No abstract

Tuberculosis (TB) is the leading cause of preventable death in HIV-positive patients, and yet often remains undiagnosed and untreated. Chest x-ray is often used to assist in diagnosis, yet this presents additional challenges due to atypical radiographic presentation and radiologist shortages in regions where co-infection is most common. We developed a deep learning algorithm to diagnose TB using clinical information and chest x-ray images from 677 HIV-positive patients with suspected TB from two hospitals in South Africa. We then sought to determine whether the algorithm could assist clinicians in the diagnosis of TB in HIV-positive patients as a web-based diagnostic assistant. Use of the algorithm resulted in a modest but statistically significant improvement in clinician accuracy (p = 0.002), increasing the mean clinician accuracy from 0.60 (95% CI 0.57, 0.63) without assistance to 0.65 (95% CI 0.60, 0.70) with assistance. However, the accuracy of assisted clinicians was significantly lower (p < 0.001) than that of the stand-alone algorithm, which had an accuracy of 0.79 (95% CI 0.77, 0.82) on the same unseen test cases. These results suggest that deep learning assistance may improve clinician accuracy in TB diagnosis using chest x-rays, which would be valuable in settings with a high burden of HIV/TB co-infection. Moreover, the high accuracy of the stand-alone algorithm suggests a potential value particularly in settings with a scarcity of radiological expertise.

The devastating Haiti earthquake rightly resulted in an outpouring of international aid. Relief teams can be of tremendous value during disasters due to natural hazards. Although nobly motivated to help, all emergency interventions have unintended consequences. In the immediate aftermath of the earthquake, many selfless individuals committed to help, but was this really all in the name of reaching out a helping hand? This case report illustrates that medical disaster tourism is alive and well. IntroductionOn 12 January 2010, a 7.0 magnitude earthquake crumbled the capital of Haiti to the ground. The world watched as this devastating event resulted in an outpouring of international aid and well-intentioned disaster relief teams raced to Port-au-Prince to help. But was this really all in the name of reaching out a helping hand, or were we witnessing disaster tourism?Three authors were volunteers who responded in the immediate aftermath of the earthquake, where, among the many selfless individuals committed only to doing the right thing, we experienced disaster tourism first-hand. Our ordeal illustrates that medical disaster tourism is alive and well; we wonder whether the medical fraternity should hang its head in shame.

IntroductionEmergency care research in Africa is not on par with other world regions. The study aimed to assess the perceptions and practices towards research among current emergency care providers in Africa.MethodsA survey was sent to all individual members of the African Federation of Emergency Medicine. The survey was available in English and French.ResultsOne hundred and sixty-eight responses were analysed (invited n = 540, responded n = 188, 34.8%, excluded n = 20). Responders’ mean age was 36.3 years (SD = 9.1); 122 (72.6%) were male, 104 (61.9%) were doctors, and 127 (75.6%) were African trained. Thirty-seven (22%) have never been involved in research; 33 (19.6%) have been involved in ⩾5 research projects. African related projects were mostly relevant to African audiences (n = 106, 63.1%). Ninety-four (56%) participants have never published. Forty-one (24.4%) were not willing to publish in open access journals requesting a publication fee; 65 (38.7%) will consider open access journals if fees are sponsored. Eighty responders (47.6%) frequently experienced access block to original articles due to subscription charges. Lack of research funding (n = 108, 64.3%), lack of research training (n = 86, 51.2%), and lack of allocated research time (n = 76, 45.2%) were the main barriers to research involvement. Improvement of research skills (n = 118, 70.2%) and having research published (n = 117, 69.6%) were the top motivational factors selected. Responders agreed that research promotes critical thinking (n = 137, 81.5%) and serve as an important educational tool (n = 134, 80.4%). However, 134 (79.8%) feel that emergency care workers need to be shown how to use research to improve clinical practice. Most agreed that insufficient emergency care research is being conducted in Africa (n = 113, 67.3%).DiscussionThere is scope to increase research involvement in emergency care in Africa, but solutions need to be find to address lack of research-related funding, training and time.