Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines.

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

Development of a core outcome set for use in adult primary glioma phase III interventional trials: A mixed methods study.

Background: Glioma interventional studies should collect data aligned with patient priorities, enabling treatment benefit assessment and informed decision-making. This requires effective data synthesis and meta-analyses, underpinned by consistent trial outcome measurement, analysis, and reporting. Development of a core outcome set (COS) may contribute to a solution. Methods: A 5-stage process was used to develop a COS for glioma trials from the UK perspective. Outcome lists were generated in stages 1: a trial registry review and systematic review of qualitative studies and 2: interviews with glioma patients and caregivers. In stage 3, the outcome lists were de-duplicated with accessible terminology, in stage 4 outcomes were rated via a 2-round Delphi process, and stage 5 comprised a consensus meeting to finalize the COS. Patient-reportable COS outcomes were identified. Results: In Delphi round 1, 96 participants rated 35 outcomes identified in stages 1 and 2, to which a further 10 were added. Participants (77/96) rated the resulting 45 outcomes in round 2. Of these, 22 outcomes met a priori threshold for inclusion in the COS. After further review, a COS consisting of 19 outcomes grouped into 7 outcome domains (survival, adverse events, activities of daily living, health-related quality of life, seizure activity, cognitive function, and physical function) was finalized by 13 participants at the consensus meeting. Conclusions: A COS for glioma trials was developed, comprising 7 outcome domains. Additional research will identify appropriate measurement tools and further validate this COS.

Non-Pharmacological Therapies for Post-Viral Syndromes, Including Long COVID: A Systematic Review.

BACKGROUND: Post-viral syndromes (PVS), including Long COVID, are symptoms sustained from weeks to years following an acute viral infection. Non-pharmacological treatments for these symptoms are poorly understood. This review summarises the evidence for the effectiveness of non-pharmacological treatments for PVS. METHODS: We conducted a systematic review to evaluate the effectiveness of non-pharmacological interventions for PVS, as compared to either standard care, alternative non-pharmacological therapy, or placebo. The outcomes of interest were changes in symptoms, exercise capacity, quality of life (including mental health and wellbeing), and work capability. We searched five databases (Embase, MEDLINE, PsycINFO, CINAHL, MedRxiv) for randomised controlled trials (RCTs) published between 1 January 2001 to 29 October 2021. The relevant outcome data were extracted, the study quality was appraised using the Cochrane risk-of-bias tool, and the findings were synthesised narratively. FINDINGS: Overall, five studies of five different interventions (Pilates, music therapy, telerehabilitation, resistance exercise, neuromodulation) met the inclusion criteria. Aside from music-based intervention, all other selected interventions demonstrated some support in the management of PVS in some patients. INTERPRETATION: In this study, we observed a lack of robust evidence evaluating the non-pharmacological treatments for PVS, including Long COVID. Considering the prevalence of prolonged symptoms following acute viral infections, there is an urgent need for clinical trials evaluating the effectiveness and cost-effectiveness of non-pharmacological treatments for patients with PVS. REGISTRATION: The study protocol was registered with PROSPERO [CRD42021282074] in October 2021 and published in BMJ Open in 2022.

Key considerations to reduce or address respondent burden in patient-reported outcome (PRO) data collection.

Patient-reported outcomes (PROs) are used in clinical trials to provide evidence of the benefits and risks of interventions from a patient perspective and to inform regulatory decisions and health policy. The collection of PROs in routine practice can facilitate monitoring of patient symptoms; identification of unmet needs; prioritisation and/or tailoring of treatment to the needs of individual patients and inform value-based healthcare initiatives. However, respondent burden needs to be carefully considered and addressed to avoid high rates of missing data and poor reporting of PRO results, which may lead to poor quality data for regulatory decision making and/or clinical care.

Symptoms, complications and management of long COVID: a review.

Globally, there are now over 160 million confirmed cases of COVID-19 and more than 3 million deaths. While the majority of infected individuals recover, a significant proportion continue to experience symptoms and complications after their acute illness. Patients with 'long COVID' experience a wide range of physical and mental/psychological symptoms. Pooled prevalence data showed the 10 most prevalent reported symptoms were fatigue, shortness of breath, muscle pain, joint pain, headache, cough, chest pain, altered smell, altered taste and diarrhoea. Other common symptoms were cognitive impairment, memory loss, anxiety and sleep disorders. Beyond symptoms and complications, people with long COVID often reported impaired quality of life, mental health and employment issues. These individuals may require multidisciplinary care involving the long-term monitoring of symptoms, to identify potential complications, physical rehabilitation, mental health and social services support. Resilient healthcare systems are needed to ensure efficient and effective responses to future health challenges.

Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines.

BACKGROUND: The application of artificial intelligence (AI) in healthcare is an area of immense interest. The high profile of 'AI in health' means that there are unusually strong drivers to accelerate the introduction and implementation of innovative AI interventions, which may not be supported by the available evidence, and for which the usual systems of appraisal may not yet be sufficient. MAIN TEXT: We are beginning to see the emergence of randomised clinical trials evaluating AI interventions in real-world settings. It is imperative that these studies are conducted and reported to the highest standards to enable effective evaluation because they will potentially be a key part of the evidence that is used when deciding whether an AI intervention is sufficiently safe and effective to be approved and commissioned. Minimum reporting guidelines for clinical trial protocols and reports have been instrumental in improving the quality of clinical trials and promoting completeness and transparency of reporting for the evaluation of new health interventions. The current guidelines-SPIRIT and CONSORT-are suited to traditional health interventions but research has revealed that they do not adequately address potential sources of bias specific to AI systems. Examples of elements that require specific reporting include algorithm version and the procedure for acquiring input data. In response, the SPIRIT-AI and CONSORT-AI guidelines were developed by a multidisciplinary group of international experts using a consensus building methodological process. The extensions include a number of new items that should be reported in addition to the core items. Each item, where possible, was informed by challenges identified in existing studies of AI systems in health settings. CONCLUSION: The SPIRIT-AI and CONSORT-AI guidelines provide the first international standards for clinical trials of AI systems. The guidelines are designed to ensure complete and transparent reporting of clinical trial protocols and reports involving AI interventions and have the potential to improve the quality of these clinical trials through improvements in their design and delivery. Their use will help to efficiently identify the safest and most effective AI interventions and commission them with confidence for the benefit of patients and the public.

Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension.

The SPIRIT 2013 (The Standard Protocol Items: Recommendations for Interventional Trials) statement aims to improve the completeness of clinical trial protocol reporting, by providing evidence-based recommendations for the minimum set of items to be addressed. This guidance has been instrumental in promoting transparent evaluation of new interventions. More recently, there is a growing recognition that interventions involving artificial intelligence need to undergo rigorous, prospective evaluation to demonstrate their impact on health outcomes.The SPIRIT-AI extension is a new reporting guideline for clinical trials protocols evaluating interventions with an AI component. It was developed in parallel with its companion statement for trial reports: CONSORT-AI. Both guidelines were developed using a staged consensus process, involving a literature review and expert consultation to generate 26 candidate items, which were consulted on by an international multi-stakeholder group in a 2-stage Delphi survey (103 stakeholders), agreed on in a consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants).The SPIRIT-AI extension includes 15 new items, which were considered sufficiently important for clinical trial protocols of AI interventions. These new items should be routinely reported in addition to the core SPIRIT 2013 items. SPIRIT-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 will be integrated, considerations around the handling of input and output data, the human-AI interaction and analysis of error cases.SPIRIT-AI will help promote transparency and completeness for clinical trial protocols for AI interventions. Its use will assist editors and peer-reviewers, as well as the general readership, to understand, interpret and critically appraise the design and risk of bias for a planned clinical trial.

Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension.

The CONSORT 2010 (Consolidated Standards of Reporting Trials) statement provides minimum guidelines for reporting randomised trials. Its widespread use has been instrumental in ensuring transparency when evaluating 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 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. Both guidelines were developed through a staged consensus process, involving a 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 on in a two-day consensus meeting (31 stakeholders) and refined through a checklist pilot (34 participants).The CONSORT-AI extension includes 14 new items, which 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 providing 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 impact of patient-reported outcome (PRO) data from clinical trials: a systematic review and critical analysis.

BACKGROUND: Patient-reported outcomes (PROs) are commonly collected in clinical trials and should provide impactful evidence on the effect of interventions on patient symptoms and quality of life. However, it is unclear how PRO impact is currently realised in practice. In addition, the different types of impact associated with PRO trial results, their barriers and facilitators, and appropriate impact metrics are not well defined. Therefore, our objectives were: i) to determine the range of potential impacts from PRO clinical trial data, ii) identify potential PRO impact metrics and iii) identify barriers/facilitators to maximising PRO impact; and iv) to examine real-world evidence of PRO trial data impact based on Research Excellence Framework (REF) impact case studies. METHODS: Two independent investigators searched MEDLINE, EMBASE, CINAHL+, HMIC databases from inception until December 2018. Articles were eligible if they discussed research impact in the context of PRO clinical trial data. In addition, the REF 2014 database was systematically searched. REF impact case studies were included if they incorporated PRO data in a clinical trial. RESULTS: Thirty-nine publications of eleven thousand four hundred eighty screened met the inclusion criteria. Nine types of PRO trial impact were identified; the most frequent of which centred around PRO data informing clinical decision-making. The included publications identified several barriers and facilitators around PRO trial design, conduct, analysis and report that can hinder or promote the impact of PRO trial data. Sixty-nine out of two hundred nine screened REF 2014 case studies were included. 12 (17%) REF case studies led to demonstrable impact including changes to international guidelines; national guidelines; influencing cost-effectiveness analysis; and influencing drug approvals. CONCLUSIONS: PRO trial data may potentially lead to a range of benefits for patients and society, which can be measured through appropriate impact metrics. However, in practice there is relatively limited evidence demonstrating directly attributable and indirect real world PRO-related research impact. In part, this is due to the wider challenges of measuring the impact of research and PRO-specific issues around design, conduct, analysis and reporting. Adherence to guidelines and multi-stakeholder collaboration is essential to maximise the use of PRO trial data, facilitate impact and minimise research waste. TRIAL REGISTRATION: Systematic Review registration PROSPERO CRD42017067799.