Search

A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real benefit to patient care. Early-stage clinical evaluation is important to assess an AI system’s actual clinical performance at small scale, ensure its safety, evaluate the human factors surrounding its use and pave the way to further large-scale trials. However, the reporting of these early studies remains inadequate. The present statement provides a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). We conducted a two-round, modified Delphi process to collect and analyze expert opinion on the reporting of early clinical evaluation of AI systems. Experts were recruited from 20 pre-defined stakeholder categories. The final composition and wording of the guideline was determined at a virtual consensus meeting. The checklist and the Explanation & Elaboration (E&E) sections were refined based on feedback from a qualitative evaluation process. In total, 123 experts participated in the first round of Delphi, 138 in the second round, 16 in the consensus meeting and 16 in the qualitative evaluation. The DECIDE-AI reporting guideline comprises 17 AI-specific reporting items (made of 28 subitems) and ten generic reporting items, with an E&E paragraph provided for each. Through consultation and consensus with a range of stakeholders, we developed a guideline comprising key items that should be reported in early-stage clinical studies of AI-based decision support systems in healthcare. By providing an actionable checklist of minimal reporting items, the DECIDE-AI guideline will facilitate the appraisal of these studies and replicability of their findings.

Background: Infants with congenital heart disease are at risk of brain injury and impaired neurodevelopment. The aim was to investigate risk factors for perioperative brain lesions in infants with congenital heart disease. Methods: Infants with transposition of the great arteries, single ventricle physiology, and left ventricular outflow tract and/or aortic arch obstruction undergoing cardiac surgery Results: Preoperatively, induced vaginal delivery (odds ratio [OR], 2.23 [95% CI, 1.06–4.70]) was associated with white matter injury and balloon atrial septostomy increased the risk of white matter injury (OR, 2.51 [95% CI, 1.23–5.20]) and arterial ischemic stroke (OR, 4.49 [95% CI, 1.20–21.49]). Postoperatively, younger postnatal age at surgery (OR, 1.18 [95% CI, 1.05–1.33]) and selective cerebral perfusion, particularly at ≤20 °C (OR, 13.46 [95% CI, 3.58–67.10]), were associated with new arterial ischemic stroke. Single ventricle physiology was associated with new white matter injury (OR, 2.88 [95% CI, 1.20–6.95]) and transposition of the great arteries with new cerebral sinus venous thrombosis (OR, 13.47 [95% CI, 2.28–95.66]). Delayed sternal closure (OR, 3.47 [95% CI, 1.08–13.06]) and lower intraoperative temperatures (OR, 1.22 [95% CI, 1.07–1.36]) also increased the risk of new cerebral sinus venous thrombosis. Conclusions: Delivery planning and surgery timing may be modifiable risk factors that allow personalized treatment to minimize the risk of perioperative brain injury in severe congenital heart disease. Further research is needed to optimize cerebral perfusion techniques for neonatal surgery and to confirm the relationship between cerebral sinus venous thrombosis and perioperative risk factors.

Background aims: \ud Mesenchymal stromal cells (MSCs) isolated from various tissues are under investigation as cellular therapeutics in a wide range of diseases. It is appreciated that the basic biological functions of MSCs vary depending on tissue source. However, in-depth comparative analyses between MSCs isolated from different tissue sources under Good Manufacturing Practice (GMP) conditions are lacking. Human clinical-grade low-purity islet (LPI) fractions are generated as a byproduct of islet isolation for transplantation. MSC isolates were derived from LPI fractions with the aim of performing a systematic, standardized comparative analysis of these cells with clinically relevant bone marrow-derived MSCs (BM MSCs).\ud \ud Methods: \ud MSC isolates were derived from LPI fractions and expanded in platelet lysate-supplemented medium or in commercially available xenogeneic-free medium. Doubling rate, phenotype, differentiation potential, gene expression, protein production and immunomodulatory capacity of LPIs were compared with those of BM MSCs.\ud \ud Results: \ud MSCs can be readily derived in vitro from non-transplanted fractions resulting from islet cell processing (i.e., LPI MSCs). LPI MSCs grow stably in serum-free or platelet lysate-supplemented media and demonstrate in vitro self-renewal, as measured by colony-forming unit assay. LPI MSCs express patterns of chemokines and pro-regenerative factors similar to those of BM MSCs and, importantly, are equally able to attract immune cells in vitro and in vivo and suppress T-cell proliferation in vitro. Additionally, LPI MSCs can be expanded to therapeutically relevant doses at low passage under GMP conditions.\ud \ud Conclusions: \ud LPI MSCs represent an alternative source of GMP MSCs with functions comparable to BM MSCs.

The CONSORT 2010 statement provides minimum guidelines for reporting randomized trials. Its widespread use has been instrumental in ensuring transparency in the evaluation of new interventions. More recently, there has been a growing recognition that interventions involving artificial intelligence (AI) need to undergo rigorous, prospective evaluation to demonstrate impact on health outcomes. The CONSORT-AI (Consolidated Standards of Reporting Trials–Artificial Intelligence) extension is a new reporting guideline for clinical trials evaluating interventions with an AI component. It was developed in parallel with its companion statement for clinical trial protocols: SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence). Both guidelines were developed through a staged consensus process involving literature review and expert consultation to generate 29 candidate items, which were assessed by an international multi-stakeholder group in a two-stage Delphi survey (103 stakeholders), agreed upon in a two-day consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants). The CONSORT-AI extension includes 14 new items that were considered sufficiently important for AI interventions that they should be routinely reported in addition to the core CONSORT 2010 items. CONSORT-AI recommends that investigators provide clear descriptions of the AI intervention, including instructions and skills required for use, the setting in which the AI intervention is integrated, the handling of inputs and outputs of the AI intervention, the human–AI interaction and provision of an analysis of error cases. CONSORT-AI will help promote transparency and completeness in reporting clinical trials for AI interventions. It will assist editors and peer reviewers, as well as the general readership, to understand, interpret and critically appraise the quality of clinical trial design and risk of bias in the reported outcomes., The CONSORT-AI and SPIRIT-AI extensions improve the transparency of clinical trial design and trial protocol reporting for artificial intelligence interventions.