MétaCan
Menu
Retour à la cohorte
Enregistrement W4393167764 · doi:10.4103/singaporemedj.smj-2023-217

Digitisation of emergency medicine: opportunities, examples and issues for consideration

2024· article· en· W4393167764 sur OpenAlexaffabout
Kendall Ho

Notice bibliographique

RevueSingapore Medical Journal · 2024
Typearticle
Langueen
DomaineMedicine
ThématiqueEmergency and Acute Care Studies
Établissements canadiensUniversity of British Columbia
Organismes subventionnairesnon disponible
Mots-clésData scienceMedical emergencyMedicineEngineering ethicsComputer scienceEngineering

Résumé

récupéré en direct d'OpenAlex

INTRODUCTION: EMERGENCY MEDICINE IN CRISIS Globally, health systems are facing unprecedented pressure in meeting patients’ needs as we emerge from coronavirus disease 2019 (COVID-19) to a new normal. Emergency departments (EDs), often referred to as the ‘canary in the coal mine’[1] that reflects the state of the health systems, are currently close to reaching the breaking point with severe overcrowding and long wait times.[2] The causes of this ED crisis are multifactorial including, but not limited to, the following: (a) lack of community-based healthcare access due to shortage of primary care health professionals and low after-hours access to health services, (b) attrition of emergency health professionals due to COVID-19 and post COVID-19 retirements, and (c) insufficient hospital-based physicians and nurses, resulting in understaffing of hospital wards, which eventually leads to patients having to be boarded in ED beds for prolonged periods before admission. As a result, patient experience suffers due to long wait times to see health professionals. Health system effectiveness is compromised, as patients who truly needed ED care may not receive timely care while those not needing ED services could have been served more optimally somewhere else. Emergency health professionals’ experience is impaired, as they are constantly stressed with having to handle an exceptionally high patient volume with no relief, contributing to accelerated burnout. To break this vicious cycle, hiring more ED health professionals and improving primary care access to family doctors are necessary. In addition, novel health system solutions are also called for to increase ED capacity to serve our patients. This article will explore how digital health can introduce innovative approaches to complement conventional solutions, bringing relief to the current crisis and creating unprecedented initiatives to support excellence in emergency care. DIGITISATION OF EMERGENCY MEDICINE Modern information and communication technologies, such as mobile phones, health apps, medical devices and wearables/sensors, are rapidly being developed and introduced into healthcare. Health professionals, patients, health administrators and technology companies are all interested in this pursuit of digital health from different perspectives. The discipline of emergency medicine can benefit greatly from digital health in practice.[3,4,5] Patient journeys through emergency medicine can be visualised conceptually in three phases: input, throughout and output.[6] This article will introduce each of these phases, discuss examples of technology-enabled solutions to illustrate how digitisation can support and enhance ED care and services, and identify issues for considerations when implementing these solutions. Input: prehospital When urgent, unexpected health issues occur, patients and their caregivers immediately consider whether these issues need to be addressed immediately, for example, sudden onset of chest pain or the first infection of a very young baby. The health system needs to assist these individuals in their timely decision-making with reliable health information and professional counsel. Decision support tools for patients, such as websites,[7,8] health apps[9,10] or chatbots[11] based on reliable information curated or shared from trusted sources, inform them to determine their next steps.Telephone based services such as 8-1-1 in Canada, healthdirect in Australia, 6-1-1-7-1-1 in Germany and 1-1-2 in UK are meant to support their citizens in real time to personalise advice tailored to patients’ individual needs. In March 2020, at the onset of COVID, with a surge of call volume, the HealthLinkBC 8-1-1 service in the Province of British Columbia (BC), Canada, which traditionally was also a phone based nurse service, added virtual physicians to complement nursing service to add assessment dimensions using both phone and videoconferencing, so that individuals can counselled at their own homes.[12] This combination of nursing and physician virtual care services resulted in over 70% of patients getting diverted away from EDs to other services such as walk-in clinics or following up with their own doctors at later times or safely managing their issues at home.[13] This type of virtual care can help individuals to obtain accurate health advice, relieve their anxiety and reduce unnecessary ED visits, thus alleviating ED waiting room overcrowding. For patients being sent from home to ED, further digital approaches can improve communication and safety, such as transmission of electronic records, vital signs or electrocardiograms of patients from pre-hospital services to ED.[14,15,16,17] Throughput: emergency department assessment and management During ED visits, enabling technologies to facilitate entries of information by patients themselves, such as chatbots or self-service kiosks, are increasingly deployed to accelerate registration.[18,19,20] In addition, we explore two examples of technology-enabled opportunities that can help improve safety and quality of care during patients’ ED visits.. Physiological sensors Due to overcrowding, patients visiting ED frequently experience prolonged delay in the waiting room before being seen and assessed by ED health professionals.[21] Nurses have trouble monitoring all the patients waiting to be seen after the initial triage. If the patient’s condition changes during the wait, it can easily escape detection. This could result in patients experiencing worsening morbidity or even unexpected mortality in the waiting room.[22] Applying physiological, wearable sensors to continuously monitor vital signs of patients can be beneficial to ensure patient stability while waiting, and also detect unexpected changes or deteriorations that may warrant accelerated interventions.[23] Initiation of such an approach is taking place with usability testing of both wearable[24] and contactless sensors,[25] and identifying ways to integrate such monitoring processes into the health professional workflow and patient journeys in ED. Further consideration of monitoring selected patients throughout their ED visit may also conceivably provide robust data about these patients and speed up decision process for patient disposition, thereby shortening patients’ duration of ED visits and reducing ED congestion.[26] Peer-to-peer virtual consultations Many patient ED visits can become time consuming when patients wait for speciality consultations, such as an orthopaedic consultation for patients with bone injuries who may or may not require admission or patients with skin conditions requiring dermatologists’ assessment to determine appropriate follow-up approaches. Conventionally, specialists or their trainees go to ED to see the patients in person. If these consultants are located far from ED when first contacted, the time taken to reach ED will significantly delay these consultations. Virtual care can facilitate consultants to connect digitally with the emergency health professionals to understand the reasons for consultation and assess selected patients via video to speed up disposition plans. In addition, in non-urban ED where there is a lack of range of specialists, having these specialists provide opinions virtually, where historically it would have been impossible, is transformative. The BC real-time virtual support network provides such a provincial patient-directed and peer-to-peer network to facilitate these types of consultations, also known as ‘tele-collaboration’ in the Singapore context,[27] to address ED patient needs and relieve congestion.[28] Output: patient disposition At the time of disposition, the opportunities to use monitoring technologies to support patient transition back home can occur in novel ways. For patients who need some monitoring but may not require hospital admissions, using remote patient monitoring solutions, such as oxygen saturation for patients with COVID-19 stable enough to go home, would be one way of avoiding their hospitalisation safely.[29] Discharging these patients to community-based virtual care services offered by their own family physicians, primary care practitioners or other virtual care providers could be additional options.[30,31,32] For well-selected patients with medical conditions, such as heart failure or infections that conventionally require hospital admissions, ‘Hospital at Home’ is a patient management model that discharges patients home, so that they can be treated in the comfort of their own homes, with health professionals visiting their homes to manage their conditions, administer therapies and remotely monitor their conditions between visits.[33] All these approaches exploit digital technologies to transition patients from hospitals to homes with virtual follow-up and monitoring to provide safe patient care at home, thereby freeing up emergency and hospital beds for other patients who require hospital admissions to receive treatment safely. The ability to discharge patients home also reduces bed blocking in ED, thus helping to alleviate ED congestion. ARTIFICIAL INTELLIGENCE The benefits of digitisation of ED services lie in not only the delivery of its services, but also the opportunity to mine the captured data from the patients and the electronic records to support the application of artificial intelligence (AI) to improve ED operations, patient care, and population and public health.[34] Examples include decision support of clinicians in the risk stratification of patients with diseases such as syncope,[35] prediction of frequent ED use,[36] prediction models of severity of patient illnesses in ED for their timely triage and management,[37,38] and even risk prediction of illnesses and management for better public health and prevention of emergency visits before they happen.[39] These emerging AI models are in their infancy as emergency medicine is just starting its digitisation journey, and the number and variety of AI applications are expected to grow rapidly in the near future. CHALLENGES IN DIGITAL EMERGENCY MEDICINE While digitisation of emergency medicine is gaining ground in popularity and usage, there are also associated challenges and limitations that warrant consideration, including data security and privacy concerns, limitations in examining patients, health equity and access concerns, health human resources issues in usurping emergency physicians from in-person EDs to staffing virtual services, and the perception that virtual ED visits may paradoxically increase in-person visits.[40] Therefore, it is important and worthwhile to conduct further health services research to discern the best practices in digital emergency medicine and how to optimally integrate it with in-person healthcare services towards seamless hybrid care. CONCLUSION Health systems globally are looking for innovative solutions to reduce ED overcrowding and improve services. Digitisation of emergency medicine offers innovative approaches and solutions worthy of evaluation, implementation and validation. In the end, digitising medicine is just an approach; what is foundational and transformative is understanding how the discipline of emergency medicine can grow in innovative and unconventional ways to serve patients, taking advantage of technologies and enabling tools in doing so. Knowledge of the advantages and pitfalls of digitisation of emergency medicine is important to ensure judicious integration of technology-enabled care into our health services to best serve our patients in times of their urgent health needs and crises. Financial support and sponsorship Nil. Conflicts of interest There are no conflicts of interest.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.

Comment cette classification a été obtenuedéplier

Prédiction distillée sur la base complète

Imitation des enseignants

Ni prévalence calibrée, ni vérité terrain. Validation humaine à venir. Apprise à partir de 10 348 étiquettes directes de Codex et de 10 348 étiquettes directes de Gemma. Le mode candidate est l'union des têtes enseignantes seuillées; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont ni des étiquettes humaines ni des étiquettes directes de modèles de pointe.

score de la tête « metaresearch » (Codex)0,001
score de la tête « metaresearch » (Gemma)0,002
Version: codex-gemma-dda1882f352aStatut de validation: machine_predicted_unvalidated
Catégories candidatesCharge utile insuffisante (le modèle a refusé de juger)
Catégories consensuellesaucune
DomaineSignal candidat: aucune · Signal consensuel: aucune
Devis d'étudeSignal candidat: Sans objet · Signal consensuel: Sans objet
GenreSignal candidat: Empirique · Signal consensuel: aucune
Score de désaccord entre enseignants0,548
Score d'incertitude au seuil0,999

Scores Codex et Gemma par catégorie

CatégorieCodexGemma
Métarecherche0,0010,002
Méta-épidémiologie (sens strict)0,0000,000
Méta-épidémiologie (sens large)0,0000,000
Bibliométrie0,0000,000
Études des sciences et des technologies0,0000,000
Communication savante0,0000,000
Science ouverte0,0000,000
Intégrité de la recherche0,0000,000
Charge utile insuffisante (le modèle a refusé de juger)0,0020,000

Scores machine (provisoires)

Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.

Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.

Tête enseignante Opus0,136
Tête enseignante GPT0,396
Écart entre enseignants0,260 · la distance entre les deux têtes enseignantes sur ce seul travail
Statut de validationscore_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découle

Classification

machine, non validée

Prédiction automatique; un appel candidat d’une seule tête enseignante, pas un consensus.

Devis d'étudeSans objet
Domainenon disponible
GenreEmpirique

Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».

En bref

Citations2
Publié2024
Routes d'admission2
Résumé présentoui

Explorer davantage

Même revueSingapore Medical JournalMême sujetEmergency and Acute Care StudiesTravaux en français237 207