Explore the vast range of titles available.

Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms. We aimed to develop and validate a set of deep learning algorithms for automated detection of the following key findings from these scans: intracranial haemorrhage and its types (ie, intraparenchymal, intraventricular, subdural, extradural, and subarachnoid); calvarial fractures; midline shift; and mass effect. We retrospectively collected a dataset containing 313 318 head CT scans together with their clinical reports from around 20 centres in India between Jan 1, 2011, and June 1, 2017. A randomly selected part of this dataset (Qure25k dataset) was used for validation and the rest was used to develop algorithms. An additional validation dataset (CQ500 dataset) was collected in two batches from centres that were different from those used for the development and Qure25k datasets. We excluded postoperative scans and scans of patients younger than 7 years. The original clinical radiology report and consensus of three independent radiologists were considered as gold standard for the Qure25k and CQ500 datasets, respectively. Areas under the receiver operating characteristic curves (AUCs) were primarily used to assess the algorithms. The Qure25k dataset contained 21 095 scans (mean age 43 years; 9030 [43%] female patients), and the CQ500 dataset consisted of 214 scans in the first batch (mean age 43 years; 94 [44%] female patients) and 277 scans in the second batch (mean age 52 years; 84 [30%] female patients). On the Qure25k dataset, the algorithms achieved an AUC of 0·92 (95% CI 0·91–0·93) for detecting intracranial haemorrhage (0·90 [0·89–0·91] for intraparenchymal, 0·96 [0·94–0·97] for intraventricular, 0·92 [0·90–0·93] for subdural, 0·93 [0·91–0·95] for extradural, and 0·90 [0·89–0·92] for subarachnoid). On the CQ500 dataset, AUC was 0·94 (0·92–0·97) for intracranial haemorrhage (0·95 [0·93–0·98], 0·93 [0·87–1·00], 0·95 [0·91–0·99], 0·97 [0·91–1·00], and 0·96 [0·92–0·99], respectively). AUCs on the Qure25k dataset were 0·92 (0·91–0·94) for calvarial fractures, 0·93 (0·91–0·94) for midline shift, and 0·86 (0·85–0·87) for mass effect, while AUCs on the CQ500 dataset were 0·96 (0·92–1·00), 0·97 (0·94–1·00), and 0·92 (0·89–0·95), respectively. Our results show that deep learning algorithms can accurately identify head CT scan abnormalities requiring urgent attention, opening up the possibility to use these algorithms to automate the triage process. Qure.ai.

Telephone triage is increasingly used to manage workload in primary care; however, supporting evidence for this approach is scarce. We aimed to assess the effectiveness and cost consequences of general practitioner-(GP)-led and nurse-led telephone triage compared with usual care for patients seeking same-day consultations in primary care. We did a pragmatic, cluster-randomised controlled trial and economic evaluation between March 1, 2011, and March 31, 2013, at 42 practices in four centres in the UK. Practices were randomly assigned (1:1:1), via a computer-generated randomisation sequence minimised for geographical location, practice deprivation, and practice list size, to either GP-led triage, nurse-led computer-supported triage, or usual care. We included patients who telephoned the practice seeking a same-day face-to-face consultation with a GP. Allocations were concealed from practices until after they had agreed to participate and a stochastic element was included within the minimisation algorithm to maintain concealment. Patients, clinicians, and researchers were not masked to allocation, but practice assignment was concealed from the trial statistician. The primary outcome was primary care workload (patient contacts, including those attending accident and emergency departments) in the 28 days after the first same-day request. Analyses were by intention to treat and per protocol. This trial was registered with the ISRCTN register, number ISRCTN20687662. We randomly assigned 42 practices to GP triage (n=13), nurse triage (n=15), or usual care (n=14), and 20 990 patients (n=6695 vs 7012 vs 7283) were randomly assigned, of whom 16 211 (77%) patients provided primary outcome data (n=5171 vs 5468 vs 5572). GP triage was associated with a 33% increase in the mean number of contacts per person over 28 days compared with usual care (2·65 [SD 1·74] vs 1·91 [1·43]; rate ratio [RR] 1·33, 95% CI 1·30–1·36), and nurse triage with a 48% increase (2·81 [SD 1·68]; RR 1·48, 95% CI 1·44–1·52). Eight patients died within 7 days of the index request: five in the GP-triage group, two in the nurse-triage group, and one in the usual-care group; however, these deaths were not associated with the trial group or procedures. Although triage interventions were associated with increased contacts, estimated costs over 28 days were similar between all three groups (roughly £75 per patient). Introduction of telephone triage delivered by a GP or nurse was associated with an increase in the number of primary care contacts in the 28 days after a patient's request for a same-day GP consultation, with similar costs to those of usual care. Telephone triage might be useful in aiding the delivery of primary care. The whole-system implications should be assessed when introduction of such a system is considered. Health Technology Assessment Programme UK National Institute for Health Research.

Purpose Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis. Methods In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (T A ) and time to biopsy diagnosis (T B ). Results The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of T A and T B . In the control group, the T A was 25.6 days [95% CI 22.0–29.9] and T B was 55.9 days [95% CI 45.5–69.6]. In comparison, the experimental group's mean T A was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p <0.001) and mean T B was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p =0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI. Conclusions Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.

Background Ghana has made progress in maternal and newborn health, but significant challenges remain, with maternal mortality at 263 per 100,000 live births and neonatal mortality at 22.8 per 1,000 live births. The Obstetric Triage Implementation Package (OTIP), which includes rapid triage protocols and midwife-led peer training, aims to improve the quality of care in a context of scarce resources. This study evaluates the effectiveness of OTIP in improving maternal and neonatal outcomes and assesses the mechanisms behind the observed effects. Methods A cluster randomized controlled trial will assess the impact of OTIP in 25 high-volume hospitals across Ghana during the final phase of its national roll-out. Hospitals will be randomized into early and late intervention groups. A complementary regression discontinuity analysis will assess the impact of OTIP at the national level. Primary outcomes include process improvements and maternal and neonatal outcomes. Secondary outcomes will assess midwives’ knowledge and attitudes. Data sources include primary surveys of 1,250 mother-newborn pairs and 750 midwives, and administrative records from the Ghana Health Service, Ministry of Health. Discussion A rigorous evaluation of OTIP would be crucial, not only to assess the effectiveness of a program in which the Government of Ghana is already investing, but also to assess the potential applicability of this training model to other areas, and to contribute to the academic literature by filling gaps in our understanding of how different training methods can overcome barriers to the diffusion of new practices. Trial registration Study protocols have been approved by the Ghana Health Service (GHS) Ethics Review Committee (GHS-ERC: 022/05/24). Trial registration number: ISRCTN15629047. Registered on 04/11/2024 while participant enrollment was ongoing, https://doi.org/10.1186/ISRCTN15629047 . The study is hence retrospectively registered.

The “very old intensive care patients” (abbreviated to VOPs; greater than 80 years old) are probably the fastest expanding subgroup of all intensive care unit (ICU) patients. Up until recently most ICU physicians have been reluctant to admit these VOPs. The general consensus was that there was little survival to gain and the incremental life expectancy of ICU admission was considered too small. Several publications have questioned this belief, but others have confirmed the poor long-term mortality rates in VOPs. More appropriate triage (resource limitation enforced decisions), admission decisions based on shared decision-making and improved prediction models are also needed for this particular patient group. Here, an expert panel proposes a research agenda for VOPs for the coming years.

Purpose The effect of pre-triage visual acuity (VA) measurement on triage accuracy in a busy ophthalmic casualty department was investigated as a possible means to improve triage quality. Methods All 576 patients attending the accident and emergency department (A&E) at the Birmingham and Midland Eye Centre (BMEC) over a period of 4 days were included in this prospective cross-sectional study. Patients were assigned to two groups: those who underwent a VA measurement prior to triage ( n  = 242) and a control group who did not have a VA measurement ( n  = 234). Clinicians who were masked from the allocation also assessed whether they agreed with the triage decision after assessing each patient. Results Triage outcomes were recorded for 469 (81%) patients. Those with a pre-triage VA measurement were more likely to be assessed as more urgent ( p  = 0.005) and less likely to be discharged ( p  = 0.04). 248 (43%) patients had clinician response with corresponding triage records, of which 136 (55%) had prior VA measurement and 112 (45%) were in the control group. Clinicians responded that patients with VA measurement prior to triage were more accurately triaged than the control group (66% and 54%; p  = 0.03). Conclusion VA measurement prior to triage can help improve triage accuracy and allow better allocation of resources at an overcrowded eye-dedicated emergency department. However, waiting times may increase due to longer triage duration and more patients to be triaged into urgent pathway. Greater staffing resources may be necessary to complement the proposed change to avoid undermining triage efficiency. Key messages What is known According to the Emergency Eye Care Commissioning Guidance published by the Royal College of Ophthalmologists in 2020, a substantial number of UK hospitals do not reference visual acuity measurements at triage. However, there is a continuous surge in demand for emergency eye care services in the UK, calling for improvements in triage as its relevance increases. What is new Patients with pre-triage VA measurement are found to have a more accurate triage outcome. Pre-triage VA measurement reduces under-triaging. Propose a new triage standard considering visual acuity results of patients.

To treat many patients despite lacking personnel resources, triage is important in disaster medicine. Various triage algorithms help but often are used incorrectly or not at all. One potential problem-solving approach is to support triage with Smart Glasses. In this study, augmented reality was used to display a triage algorithm and telemedicine assistance was enabled to compare the duration and quality of triage with a conventional one. A specific Android app was designed for use with Smart Glasses, which added information in terms of augmented reality with two different methods-through the display of a triage algorithm in data glasses and a telemedical connection to a senior emergency physician realized by the integrated camera. A scenario was created (ie, randomized simulation study) in which 31 paramedics carried out a triage of 12 patients in 3 groups as follows: without technical support (control group), with a triage algorithm display, and with telemedical contact. A total of 362 assessments were performed. The accuracy in the control group was only 58%, but the assessments were quicker (on average 16.6 seconds). In contrast, an accuracy of 92% (P=.04) was achieved when using technical support by displaying the triage algorithm. This triaging took an average of 37.0 seconds. The triage group wearing data glasses and being telemedically connected achieved 90% accuracy (P=.01) in 35.0 seconds. Triage with data glasses required markedly more time. While only a tally was recorded in the control group, Smart Glasses led to digital capture of the triage results, which have many tactical advantages. We expect a high potential in the application of Smart Glasses in disaster scenarios when using telemedicine and augmented reality features to improve the quality of triage.

Chest pain accounts for ∼10% of emergency department visits, though most cases are not acute coronary syndrome (ACS), underscoring the need for effective prehospital triage. The HARTc 2.0 study evaluates the modified History, Electrocardiogram, Age, Risk Factors, and Troponin (HEART) score incorporating point-of-care (POC) high-sensitivity cardiac troponin-I (hs-cTnI) capillary fingerprick testing with sex-specific cut-offs to improve ACS risk stratification. The randomized controlled trial compares a prehospital triage strategy using this modified HEART score and a 0/2-hour POC hs-cTnI algorithm to standard care using HEAR score and in-hospital 0/1-hour hs-cTnT testing. Cost-effectiveness and diagnostic timing are also assessed. The HARTc 2.0 study consists of 4 prospective phases to improve prehospital risk stratification for patients with suspected ACS. Phase 0 investigates technical operability of the Siemens Atellica VTLi POC hs-cTnI device. Phase 1 verifies preanalytical and analytical performance. Phase 2 evaluates clinical comparability between modified HEART score (with POC hs-cTnI) and standard HEART score. Phase 3 is a multicenter randomized controlled trial assessing the impact of prehospital risk stratification—into low, intermediate, or high-risk for ACS—on clinical decision-making, time-to-diagnosis, and cost-effectiveness. This trial evaluates modified HEART score with POC hs-cTnI testing, incorporating sex-specific cut-offs, to improve prehospital ACS risk stratification. Phases 0 and 1 confirm the reliability of capillary whole blood POC hs-cTnI. Furthermore, the trial is a randomized trial which evaluates prehospital risk stratification for ACS using a 0/2-hour POC hs-cTnI algorithm on clinical decision-making, time-to-diagnosis, as well as its cost-effectiveness. Improved prehospital risk stratification for ACS aims to enhance triage accuracy, time-to-diagnosis and time-to-treatment, thereby reducing unnecessary hospital admissions and improve resource allocation in prehospital and emergency care. NL80873.000.22, NL9475 (registered in the Dutch Trial Register, the Netherlands).

Triage is the process of prioritizing patients in the emergency department (ED). This has a pivotal role in ensuring patient safety and that the ED operates smoothly; therefore, triage training education is an important aspect of triage nurses’ preparedness in different emergency situations. This study employed a quasi-experimental research design using a non-equivalent control group pre–post-test design to verify the effect of the Korean Triage and Acuity Scale (KTAS) education using role-playing on the knowledge of triage, triage performance ability, and triage competency in nursing students. Participants were 78 fourth-year nursing students from Shinseong University in South Korea; 39 were assigned to the experimental group, and 39 to the control group. The intervention was conducted for three weeks, from January 31 to February 16, 2024. The experimental group received KTAS education through role-playing, whereas the control group received triage education through lectures. Triage knowledge (t = 2.94, p = .004) and triage performance ability (t = 3.11, p = .003) were significantly improved in the experimental group. However, there was no significant difference in triage competency between groups (t = 1.32, p = .192). The post-test score of triage record in the experimental group showed a significant improvement over time (t = 0.56, p < .001). This study demonstrated that KTAS education using role-playing was more effective in improving triage knowledge and performance ability than traditional lecture methods for nursing students. Triage education programs should be developed considering the effectiveness of various teaching methods.

•There is a lack of evidence from a large prospective, international randomized controlled trial evaluating whether implementing the more rapid ESC-0/1h-algorithm at late-adopting centers across diverse countries and healthcare systems is both safe and effective.•PRESC1SE-MI is among the largest investigator-initiated, international, randomized clinical trials in cardiovascular medicine. It will assess whether the more rapid ESC-0/1h-algorithm is at least as safe and even more effective than the ESC-0/3h-algorithm.•The co-primary endpoint is a composite of type 1 myocardial infarction or all-cause death at 30 days and length of stay in the Emergency Department.•PRESC1SE-MI could improve patient care, reduce overcrowding in the Emergency Department, and lower healthcare costs. International practice guidelines recommend the more rapid European Society of Cardiology (ESC) 0/1h-algorithm for the triage of patients with suspected myocardial infarction (MI) as the preferred option and consider the ESC 0/3h-algorithm as an alternative. However, many centers worldwide have not yet adopted the ESC 0/1h-algorithm in clinical practice due to uncertainty which approach best balances safety and efficacy. PRESC1SE-MI (PRospective Evaluation of the European Society of Cardiology 0/1h-algorithm`s Safety and Efficacy for Triage of Patients with Suspected Myocardial Infarction) is an international, investigator-initiated multicenter, stepped-wedge, cluster randomized controlled trial. At least 52,156 consecutive adult patients with nontraumatic acute chest discomfort and suspected MI presenting to the Emergency Department (ED) will be enrolled. Sites still using the ESC 0/3h-algorithm as standard-of-care will be randomized to implement the more rapid ESC 0/1h-algorithm at an early or late implementation step. During the validation phase, participating sites continue to use the ESC 0/3h-algorithm. The co-primary outcomes are a composite of type 1 MI or all-cause death at 30 days (safety), and the length of stay in the ED (efficacy). The trial is designed to show noninferiority for safety and superiority for efficacy, with a power of at least 90%. PRESC1SE-MI is the largest international multicenter trial to date evaluating the safety and the efficacy of the implementation of the more rapid ESC 0/1h-algorithm at late adopting centers across multiple countries and healthcare systems. Its findings have the potential to improve patient care and reduce healthcare costs. Trial registration:https://clinicaltrials.gov/study/NCT05649384.