Background Emerging machine learning technologies are beginning to transform medicine and healthcare and could also improve the diagnosis and treatment of rare diseases. Currently, there are no systematic reviews that investigate, from a general perspective, how machine learning is used in a rare disease context. This scoping review aims to address this gap and explores the use of machine learning in rare diseases, investigating, for example, in which rare diseases machine learning is applied, which types of algorithms and input data are used or which medical applications (e.g., diagnosis, prognosis or treatment) are studied. Methods Using a complex search string including generic search terms and 381 individual disease names, studies from the past 10 years (2010–2019) that applied machine learning in a rare disease context were identified on PubMed. To systematically map the research activity, eligible studies were categorized along different dimensions (e.g., rare disease group, type of algorithm, input data), and the number of studies within these categories was analyzed. Results Two hundred eleven studies from 32 countries investigating 74 different rare diseases were identified. Diseases with a higher prevalence appeared more often in the studies than diseases with a lower prevalence. Moreover, some rare disease groups were investigated more frequently than to be expected (e.g., rare neurologic diseases and rare systemic or rheumatologic diseases), others less frequently (e.g., rare inborn errors of metabolism and rare skin diseases). Ensemble methods (36.0%), support vector machines (32.2%) and artificial neural networks (31.8%) were the algorithms most commonly applied in the studies. Only a small proportion of studies evaluated their algorithms on an external data set (11.8%) or against a human expert (2.4%). As input data, images (32.2%), demographic data (27.0%) and “omics” data (26.5%) were used most frequently. Most studies used machine learning for diagnosis (40.8%) or prognosis (38.4%) whereas studies aiming to improve treatment were relatively scarce (4.7%). Patient numbers in the studies were small, typically ranging from 20 to 99 (35.5%). Conclusion Our review provides an overview of the use of machine learning in rare diseases. Mapping the current research activity, it can guide future work and help to facilitate the successful application of machine learning in rare diseases.

Representative surveys indicate that eating disorders are an increasing problem, especially among (pre)adolescents. We assessed the effects of a German school-based primary prevention program ("Torera") for seventh graders. Torera especially relates to pathological eating behavior in the realm of bulimia nervosa or binge eating disorder. The program is built upon two previously evaluated modules for sixth graders with a gender-specific adaption. The coeducational intervention involves nine manual-guided lessons touching a wide range of eating-related problems. Twenty-two Thuringian secondary schools (n = 256 boys and 277 girls, aged 11-13 years at baseline) participated in a trial with 2 control groups (untreated and pretreated) with pre-post assessment. Primary outcomes were conspicuous eating behavior and body self-esteem, measured by standardized questionnaires (SCOFF, EAT-26D, and FBeK). Girls and students at risk showed significant improvement with small (d = 0.35) to medium (d = 0.66) effect sizes on eating behavior, significantly mediated by body self-esteem. Boys only improved with respect to eating attitudes, revealing a small effect size (d = 0.35). With relatively low implementation costs (about 2.50 per student), Torera provides an efficient model for reducing risky eating behavior and strengthening body self-esteem without negative side effects. To improve the effectiveness of the intervention, further research efforts focusing on at-risk groups (secondary prevention) and structural actions for prevention (e.g., offering healthy school catering) are needed.

Objective:To examine child behavior change scores from randomized controlled trials (RCTs) of parent interventions for pediatric traumatic brain injury (TBI). Methods: MEDLINE, EMBASE, PsycINFO, and CINAHL were searched to identify studies that examined parent interventions for pediatric TBI. Inclusion criteria included (i) a parent intervention for children with TBI; (ii) an RCT study design; (iii) statistical data for child behavior outcome(s); and (iv) studies that were published in English. Results: Seven studies met inclusion criteria. All interventions reported improved child behavior after pediatric TBI; however, child and parent factors contributed to behavior change scores in some interventions. Factors found to contribute to the level of benefit included age of child, baseline behavior levels, sociodemographics (eg, parent income, parent education), and parent mental health. Conclusion: Improved child behavior outcomes resulting from parent interventions for pediatric TBI are well supported by the evidence in the peer-reviewed literature. Clinicians are encouraged to consider child and parent factors as they relate to child behavior outcomes.