Scorbuto: ancora un problema dei nostri giorni?

Scurvy is a condition due to chronic ascorbic acid deficiency responsible for vascular fragility and impaired bone formation. The result is gingival bleeding, petechial lesions and articular and bone pain or limb swelling. Children may also present with irritability, limping or refusal to walk. Because of these symptoms it can be misdiagnosed with osteomyelitis, septic arthritis, bone and soft tissue tumour, leukaemia, bleeding disorders and other rheumatologic conditions. In highly developed countries it is rare, but should be suspected in children with underlying chronic condition characterized by selective eating as in developmental delay or autism spectrum disorders. The paper presents an emblematic case.

Deep learning from “passive feeding” to “selective eating” of real-world data

Artificial intelligence (AI) based on deep learning has shown excellent diagnostic performance in detecting various diseases with good-quality clinical images. Recently, AI diagnostic systems developed from ultra-widefield fundus (UWF) images have become popular standard-of-care tools in screening for ocular fundus diseases. However, in real-world settings, these systems must base their diagnoses on images with uncontrolled quality (“passive feeding”), leading to uncertainty about their performance. Here, using 40,562 UWF images, we develop a deep learning–based image filtering system (DLIFS) for detecting and filtering out poor-quality images in an automated fashion such that only good-quality images are transferred to the subsequent AI diagnostic system (“selective eating”). In three independent datasets from different clinical institutions, the DLIFS performed well with sensitivities of 96.9%, 95.6% and 96.6%, and specificities of 96.6%, 97.9% and 98.8%, respectively. Furthermore, we show that the application of our DLIFS significantly improves the performance of established AI diagnostic systems in real-world settings. Our work demonstrates that “selective eating” of real-world data is necessary and needs to be considered in the development of image-based AI systems.

Eggs, sugar, grated bones: colour-based food preferences in autism, eating disorders, and beyond

In 1913, eccentric French composer Erik Satie wrote a fragmentary, diary-like essay where he depicted a strikingly rigid diet consisting solely of white foods: eggs, sugar, coconuts, rice, cream cheese, fuchsia juice and so on. Satie’s brief essay has later been used as one of many puzzle pieces in attempts to retrospectively diagnose him with autism spectrum disorder. With Satie’s white meal as a starting point, this paper explores colour-based food preferences and selective eating in clinical and non-clinical populations, with a special focus on autism spectrum disorder and avoidant/restrictive food intake disorder (ARFID). General colour preferences and their causes as well as the impact of colour on taste and food identification are also explored. Selective eating during childhood is immensely common and does not generally lead to disordered eating in the long run, although subgroups may experience rigidity around food of a more enduring nature. Problems related to eating were repeatedly described in Kanner’s original 1943 autism case series and continue to be common in autism. Most studies on eating and sensory sensitivity in autism show that the texture and consistency of the food are the most common factors behind selective eating. In contrast, colour-based food preferences appear to be relatively rare, although numerous anecdotal reports exist. Foods that are white or colourless may be particularly appealing or tolerable for individuals with sensory hypersensitivity, which can occur in autism or ARFID. Ultimately, in the case of Erik Satie, this paper concludes that his description of a strictly white diet should not be read as an autobiographical account but rather as an ironic take on contemporary symbolist literature, with the famously decadent all-black dinner party in French novelist Joris-Karl Huysmans’ À Rebours (1884; also known as Against Nature) as an obvious source of inspiration.