eLearning improves allied health professionals' knowledge and confidence to manage medically unexplained chronic fatigue states: A randomized controlled trial.

OBJECTIVES: To evaluate the impact of eLearning by allied health professionals on improving the knowledge and confidence to manage people with medically unexplained chronic fatigue states (FS). METHODS: Using a parallel randomized controlled trial design, participants were randomized 1:1 to a 4-week eLearning or wait-list control group. Knowledge and self-reported confidence in clinical skills to implement a therapeutic intervention for patients with FS were assessed at baseline, post-intervention and follow-up. Secondary outcomes (adherence and satisfaction with online education, knowledge retention) were also assessed. Data was analyzed using intention-to-treat. RESULTS: There were 239 participants were randomized (eLearning n = 119, control n = 120), of whom 101 (85%) eLearning and 107 (89%) control participants completed baseline assessments and were included in the analysis. Knowledge (out of 100) improved significantly more in the eLearning group compared to the control group [mean difference (95% CI) 8.6 (5.9 to 11.4), p < 0.001]. Knowledge was reduced in the eLearning group at follow-up but was still significantly higher than baseline [6.0 (3.7 to 8.3), p < 0.001]. Median change (out of 5) in confidence in clinical skills to implement the FS intervention was also significantly greater in the eLearning group compared to the control group [knowledge: eLearning (1.2), control (0); clinical skills: eLearning (1), control (0.1); both p < 0.001)]. Average time spent on the eLearning program was 8.8 h. Most participants (80%) rated the lesson difficulty as at the "right level", and 91% would recommend it to others. CONCLUSIONS: eLearning increased knowledge and confidence to manage FS amongst allied health professionals and was well-accepted. REGISTRATION: ACTRN12616000296437 https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=370222&isReview=true.

Task-sharing with artificial intelligence: a design hypothesis for an Emergency Unit in sub-Saharan Africa.

In sub-Saharan Africa, there is a significant unmet need for emergency care, with a shortage of trained providers. One model to increase the number of providers is to task-share: roles traditionally filled by clinicians are shared with lay workers who have received task-specific training. Separately, there has been much recent interest in the possible implications of artificial intelligence (AI) on healthcare. This paper proposes that, by combining the task-sharing model with AI, it is possible to design an Emergency Unit (EU) that shares the tasks currently undertaken by physicians and nurses with lay providers, with the activities of lay providers guided and supervised by AI. The proposed model would free emergency care clinicians to focus on higher-acuity and complex cases while AI-supervised routine care is provided by lay providers. The paper outlines the model for such an implementation and considers the potential benefits to patient care, as well as considering the risks, costs, effect on providers, and ethical questions. The paper concludes that AI and healthcare workers can operate as a team, with significant potential to augment human resources for health in sub-Saharan Africa.

A pilot study of a novel, incentivised mHealth technology to monitor the vaccine supply chain in rural Zambia.

INTRODUCTION: The World Health Organization estimates that up to half of vaccines are wasted, however only a minority of mHealth programs in Africa have been directed at vaccine supply chain optimisation. We piloted a novel mHealth solution dependent only on short message services (SMS) technology that allowed workers in rural health centres in Zambia to report vaccine stock levels directly to an online platform. Small airtime incentives were offered to encourage users to engage with the system, as well as weekly reminder messages asking for stock updates. METHODS: The primary outcome measured was the percentage-of-doses-tracked, calculated over the study period. Each vaccine box was randomly allocated to offer either a standard or double airtime incentive and either weekly or daily reminders, in a 2 x 2 design; ANOVA was used to calculate if any of these factors affected time-to-reply. RESULTS: Over the study period, the total percentage-of-doses-tracked was 39.9%. Within the subset of users who sent at least one message to the platform, the percentage-of-doses-tracked was 93.8%. There was no significant difference in average time-to-reply between the standard airtime incentive and double airtime incentive groups, nor was there a significant difference between the standard reminder and daily follow-up reminder groups. CONCLUSION: This pilot study found that in an active subgroup of health workers, an incentivised mHealth solution was able to collect tracking data for 93.8% of doses. More research is needed to identify methods to encourage healthcare workers to engage in timely stock reporting practices.

Too hot to handle? Heat resilience in urban South Sudan

South Sudan is at risk from the impact of climate change. This paper reviews the climate change issues faced by South Sudan, and the strategy as outlined to the United Nations. The author argues that the policy overlooks a key potential cause of future morbidity and mortality: increased ambient temperatures, particularly in urban centres due to the urban heat island effect. The capital is especially susceptible to heat-related mortality as it faces a 'triple threat': rapidly rising temperatures, an at-risk population profile, and inadequate planning for the pressures of urbanisation. Four low-cost, evidence-based recommendations are given to mitigate the impact of heatwaves on human health, and it is concluded that South Sudan has great potential to become a regional leader in heat resilience

Should Artificial Intelligence Augment Medical Decision Making? The Case for an Autonomy Algorithm.

A significant proportion of elderly and psychiatric patients do not have the capacity to make health care decisions. We suggest that machine learning technologies could be harnessed to integrate data mined from electronic health records (EHRs) and social media in order to estimate the confidence of the prediction that a patient would consent to a given treatment. We call this process, which takes data about patients as input and derives a confidence estimate for a particular patient's predicted health care-related decision as an output, the autonomy algorithm. We suggest that the proposed algorithm would result in more accurate predictions than existing methods, which are resource intensive and consider only small patient cohorts. This algorithm could become a valuable tool in medical decision-making processes, augmenting the capacity of all people to make health care decisions in difficult situations.

A Storytelling Approach: Insights from the Shambaa.

Narrative medicine explores the stories that patients tell; this paper, conversely, looks at some of the stories that patients are told. The paper starts by examining the 'story' told by the Shambaa people of Tanzania to explain the bubonic plague and contrasts this with the stories told by Ghanaian communities to explain lymphatic filariasis. By harnessing insights from memory studies, these stories' memorability is claimed to be due to their use mnemonic devices woven into stories. The paper suggests that stories can be unpatronising, informative, and appropriate vehicles for communicating medical information to all age groups across all cultures.

The case for a regional approach to publication impact.

Healthcare-related research is largely regional. Put simply, this is because disease burdens differ between world regions. Even global burdens, such as ischaemic heart disease and cancer, display distinctive characteristics in certain regions that are not seen in others. Regional differences in infrastructure, resources and human capital further compound the differences seen, as they affect the way in which the local scientific community can interact with the local disease burden. As such, it seems fair to assume that healthcare-related research ought to be regionally distributed. Although translation of research between regions can sometimes be done, the larger the gap in infrastructure, resources or human capital between regions, the less likely it is that it can be adequately bridged. A recent example of this pertains to accepted life-saving treatment for sepsis in high-income settings, which had the opposite effect when implemented and evaluated in low-income Zambia. This regionality of clinical medicine is, however, not reflected in academic publishing; the impact of a journal is measured and understood by metrics that use the world as their denominator. Therefore, top medical journals are perceived to be relevant equally to all contexts and regions. However, there is a strong case to be made that this lack of granularity is deleterious, and that the creation of a regional impact metric would place clinicians, researchers, and libraries in a better position to understand which journals are relevant to their context and practice.