How is informed decision-making about breast cancer screening addressed in Europe? An international survey of 28 countries

Benefits and harms associated with the use of AI-related algorithmic decision-making systems by healthcare professionals: a systematic review

Background

Despite notable advancements in artificial intelligence (AI) that enable complex systems to perform certain tasks more accurately than medical experts, the impact on patient-relevant outcomes remains uncertain. To address this gap, this systematic review assesses the benefits and harms associated with AI-related algorithmic decision-making (ADM) systems used by healthcare professionals, compared to standard care.

Methods

In accordance with the PRISMA guidelines, we included interventional and observational studies published as peer-reviewed full-text articles that met the following criteria: human patients; interventions involving algorithmic decision-making systems, developed with and/or utilizing machine learning (ML); and outcomes describing patient-relevant benefits and harms that directly affect health and quality of life, such as mortality and morbidity. Studies that did not undergo preregistration, lacked a standard-of-care control, or pertained to systems that assist in the execution of actions (e.g., in robotics) were excluded. We searched MEDLINE, EMBASE, IEEE Xplore, and Google Scholar for studies published in the past decade up to 31 March 2024. We assessed risk of bias using Cochrane's RoB 2 and ROBINS-I tools, and reporting transparency with CONSORT-AI and TRIPOD-AI. Two researchers independently managed the processes and resolved conflicts through discussion. This review has been registered with PROSPERO (CRD42023412156) and the study protocol has been published.

Findings

Out of 2,582 records identified after deduplication, 18 randomized controlled trials (RCTs) and one cohort study met the inclusion criteria, covering specialties such as psychiatry, oncology, and internal medicine. Collectively, the studies included a median of 243 patients (IQR 124-828), with a median of 50.5% female participants (range 12.5-79.0, IQR 43.6-53.6) across intervention and control groups. Four studies were classified as having low risk of bias, seven showed some concerns, and another seven were assessed as having high or serious risk of bias. Reporting transparency varied considerably: six studies showed high compliance, four moderate, and five low compliance with CONSORT-AI or TRIPOD-AI. Twelve studies (63%) reported patient-relevant benefits. Of those with low risk of bias, interventions reduced length of stay in hospital and intensive care unit (10.3 vs. 13.0 days, p = 0.042; 6.3 vs. 8.4 days, p = 0.030), in-hospital mortality (9.0% vs. 21.3%, p = 0.018), and depression symptoms in non-complex cases (45.1% vs. 52.3%, p = 0.03). However, harms were frequently underreported, with only eight studies (42%) documenting adverse events. No study reported an increase in adverse events as a result of the interventions.

Interpretation

The current evidence on AI-related ADM systems provides limited insights into patient-relevant outcomes. Our findings underscore the essential need for rigorous evaluations of clinical benefits, reinforced compliance with methodological standards, and balanced consideration of both benefits and harms to ensure meaningful integration into healthcare practice.

Funding

This study did not receive any funding.

A kind reminder-A qualitative process evaluation of women's perspectives on receiving a reminder of type 2 diabetes follow-up screening after gestational diabetes

RATIONALE, AIMS AND OBJECTIVES

Women with previous gestational diabetes mellitus (GDM) are more than eight times more likely to develop type 2 diabetes (T2DM) compared to women without GDM. Annual follow-up T2DM-screening is recommended, but participation rates decrease rapidly after the first year. In the North Denmark Region, an electronic reminder has been tested with the aim of improving follow-up care for women with prior GDM. The aim of this study was to explore women's perspectives on receiving an electronic reminder, and the role of reminders in both women's decision-making and informed choice regarding participation in follow-up screening.

METHODS

A qualitative process evaluation informed by a critical realistic perspective. Data consisted of 20 semi-structured interviews with women previously diagnosed with GDM who had received the reminder. Interviews were analyzed using reflexive thematic analysis.

RESULTS

The reminder affected women's decision-making and informed choices through a range of mechanisms. Its personalized design prompted feelings of co-responsibility and care from the healthcare system, supported continuity in women's care pathways, and helped women bridge the gap between healthcare sectors. Women's perception of diabetes risk and the importance of follow-up influenced their decision-making. Participation in follow-up screening was influenced by several contextual factors, as women's everyday life impeded their prioritizing follow-up screening. Women who experienced being met by their general practitioner (GP) with acknowledgement rather than stigmatization and received supportive information tailored to their life situation were more motivated to participate in future follow-up screenings.

CONCLUSION

The reminder indicated both concern and co-responsibility for women's follow-up care after GDM and was well received by the women. It supported participation in follow-up screening through an emphasis on shared decision-making and informed choice. Women's interaction with their GP played a significant role.

How to dampen the surge of non-communicable diseases in Southeast Asia: insights from a systematic review and meta-analysis

Non-communicable diseases (NCDs), such as diabetes, cancer, cardiovascular diseases and chronic respiratory diseases, have overtaken infectious diseases as the number one cause of death worldwide. The rise of these diseases is especially grave in Southeast Asia, where existing research however falls short on offering guidance on how policy can best prevent and control NCDs in the region. Additionally, low- and middle-income countries in Southeast Asia cannot directly incorporate lessons drawn from interventions in richer countries, since health system capacities and human and financial resources are thoroughly different. Preventive interventions, thus, need to correspond to local capacities and require contextual solutions. In this article, we provide a systematic review of a wide scope of NCD interventions conducted in Southeast Asia to inform about existing intervention designs and to derive sound evidence of their effectiveness. Our literature search results in 51 studies from five Southeast Asian countries from which we can extract 204 estimates. We sort the studies into six intervention categories and analyse them with respect to 23 different health and behavioural outcomes. While we find positive and significant average effects across all six types of interventions, we also document evidence of substantial publication bias. Using a meta-regression approach in which we correct for the publication bias, we instead fail to confirm positive average effects for some interventions. Especially dietary and physical activity interventions fail to achieve improvements in analysed health outcomes, while programs focusing on smoking cessation, on the take-up of preventive screening activities or educating patients on how to cope with NCDs achieve sizeable effects. We also present evidence that the size of the effect differs with the participants' characteristics as well as with design features of the intervention. For local policymakers, the results provide important knowledge on how to address the increasing NCD burden in the coming years.

COVID-19 Unintended Effects on Breast Cancer in Italy After the Great Lockdown

Italy introduced social distancing measures, which limited the spread of COVID-19; all the non-life-threatening treatments have been temporarily suspended, including screening programs. This decision leads to unintended effects on the ability to detected neoplasia in their first stages. Possible future outcomes of the ability to detect new breast cancer cases based on two alternative scenarios show that the reduction in organized screening activities will limit the ability to detect no <3.43% of the new cases; the economic crisis will reduce voluntary screening, increasing the undetected new cases up to 11.73%. Cases diagnosed with delay will show up in their advanced stage along with unknown effects on mortality and health care costs. Global health care policies should be implemented to counterbalance these adverse effects.