Optimising Prehospital Pathways to Improve Acute Stroke Reperfusion Therapy Delivery: Systems-Based Approaches

Chowdhury, Seemub Zaman; Wardman, Daniel L.; Cordato, Dennis; Thomas, Peter; Zagami, Alessandro S; Middleton, Paul; McDougall, Alan; Cheung, Andrew; Manning, Nathan; Wenderoth, Jason; Beran, Roy G.; Spring, Kevin; Calic, Zeljka; Killingsworth, Murray C.; Bhaskar, Sonu

doi:10.1007/s42399-021-01069-x

Cited by 6 publications

(4 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of the low utility of 12-lead ECG and biochemical tests in the prehospital setting, a novel diagnostic tool with vital signs, 3-lead ECG monitoring, and symptoms is warranted to improve the diagnostic accuracy of EMS personnel. Optimized prehospital system interventions in the field of stroke potentially reduce treatment delays and improve clinical outcomes 7 , 8 . With the development of machine learning approaches, early prediction models for stroke have demonstrated their accurate and stable performance 9 .…”

Section: Introductionmentioning

confidence: 99%

Prehospital diagnostic algorithm for acute coronary syndrome using machine learning: a prospective observational study

Takeda

Oami

Hayashi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Rapid and precise prehospital recognition of acute coronary syndrome (ACS) is key to improving clinical outcomes. The aim of this study was to investigate a predictive power for predicting ACS using the machine learning-based prehospital algorithm. We conducted a multicenter observational prospective study that included 10 participating facilities in an urban area of Japan. The data from consecutive adult patients, identified by emergency medical service personnel with suspected ACS, were analyzed. In this study, we used nested cross-validation to evaluate the predictive performance of the model. The primary outcomes were binary classification models for ACS prediction based on the nine machine learning algorithms. The voting classifier model for ACS using 43 features had the highest area under the receiver operating curve (AUC) (0.861 [95% CI 0.775–0.832]) in the test score. After validating the accuracy of the model using the external cohort, we repeated the analysis with a limited number of selected features. The performance of the algorithms using 17 features remained high AUC (voting classifier, 0.864 [95% CI 0.830–0.898], support vector machine (radial basis function), 0.864 [95% CI 0.829–0.887]) in the test score. We found that the machine learning-based prehospital algorithms showed a high predictive power for predicting ACS.

show abstract

Section: Introductionmentioning

confidence: 99%

Prehospital diagnostic algorithm for acute coronary syndrome using machine learning: a prospective observational study

Takeda

Oami

Hayashi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This new design has similar organization, as the one proposed by Brenne et al for palliative care in Norway, and could help picture the different pathways available to cancer patients as done in other studies for other health conditions like acute stroke reperfusion delivery [ 14 , 33 ].…”

Section: Methodsmentioning

confidence: 99%

Identification of an oncological clinical pathway through questionnaires to health professionals

Forrester,

Breitenfeld,

Castelo-Branco

et al. 2023

BMC Health Serv Res

View full text Add to dashboard Cite

Background Clinical Pathways in Oncology can benefit patients using organized interventions to standardize and increase care efficiency. Healthcare systems should have tools to identify their oncological clinical pathways for a better institutional organization to reduce mortality rates and contain costs without compromising quality. Our objective is to determine the regional Oncology Clinical Pathway from a first basic hypothesis using questionnaires directed to healthcare professionals considered key deciders within the Pathway. Methods Study design consisted of data analysis of two structured region-wide questionnaires; built using available literature on Oncology Clinical Pathways, in a Portuguese Healthcare context and pre-tested in a focus group of key deciders (Physicians and nurses with management functions) from which a design was created. Queries analyzed the patients: tumor staging at service arrival; time intervals on tumor suspicion/diagnosis confirmation and diagnosis/first treatment; referral pathway; diagnostic networks and patient Follow-up. One questionnaire was sent to key deciders directly involved with Oncology patients at a Regional Hospital. 15 physicians and 18 nurses of this sample answered the questionnaire (approx. response rate = 67%). Another questionnaire sent to healthcare professionals in Primary Healthcare Centers yielded response rate 19.2%, N = 29 physicians and 46 nurses. Finally, we performed a descriptive analysis and a Cronbach Alpha reliability analysis. Results Our findings reveal: different appreciations of tumor staging at arrival in Primary Healthcare Centers and Regional Hospitals (the latter receiving more metastatic cases); approximately 4 weeks between tumor suspicion-diagnostic and divided opinions regarding diagnostic-treatment time intervals. Primary Healthcare Centers depend on private laboratories for diagnostics confirmation, while the Hospitals resolve this locally. Referral pathways indicate almost half of the patients being sent from primary healthcare centers to National Reference Hospitals instead of a Regional Hospital. Patient follow-up is developed throughout the institutions, however, is more established at Regional Hospitals. As patients advance through the Oncology Clinical Pathway and toward treatment stages the number of healthcare professionals involved reduce. Conclusion Our questionnaires enable us to understand the real pathway between the different institutions involved and the main entry points of the patients into the Oncology Clinical Pathway.

show abstract

“…2, which has similar organization, as the one proposed by Brenne et al for palliative care in Norway, and could help picture the different pathways available to cancer patients as done in other studies for other health conditions like acute stroke reperfusion delivery. (28) (29) The nal versions of the questionnaires were applied con dentially (via online and physically delivered to nurses and physicians) in a local health unit overseeing two regional hospitals and 14 Healthcare Centers in a Portuguese interior region. The study intended to collect quantitative and qualitative data that could help identify and analyze the characteristics of the oncological clinical pathway of this region.…”

Section: Methodsmentioning

confidence: 99%

Identification of an Oncological Clinical Pathway through Questionnaires to health professionals

Forrester

Breitenfeld

Castelo‐Branco

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Quality oncological care demands the joint effort from different healthcare professionals; therefore, Clinical Pathways could benefit a well-defined group of patients using organized interventions to standardize and increase care processes efficiency. The objective is to develop an integrated patient centered care based on evidence guidelines, patients feedback and best practices to facilitate communication and coordination between the multidisciplinary teams. Official health entities should have tools to identify their oncological clinical pathways for a better institutional organization while aiming to reduce mortality rates and contain costs without compromising the quality. Methods With the use of specifically designed questionnaires, we intended to identify a physical oncology clinical pathway. By determining the tumor staging at service arrival; time intervals on tumor suspicion/diagnosis confirmation and diagnosis/first treatment; referral pathway; diagnostic networks and patient Follow-up from a sample of nurses and physicians in a regional health unit, overseeing two regional hospitals (RHs) and 14 primary healthcare centers (PHCs) in a rural interior region in Portugal, we were able to determine and identify the oncology clinical pathway available to cancer patients in the region. Results Our findings point to different appreciations of tumor staging at arrival in PHCs and RHs (the latter receiving more metastatic cases); consensus of approximately 4 weeks between tumor suspicion-diagnostic and divided opinions regarding diagnostic-treatment time interval. Moreover, PHCs depend on private laboratories for their diagnostics confirmation, contrarily to the RHs which are resolved locally. Referral pathways indicate almost half of the patients being sent from primary healthcare centers to National Reference Hospitals instead of being treated at a Regional Hospital. Patient follow-up is carried out throughout the local health unit, however, is more developed at RHs. As patients advance through the clinical pathway and approach their treatment stages the number of healthcare professionals reduce leaving mostly Hospital staff involved in this phase and healthcare centers staff primarily involved in diagnostic stages. Conclusion Our questionnaires helped gain insight on the clinical pathway to not only illustrate it but also analyze important sections, strength of association between its parts and points of entry for patients into the healthcare system.

show abstract

Optimising Prehospital Pathways to Improve Acute Stroke Reperfusion Therapy Delivery: Systems-Based Approaches

Cited by 6 publications

References 108 publications

Prehospital diagnostic algorithm for acute coronary syndrome using machine learning: a prospective observational study

Prehospital diagnostic algorithm for acute coronary syndrome using machine learning: a prospective observational study

Identification of an oncological clinical pathway through questionnaires to health professionals

Identification of an Oncological Clinical Pathway through Questionnaires to health professionals

Contact Info

Product

Resources

About