FreshRSS

🔒
❌ Acerca de FreshRSS
Hay nuevos artículos disponibles. Pincha para refrescar la página.
AnteayerTus fuentes RSS

Artificial intelligence to improve the detection and risk stratification of acute pulmonary embolism (AID-PE): protocol for a pragmatic quasi-experimental comparator study

Por: Gunning · S. G. S. · Page · J. · Rossdale · J. · Charters · P. F. P. · Hudson · B. · Lyen · S. · Mackenzie Ross · R. · Seatter · A. · Bartlett · J. W. · Austin · L. · Myring · G. · McLeod · H. · Mitchell · P. · Stimpson · D. · Cookson · A. · Suntharalingam · J. · Rodrigues · J. C. L.
Introduction

Pulmonary embolism (PE) is a potentially fatal condition requiring timely diagnosis and treatment. CT pulmonary angiography (CTPA) is the gold standard for diagnosis and indicates PE severity through radiological markers of right heart strain. However, accurate interpretation and communication of these findings is often suboptimal in real-world practice. Artificial intelligence (AI) could alleviate pressure on radiology services by supporting PE identification, risk stratification and worklist prioritisation. Before widespread adoption, AI tools must be rigorously validated for diagnostic accuracy, safety and clinical impact.

Methods and analysis

This pragmatic single-centre, non-randomised quasi-experimental study will evaluate the diagnostic accuracy, feasibility, and clinical-cost impact of AI-assisted PE detection and risk stratification using AIDOC and IMBIO software. We will recruit two consecutive cohorts of adult patients undergoing CTPAs for suspected PE: a comparator cohort (12 months pre-AI implementation) and an intervention cohort (12 months post-AI implementation). AI will be applied retrospectively to the comparator cohort, while in the intervention cohort, radiologists will have contemporaneous access to the AI’s interpretation of CTPA images.

A subset of retrospective scans, both PE-positive and PE-negative, will undergo expert thoracic radiologist review to establish a reference standard. Data on patient demographics, clinical management and outcomes will be collected. Clinical management pathways and patient outcomes will be compared between cohorts to assess AI’s influence on acute PE management. Health economic modelling will assess the cost-effectiveness of integrating AI technology within the diagnostic workflow of acute PE.

Ethics and dissemination

This study was approved by the UK Healthcare Research authority (IRAS 311735, 10 May 2023). Ethical approval was granted by West of Scotland Research Ethics Service (23/WS/0067, 3 May 2023). Results will be shared with stakeholders, presented at national and international conferences, and published in open-access peer-reviewed journals.

Trial registration number

NCT06093217.

Is this to be another project that fizzles out? Using the i‐PARIHS framework to evaluate implementation of a mentoring programme

Abstract

It is well-known that the implementation of evidence into clinical practice is complex and challenging. The integrated Promoting Action on Research Implementation in Health Services (i-PARIHS) framework conceptualizes successful implementation of evidence into practice. As the implementation of the mentoring programme proved to be a challenge, it seemed valuable to retrospectively study the implementation process using a framework like the i-PARIHS.

Aim

The aim of this study was to evaluate implementation of a multifaceted mentoring programme for bedside nurses using the i-PARIHS framework, to identify factors that influenced the implementation.

Design

A secondary analysis of qualitative data using the i-PARIHS framework as the theoretical lens.

Method

A directed content analysis was performed, driven theoretically by the i-PARIHS framework. The analysis focused separately on (a) characteristics of the innovation and (b) successful and hindering factors in the implementation process.

Results

The results showed that successful factors influencing implementation of the mentoring programme included supportive and actively involved formal leaders and supervisors at the unit level. A major hindering factor was lack of resources in the form of personnel, time and money. A lack of facilitators, particularly experienced facilitators, throughout the organization hindered implementation. The i-PARIHS framework offered a structured how-to guide to identify factors that influenced the implementation process.

Conclusion

Implementation of the mentoring programme was a challenge for the organization. Investment into implementation should continue, with a more structured facilitation process. A structured and prioritized management system, including supportive leadership at the unit level, should be established by the hospital board.

Implications for the profession

There is a need for experienced facilitators throughout the organization. This is crucial to achieve sustainability in the mentoring programme and ensure that the large investments of staff resources and money do not fizzle out.

Impact

What problem did the study address?

Implementing a mentoring programme for nurses in a large university hospital proved to be a challenge. Therefore, it seemed valuable to retrospectively study the implementation process using a framework like the i-PARIHS.

What were the main findings?

A lack of facilitators, particularly experienced facilitators, throughout the organization hindered the implementation. The i-PARIHS framework offered a structured how-to guide to identify factors that influenced the implementation process.

Where and on whom will the research have an impact?

Our findings are important for leaders on all levels in a hospital setting, including the hospital board, heads of departments and nurse managers.

Reporting Method

Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groups is used.

Patient or Public Contribution

No patient or public contribution.

❌