Recurrent aphthous stomatitis (RAS; recurrent aphthous ulcers – RAU; canker sores) is a chronic inflammatory, ulcerative condition of the oral mucosa. Its prevalence in the general population ranges between 5% and 20%, depending on the method and group studied. The etiopathogenesis of the disease is considered to be multifactorial, but remains still not fully understood. In patients with RAS, an enhanced immunologic response occurs to some trigger factors that may include: mechanical injury, stress or bacterial and viral antigens. Higher prevalence of aphthae in relatives may also indicate the genetic background of the condition. The inheritance of some specific gene polymorphisms, especially those encoding proinflammatory cytokines, which play a role in the formation of aphthous ulcer, may predispose family members to RAS. The purpose of this paper was to present the main clinical features of recurrent aphthous stomatitis, epidemiologic data and crucial etiopathogenetic factors with a special emphasis on genetic background of the condition.
recurrent aphthous stomatitis; genetic background; etiology
Reviewing the literature, no studies were cited to report the prevalence of recurrent aphthous ulceration in Jordan. The aim of this study is to report the prevalence of recurrent aphthous ulceration in Jordanian subjects.
A total of 684 dental patients who attended Jordan University of Science and Technology interviewed and administered to fill questionnaires related to history, size, shape, and duration of recurrent aphthous ulceration. Other related questions were also asked.
About 78% of subjects experienced recurrent aphthous ulceration. Approximately 85% of ulcers were less than one cm in diameter, 66% were circular in shape, 92% were painful, 82% interfered with eating, and 55% located in lips and buccal mucosa. Only 50%of participants related ulcers to stress. Sixty eight percent reported no association with tiredness and 85% no association with types of food ingested. Of the 39% who had blood tests carried out, 7% had vitamin B12 and 4% hemoglobin deficiency.
Recurrent aphthous ulceration is a common problem in Jordanian adults.
Behçet's disease (BD) is a multisystemic chronic inflammatory disease. It is characterized by recurrent oral and genital ulcers, uveitis, skin lesions and other manifestations, including neurologic, vascular, joint, and gastrointestinal ulcers of variable severity. Recurrent aphthous ulcer (RAU) represents a very common, but poorly understood, mucosal disorder. If a patient of RAU without any other typical symptoms of BD has gastrointestinal symptoms, it is difficult to distinguish this RAU from true BD with gastrointestinal involvement. Because pathognomonic clinical features and tools are absent, the differential diagnosis of these two diseases relies on the characteristic clinical features and the judgement of an experienced physician. Sixty-five out of a total 960 RAU patients and forty-four of 556 BD patients with gastrointestinal symptoms between January 1996 and December 2003 participated in this study. All were evaluated with esophagogastroduodenoscopy and colonoscopy. Clinical, endoscopic and histopathologic findings were analyzed and ELISA tests were conducted to detect serum levels of ASCA and pANCA. No significant difference was found between the two groups. Differential diagnosis between RAU with gastrointestinal symptoms and BD with gastrointestinal involvement requires further prospective, large-scale study.
Behçet's Syndrome; Stomatitis, Aphthous; Saccharomyces cerevisiae; Antibodies, Antineutrophil Cytoplasmic; Gastrointestinal Tract
Amlexanox has been developed as a 5 percent topical oral paste for the treatment of patients with recurrent aphthous stomatitis (RAS) in most European countries. However, it is not yet available in China and has not been generally accepted in clinical treatment. The aim of this study was to explore the effectiveness of amlexanox oral adhesive pellicles in the treatment of minor recurrent aphthous ulcers, and compare the results with those of amlexanox oral adhesive tablets in order to analyse the difference between the two dosage forms of amlexanox.
We performed a randomized, blinded, placebo-controlled, parallel, multicenter clinical study. A total of 216 patients with minor recurrent aphthous ulcers (MiRAU) were recruited and randomized to amlexanox pellicles or placebo pellicles. Pellicles were consecutively applied four times per day, for five days. The size and pain level of ulcers were measured and recorded on treatment days 0, 4 and 6. Finally, the results were compared with those of our previous 104 cases treated with amlexanox tablets.
Amlexanox oral adhesive pellicles significantly reduced ulcer size (P= 0.017 for day 4, P=0.038 for day 6) and alleviated ulcer pain (P=0.021 for day 4, P=0.036 for day 6). No significant difference was observed in the treatment effectiveness between the pellicle and tablet form of amlexanox.
Amlexanox oral adhesive pellicles are as effective and safe as amlexanox oral adhesive tablets in the treatment of MiRAU for this Chinese cohort. However, pellicles seem to be more comfortable to use when compared with the dosage form of tablets. Therefore, in clinical practice, amlexanox oral adhesive pellicles may be a better choice for RAS patients.
Nederlands Trial Register NTR1727.
The recurrent aphthous ulcer (RAU) is a pathological change found in the oral mucosa, characterized by painful single or multiple ulcers. The etiologic aspect of RAU is not well understood; however it is known that due to lower CD4 cell counts patients had higher prevalence of these oral lesions, and immunosuppressed patients with HIV are predisposed. Patient FC is African descent, 26 years old, male, HIV + CD4 67 cells/mm3, with minor RAU in the upper and lower right side lip, measuring about 4 mm, and major RAU in tongue and the tonsillar pillar measuring 2 cm. The patient was treated with laser therapy with the objective to help reverse the damage and decrease the symptoms. After one week there was remission of the lesions. The laser showed to be an important alternative therapy that promoted analgesic, healing effects and improving the quality of life of patients.
Objective: The aim of this study is to report the prevalence and risk factors of recurrent aphthous ulceration (RAU) in patients attending Piramird dental speciality for seeking dental treatment.
Study design: A cross-sectional survey was carried out among patients (n=1100) who were visiting the department of oral medicine at Piramird dental speciality center in Sulaimani from December 2011-February 2012. The age range of the patients were between 10-79 years, with mean age of (34.27±14.14). 446 (44.6%) of participants were males and 554 (55.4%) were females, with male/female ratios of 0.80:1. All individuals had to answer specific questions including personal data (age, sex), level of education, occupation and smoking habit; etc. Additional questions were related to the risk factors that might be related to the condition. Chi Square test was used to analyze the data.
Result: The life time prevalence of RAU experience was 28.2% (n=282). It was highly significantly more common among females (31.76%) (p<0.004). The most commonly affected age group was 20-29 years (36.28%). The highest prevalence of RAU experience was seen among mere students (36.8%); Among non smokers there were highly significantly more patients with RAU experience (30%) than in heavy smoker patients (12.22%), (p=0.000). 34.4% of patients had family history of RAU. Lips and buccal mucosae were the commonest sites of ulcerations (73.10%), and the major risk factor was stress (43.3%).
Conclusion: This study has provided information about the epidemiologic aspects of recurrent aphthous ulceration, Based on the finding of this study, RAU is a common, recurrent painful oral ulceration. This study point to the importance of a thorough history taking to identify the patient’s main risk factors to get preventive measures, therefore treatment will be tailored for each patient accordingly. And the author concluded that stress was the major risk factor, thus, stress-management interventions suggested to be beneficial in reducing RAU recurrence episodes.
Key words:Recurrent aphthous ulceration, prevalence, stress.
Background and aims
Recurrent aphthous stomatitis is a condition comprised of oral painful ulcers appearing at inter-vals in different intraoral sites, triggered by a variety of causative agents in certain subgroups of patients. Since there are no studies on the subject in Northwest Iran, the aims of the present study were to evaluate the prevalence of aphthous ulcer and to assess the association of some influencing factors on minor aphtha.
Materials and methods
Of all patients examined during a two-year period, 33 patients were diagnosed with aphthous lesions. A questionnaire was used to collect the data including age, gender, familial history, smoking habit, and food allergy of the patients. Chi-square test was used to assess the association of variables.
The prevalence of aphthous lesions was found to be 0.3%, and was significantly higher in females compared with males (23 females and 10 males, respectively; P = 0.024). Familial involvement of aphthous ulcer was reported in 42.4% of the patients (P = 0.411). The aphthous ulcer was seen less frequently in smokers compared with non-smokers (P = 0.024).
A relatively low prevalence of minor aphtha was found in the studied population. Higher prevalence in females and non-smokers were observed.
Age; minor aphtha; sex; smoking
The prevalence of recurrent herpes labialis (RHL) and recurrent aphthous ulcers (RAU) in young adults - - 635 armed-forces recruits and 9897 health-profession students - - in 48 institutions in 21 countries was determined by a questionnaire survey. Two or more occurrences (lifetime prevalence) of RHL were reported by 33.2% of men and 28.0% of women; the corresponding figures for RAU were 38.7% and 49.7%. North American respondents, mainly from Canada, had a significantly higher prevalence of both lesions. There were some differences in relation to profession. Approximately 15% of all the people surveyed had had herpes labialis and 25% had had aphthous ulcers at least once during the previous year. Persons with a history of recurrence of one lesion were more likely to have a history of recurrence of the other.
Accurate evaluation of glomerular filtration rates (GFRs) is of critical importance in clinical practice. A previous study showed that models based on artificial neural networks (ANNs) could achieve a better performance than traditional equations. However, large-sample cross-sectional surveys have not resolved questions about ANN performance.
A total of 1,180 patients that had chronic kidney disease (CKD) were enrolled in the development data set, the internal validation data set and the external validation data set. Additional 222 patients that were admitted to two independent institutions were externally validated. Several ANNs were constructed and finally a Back Propagation network optimized by a genetic algorithm (GABP network) was chosen as a superior model, which included six input variables; i.e., serum creatinine, serum urea nitrogen, age, height, weight and gender, and estimated GFR as the one output variable. Performance was then compared with the Cockcroft-Gault equation, the MDRD equations and the CKD-EPI equation.
In the external validation data set, Bland-Altman analysis demonstrated that the precision of the six-variable GABP network was the highest among all of the estimation models; i.e., 46.7 ml/min/1.73 m2 vs. a range from 71.3 to 101.7 ml/min/1.73 m2, allowing improvement in accuracy (15% accuracy, 49.0%; 30% accuracy, 75.1%; 50% accuracy, 90.5% [P<0.001 for all]) and CKD stage classification (misclassification rate of CKD stage, 32.4% vs. a range from 47.3% to 53.3% [P<0.001 for all]). Furthermore, in the additional external validation data set, precision and accuracy were improved by the six-variable GABP network.
A new ANN model (the six-variable GABP network) for CKD patients was developed that could provide a simple, more accurate and reliable means for the estimation of GFR and stage of CKD than traditional equations. Further validations are needed to assess the ability of the ANN model in diverse populations.
of neural network architecture prior to data analysis is crucial
for successful data mining. This can be challenging when the underlying
model of the data is unknown. The goal of this study was to determine
whether optimizing neural network architecture using genetic programming
as a machine learning strategy would improve the ability of neural networks
to model and detect nonlinear interactions among genes in studies
of common human diseases.
data, we show that a genetic programming optimized neural network approach
is able to model gene-gene interactions as well as a traditional
back propagation neural network. Furthermore, the genetic programming
optimized neural network is better than the traditional back propagation
neural network approach in terms of predictive ability and power
to detect gene-gene interactions when non-functional polymorphisms
This study suggests
that a machine learning strategy for optimizing neural network architecture
may be preferable to traditional trial-and-error approaches for
the identification and characterization of gene-gene interactions
in common, complex human diseases.
This study was designed to identify the cells responsible for the spontaneous cell mediated cytotoxic effect (SCMC) exerted by peripheral blood leucocytes from patients with recurrent aphthous ulceration, towards cultured oral epithelial cells. Peripheral blood leucocytes from recurrent aphthous ulceration patients exerted a significantly greater (p less than 0.01) degree of cytotoxicity towards the oral epithelial target cells than did peripheral blood leucocytes from healthy control subjects, or from patients with non-specific ulceration. Depletion of CD-5 positive cells (T-lymphocytes) resulted in a significant decrease in the SCMC in aphthous patients. Depletion of CD-16 positive cells (NK-cells) produced no significant change in cytotoxicity. T-lymphocytes, therefore, appear to be intimately involved in the in vitro SCMC effect in recurrent aphthous ulceration.
Cholesteryl esters have antimicrobial activity and likely contribute to the innate immunity system. Improved separation techniques are needed to characterize these compounds. In this study, optimization of the reversed-phase high-performance liquid chromatography separation of six analyte standards (four cholesteryl esters plus cholesterol and tri-palmitin) was accomplished by modeling with an artificial neural network–genetic algorithm (ANN-GA) approach. A fractional factorial design was employed to examine the significance of four experimental factors: organic component in the mobile phase (ethanol and methanol), column temperature, and flow rate. Three separation parameters were then merged into geometric means using Derringer’s desirability function and used as input sources for model training and testing. The use of genetic operators proved valuable for the determination of an effective neural network structure. Implementation of the optimized method resulted in complete separation of all six analytes, including the resolution of two previously co-eluting peaks. Model validation was performed with experimental responses in good agreement with model-predicted responses. Improved separation was also realized in a complex biological fluid, human milk. Thus, the first known use of ANN-GA modeling for improving the chromatographic separation of cholesteryl esters in biological fluids is presented and will likely prove valuable for future investigators involved in studying complex biological samples.
FigureANN-derived response surface plot for two interacting factors and overall response
Electronic supplementary material
The online version of this article (doi:10.1007/s00216-010-3778-5) contains supplementary material, which is available to authorized users.
Lipids; Cholesteryl linoleate; Innate immunity; Biological fluids; Artificial neural networks; Genetic algorithms
Recurrent Aphthous Ulcer (RAU) is an inflammatory disease characterized by recurrent, painful oral ulcers. It is of multifactorial etiology. Salivary immunoglobulins have important role in the protection of mucosal surfaces.
The aim of this study was to determine salivary immunoglobulin A1 (IgA1) and IgA2 in acute and remission phases of the disease.
Materials and Methods:
Thirty clinically confirmed cases of RAU and 30 age-and sex-matched controls were included in the study. After detailed case history and thorough clinical examination, 2 mL of saliva was collected in both acute and remission phases of the disease. The obtained saliva samples were subjected to quantification of IgA1 and IgA2 levels using RID kit.
The mean IgA2 level was significantly higher (P<.001) in both acute and remission phase of the study group. The mean IgA1 level also showed a significant increase in the acute phase compared to remission as well as controls (P<.05). Females exhibited a higher level in acute phase for IgA1 and in both phases for IgA2 (P<.05).
The results associated with clinical observations suggest that acute phase is characterized with increase in IgA2 that might reflect increased immune response as a possible result of the microbial stimulation seen in the acute phase in comparison to the remission period. IgA plays an important role in the pathogenesis of RAU and it can be used as a parameter to assess the mucosal immune status
Radial immunodiffusion; recurrent aphthous stomatitis; recurrent aphthous ulcer; salivary IgA subclasses; secretory IgA
Behçet's disease is a multisystem inflammatory disorder characterized by recurrent oral aphthous ulcers, genital ulcers, uveitis, and skin lesions. The cause of Behçet's disease remains unknown, but epidemiologic findings suggest that an autoimmune process is triggered by an environmental agent in a genetically predisposed individual. An infectious agent could operate through molecular mimicry, and subsequently the disease could be perpetuated by an abnormal immune response to an autoantigen in the absence of ongoing infection. Potentia bacterial are Saccharomyces cerevisiae, mycobacteria, Borrelia burgdorferi, Helicobacter pylori, Escherichia coli, Staphylococcus aureus, and Mycoplasma fermentans, but the most commonly investigated microorganism is Streptococcus sanguinis. The relationship between streptococcal infections and Behçet's disease is suggested by clinical observations that an unhygienic oral condition is frequently noted in the oral cavity of Behçet's disease patients. Several viral agents, including herpes simplex virus-1, hepatitis C virus, parvovirus B19, cytomegalovirus, Epstein-Barr virus and varicella zoster virus, may also have some role.
Jejunal biopsies in 33 patients with troublesome recurrent aphthous ulceration seen over one year showed eight with flat mucosa compatible with coeliac disease. All remitted completely on a gluten-free diet, both clinically and haematologically, and the aphthous ulceration did not recur. Gluten sensitivity is aetiologically important in patients with recurrent aphthous ulceration and flat mucosa, and patients with recurrent ulceration should undergo jejunal biopsy.
Objective: Patients with an oral ulcer may present initially to a general physician or a dental practitioner. Majority of the ulcers are benign and resolve spontaneously but small proportions are malignant. The aim of the present study was to determine the prevalence of recurrent aphthous ulcerations in the Indian population.
Material and Methods: 3244 patients attending the Department of Oral Medicine and Radiology during the period from November, 2010 to December, 2012 with various complaints were examined. Of the patients examined 1669 were females and 1575 were males.
Results: 705 patients presented with recurrent aphthous ulceration (21.7%). Females (56.3%) were more commonly affected than males (43.7%). Patients in the third and fourth decade were most commonly affected. Stress was the most common factor associated with recurrent aphthous stomatitis (386 patients). 54.5% patients did not take any medications and 72.9% patients opined that the condition needed no dental consultation.
Conclusion: The results of the present study indicate that recurrent aphthous ulceration is a common mucosal disorder in the Indian population. The early and proper diagnosis of the ulcers will help the dental practitioner in providing information to the patient regarding awareness and management of the condition.
Key words:Recurrent aphthous ulcers, prevalence, Indian population.
The aim of the present study was to analyze the influence of smoking on the salivary immunoglobulin response in smokers and to evaluate the salivary immunoglobulin A in patients with recurrent aphthous ulcers.
Materials and Methods:
The study included total of 80 subjects, of whom 40 were having history of chronic smoking habit, 20 were clinically diagnosed cases of recurrent aphthous ulcer and 20 were in the control group. Sample of unstimulated saliva was collected, centrifuged and analyzed for the level of salivary immunoglobulin A with turbidimetric immunoassay. For all the tests, a P- value of < 0.05 was considered for statistical significance.
The mean salivary immunoglobulin A level in control group was 0.20 Grams/litre and in smokers the mean salivary immunoglobulin A level was 0.13 Grams / Litre. In patients with recurrent aphthous ulcers mean salivary immunoglobulin A level was 0.31 Grams / Litre. The mean salivary immunoglobulin A levels showed a decreasing trend from controls to smokers. These results were highly significant for values between control groups to smokers.
The mean salivary immunoglobulin A levels demonstrated a progressive decrease from controls to smokers. This investigative procedure although non-specific, can be used as a diagnostic marker in smokers and patients with recurrent aphthous ulcers.
Controls; recurrent aphthous ulcers; salivary immunoglobulin A; smokers
This paper presents a neural network predictive control strategy to optimize power distribution for a fuel cell/ultracapacitor hybrid power system of a robot. We model the nonlinear power system by employing time variant auto-regressive moving average with exogenous (ARMAX), and using recurrent neural network to represent the complicated coefficients of the ARMAX model. Because the dynamic of the system is viewed as operating- state- dependent time varying local linear behavior in this frame, a linear constrained model predictive control algorithm is developed to optimize the power splitting between the fuel cell and ultracapacitor. The proposed algorithm significantly simplifies implementation of the controller and can handle multiple constraints, such as limiting substantial fluctuation of fuel cell current. Experiment and simulation results demonstrate that the control strategy can optimally split power between the fuel cell and ultracapacitor, limit the change rate of the fuel cell current, and so as to extend the lifetime of the fuel cell.
Dissolution of protein macromolecules from poly(lactic-co-glycolic acid) (PLGA) particles is a complex process and still not fully understood. As such, there are difficulties in obtaining a predictive model that could be of fundamental significance in design, development, and optimization for medical applications and toxicity evaluation of PLGA-based multiparticulate dosage form. In the present study, two models with comparable goodness of fit were proposed for the prediction of the macromolecule dissolution profile from PLGA micro- and nanoparticles. In both cases, heuristic techniques, such as artificial neural networks (ANNs), feature selection, and genetic programming were employed. Feature selection provided by fscaret package and sensitivity analysis performed by ANNs reduced the original input vector from a total of 300 input variables to 21, 17, 16, and eleven; to achieve a better insight into generalization error, two cut-off points for every method was proposed. The best ANNs model results were obtained by monotone multi-layer perceptron neural network (MON-MLP) networks with a root-mean-square error (RMSE) of 15.4, and the input vector consisted of eleven inputs. The complicated classical equation derived from a database consisting of 17 inputs was able to yield a better generalization error (RMSE) of 14.3. The equation was characterized by four parameters, thus feasible (applicable) to standard nonlinear regression techniques. Heuristic modeling led to the ANN model describing macromolecules release profiles from PLGA microspheres with good predictive efficiency. Moreover genetic programming technique resulted in classical equation with comparable predictability to the ANN model.
poly(lactic-co-glycolic acid) (PLGA) microparticles; genetic programming; feature selection; artificial neural networks; molecular descriptors
In this study, artificial neural network (ANN) analysis of virotherapy in preclinical
breast cancer was investigated.
Materials and Methods:
In this research article, a multilayer feed-forward neural network
trained with an error back-propagation algorithm was incorporated in order to develop a
predictive model. The input parameters of the model were virus dose, week and tamoxifen
citrate, while tumor weight was included in the output parameter. Two different training
algorithms, namely quick propagation (QP) and Levenberg-Marquardt (LM), were used
to train ANN.
The results showed that the LM algorithm, with 3-9-1 arrangement is more efficient
compared to QP. Using LM algorithm, the coefficient of determination (R2) between
the actual and predicted values was determined as 0.897118 for all data.
It can be concluded that this ANN model may provide good ability to predict
the biometry information of tumor in preclinical breast cancer virotherapy. The results
showed that the LM algorithm employed by Neural Power software gave the better performance
compared with the QP and virus dose, and it is more important factor compared to
tamoxifen and time (week).
Neural Network Model; Breast Cancer; Virotherapy
Target threat assessment is a key issue in the collaborative attack. To improve the accuracy and usefulness of target threat assessment in the aerial combat, we propose a variant of wavelet neural networks, MWFWNN network, to solve threat assessment. How to select the appropriate wavelet function is difficult when constructing wavelet neural network. This paper proposes a wavelet mother function selection algorithm with minimum mean squared error and then constructs MWFWNN network using the above algorithm. Firstly, it needs to establish wavelet function library; secondly, wavelet neural network is constructed with each wavelet mother function in the library and wavelet function parameters and the network weights are updated according to the relevant modifying formula. The constructed wavelet neural network is detected with training set, and then optimal wavelet function with minimum mean squared error is chosen to build MWFWNN network. Experimental results show that the mean squared error is 1.23 × 10−3, which is better than WNN, BP, and PSO_SVM. Target threat assessment model based on the MWFWNN has a good predictive ability, so it can quickly and accurately complete target threat assessment.
Recurrent aphthous stomatitis (RAS) appears to be the most common type of oral ulcers. The lesion is usually self limited but its painful presentation results in some difficulties. Therefore, an efficient therapeutic strategy is required and currently existing therapies seem to be inadequate because of its unclear etiology. Here the therapeutic effect of triamcinolone acetonide ointment as a relatively expensive medication has been compared with phenytoin syrup on aphthous ulcers in patients with Behcet’s syndrome.
Thirty out of 60 our patients with Behcet’s syndrome were randomly treated by phenytoin syrup and the remaining were advised to use 0.1% triamcinolone acetonide ointment. After a week, they were visited again to determine the status of aphthous ulcers.
Positive response in the triamcinolone acetonide group and phenytoin group was 86.7% and 53.3%, respectively.
The effectiveness of triamcinolone acetonide ointment was more than phenytoin on aphthous ulcers in patients with Behcet’s syndrome.
Phenytoin; Triamcinolone Acetonide; Aphthous ulcer; Behcet’s syndrome
Echo-state networks (ESN) are part of a group of reservoir computing methods and are basically a form of recurrent artificial neural networks (ANN). These methods can perform classification tasks on time series data. The recurrent ANN of an echo-state network has an 'echo-state' characteristic. This 'echo-state' functions as a fading memory: samples that have been introduced into the network in a further past, are faded away. The echo-state approach for the training of recurrent neural networks was first described by Jaeger H. et al. In clinical medicine, until this moment, no original research articles have been published to examine the use of echo-state networks.
This study examines the possibility of using an echo-state network for prediction of dialysis in the ICU. Therefore, diuresis values and creatinine levels of the first three days after ICU admission were collected from 830 patients admitted to the intensive care unit (ICU) between May 31th 2003 and November 17th 2007. The outcome parameter was the performance by the echo-state network in predicting the need for dialysis between day 5 and day 10 of ICU admission. Patients with an ICU length of stay <10 days or patients that received dialysis in the first five days of ICU admission were excluded. Performance by the echo-state network was then compared by means of the area under the receiver operating characteristic curve (AUC) with results obtained by two other time series analysis methods by means of a support vector machine (SVM) and a naive Bayes algorithm (NB).
The AUC's in the three developed echo-state networks were 0.822, 0.818, and 0.817. These results were comparable to the results obtained by the SVM and the NB algorithm.
This proof of concept study is the first to evaluate the performance of echo-state networks in an ICU environment. This echo-state network predicted the need for dialysis in ICU patients. The AUC's of the echo-state networks were good and comparable to the performance of other classification algorithms. Moreover, the echo-state network was more easily configured than other time series modeling technologies.
Microarray technology can acquire information about thousands of genes simultaneously. We analyzed published breast cancer microarray databases to predict five-year recurrence and compared the performance of three data mining algorithms of artificial neural networks (ANN), decision trees (DT) and logistic regression (LR) and two composite models of DT-ANN and DT-LR. The collection of microarray datasets from the Gene Expression Omnibus, four breast cancer datasets were pooled for predicting five-year breast cancer relapse. After data compilation, 757 subjects, 5 clinical variables and 13,452 genetic variables were aggregated. The bootstrap method, Mann–Whitney U test and 20-fold cross-validation were performed to investigate candidate genes with 100 most-significant p-values. The predictive powers of DT, LR and ANN models were assessed using accuracy and the area under ROC curve. The associated genes were evaluated using Cox regression.
The DT models exhibited the lowest predictive power and the poorest extrapolation when applied to the test samples. The ANN models displayed the best predictive power and showed the best extrapolation. The 21 most-associated genes, as determined by integration of each model, were analyzed using Cox regression with a 3.53-fold (95% CI: 2.24-5.58) increased risk of breast cancer five-year recurrence…
The 21 selected genes can predict breast cancer recurrence. Among these genes, CCNB1, PLK1 and TOP2A are in the cell cycle G2/M DNA damage checkpoint pathway. Oncologists can offer the genetic information for patients when understanding the gene expression profiles on breast cancer recurrence.
Breast cancer; Microarray; Artificial neural network; Logistic regression; Decision tree
During the past decade, polymer nanocomposites attracted considerable investment in research and development worldwide. One of the key factors that affect the quality of polymer nanocomposite products in machining is surface roughness. To obtain high quality products and reduce machining costs it is very important to determine the optimal machining conditions so as to achieve enhanced machining performance. The objective of this paper is to develop a predictive model using a combined design of experiments and artificial intelligence approach for optimization of surface roughness in milling of polyamide-6 (PA-6) nanocomposites. A surface roughness predictive model was developed in terms of milling parameters (spindle speed and feed rate) and nanoclay (NC) content using artificial neural network (ANN). As the present study deals with relatively small number of data obtained from full factorial design, application of genetic algorithm (GA) for ANN training is thought to be an appropriate approach for the purpose of developing accurate and robust ANN model. In the optimization phase, a GA is considered in conjunction with the explicit nonlinear function derived from the ANN to determine the optimal milling parameters for minimization of surface roughness for each PA-6 nanocomposite.