Women’s attitudes to the use of AI image readers: a case study from a national breast screening programme

Lennox-Chhugani, Niamh; Chen, Yan; Pearson, Veronica; Trzcinski, Bernadette; James, Jonathan

doi:10.1136/bmjhci-2020-100293

Cited by 36 publications

(22 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of this study also complement the existing literature on AI diagnostics, which suggests that the public has a high level of trust in computerized decision-making in health care and that AI in cancer screening is increasingly accepted [24][25][26].…”

Section: Principal Findingssupporting

confidence: 69%

“…Recent advances in technology may provide a solution to these challenges. Robotics-assisted procedures have expanded rapidly in recent decades [22,23], and existing literature suggests that health users are increasingly more accepting of artificial intelligence (AI) and machine learning algorithms in cancer screening [24][25][26]. It is theoretically feasible to create a fully automated robotic CBE (R-CBE) platform by combining soft robotic technology and machine learning algorithms trained by breast specialists.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Acceptability of Automated Robotic Clinical Breast Examination: Survey Study

Jenkinson¹,

Houghton²,

Zalk³

et al. 2023

J Particip Med

View full text Add to dashboard Cite

Background In the United Kingdom, women aged 50 to 70 years are invited to undergo mammography. However, 10% of invasive breast cancers occur in women aged ≤45 years, representing an unmet need for young women. Identifying a suitable screening modality for this population is challenging; mammography is insufficiently sensitive, whereas alternative diagnostic methods are invasive or costly. Robotic clinical breast examination (R-CBE)—using soft robotic technology and machine learning for fully automated clinical breast examination—is a theoretically promising screening modality with early prototypes under development. Understanding the perspectives of potential users and partnering with patients in the design process from the outset is essential for ensuring the patient-centered design and implementation of this technology. Objective This study investigated the attitudes and perspectives of women regarding the use of soft robotics and intelligent systems in breast cancer screening. It aimed to determine whether such technology is theoretically acceptable to potential users and identify aspects of the technology and implementation system that are priorities for patients, allowing these to be integrated into technology design. Methods This study used a mixed methods design. We conducted a 30-minute web-based survey with 155 women in the United Kingdom. The survey comprised an overview of the proposed concept followed by 5 open-ended questions and 17 closed questions. Respondents were recruited through a web-based survey linked to the Cancer Research United Kingdom patient involvement opportunities web page and distributed through research networks’ mailing lists. Qualitative data generated via the open-ended questions were analyzed using thematic analysis. Quantitative data were analyzed using 2-sample Kolmogorov-Smirnov tests, 1-tailed t tests, and Pearson coefficients. Results Most respondents (143/155, 92.3%) indicated that they would definitely or probably use R-CBE, with 82.6% (128/155) willing to be examined for up to 15 minutes. The most popular location for R-CBE was at a primary care setting, whereas the most accepted method for receiving the results was an on-screen display (with an option to print information) immediately after the examination. Thematic analysis of free-text responses identified the following 7 themes: women perceive that R-CBE has the potential to address limitations in current screening services; R-CBE may facilitate increased user choice and autonomy; ethical motivations for supporting R-CBE development; accuracy (and users’ perceptions of accuracy) is essential; results management with clear communication is a priority for users; device usability is important; and integration with health services is key. Conclusions There is a high potential for the acceptance of R-CBE in its target user group and a high concordance between user expectations and technological feasibility. Early patient participation in the design process allowed the authors to identify key development priorities for ensuring that this new technology meets the needs of users. Ongoing patient and public involvement at each development stage is essential.

show abstract

Section: Principal Findingssupporting

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Acceptability of Automated Robotic Clinical Breast Examination: Survey Study

Jenkinson¹,

Houghton²,

Zalk³

et al. 2023

J Particip Med

View full text Add to dashboard Cite

show abstract

“…GI-patients (64.9%) and GI-physicians (81.3%) believed that AI will improve quality of care, again comparable with literature 21 . Human interaction in addition to AI use was considered critical for the experience of high-quality care 22 . The importance of human interactions is further supported by evidence showing that patients' compliance was higher for physicians and for physicians using AI compared to an AI-system alone 8 .…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence in (gastrointestinal) healthcare: patients’ and physicians’ perspectives

Zander

Loon

Janssen

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Artificial intelligence (AI) is entering into daily life and has the potential to play a significant role in healthcare. Aim was to investigate the perspectives (knowledge, experience, and opinion) on AI in healthcare among patients with gastrointestinal (GI) disorders, gastroenterologists, and GI-fellows. In this prospective questionnaire study 377 GI-patients, 35 gastroenterologists, and 45 GI-fellows participated. Of GI-patients, 62.5% reported to be familiar with AI and 25.0% of GI-physicians had work-related experience with AI. GI-patients preferred their physicians to use AI (mean 3.9) and GI-physicians were willing to use AI (mean 4.4, on 5-point Likert-scale). More GI-physicians believed in an increase in quality of care (81.3%) than GI-patients (64.9%, χ2(2) = 8.2, p = 0.017). GI-fellows expected AI implementation within 6.0 years, gastroenterologists within 4.2 years (t(76) = − 2.6, p = 0.011), and GI-patients within 6.1 years (t(193) = − 2.0, p = 0.047). GI-patients and GI-physicians agreed on the most important advantages of AI in healthcare: improving quality of care, time saving, and faster diagnostics and shorter waiting times. The most important disadvantage for GI-patients was the potential loss of personal contact, for GI-physicians this was insufficiently developed IT infrastructures. GI-patients and GI-physicians hold positive perspectives towards AI in healthcare. Patients were significantly more reserved compared to GI-fellows and GI-fellows were more reserved compared to gastroenterologists.

show abstract

“…These different roles for AI in the screening pathway have profound implications on the amount of automation, associated risks, participants’ acceptance, regulatory approval, and the downstream effects of any human-AI interaction [14]. While AI used for triaging and decision-referral showed potential for drastically reducing workload [15,16], the fact that a large number of cases would not be assessed by any human reader poses clinical risks and may hinder its acceptance by screening participants [17]. A large majority of screening participants seem to agree that some level of human oversight is desired [18].…”

Section: Introductionmentioning

confidence: 99%

A novel workflow for the safe and effective integration of AI as supporting reader in double reading breast cancer screening: A large-scale retrospective evaluation

Glocker

Oberije

et al. 2022

Preprint

View full text Add to dashboard Cite

Objectives To evaluate the effectiveness of a novel strategy for using AI as a supporting reader for the detection of breast cancer in mammography-based double reading screening practice. Instead of replacing a human reader, here AI serves as the second reader only if it agrees with the recall/no-recall decision of the first human reader. Otherwise, a second human reader makes an assessment, enacting standard human double reading. Design Retrospective large-scale, multi-site, multi-device, evaluation study. Participants 280,594 cases from 180,542 female participants who were screened for breast cancer with digital mammography between 2009 and 2019 at seven screening sites in two countries (UK and Hungary). Main outcome measures Primary outcome measures were cancer detection rate, recall rate, sensitivity, specificity, and positive predictive value. Secondary outcome was reduction in workload measured as arbitration rate and number of cases requiring second human reading. Results The novel workflow was found to be superior or non-inferior on all screening metrics, almost halving arbitration and reducing the number of cases requiring second human reading by up to 87.50% compared to human double reading. Conclusions AI as a supporting reader adds a safety net in case of AI discordance compared to alternative workflows where AI replaces the second human reader. In the simulation using large-scale historical data, the proposed workflow retains screening performance of the standard of care of human double reading while drastically reducing the workload. Further research should study the impact of the change in case mix for the second human reader as they would only assess cases where the AI and first human reader disagree.

show abstract

Women’s attitudes to the use of AI image readers: a case study from a national breast screening programme

Cited by 36 publications

References 37 publications

Acceptability of Automated Robotic Clinical Breast Examination: Survey Study

Acceptability of Automated Robotic Clinical Breast Examination: Survey Study

Artificial intelligence in (gastrointestinal) healthcare: patients’ and physicians’ perspectives

A novel workflow for the safe and effective integration of AI as supporting reader in double reading breast cancer screening: A large-scale retrospective evaluation

Contact Info

Product

Resources

About