Search

Background: Retrospective studies have shown promising results using artificial intelligence (AI) to improve mammography screening accuracy and reduce screen-reading workload; however, to our knowledge, a randomised trial has not yet been conducted. We aimed to assess the clinical safety of an AI-supported screen-reading protocol compared with standard screen reading by radiologists following mammography., Methods: In this randomised, controlled, population-based trial, women aged 40-80 years eligible for mammography screening (including general screening with 1·5-2-year intervals and annual screening for those with moderate hereditary risk of breast cancer or a history of breast cancer) at four screening sites in Sweden were informed about the study as part of the screening invitation. Those who did not opt out were randomly allocated (1:1) to AI-supported screening (intervention group) or standard double reading without AI (control group). Screening examinations were automatically randomised by the Picture Archive and Communications System with a pseudo-random number generator after image acquisition. The participants and the radiographers acquiring the screening examinations, but not the radiologists reading the screening examinations, were masked to study group allocation. The AI system (Transpara version 1.7.0) provided an examination-based malignancy risk score on a 10-level scale that was used to triage screening examinations to single reading (score 1-9) or double reading (score 10), with AI risk scores (for all examinations) and computer-aided detection marks (for examinations with risk score 8-10) available to the radiologists doing the screen reading. Here we report the prespecified clinical safety analysis, to be done after 80 000 women were enrolled, to assess the secondary outcome measures of early screening performance (cancer detection rate, recall rate, false positive rate, positive predictive value [PPV] of recall, and type of cancer detected [invasive or in situ]) and screen-reading workload. Analyses were done in the modified intention-to-treat population (ie, all women randomly assigned to a group with one complete screening examination, excluding women recalled due to enlarged lymph nodes diagnosed with lymphoma). The lowest acceptable limit for safety in the intervention group was a cancer detection rate of more than 3 per 1000 participants screened. The trial is registered with ClinicalTrials.gov, NCT04838756, and is closed to accrual; follow-up is ongoing to assess the primary endpoint of the trial, interval cancer rate., Findings: Between April 12, 2021, and July 28, 2022, 80 033 women were randomly assigned to AI-supported screening (n=40 003) or double reading without AI (n=40 030). 13 women were excluded from the analysis. The median age was 54·0 years (IQR 46·7-63·9). Race and ethnicity data were not collected. AI-supported screening among 39 996 participants resulted in 244 screen-detected cancers, 861 recalls, and a total of 46 345 screen readings. Standard screening among 40 024 participants resulted in 203 screen-detected cancers, 817 recalls, and a total of 83 231 screen readings. Cancer detection rates were 6·1 (95% CI 5·4-6·9) per 1000 screened participants in the intervention group, above the lowest acceptable limit for safety, and 5·1 (4·4-5·8) per 1000 in the control group-a ratio of 1·2 (95% CI 1·0-1·5; p=0·052). Recall rates were 2·2% (95% CI 2·0-2·3) in the intervention group and 2·0% (1·9-2·2) in the control group. The false positive rate was 1·5% (95% CI 1·4-1·7) in both groups. The PPV of recall was 28·3% (95% CI 25·3-31·5) in the intervention group and 24·8% (21·9-28·0) in the control group. In the intervention group, 184 (75%) of 244 cancers detected were invasive and 60 (25%) were in situ; in the control group, 165 (81%) of 203 cancers were invasive and 38 (19%) were in situ. The screen-reading workload was reduced by 44·3% using AI., Interpretation: AI-supported mammography screening resulted in a similar cancer detection rate compared with standard double reading, with a substantially lower screen-reading workload, indicating that the use of AI in mammography screening is safe. The trial was thus not halted and the primary endpoint of interval cancer rate will be assessed in 100 000 enrolled participants after 2-years of follow up., Funding: Swedish Cancer Society, Confederation of Regional Cancer Centres, and the Swedish governmental funding for clinical research (ALF)., Competing Interests: Declaration of interests KL has been an advisory board member for Siemens Healthineers and has received lecture honorarium from AstraZeneca. SH is head of BreastScreen Norway at the Cancer Registry of Norway which has a research agreement with Screenpoint Medical. All other authors declare no competing interests., (Copyright © 2023 Elsevier Ltd. All rights reserved.)

Objectives: Artificial intelligence (AI) is increasingly tested and integrated into breast cancer screening. Still, there are unresolved issues regarding its possible ethical, social and legal impacts. Furthermore, the perspectives of different actors are lacking. This study investigates the views of breast radiologists on AI-supported mammography screening, with a focus on attitudes, perceived benefits and risks, accountability of AI use, and potential impact on the profession., Methods: We conducted an online survey of Swedish breast radiologists. As early adopter of breast cancer screening, and digital technologies, Sweden is a particularly interesting case to study. The survey had different themes, including: attitudes and responsibilities pertaining to AI, and AI's impact on the profession. Responses were analysed using descriptive statistics and correlation analyses. Free texts and comments were analysed using an inductive approach., Results: Overall, respondents (47/105, response rate 44.8%) were highly experienced in breast imaging and had a mixed knowledge of AI. A majority (n=38, 80.8%) were positive/somewhat positive towards integrating AI in mammography screening. Still, many considered there to be potential risks to a high/somewhat high degree (n=16, 34.1%) or were uncertain (n=16, 34.0%). Several important uncertainties were identified, such as defining liable actor(s) when AI is integrated into medical decision-making., Conclusions: Swedish breast radiologists are largely positive towards integrating AI in mammography screening, but there are significant uncertainties that need to be addressed, especially regarding risks and responsibilities. The results stress the importance of understanding actor-specific and context-specific challenges to responsible implementation of AI in healthcare., Competing Interests: Competing interests: KL is on an advisory board for Siemens Healthineers., (© Author(s) (or their employer(s)) 2023. Re-use permitted under CC BY. Published by BMJ.)

In this conceptual article, we argue that artificial intelligence (AI) systems are contributing to the generation of an environment of affordances for everyday information practices through which they exert influence on people and the planet in ways that often are left unrecognized. We illustrate our insights by focusing on the practices of information seeking in everyday life, suggesting that the affordances of AI systems integrated into search engines, social media platforms, streaming services, and media generation, shape such practices in ways that may, paradoxically, result both in the increase and reduction of diversity of and access to information. We discuss the potential implications of these developments in terms of the sustainability of information ecosystems and suggest solutions for addressing them through regulation and education. Drawing from the fields of library and information science and science and technology studies and research on affordances, everyday information practices, and sustainability, the article seeks to respond to the need for more nuanced theoretical insights on the impact and implications of AI on information practices and to develop conceptual tools with which to examine the co‐evolution of humans and information systems from a systemic perspective. [ABSTRACT FROM AUTHOR]

In the context of geo-infrastructures and specifically tunneling projects, analyzing the large-scale sensor-based measurement-while-drilling (MWD) data plays a pivotal role in assessing rock engineering conditions. However, handling the big MWD data due to multiform stacking is a time-consuming and challenging task. Extracting valuable insights and improving the accuracy of geoengineering interpretations from MWD data necessitates a combination of domain expertise and data science skills in an iterative process. To address these challenges and efficiently normalize and filter out noisy data, an automated processing approach integrating the stepwise technique, mode, and percentile gate bands for both single and peer group-based holes was developed. Subsequently, the mathematical concept of a novel normalizing index for classifying such big datasets was also presented. The visualized results from different geo-infrastructure datasets in Sweden indicated that outliers and noisy data can more efficiently be eliminated using single hole-based normalizing. Additionally, a relational unified PostgreSQL database was created to store and automatically transfer the processed and raw MWD as well as real time grouting data that offers a cost effective and efficient data extraction tool. The generated database is expected to facilitate in-depth investigations and enable application of the artificial intelligence (AI) techniques to predict rock quality conditions and design appropriate support systems based on MWD data. [ABSTRACT FROM AUTHOR]

Uncertainty quantification (UQ) is an important benchmark to assess the performance of artificial intelligence (AI) and particularly deep learning ensembled-based models. However, the ability for UQ using current AI-based methods is not only limited in terms of computational resources but it also requires changes to topology and optimization processes, as well as multiple performances to monitor model instabilities. From both geo-engineering and societal perspectives, a predictive groundwater table (GWT) model presents an important challenge, where a lack of UQ limits the validity of findings and may undermine science-based decisions. To overcome and address these limitations, a novel ensemble, an automated random deactivating connective weights approach (ARDCW), is presented and applied to retrieved geographical locations of GWT data from a geo-engineering project in Stockholm, Sweden. In this approach, the UQ was achieved via a combination of several derived ensembles from a fixed optimum topology subjected to randomly switched off weights, which allow predictability with one forward pass. The process was developed and programmed to provide trackable performance in a specific task and access to a wide variety of different internal characteristics and libraries. A comparison of performance with Monte Carlo dropout and quantile regression using computer vision and control task metrics showed significant progress in the ARDCW. This approach does not require changes in the optimization process and can be applied to already trained topologies in a way that outperforms other models. [ABSTRACT FROM AUTHOR]