams working in the pre-hospital setting are therefore looking for ways to improve the transmission of information from the site of an emergency event and to make it easier for emergency medical dispatch centres (EMDC) to recognise life-threatening conditions with minimal deviation. For emergency unit procedures already at the scene of the event, methods are being sought to efficiently and temporarily replace a non-functioning cardiopulmonary system. In the case of traumatic cardiac arrest (TCA), the focus is mainly on effective affecting noncompressible haemorrhage.

show abstract

Section: Artificial Intelligence and Machine Learning Modelsmentioning

confidence: 99%

Section: Artificial Intelligence and Machine Learning Modelsmentioning

confidence: 99%