Interhospital transfer vs. direct presentation of patients with a large vessel occlusion not eligible for IV thrombolysis

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.

ELECTRA-STROKE: Electroencephalography controlled triage in the ambulance for acute ischemic stroke—Study protocol for a diagnostic trial

Background

Endovascular thrombectomy (EVT) is the standard treatment for large vessel occlusion stroke of the anterior circulation (LVO-a stroke). Approximately half of EVT-eligible patients are initially presented to hospitals that do not offer EVT. Subsequent inter-hospital transfer delays treatment, which negatively affects patients' prognosis. Prehospital identification of patients with LVO-a stroke would allow direct transportation of these patients to an EVT-capable center. Electroencephalography (EEG) may be suitable for this purpose because of its sensitivity to cerebral ischemia. The hypothesis of ELECTRA-STROKE is that dry electrode EEG is feasible for prehospital detection of LVO-a stroke.

Methods

ELECTRA-STROKE is an investigator-initiated, diagnostic study. EEG recordings will be performed in patients with a suspected stroke in the ambulance. The primary endpoint is the diagnostic accuracy of the theta/alpha ratio for the diagnosis of LVO-a stroke, expressed by the area under the receiver operating characteristic (ROC) curve. EEG recordings will be performed in 386 patients.

Discussion

If EEG can be used to identify LVO-a stroke patients with sufficiently high diagnostic accuracy, it may enable direct routing of these patients to an EVT-capable center, thereby reducing time-to-treatment and improving patient outcomes.

Clinical trial registration

ClinicalTrials.gov, identifier: NCT03699397.

Access to Endovascular Thrombectomy for Stroke in Rural Versus Urban Regions

PURPOSE

Endovascular thrombectomy (EVT) significantly improves outcomes for acute ischemic stroke patients with large vessel occlusion (LVO) who present in a time sensitive manner. Prolonged EVT access times may reduce benefits for eligible patients. We evaluated the efficiency of EVT services including EVT rates, onset-to-CTA time and onset-to-groin puncture time in our province.

MATERIALS AND METHODS

Three areas were defined: zone I- urban region, zone II-areas within 1 h drive distance from the Comprehensive Stroke Center (CSC); and zone III-areas more than 1hr drive distance from the CSC. In this retrospective cohort study, EVT rate, onset-to-groin puncture time and onset-to-CTA time were compared among the three groups using Krustal-Wallis and Wilcoxon tests.

RESULTS

The EVT rate per 100,000 inhabitants for urban zone I was 8.6 as compared to 5.1 in zone II, and 7.5 in zone III. Compared to zone I (114 min; 95% CI (96, 132); n = 128), mean onset-to-CTA time was 19 min longer in zone II (133 min; 95% CI (77, 189); n = 23; p = 0.0459) and 103 min longer in zone III (217 min, 95% CI (162, 272); n = 44; p < 0.0001). Compared to zone I (209 min, 95% CI (181, 238)), mean onset-to-groin puncture time was 22 min longer in zone II (231 min, 95% CI (174, 288); p = 0.046) but 163 min longer in zone III (372 min, 95% CI (312, 432); p < 0.0001).

CONCLUSION

EVT access in rural areas is considerably reduced with significantly longer onset-to-groin puncture times and onset-to-CTA times when compared to our urban area. This may help in modifying the patient transfer policy for EVT referral.

Direct admission versus secondary transfer for acute ischemic stroke patients treated with thrombectomy: a systematic review and meta-analysis

BACKGROUND AND PURPOSE

Randomized controlled trials have demonstrated that mechanical thrombectomy (MT) could provide more benefit than standard medical care for acute ischemic stroke (AIS) patients due to emergent large vessel occlusion. However, most primary stroke centers (PSCs) are unable to perform MT, and MT can only be performed in comprehensive stroke centers (CSCs) with on-site interventional neuroradiologic services. Therefore, there is an ongoing debate regarding whether patients with suspected AIS should be directly admitted to CSCs or secondarily transferred to CSCs from PSCs. This meta-analysis was aimed to investigate the two transportation paradigms of direct admission and secondary transfer, which one could provide more benefit for AIS patients treated with MT.

METHODS

We conducted a systematic review and meta-analysis through searching PubMed, Embase and the Cochrane Library database up to March 2020. Primary outcomes are as follows: symptomatic intracerebral hemorrhage (sICH) within 7 days; favorable functional outcome at 3 months; mortality in hospital; mortality at 3 months; and successful recanalization rate.

RESULTS

Our pooled results showed that patients directly admitted to CSCs had higher chances of achieving a favorable functional outcome at 3 months than those secondarily transferred to CSCs (OR = 1.26; 95% CI, 1.12-1.42; P < 0.001). In addition, no significant difference was found between the two transportation paradigms in the rate of sICH (OR = 0.86; 95% CI, 0.62-1.18; P = 0.35), mortality in hospital (OR = 0.84; 95% CI, 0.51-1.39; P = 0.51), mortality at 3 months (OR = 1.01; 95% CI, 0.85-1.21; P = 0.91), and successful recanalization (OR = 1.03; 95% CI, 0.88-1.20; P = 0.74). However, in the 100% bridging thrombolysis usage rate subgroup, our subgroup analysis indicated that no difference was found in any outcome between the two transportation paradigms.

CONCLUSION

Patients with AIS directly admitted to CSCs for MT may be a feasible transportation paradigm for AIS patients. However, more large-scale randomized prospective trials are required to further investigate this issue.