Neil Barr

Dr. Neil Barr


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
SMSankavi Muralitharan
Sankavi Muralitharan
WNWalter Nelson
Walter Nelson
SDShuang Di
Shuang Di
MMMichael McGillion
Michael McGillion
PDPhilip J Devereaux
Philip J Devereaux
JPJeremy Petch
Jeremy Petch
Background: Timely identification of patients at a high risk of clinical deterioration is key to prioritizing care, allocating resources effectively, and preventing adverse outcomes. Vital signs–based, aggregate-weighted early warning systems are commonly used to predict the risk of outcomes related to cardiorespiratory instability and sepsis, which are strong predictors of poor outcomes and mortality. Machine learning models, which can incorporate trends and capture relationships among parameters that aggregate-weighted models cannot, have recently been showing promising results. Objective: This study aimed to identify, summarize, and evaluate the available research, current state of utility, and challenges with machine learning–based early warning systems using vital signs to predict the risk of physiological deterioration in acutely ill patients, across acute and ambulatory care settings. Methods: PubMed, CINAHL, Cochrane Library, Web of Science, Embase, and Google Scholar were searched for peer-reviewed, original studies with keywords related to “vital signs,” “clinical deterioration,” and “machine learning.” Included studies used patient vital signs along with demographics and described a machine learning model for predicting an outcome in acute and ambulatory care settings. Data were extracted following PRISMA, TRIPOD, and Cochrane Collaboration guidelines. Results: We identified 24 peer-reviewed studies from 417 articles for inclusion; 23 studies were retrospective, while 1 was prospective in nature. Care settings included general wards, intensive care units, emergency departments, step-down units, medical assessment units, postanesthetic wards, and home care. Machine learning models including logistic regression, tree-based methods, kernel-based methods, and neural networks were most commonly used to predict the risk of deterioration. The area under the curve for models ranged from 0.57 to 0.97. Conclusions: In studies that compared performance, reported results suggest that machine learning–based early warning systems can achieve greater accuracy than aggregate-weighted early warning systems but several areas for further research were identified. While these models have the potential to provide clinical decision support, there is a need for standardized outcome measures to allow for rigorous evaluation of performance across models. Further research needs to address the interpretability of model outputs by clinicians, clinical efficacy of these systems through prospective study design, and their potential impact in different clinical settings.

6 June 2017 in Journal of Health Services Research & Policy
Verified
Journal Article
Closed access
NBNeil Barr
Neil Barr
DVDiana Vania
Diana Vania
GRGlen Randall
Glen Randall
GMGillian Mulvale
Gillian Mulvale
Objectives: Information and communication technology is often lauded as the key to enhancing communication among health care providers. However, its impact on interprofessional collaboration is unclear. The objective of this study was to determine the extent to which it improves communication and, subsequently, enhances interprofessional collaboration in chronic disease management. Methods: A systematic review of academic literature using two electronic platforms: HealthSTAR and Web of Science (core collection and MEDLINE). To be eligible for inclusion in the review, articles needed to be peer-reviewed; accessible in English and focused on how technology supports, or might support, collaboration (through enhanced communication) in chronic disease management. Studies were assessed for quality and a narrative synthesis conducted. Results: The searches identified 289 articles of which six were included in the final analysis (three used qualitative methods, two were descriptive and one used mixed methods). Various forms of information and communication technology were described including electronic health records, online communities/learning resources and telehealth/telecare. Three themes emerged from the studies that may provide insights into how communication that facilitates collaboration in chronic disease management might be enhanced: professional conflict, collective engagement and continuous learning. Conclusions: The success of technology in enhancing collaboration for chronic disease management depends upon supporting the social relationships and organization in which the technology will be placed. Decision-makers should take into account and work toward balancing the impact of technology together with the professional and cultural characteristics of health care teams.

20 February 2017 in Community Mental Health Journal
Verified
Journal Article
Closed access
PDF file
TNTram Nguyen
Tram Nguyen
MEMark Embrett
Mark Embrett
NBNeil Barr
Neil Barr
GMGillian M. Mulvale
Gillian M. Mulvale
DVDiana K. Vania
Diana K. Vania
BDBriano DiRezze
Briano DiRezze

23 October 2017 in Healthcare Management Forum
Verified
Journal Article
Closed access
NBNeil Barr
Neil Barr
CLChristopher J. Longo
Christopher J. Longo
MEMark Embrett
Mark Embrett
GMGillian M. Mulvale
Gillian M. Mulvale
TNTram Nguyen
Tram Nguyen
GRGlen E. Randall
Glen E. Randall
The transition from Child and Adolescent Mental Health Services (CAMHS) to Adult Mental Health Services (AMHS) can be challenging for youth, their families, and healthcare providers. The purpose of this study was to identify, summarize, and assess evidence found in scholarly literature regarding the economic impact on youth and their families during the transition from CAMHS to AMHS. Relevant studies were identified through a search of 7 electronic platforms. The search identified 829 articles; 5 of which met all inclusion criteria. Evidence from the included studies suggests that, when continuity of care is lacking, transitions from CAMHS to AMHS have substantial impacts on the financial demands of youth and their families. These demands are due to increases in the cost of care, loss of employment income and productivity, and changes in insurance coverage. However, there remains limited information in this area, which highlights the need for further research.

9 October 2017 in Health Informatics Journal
Verified
Journal Article
Closed access
NBNeil Barr
Neil Barr
GRGlen E Randall
Glen E Randall
NANorman P Archer
Norman P Archer
DMDavid M Musson
David M Musson
The use of Internet-enabled technology (information and communication technology such as smartphone applications) may enrich information exchange among providers and, consequently, improve health care delivery. The purpose of this systematic review was to gain a greater understanding of the role that Internet-enabled technology plays in enhancing communication among physicians. Studies were identified through a search in three electronic platforms: the Association for Computing Machinery Digital Library, ProQuest, and Web of Science. The search identified 5140 articles; of these, 21 met all inclusion criteria. In general, physicians were satisfied with Internet-enabled technology, but consensus was lacking regarding whether Internet-enabled technology improved efficiency or made a difference to clinical decision-making. Internet-enabled technology can play an important role in enhancing communication among physicians, but the extent of that benefit is influenced by (1) the impact of Internet-enabled technology on existing work practices, (2) the availability of adequate resources, and (3) the nature of institutional elements, such as privacy legislation.

11 September 2019 in Health Information Management Journal
Verified
Journal Article
Closed access
PDF file
NBNeil Barr
Neil Barr
GRGlen E Randall
Glen E Randall
Background: The use of information and communication technology (ICT) has tremendous potential to enhance communication among physicians, leading to improvements in service delivery. However, the protection of health information in digital/electronic format is an ongoing concern. Objective: The purpose of this study was to examine guidance for the protection of health information when using ICT from all 10 of Canada’s provincial regulatory colleges for physicians and to discuss the potential policy and service delivery implications. Method: A search of the regulatory college websites was conducted, followed by a document analysis (content and thematic). Results: The college website search identified 522 documents; 12 of these documents (from 8 of the 10 colleges) met the study criteria. These documents were notable for the considerable variation in the scope and detail of guidance provided across the colleges. Conclusion: While the federal–provincial division of powers in Canada enables different jurisdictional approaches to health service delivery and, thus, opportunities for policy learning, this governing structure may also contribute to a lack of incentive for collaboration, leading to an absence of standardised guidance for health information protection when using ICT. This, in turn, may result in unequal and inequitable protection of health information across the provinces. Therefore, a macro-level approach to policy development in this area may hold the greatest promise for enhancing the protection of health information and doing so in a more standardised manner in countries with federal systems of governance.