Search

Machine learning (ML) models, especially deep neural networks, are increasingly being used for the analysis of medical images and as a supporting tool for clinical decision-making. In this study, we propose an artificial intelligence system to facilitate dental decision-making for the removal of mandibular third molars (M3M) based on 2-dimensional orthopantograms and the risk assessment of such a procedure. A total of 4,516 panoramic radiographic images collected at the Center of Dental Medicine at the University of Zurich, Switzerland, were used for training the ML model. After image preparation and preprocessing, a spatially dependent U-Net was employed to detect and retrieve the region of the M3M and inferior alveolar nerve (IAN). Image patches identified to contain a M3M were automatically processed by a deep neural network for the classification of M3M superimposition over the IAN (task 1) and M3M root development (task 2). A control evaluation set of 120 images, collected from a different data source than the training data and labeled by 5 dental practitioners, was leveraged to reliably evaluate model performance. By 10-fold cross-validation, we achieved accuracy values of 0.94 and 0.93 for the M3M–IAN superimposition task and the M3M root development task, respectively, and accuracies of 0.9 and 0.87 when evaluated on the control data set, using a ResNet-101 trained in a semisupervised fashion. Matthew's correlation coefficient values of 0.82 and 0.75 for task 1 and task 2, evaluated on the control data set, indicate robust generalization of our model. Depending on the different label combinations of task 1 and task 2, we propose a diagnostic table that suggests whether additional imaging via 3-dimensional cone beam tomography is advisable. Ultimately, computer-aided decision-making tools benefit clinical practice by enabling efficient and risk-reduced decision-making and by supporting less experienced practitioners before the surgical removal of the M3M. [ABSTRACT FROM AUTHOR]

Summary: Background: Many cancer types display sex and age disparity in incidence and outcome. The mutational load of tumours, including melanoma, varies according to sex and age. However, there are no tools to explore systematically whether clinical variables such as age and sex determine the genomic landscape of cancer. Objectives: To establish a mathematical approach using melanoma mutational data to analyse how sex and age shape the tumour genome. Methods: We model how age‐related (clock‐like) somatic mutations that arise during cell division, and extrinsic (environmental ultraviolet radiation) mutations accumulate in cancer genomes. Results: Melanoma is driven primarily by cell‐intrinsic age‐related mutations and extrinsic ultraviolet radiation‐induced mutations, and we show that these mutation types differ in magnitude and chronology and by sex in the distinct molecular melanoma subtypes. Our model confirms that age and sex are determinants of cellular mutation rate, shaping the final mutation composition. We show mathematically for the first time how, similarly to noncancer tissues, melanoma genomes reflect a decline in cell division during ageing. We find that clock‐like mutations strongly correlate with the acquisition of ultraviolet‐induced mutations, but critically, men present a higher number and rate of cell‐division‐linked mutations. Conclusions: These data indicate that the contribution of environmental damage to melanoma likely extends beyond genetic damage to affect cell division. Sex and age determine the final mutational composition of melanoma. What is already known about this topic? Cancer incidence and mortality are influenced by sex and age.Melanoma is more frequent in men, and the incidence and mortality rise with increasing age.The main mutations driving melanoma are linked predominantly to ultraviolet (UV) radiation damage and to errors accumulated in the DNA after each cell division, which are unrepaired.These clock‐like mutations linked to cell division accumulate steadily over time in both healthy tissue and cancers. What does this study add? Clock and UV mutations are tightly correlated and arise in melanoma as a function of age and sex.The molecular subtypes have a distinct pattern and rate of UV and clock mutations, and clock mutations depend on the amount of UV damage.The rate of clock mutations decreases as individuals age, reflecting a decrease in tissue proliferation during ageing.Men have more clock mutations, which reflect a distinct proliferation rate. What is the translational message? This study indicates that age and sex shape the rate of mutations observed in melanoma.The burden of mutation affects response to novel immunotherapies, so this work supports the rationale to stratify patients by their mutational landscape, age and sex to discriminate possible responders most easily.These data can better inform public health prevention campaigns. Linked Comment: Toland. Br J Dermatol 2021; 184:197–198. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study was to calculate the burden of wounds in several disciplines within a resource-constrained hospital to be a baseline for further studies. Material and methods: An observational, cross-sectional study was performed at Robert Mangaliso Sobukwe Hospital during November 2013. All inpatients and outpatients who presented at all clinical units on the specific day of the study were included, and data concerning the presence and type of wounds was collected. Simple statistics were used to determine the burden of wounds in the hospital and for each discipline. Results: Out of the 518 patients admitted, 179 presented with a wound, resulting in a wound burden of 34.6%. The burns unit (100%), ICU (75%) and general surgery (65%) were the predominant disciplines in this study. Acute wounds (including surgical wounds) with 45%, and traumatic wounds (including burn wounds) with 18%, were the most prevalent. Amongst chronic wounds, pressure injuries (9%) were predominant. Thirteen percent of wounds presented with clinical signs of infection and a positive culture. Conclusion: The lack of published statistics on wounds in South Africa limited the author in comparing the burden amongst hospitals, but showed to be in line with a few studies in Africa, Europe and the United Kingdom. Studies from first world countries indicated that a multidisciplinary wound care team can play a role in the timeous diagnosis and effective and efficient management of patients with wounds so as to prevent complications. The final outcome should reflect a decrease in the clinical and financial burden of wounds. The reason that international studies were used for comparison is because no local studies were available; comparison to other countries also shows how our data compare with international studies. This is also the reason for the publication of the results for future comparison. [ABSTRACT FROM AUTHOR]

Background: The evaluation of ammonia detoxification by pre- and probiotics by means of colonic lactose-[(15)N(2)]ureide ((15)N-LU) degradation is of great interest both scientifically and in terms of nutrition physiology.Objective: Pre- and probiotics were supplemented in healthy adults to evaluate the effect of the ammonia metabolism in the human colon by means of (15)N-LU.Methods: A total of 14 participants aged 20-28 years daily received a regular diet either without (no treatment) or with supplementation of 30 g fibre of potatoes (FPs), 30 g wrinkle pea starch (WPS, resistant starch content: 12 and 70%, respectively) and 375 g Lactobacillus acidophilus (LC1) yoghurt, over a 10-day period in a randomised order. After 1 week, 5.7 mg/kg body weight (15)N-LU was administered together with breakfast. A venous blood sample was taken after 6 h. Urine and faeces were collected over a period of 48 and 72 h, respectively. The (15)N abundances were measured by isotope ratio mass spectrometry.Results: The mean renal (15)N-excretion differed significantly between the supplementation of FP and no treatment (32.5 versus 46.3%, P=0.034), FP and LC1 (32.5 versus 51.6%, P=0.001), and WPS and LC1 (38.5 versus 51.6%, P=0.048). The mean faecal (15)N-excretion amounted to 42.7% (no treatment), 59.7% (FP), 41.8% (WPS) and 44.0% (LC1). In comparison with no treatment, the urinary (15)NH(3)-enrichment was significantly decreased at 16 h after FP supplementation.Conclusion: The prebiotic intake of FP and WPS lowered the colonic generation and the renal excretion of toxic (15)NH(3), respectively, when using (15)N-LU as a xenobiotic marker. [ABSTRACT FROM AUTHOR]