How AI should be used in radiology: assessing ambiguity and completeness of intended use statements of commercial AI products.

Intended use statements (IUSs) are mandatory to obtain regulatory clearance for artificial intelligence (AI)-based medical devices in the European Union. In order to guide the safe use of AI-based medical devices, IUSs need to contain comprehensive and understandable information. This study analyzes the IUSs of CE-marked AI products listed on AIforRadiology.com for ambiguity and completeness. We retrieved 157 IUSs of CE-marked AI products listed on AIforRadiology.com in September 2022. Duplicate products (n = 1), discontinued products (n = 3), and duplicate statements (n = 14) were excluded. The resulting IUSs were assessed for the presence of 6 items: medical indication, part of the body, patient population, user profile, use environment, and operating principle. Disclaimers, defined as contra-indications or warnings in the IUS, were identified and compared with claims. Of 139 AI products, the majority (n = 78) of IUSs mentioned 3 or less items. IUSs of only 7 products mentioned all 6 items. The intended body part (n = 115) and the operating principle (n = 116) were the most frequently mentioned components, while the intended use environment (n = 24) and intended patient population (n = 29) were mentioned less frequently. Fifty-six statements contained disclaimers that conflicted with the claims in 13 cases. The majority of IUSs of CE-marked AI-based medical devices lack substantial information and, in few cases, contradict the claims of the product. To ensure correct usage and to avoid off-label use or foreseeable misuse of AI-based medical devices in radiology, manufacturers are encouraged to provide more comprehensive and less ambiguous intended use statements. • Radiologists must know AI products' intended use to avoid off-label use or misuse. • Ninety-five percent (n = 132/139) of the intended use statements analyzed were incomplete. • Nine percent (n = 13) of the intended use statements held disclaimers contradicting the claim of the AI product. • Manufacturers and regulatory bodies must ensure that intended use statements are comprehensive.

van Leeuwen KG ，Hedderich DM ，Harvey H ，Schalekamp S ... -  《Insights into Imaging》

Clinical use of artificial intelligence products for radiology in the Netherlands between 2020 and 2022.

To map the clinical use of CE-marked artificial intelligence (AI)-based software in radiology departments in the Netherlands (n = 69) between 2020 and 2022. Our AI network (one radiologist or AI representative per Dutch hospital organization) received a questionnaire each spring from 2020 to 2022 about AI product usage, financing, and obstacles to adoption. Products that were not listed on www.AIforRadiology.com by July 2022 were excluded from the analysis. The number of respondents was 43 in 2020, 36 in 2021, and 33 in 2022. The number of departments using AI has been growing steadily (2020: 14, 2021: 19, 2022: 23). The diversity (2020: 7, 2021: 18, 2022: 34) and the number of total implementations (2020: 19, 2021: 38, 2022: 68) has rapidly increased. Seven implementations were discontinued in 2022. Four hospital organizations said to use an AI platform or marketplace for the deployment of AI solutions. AI is mostly used to support chest CT (17), neuro CT (17), and musculoskeletal radiograph (12) analysis. The budget for AI was reserved in 13 of the responding centers in both 2021 and 2022. The most important obstacles to the adoption of AI remained costs and IT integration. Of the respondents, 28% stated that the implemented AI products realized health improvement and 32% assumed both health improvement and cost savings. The adoption of AI products in radiology departments in the Netherlands is showing common signs of a developing market. The major obstacles to reaching widespread adoption are a lack of financial resources and IT integration difficulties. The clinical impact of AI starts with its adoption in daily clinical practice. Increased transparency around AI products being adopted, implementation obstacles, and impact may inspire increased collaboration and improved decision-making around the implementation and financing of AI products. • The adoption of artificial intelligence products for radiology has steadily increased since 2020 to at least a third of the centers using AI in clinical practice in the Netherlands in 2022. • The main areas in which artificial intelligence products are used are lung nodule detection on CT, aided stroke diagnosis, and bone age prediction. • The majority of respondents experienced added value (decreased costs and/or improved outcomes) from using artificial intelligence-based software; however, major obstacles to adoption remain the costs and IT-related difficulties.

van Leeuwen KG ，de Rooij M ，Schalekamp S ，van Ginneken B ，Rutten MJCM ... -  《-》

Artificial intelligence in radiology: 100 commercially available products and their scientific evidence.

van Leeuwen KG ，Schalekamp S ，Rutten MJCM ，van Ginneken B ，de Rooij M ... -  《-》

Quantification of US Food and Drug Administration Premarket Approval Statements for High-Risk Medical Devices With Pediatric Age Indications.

Lee SJ ，Cho L ，Klang E ，Wall J ，Rensi S ，Glicksberg BS ... -  《JAMA Network Open》

Impact of drug loading on release from levonorgestrel intrauterine systems.

Levonorgestrel intrauterine systems (LNG-IUSs) are polydimethylsiloxane (PDMS) based non-biodegradable complex drug-device combination products providing efficacy for up to several years based on the strength. A large amount of LNG (e.g., 52 mg in Mirena and Liletta) must be loaded in the LNG-IUS products to maintain the long-acting effect even though LNG is a potent hormone. However, the high amount of LNG not only poses the potential risk of dose dumping, but also leads to drug waste due to incomplete drug utilization close to the end of usage. It has been unclear whether the duration of usage of these products should be extended for full drug utilization or products with lower drug loading should be developed. Therefore, it is critical to understand the impact of strength (or drug loading) on drug release from LNG-IUSs. In the current study, drug reservoirs with a broad range of drug loading (from 0.5% w/w to 50% w/w) were prepared and assembled into LNG-IUSs. Different accelerated release conditions were used to perform release testing of LNG-IUSs with different drug loading. 5% to 10% variation in excipient of the LNG-IUSs did not significantly alter the drug release profiles of the LNG-IUSs. The release rate of LNG-IUSs is inversely proportional to their drug loading at high drug loading (10% w/w, 25% w/w and 50% w/w). Drug release was incomplete for LNG-IUS with low drug loading (2.5% w/w and 1% w/w) and no drug release could be detected for the LNG-IUS with 0.5% w/w drug loading. In addition, the burst effect of the LNG-IUSs with different drug loading was investigated. This is the first research report covering ultra-long duration (more than four years) of real-time drug release from LNG-IUSs with different drug loading (0.5%-50% w/w). The amount of excipient (PDMS) used in the reservoir of LNG-IUSs was determined to be not a critical quality parameter in the formulation design since LNG-IUSs (50% w/w drug loading) with up to 10% variation in excipient did not show significant differences in their release profiles. The drug release kinetics/mechanism remained the same for LNG-IUSs with drug loading ranging from 1% to 50%. In addition, the accelerated release testing methods were confirmed to be representative of the real-time release profiles and this can give confidence in extending the duration of usage for these products provided that the device remains physically intact (no tearing or damage in the outer membrane) and the release rate is within the therapeutic window. It is recommended to perform both real-time and accelerated release testing simultaneously for LNG-IUSs to understand the burst effect as well as the complete release characteristics. Lastly, drug/polymer interaction may play a role when designing LNG-IUS formulations with low drug loading (<5% w/w) since drug/polymer interaction is significant when only a small amount of drug present.

Bao Q ，Fanse S ，Lu XJ ，Burgess DJ ... -  《-》