Can I see the doctor please?
Related Articles
Enhancing diagnostic capability with multi-agents conversational large language models
Large Language Models (LLMs) show promise in healthcare tasks but face challenges in complex medical scenarios. We developed a Multi-Agent Conversation (MAC) framework for disease diagnosis, inspired by clinical Multi-Disciplinary Team discussions. Using 302 rare disease cases, we evaluated GPT-3.5, GPT-4, and MAC on medical knowledge and clinical reasoning. MAC outperformed single models in both primary and follow-up consultations, achieving higher accuracy in diagnoses and suggested tests. Optimal performance was achieved with four doctor agents and a supervisor agent, using GPT-4 as the base model. MAC demonstrated high consistency across repeated runs. Further comparative analysis showed MAC also outperformed other methods including Chain of Thoughts (CoT), Self-Refine, and Self-Consistency with higher performance and more output tokens. This framework significantly enhanced LLMs’ diagnostic capabilities, effectively bridging theoretical knowledge and practical clinical application. Our findings highlight the potential of multi-agent LLMs in healthcare and suggest further research into their clinical implementation.
Native learning ability and not age determines the effects of brain stimulation
Healthy aging often entails a decline in cognitive and motor functions, affecting independence and quality of life in older adults. Brain stimulation shows potential to enhance these functions, but studies show variable effects. Previous studies have tried to identify responders and non-responders through correlations between behavioral change and baseline parameters, but results lack generalization to independent cohorts. We propose a method to predict an individual’s likelihood of benefiting from stimulation, based on baseline performance of a sequential motor task. Our results show that individuals with less efficient learning mechanisms benefit from stimulation, while those with optimal learning strategies experience none or even detrimental effects. This differential effect, first identified in a public dataset and replicated here in an independent cohort, was linked to one’s ability to integrate task-relevant information and not age. This study constitutes a further step towards personalized clinical-translational interventions based on brain stimulation.
The Reliever Reliance Test: evaluating a new tool to address SABA over-reliance
Over-use of SABA is associated with poor asthma control and greater risk of exacerbations and death. Identifying and addressing the beliefs driving SABA over-reliance is key to reducing over-use. This study aimed to assess the utility, impact and acceptability of the Reliever Reliance Test (RRT), a brief patient self-test behaviour-change tool to identify and address SABA over-reliance. Patients with asthma who completed the RRT in Argentina were invited to an online survey exploring the acceptability of the RRT, and its impact on patients’ perceptions of SABA and intention to discuss asthma treatment with a doctor. 93 patients completed the questionnaire. The RRT classified 76/93 (82%) as medium-to-high risk of SABA over-reliance (a mindset where SABA is perceived as the most important aspect of asthma treatment), with 73% of these reporting SABA overuse (3 or more times a week). 75% intended to follow the RRT recommendations to review their asthma treatment with their doctor. The RRT is acceptable to patients and was effective at raising awareness of, identifying and addressing SABA over-reliance and encouraging patients to review their treatment with their doctor.
A severe local flood and social events show a similar impact on human mobility
While a social event, such as a concert or a food festival, is a common experience to people, a natural disaster is experienced by a fewer individuals. The ordinary and common ground experience of social events could be, therefore, used to better understand the complex impacts of uncommon, but devastating natural events on society, such as floods. Based on this idea, we present a comparison — in terms of human mobility — between an extreme local flood that occurred in 2017 in Switzerland, and social events which took place in the same region, in the weeks before and after the inundation. Using mobile phone location data, we show that the severe local flood and social events have a similar impact on human mobility, both at the national scale and at a local scale. At the national level, we found a small difference between the distributions of visitors and their travelled distances among the several weeks in which the events took place. At the local level, instead, we detected the anomalies (in time series) in the number of people travelling each road and railway, and we found that the distributions of anomalies, and of their clusters, are comparable between the flood and the social events. Hence, our findings suggest that the knowledge on ubiquitous social events can be employed to characterise the impacts of rare natural disasters on human mobility. The proposed methods at the local level can thus be used to analyse the disturbances in complex spatial networks and, in general, as complementary approaches for the analyses of complex systems.
BREATHLEssness in INDIA (BREATHE-INDIA): realist review to develop explanatory programme theory about breathlessness self-management in India
Breathlessness is highly prevalent in low and middle-income countries (LMICs). Low-cost, non-drug, breathlessness self-management interventions are effective in high-income countries. However, health beliefs influence acceptability and have not been explored in LMIC settings. Review with stakeholder engagement to co-develop explanatory programme theories for whom, if, and how breathlessness self-management might work in community settings in India. Iterative and systematic searches identified peer-reviewed articles, policy and media, and expert-identified sources. Data were extracted in terms of contribution to theory (high, medium, low), and theories developed with stakeholder groups (doctors, nurses and allied professionals, people with lived experiences, lay health workers) and an International Steering Group (RAMESES guidelines (PROSPERO42022375768)). One hundred and four data sources and 11 stakeholder workshops produced 8 initial programme theories and 3 consolidated programme theories. (1) Context: breathlessness is common due to illness, environment, and lifestyle. Cultural beliefs shape misunderstandings about breathlessness; hereditary, part of aging, linked to asthma. It is stigmatised and poorly understood as a treatable issue. People often use rest, incense, or tea, while avoiding physical activity due to fear of worsening breathlessness. Trusted voices, such as healthcare workers and community members, can help address misconceptions with clear, simple messages. (2) Breathlessness intervention applicability: nonpharmacological interventions can work across different contexts when they address unhelpful beliefs and behaviours. Introducing concepts like “too much rest leads to deconditioning” aligns with cultural norms while promoting beneficial behavioural changes, such as gradual physical activity. Acknowledging breathlessness as a medical issue is key to improving patient and family well-being. (3) Implementation: community-based healthcare workers are trusted but need simple, low-cost resources/skills integrated into existing training. Education should focus on managing acute episodes and daily breathlessness, reducing fear, and encouraging behavioural change. Evidence-based tools are vital to gain support from policymakers and expand implementation. Breathlessness management in India must integrate symptom management alongside public health and disease treatment strategies. Self-management interventions can be implemented in an LMIC setting. However, our novel methods indicate that understanding the context for implementation is essential so that unhelpful health beliefs can be addressed at the point of intervention delivery.
Responses