Basic principles of artificial intelligence in dermatology explained using melanoma.

The use of artificial intelligence (AI) continues to establish itself in the most diverse areas of medicine at an increasingly fast pace. Nevertheless, many healthcare professionals lack the basic technical understanding of how this technology works, which severely limits its application in clinical settings and research. Thus, we would like to discuss the functioning and classification of AI using melanoma as an example in this review to build an understanding of the technology behind AI. For this purpose, elaborate illustrations are used that quickly reveal the technology involved. Previous reviews tend to focus on the potential applications of AI, thereby missing the opportunity to develop a deeper understanding of the subject matter that is so important for clinical application. Malignant melanoma has become a significant burden for healthcare systems. If discovered early, a better prognosis can be expected, which is why skin cancer screening has become increasingly popular and is supported by health insurance. The number of experts remains finite, reducing their availability and leading to longer waiting times. Therefore, innovative ideas need to be implemented to provide the necessary care. Thus, machine learning offers the ability to recognize melanomas from images at a level comparable to experienced dermatologists under optimized conditions.

Novel Method for Three-Dimensional Facial Expression Recognition Using Self-Normalizing Neural Networks and Mobile Devices.

Introduction To date, most ways to perform facial expression recognition rely on two-dimensional images, advanced approaches with three-dimensional data exist. These however demand stationary apparatuses and thus lack portability and possibilities to scale deployment. As human emotions, intent and even diseases may condense in distinct facial expressions or changes therein, the need for a portable yet capable solution is signified. Due to the superior informative value of three-dimensional data on facial morphology and because certain syndromes find expression in specific facial dysmorphisms, a solution should allow portable acquisition of true three-dimensional facial scans in real time. In this study we present a novel solution for the three-dimensional acquisition of facial geometry data and the recognition of facial expressions from it. The new technology presented here only requires the use of a smartphone or tablet with an integrated TrueDepth camera and enables real-time acquisition of the geometry and its categorization into distinct facial expressions. Material and Methods Our approach consisted of two parts: First, training data was acquired by asking a collective of 226 medical students to adopt defined facial expressions while their current facial morphology was captured by our specially developed app running on iPads, placed in front of the students. In total, the list of the facial expressions to be shown by the participants consisted of "disappointed", "stressed", "happy", "sad" and "surprised". Second, the data were used to train a self-normalizing neural network. A set of all factors describing the current facial expression at a time is referred to as "snapshot". Results In total, over half a million snapshots were recorded in the study. Ultimately, the network achieved an overall accuracy of 80.54% after 400 epochs of training. In test, an overall accuracy of 81.15% was determined. Recall values differed by the category of a snapshot and ranged from 74.79% for "stressed" to 87.61% for "happy". Precision showed similar results, whereas "sad" achieved the lowest value at 77.48% and "surprised" the highest at 86.87%. Conclusions With the present work it can be demonstrated that respectable results can be achieved even when using data sets with some challenges. Through various measures, already incorporated into an optimized version of our app, it is to be expected that the training results can be significantly improved and made more precise in the future. Currently a follow-up study with the new version of our app that encompasses the suggested alterations and adaptions, is being conducted. We aim to build a large and open database of facial scans not only for facial expression recognition but to perform disease recognition and to monitor diseases' treatment progresses.

Continuous facility location on graphs.

We study a continuous facility location problem on undirected graphs where all edges have unit length and where the facilities may be positioned on the vertices as well as on interior points of the edges. The goal is to cover the entire graph with a minimum number of facilities with covering range δ > 0 . In other words, we want to position as few facilities as possible subject to the condition that every point on every edge is at distance at most δ from one of these facilities. We investigate this covering problem in terms of the rational parameter δ . We prove that the problem is polynomially solvable whenever δ is a unit fraction, and that the problem is NP-hard for all non unit fractions δ . We also analyze the parametrized complexity with the solution size as parameter: The resulting problem is fixed parameter tractable for δ < 3 / 2 , and it is W[2]-hard for δ ≥ 3 / 2 .

Novel and flexible ultrasound simulation with smartphones and tablets in fetal echocardiography.

PURPOSE: Evaluation of a novel ultrasound-simulation-app for training fetal echocardiography as a possible useful addition for students, residents and specialist doctors. Furthermore, comparison to a conventional learning-method with special attention on orientation and recognition of physiological structures. METHODS: Prospective two-arm study with the participation of 226 clinical students. 108 students were given an extract from a textbook on fetal echocardiography (PDF-group, n = 108) for 30 min to study. 118 students were able to use the new ultrasound-simulator-app (Simulator-group, n = 118) to learn for 30 min. The knowledge of the students was examined both before and after the learning-period by having them identify sonographic structures in videos using single-choice selection. RESULTS: There were no significant differences between the two groups regarding age (p = 0.87), gender (p = 0.28), and the number of previously performed ultrasound-examinations (p = 0.45). In the Simulator-group, there was a significantly higher learning effect regarding the proportion of students with an increase of correct answers in the video test examination (p = 0.005). At the end of learning, the students in the Simulator-group needed significantly less time to display the structures in the app's simulation (median initially 10.9 s vs. 6.8 s at the end; p < 0.001). CONCLUSIONS: The novel ultrasound-simulation-app seems to be a useful addition and improvement to ultrasound training. Previous difficulties such as simultaneously having patients, ultrasound-machines, and professors at disposal can thus be avoided. This means that another important step towards remote learning can be taken, which has been proven increasingly essential lately, due to the COVID-19 pandemic.

Increasing pupil size is associated with improved detection performance in the periphery.

Visible light enters our body via the pupil. By changing its size, the pupil shapes visual input. Small apertures increase the resolution of high spatial frequencies, thus allowing discrimination of fine details. Large apertures, in contrast, provide a better signal-to-noise ratio, because more light can enter the eye. This should lead to better detection performance of peripheral stimuli. Experiment 1 shows that the effect can reliably be demonstrated even in a less controlled online setting. In Experiment 2, pupil size was measured in a laboratory using an eye tracker. The findings replicate findings showing that large pupils provide an advantage for peripheral detection of faint stimuli. Moreover, not only pupil size during information intake in the current trial n, but also its interaction with pupil size preceding information intake, i.e., in trial n-1, predicted performance. This suggests that in addition to absolute pupil size, the extent of pupillary change provides a mechanism to modulate perceptual functions. The results are discussed in terms of low-level sensory as well as higher-level arousal-driven changes in stimulus processing.

Is There Any Evidence of Monocytes Involvement in Alzheimer's Disease? A Pilot Study on Human Postmortem Brain.

BACKGROUND: The role of neuroinflammation has become more evident in the pathogenesis of neurodegenerative diseases. Increased expression of microglial markers is widely reported in Alzheimer's disease (AD), but much less is known about the role of monocytes in AD pathogenesis. In AD animal models, bone marrow-derived monocytes appear to infiltrate the parenchyma and contribute to the phagocytosis of amyloid-ß depositions, but this infiltration has not been established in systematic studies of the human brain postmortem. OBJECTIVE: In addition to assessing the distribution of different subtypes of microglia by immunostaining for CD68, HLA-DR, CD163, and CD206, we focused on the involvement of C-chemokine receptor type2 (CCR2) positive monocytes during the AD course. METHODS: We used formalin-fixed and paraffin-embedded tissue from four vulnerable brain regions (hippocampus, occipital lobe, brainstem, and cerebellum) from neuropathologically characterized AD cases at different Braak stages and age-matched controls. RESULTS: Only singular migrated CCR2-positive cells were found in all brain regions and stages. The brainstem showed the highest number of positive cells overall, followed by the hippocampus. This mechanism of recruitment seems to work less efficiently in the human brain at an advanced age, and the ingress of monocytes obviously takes place in much reduced numbers or not at all. CONCLUSION: In contrast to studies on animal models, we observed only a quite low level of myeloid monocytes associated with AD pathology. Furthermore, we provide evidence associating early microglial reactions carried out in particular by pro-inflammatory cells with early effects on tangle- and plaque-positive vulnerable brain regions.

Additional plerixafor to granulocyte colony-stimulating factors for haematopoietic stem cell mobilisation for autologous transplantation in people with malignant lymphoma or multiple myeloma.

BACKGROUND: Autologous stem cell transplantation is widely used to restore functioning bone marrow in people with malignant lymphoma or multiple myeloma after myeloablative chemotherapy. Results of some clinical trials indicate that plerixafor in addition to granulocyte colony-stimulating factors (G-CSF) compared to G-CSF only could lead to an increased mobilisation and release of CD34-positive cells, facilitating effective apheresis. OBJECTIVES: To evaluate the efficacy and safety of additional plerixafor to G-CSF for haematopoietic stem cell mobilisation in people with malignant lymphoma or multiple myeloma. SEARCH METHODS: We searched the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE (from 1990 to September 2015), as well as conference proceedings (American Society of Hematology; American Society of Clinical Oncology; European Hematology Association; American Society for Blood and Marrow Transplantation; European Group for Blood and Marrow Transplantation) for studies. Two review authors independently screened search results. SELECTION CRITERIA: We included randomised controlled trials (RCTs) comparing plerixafor in addition to G-CSF compared to G-CSF only for stem cell mobilisation in people with malignant lymphoma or multiple myeloma of all stages and ages. We included full text as well as abstracts and unpublished data if sufficient information on study design, participant characteristics, interventions, and outcomes was available. We excluded cross-over trials, quasi-randomised trials, and post-hoc retrospective trials. DATA COLLECTION AND ANALYSIS: Two review authors independently screened the results of the search strategies, extracted data, assessed quality, and analysed data according to standard Cochrane methods. We performed final interpretation with an experienced clinician. MAIN RESULTS: We identified four RCTs fitting the inclusion criteria. However, two of these closed prematurely due to low recruitment and did not report results. The remaining two trials evaluated 600 participants with multiple myeloma or non-Hodgkin lymphoma. In both studies the experimental group received G-CSF plus plerixafor and the control group received G-CSF plus placebo.The meta-analysis showed no evidence for differences between plerixafor and placebo group regarding mortality at 12 months (600 participants; risk ratio (RR) 1.00, 95% confidence interval (CI) 0.59 to 1.69; P = 1.00; moderate-quality evidence) and adverse events during stem cell mobilisation and collection (593 participants; RR 1.02, 95% CI 0.99 to 1.06; P = 0.19; high-quality evidence).Regarding the outcome successful stem cell collection, the meta-analysis showed an advantage for those participants randomised to the plerixafor group (600 participants; RR 2.42, 95% CI 1.98 to 2.96; P < 0.00001; high-quality evidence).As there was high heterogeneity between studies for the number of transplanted participants, we did not meta-analyse these data. In the multiple myeloma study, 95.9% (142 participants) in the plerixafor arm and 88.3% (136 participants) in the placebo arm underwent transplantation (RR 1.09, 95% CI 1.02 to 1.16); in the non-Hodgkin lymphoma trial, 90% (135 participants) in the plerixafor group versus 55.4% (82 participants) in the placebo group could be transplanted (RR 1.62, 95% CI 1.39 to 1.89). In both trials there was no evidence for a difference between participants in the plerixafor and placebo group in terms of time to neutrophil and platelet engraftment in transplanted participants.None of the trials reported on the outcomes quality of life and progression-free survival. AUTHORS' CONCLUSIONS: The results of the analysed data suggest that additional plerixafor leads to increased stem cell collection in a shorter time. There was insufficient evidence to determine whether additional plerixafor affects survival or adverse events.The two trials included in the meta-analysis, both of which were conducted by the Genzyme Corporation, the manufacturer of plerixafor, were published several times. Two more RCTs examining the addition of plerixafor to a G-CSF mobilisation regimen terminated early without publishing any outcome. The trials included nine and five participants, respectively. Another RCT with 100 participants was recently completed, but has not yet published outcomes. Due to the unpublished RCTs, it is possible that our review is affected by publication bias, even though two trials failed to recruit a sufficient number of participants to analyse any data.

miRNA-197 and miRNA-223 Predict Cardiovascular Death in a Cohort of Patients with Symptomatic Coronary Artery Disease.

BACKGROUND: Circulating microRNAs (miRNAs) have been described as potential diagnostic biomarkers in cardiovascular disease and in particular, coronary artery disease (CAD). Few studies were undertaken to perform analyses with regard to risk stratification of future cardiovascular events. miR-126, miR-197 and miR-223 are involved in endovascular inflammation and platelet activation and have been described as biomarkers in the diagnosis of CAD. They were identified in a prospective study in relation to future myocardial infarction. OBJECTIVES: The aim of our study was to further evaluate the prognostic value of these miRNAs in a large prospective cohort of patients with documented CAD. METHODS: Levels of miR-126, miR-197 and miR-223 were evaluated in serum samples of 873 CAD patients with respect to the endpoint cardiovascular death. miRNA quantification was performed using real time polymerase chain reaction (RT-qPCR). RESULTS: The median follow-up period was 4 years (IQR 2.78-5.04). The median age of all patients was 64 years (IQR 57-69) with 80.2% males. 38.9% of the patients presented with acute coronary syndrome (ACS), 61.1% were diagnosed with stable angina pectoris (SAP). Elevated levels of miRNA-197 and miRNA-223 reliably predicted future cardiovascular death in the overall group (miRNA-197: hazard ratio (HR) 1.77 per one standard deviation (SD) increase (95% confidence interval (CI) 1.20; 2.60), p = 0.004, C-index 0.78; miRNA-223: HR 2.23 per one SD increase (1.20; 4.14), p = 0.011, C-index 0.80). In ACS patients the prognostic power of both miRNAs was even higher (miRNA-197: HR 2.24 per one SD increase (1.25; 4.01), p = 0.006, C-index 0.89); miRA-223: HR 4.94 per one SD increase (1.42; 17.20), p = 0.012, C-index 0.89). CONCLUSION: Serum-derived circulating miRNA-197 and miRNA-223 were identified as predictors for cardiovascular death in a large patient cohort with CAD. These results reinforce the assumption that circulating miRNAs are promising biomarkers with prognostic value with respect to future cardiovascular events.

Perceived fitness protects against stress-based mental health impairments among police officers who report good sleep.

OBJECTIVES: This study examined a cognitive stress-moderation model that posits that the harmful effects of chronic stress are decreased in police officers who perceive high levels of physical fitness. It also determined whether the stress-buffering effect of perceived fitness is influenced by officers' self-reported sleep. METHODS: A total of 460 police officers (n=116 females, n=344 males, mean age: M=40.7; SD=9.7) rated their physical fitness and completed a battery of self-report stress, mental health, and sleep questionnaires. Three-way analyses of covariance were performed to examine whether officers' self-reported mental health status depends on the interaction between stress, perceived fitness and sleep. RESULTS: Highly stressed officers perceived lower mental health and fitness and were overrepresented in the group of poor sleepers. Officers with high fitness self-reports revealed increased mental health and reported good sleep. In contrast, poor sleepers scored lower on the mental health index. High stress was more closely related to low mental health among poor sleepers. Most importantly, perceived fitness revealed a stress-buffering effect, but only among officers who reported good sleep. CONCLUSIONS: High perceived fitness and good sleep operate as stress resilience resources among police officers. The findings suggest that multimodal programs including stress management, sleep hygiene and fitness training are essential components of workplace health promotion in the police force.

Relationship of hyperactivity/inattention with adiposity and lifestyle characteristics in preschool children.

We performed a cross-sectional study in 450 nonreferred preschool children aged 4 to 6 years to assess the association between hyperactivity/inattention with adiposity and lifestyle characteristics. Measurements included scores of hyperactivity/inattention, adiposity, objectively measured physical activity, television viewing, and eating habits. Higher scores of hyperactivity/inattention were associated with lower percentage body fat, higher levels of physical activity, and less time spent in sedentary activity (all P ≤ .01). However, higher scores of hyperactivity/inattention were also associated with more television viewing and less healthy eating habits (all P ≤ .04). Except for some selected eating habits (P ≥ .07), those relationships remained significant after adjustment for age, sex, and sociodemographic confounders. To conclude, higher scores of hyperactivity/inattention are linked to different lifestyle characteristics that may in part contribute to a future development of overweight/obesity. Precise mechanisms explaining these associations and possible preventive approaches should be further investigated.

Relationship of aerobic fitness and motor skills with memory and attention in preschoolers (Ballabeina): a cross-sectional and longitudinal study.

BACKGROUND: The debate about a possible relationship between aerobic fitness and motor skills with cognitive development in children has recently re-emerged, because of the decrease in children's aerobic fitness and the concomitant pressure of schools to enhance cognitive performance. As the literature in young children is scarce, we examined the cross-sectional and longitudinal relationship of aerobic fitness and motor skills with spatial working memory and attention in preschool children. METHODS: Data from 245 ethnically diverse preschool children (mean age: 5.2 (0.6) years, girls: 49.4%) analyzed at baseline and 9 months later. Assessments included aerobic fitness (20 m shuttle run) and motor skills with agility (obstacle course) and dynamic balance (balance beam). Cognitive parameters included spatial working memory (IDS) and attention (KHV-VK). All analyses were adjusted for age, sex, BMI, migration status, parental education, native language and linguistic region. Longitudinal analyses were additionally adjusted for the respective baseline value. RESULTS: In the cross-sectional analysis, aerobic fitness was associated with better attention (r=0.16, p=0.03). A shorter time in the agility test was independently associated with a better performance both in working memory (r=-0.17, p=0.01) and in attention (r=-0.20, p=0.01). In the longitudinal analyses, baseline aerobic fitness was independently related to improvements in attention (r=0.16, p=0.03), while baseline dynamic balance was associated with improvements in working memory (r=0.15, p=0.04). CONCLUSIONS: In young children, higher baseline aerobic fitness and motor skills were related to a better spatial working memory and/or attention at baseline, and to some extent also to their future improvements over the following 9 months. TRIAL REGISTRATION: clinicaltrials.gov NCT00674544.

Effect of school based physical activity programme (KISS) on fitness and adiposity in primary schoolchildren: cluster randomised controlled trial.

OBJECTIVE: To assess the effectiveness of a school based physical activity programme during one school year on physical and psychological health in young schoolchildren. DESIGN: Cluster randomised controlled trial. SETTING: 28 classes from 15 elementary schools in Switzerland randomly selected and assigned in a 4:3 ratio to an intervention (n=16) or control arm (n=12) after stratification for grade (first and fifth grade), from August 2005 to June 2006. PARTICIPANTS: 540 children, of whom 502 consented and presented at baseline. INTERVENTION: Children in the intervention arm (n=297) received a multi-component physical activity programme that included structuring the three existing physical education lessons each week and adding two additional lessons a week, daily short activity breaks, and physical activity homework. Children (n=205) and parents in the control group were not informed of an intervention group. For most outcome measures, the assessors were blinded. MAIN OUTCOME MEASURES: Primary outcome measures included body fat (sum of four skinfolds), aerobic fitness (shuttle run test), physical activity (accelerometry), and quality of life (questionnaires). Secondary outcome measures included body mass index and cardiovascular risk score (average z score of waist circumference, mean blood pressure, blood glucose, inverted high density lipoprotein cholesterol, and triglycerides). RESULTS: 498 children completed the baseline and follow-up assessments (mean age 6.9 (SD 0.3) years for first grade, 11.1 (0.5) years for fifth grade). After adjustment for grade, sex, baseline values, and clustering within classes, children in the intervention arm compared with controls showed more negative changes in the z score of the sum of four skinfolds (-0.12, 95 % confidence interval -0.21 to -0.03; P=0.009). Likewise, their z scores for aerobic fitness increased more favourably (0.17, 0.01 to 0.32; P=0.04), as did those for moderate-vigorous physical activity in school (1.19, 0.78 to 1.60; P<0.001), all day moderate-vigorous physical activity (0.44, 0.05 to 0.82; P=0.03), and total physical activity in school (0.92, 0.35 to 1.50; P=0.003). Z scores for overall daily physical activity (0.21, -0.21 to 0.63) and physical quality of life (0.42, -1.23 to 2.06) as well as psychological quality of life (0.59, -0.85 to 2.03) did not change significantly. CONCLUSIONS: A school based multi-component physical activity intervention including compulsory elements improved physical activity and fitness and reduced adiposity in children. Trial registration Current Controlled Trials ISRCTN15360785.

Effects of a school-based physical activity program on physical and psychosocial quality of life in elementary school children: a cluster-randomized trial.

The present study tested the effect of a school-based physical activity (PA) program on quality of life (QoL) in 540 elementary school children. First and fifth graders were randomly assigned to a PA program or a no-PA control condition during one academic year. QoL was assessed by the Child Health Questionnaire at baseline and postintervention. Based on mixed linear model analyses, physical QoL in first graders and physical and psychosocial QoL in fifth graders were not affected by the intervention. In first graders, the PA intervention had a positive impact on psychosocial QoL (effect size [d], 0.32; p < .05). Subpopulation analyses revealed that this effect was caused by an effect in urban (effect size [d], 0.38; p < .05) and overweight first graders (effect size [d], 0.45; p < .05). In conclusion, a school-based PA intervention had little effect on QoL in elementary school children.

Influence of a lifestyle intervention in preschool children on physiological and psychological parameters (Ballabeina): study design of a cluster randomized controlled trial.

BACKGROUND: Childhood obesity and physical inactivity are increasing dramatically worldwide. Children of low socioeconomic status and/or children of migrant background are especially at risk. In general, the overall effectiveness of school-based programs on health-related outcomes has been disappointing. A special gap exists for younger children and in high risk groups. METHODS/DESIGN: This paper describes the rationale, design, curriculum, and evaluation of a multicenter preschool randomized intervention study conducted in areas with a high migrant population in two out of 26 Swiss cantons. Twenty preschool classes in the German (canton St. Gallen) and another 20 in the French (canton Vaud) part of Switzerland were separately selected and randomized to an intervention and a control arm by the use of opaque envelopes. The multidisciplinary lifestyle intervention aimed to increase physical activity and sleep duration, to reinforce healthy nutrition and eating behaviour, and to reduce media use. According to the ecological model, it included children, their parents and the teachers. The regular teachers performed the majority of the intervention and were supported by a local health promoter. The intervention included physical activity lessons, adaptation of the built infrastructure; promotion of regional extracurricular physical activity; playful lessons about nutrition, media use and sleep, funny homework cards and information materials for teachers and parents. It lasted one school year. Baseline and post-intervention evaluations were performed in both arms. Primary outcome measures included BMI and aerobic fitness (20 m shuttle run test). Secondary outcomes included total (skinfolds, bioelectrical impedance) and central (waist circumference) body fat, motor abilities (obstacle course, static and dynamic balance), physical activity and sleep duration (accelerometry and questionnaires), nutritional behaviour and food intake, media use, quality of life and signs of hyperactivity (questionnaires), attention and spatial working memory ability (two validated tests). Researchers were blinded to group allocation. DISCUSSION: The purpose of this paper is to outline the design of a school-based multicenter cluster randomized, controlled trial aiming to reduce body mass index and to increase aerobic fitness in preschool children in culturally different parts of Switzerland with a high migrant population. TRIAL REGISTRATION: Trial Registration: (clinicaltrials.gov) NCT00674544.