Perspectives of radiologists in Ghana about the emerging role of artificial intelligence in radiology

Edzie, Emmanuel Kobina Mesi; Dzefi-Tettey, Klenam; Asemah, Abdul Raman; Brakohiapa, Edmund Kwakye; Asiamah, Samuel; Quarshie, Frank; Amankwa, Adu Tutu; Raj, Amrit; Nimo, Obed; Boadi, Evans; Edzie, Richard Ato; Osei, Bernard; Turkson, Veronica; Kusodzi, Henry

doi:10.1016/j.heliyon.2023.e15558

Cited by 3 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The positive attitudes towards data-driven algorithms indicate a general acceptance of this new technology, consistent with prior research. [27][28][29][30] However, conditions must be met to make them appropriate for clinical care, especially in LRS (e.g. actionability, transparency, explainability).…”

Section: Discussionmentioning

confidence: 99%

“…They also need to be addressed during the implementation process, together with training programmes, to acquire adequate new skills to adopt a critical care strategy incorporating a data-driven algorithm. 30 Training can help nurses recognise conditions that limit the performance of an algorithm and increase con dence in the algorithm's output, for example, when a score does not match the current vital signs, and help nurses interpret the algorithm for the particular case at hand, and decide the most appropriate follow-up clinical steps. 36 Training programmes should be designed for target groups with different levels of clinical expertise, for example, in our case, to address variations in familiarity with vital sign monitoring, data visualisations, and algorithms.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Cautiously optimistic about data-driven algorithms in paediatric critical care, nurses’ perspectives in low-resource settings: a pre-implementation and human-centred design study in Malawi

Rakers,

Mwale,

de Mare

et al. 2024

Preprint

View full text Add to dashboard Cite

Introduction Paediatric critical care nurses face challenges in promptly detecting patient deterioration and delivering high-quality care, especially in low-resource settings (LRS). Patient monitors equipped with data-driven algorithms that integrate monitor and clinical data can optimise scarce resources (e.g. trained staff) offering solutions to these challenges. Poor algorithm output design and workflow integration are important factors hindering successful implementation. This study aims to explore nurses' perspectives to inform the development of a data-driven algorithm and user-friendly interface for future integration into a continuous monitoring system for critical care in LRS. Methods Human-centred design methods, including contextual inquiry, semi-structured interviews, and co-design sessions, were carried out at the high-dependency units of Queen Elizabeth Central Hospital and Zomba Central Hospital in Malawi. Triangulating these methods, and employing qualitative content analysis principles, we identified what algorithm could assist nurses and used co-creation methods to design a user interface prototype. Results Workflow observations demonstrated the effects of personnel shortages and limited monitor equipment availability for vital sign monitoring. Interviews emphasised the advantages of predictive algorithms in anticipating deterioration, underlining the need to integrate the algorithm’s output, the (constant) monitoring data, and the patient's present clinical condition. Nurses preferred a scoring system represented with familiar scales and colour codes. During co-design sessions, trust, usability and context specificity were emphasized as requirements for these algorithms. Four prototype components were examined, with nurses favouring explainable and transparent scores represented by colour codes and visual representations of score changes. Conclusions Nurses in LRS perceive that data-driven algorithms, especially for predicting patient deterioration, could improve the provision of critical care. This can be achieved by translating nurses' perspectives into design strategies, as has been carried out in this study. The lessons learned are summarised as actionable pre-implementation recommendations for the development and implementation of data-driven algorithms in LRS.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Cautiously optimistic about data-driven algorithms in paediatric critical care, nurses’ perspectives in low-resource settings: a pre-implementation and human-centred design study in Malawi

Rakers,

Mwale,

de Mare

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Understanding the factors influencing acceptability of AI in medical imaging domains among healthcare professionals: A scoping review

Hua,

Petrina,

Young

et al. 2024

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Radiology Residents' and Radiologists' Perception and Attitude Towards Medical Artificial Intelligence in Radiology– An Initial National Multicenter Survey

Menur,

Abraham,

Sisay

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction : Recent advances in artificial intelligence and machine learning (AI/ML) are transforming radiology practices. While AI/ML innovations present opportunities to augment radiologists' capabilities, some have expressed concerns about AI/ML potentially replacing radiologists in the future. These uncertainties have led to varied perspectives among radiology professionals regarding the role of AI/ML in the field. This study aimed to assess respondents' knowledge, research involvement, utilization of AI/ML applications, and attitudes towards the impact of AI/ML on radiology practice and training. Methods Between June and July of 2022, we conducted a web-based survey of radiologists and radiology residents from 5 major institutions in Ethiopia with radiology residency programs. The survey was distributed through the Ethiopian Radiological Society, and social media. Group comparison was tested by chi-square test for categorical responses and Mann-Whitney test for ordinal rating scale responses. Results Of the 276 respondents, 94.5% were novices when it came to AI/ML, and radiologists were more likely than residents to have read a journal paper on AI in radiology in the previous 6 months (33.3% vs. 18.9%). Only 1.8% of respondents had active or previous involvement in AI research, though 92% were eager to join such research efforts. Most of respondents intended to expand their AI/ML knowledge (84.6%) and believed AI/ML would substantially influence radiology practice (72.3%). While few felt AI/ML could replace radiologists (16.8%), most supported integrating AI/ML training into radiology residency curricula (82.9%). Conclusion This study suggests that radiology residents and radiologists in Ethiopia are generally positive and open-minded towards AI/ML in radiology, despite their limited knowledge and experience with the technology. The majority of respondents believe that AI and data science skills should be introduced during residency training. Recommendations : Medical AI training should be incorporated into radiology residency programs to prepare future radiologists for the changing landscape of radiology practice.

show abstract

Perspectives of radiologists in Ghana about the emerging role of artificial intelligence in radiology

Cited by 3 publications

References 24 publications

Cautiously optimistic about data-driven algorithms in paediatric critical care, nurses’ perspectives in low-resource settings: a pre-implementation and human-centred design study in Malawi

Cautiously optimistic about data-driven algorithms in paediatric critical care, nurses’ perspectives in low-resource settings: a pre-implementation and human-centred design study in Malawi

Understanding the factors influencing acceptability of AI in medical imaging domains among healthcare professionals: A scoping review

Radiology Residents' and Radiologists' Perception and Attitude Towards Medical Artificial Intelligence in Radiology– An Initial National Multicenter Survey

Contact Info

Product

Resources

About