[Show abstract][Hide abstract] ABSTRACT: Elderly patients are at increased risk for peptic ulcer and cancer. Predictive factors of relevant endoscopic findings at
upper endoscopy in the elderly are unknown. This was a post hoc analysis of a nationwide, endoscopic study. A total of 3,147
elderly patients were selected. Demographic, clinical, and endoscopic data were systematically collected. Relevant findings
and new diagnoses of peptic ulcer and malignancy were computed. Both univariate and multivariate analyses were performed.
A total of 1,559 (49.5%), 213 (6.8%), 93 (3%) relevant findings, peptic ulcers, and malignancies were detected. Peptic ulcers
and malignancies were more frequent in >85-year-old patients (OR 3.1, 95% CI=2.0–4.7, p=0.001). The presence of dysphagia (OR=5.15), weight loss (OR=4.77), persistent vomiting (OR=3.68), anaemia (OR=1.83),
and male gender (OR=1.9) were significantly associated with a malignancy, whilst overt bleeding (OR=6.66), NSAIDs use
(OR=2.23), and epigastric pain (OR=1.90) were associated with the presence of peptic ulcer. Peptic ulcer or malignancies
were detected in 10% of elderly patients, supporting the use of endoscopy in this age group. Very elderly patients appear
to be at higher risk of such lesions.
KeywordsElderly patients–Upper endoscopy–Peptic ulcer–Malignancy–Predictive factors
Internal and Emergency Medicine 05/2011; 8(2):1-6. DOI:10.1007/s11739-011-0598-3 · 2.62 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Risk stratification systems that accurately identify patients with a high risk for bleeding through the use of clinical predictors of mortality before endoscopic examination are needed. Computerized (artificial) neural networks (ANNs) are adaptive tools that may improve prognostication.
To assess the capability of an ANN to predict mortality in patients with nonvariceal upper GI bleeding and compare the predictive performance of the ANN with that of the Rockall score.
Prospective, multicenter study.
Academic and community hospitals.
This study involved 2380 patients with nonvariceal upper GI bleeding.
Upper GI endoscopy.
The primary outcome variable was 30-day mortality, defined as any death occurring within 30 days of the index bleeding episode. Other outcome variables were recurrent bleeding and need for surgery.
We performed analysis of certified outcomes of 2380 patients with nonvariceal upper GI bleeding. The Rockall score was compared with a supervised ANN (TWIST system, Semeion), adopting the same result validation protocol with random allocation of the sample in training and testing subsets and subsequent crossover. Overall, death occurred in 112 cases (4.70%). Of 68 pre-endoscopic input variables, 17 were selected and used by the ANN versus 16 included in the Rockall score. The sensitivity of the ANN-based model was 83.8% (76.7-90.8) versus 71.4% (62.8-80.0) for the Rockall score. Specificity was 97.5 (96.8-98.2) and 52.0 (49.8 4.2), respectively. Accuracy was 96.8% (96.0-97.5) versus 52.9% (50.8-55.0) (P<.001). The predictive performance of the ANN-based model for prediction of mortality was significantly superior to that of the complete Rockall score (area under the curve 0.95 [0.92-0.98] vs 0.67 [0.65-0.69]; P<.001).
External validation on a subsequent independent population is needed, patients with variceal bleeding and obscure GI hemorrhage are excluded.
In patients with nonvariceal upper GI bleeding, ANNs are significantly superior to the Rockall score in predicting the risk of death.
[Show abstract][Hide abstract] ABSTRACT: a b s t r a c t Background: Inappropriateness of upper endoscopy (EGD) indication causes decreased diagnostic yield. Our aim of was to identify predictors of appropriateness rate for EGD among endoscopic centres. Methods: A post-hoc analysis of two multicentre cross-sectional studies, including 6270 and 8252 patients consecutively referred to EGD in 44 (group A) and 55 (group B) endoscopic Italian centres in 2003 and 2007, respectively, was performed. A multiple forward stepwise regression was applied to group A, and independently validated in group B. A <70% threshold was adopted to define inadequate appropriateness rate clustered by centre. Results: discrete variability of clustered appropriateness rates among the 44 group A centres was observed (median: 77%; range: 41–97%), and a <70% appropriateness rate was detected in 11 (25%). Independent predictors of centre appropriateness rate were: percentage of patients referred by general practitioners (GP), rate of urgent examinations, prevalence of relevant diseases, and academic status. For group B, sensitivity, specificity and area under receiver operating characteristic curve of the model in detecting centres with a <70% appropriateness rate were 54%, 93% and 0.72, respectively. Conclusions: A simple predictive rule, based on rate of patients referred by GPs, rate of urgent exam-inations, prevalence of relevant diseases and academic status, identified a small subset of centres characterised by a high rate of inappropriateness. These centres may be presumed to obtain the largest benefit from targeted educational programs.
[Show abstract][Hide abstract] ABSTRACT: Inappropriateness of upper endoscopy (EGD) indication causes decreased diagnostic yield. Our aim of was to identify predictors of appropriateness rate for EGD among endoscopic centres.
A post-hoc analysis of two multicentre cross-sectional studies, including 6270 and 8252 patients consecutively referred to EGD in 44 (group A) and 55 (group B) endoscopic Italian centres in 2003 and 2007, respectively, was performed. A multiple forward stepwise regression was applied to group A, and independently validated in group B. A <70% threshold was adopted to define inadequate appropriateness rate clustered by centre.
discrete variability of clustered appropriateness rates among the 44 group A centres was observed (median: 77%; range: 41-97%), and a <70% appropriateness rate was detected in 11 (25%). Independent predictors of centre appropriateness rate were: percentage of patients referred by general practitioners (GP), rate of urgent examinations, prevalence of relevant diseases, and academic status. For group B, sensitivity, specificity and area under receiver operating characteristic curve of the model in detecting centres with a <70% appropriateness rate were 54%, 93% and 0.72, respectively.
A simple predictive rule, based on rate of patients referred by GPs, rate of urgent examinations, prevalence of relevant diseases and academic status, identified a small subset of centres characterised by a high rate of inappropriateness. These centres may be presumed to obtain the largest benefit from targeted educational programs.
[Show abstract][Hide abstract] ABSTRACT: Selecting patients appropriately for upper endoscopy (EGD) is crucial for efficient use of endoscopy. The objective of this study was to compare different clinical strategies and statistical methods to select patients for EGD, namely appropriateness guidelines, age and/or alarm features, and multivariate and artificial neural network (ANN) models.
A nationwide, multicenter, prospective study was undertaken in which consecutive patients referred for EGD during a 1-month period were enrolled. Before EGD, the endoscopist assessed referral appropriateness according to the American Society for Gastrointestinal Endoscopy (ASGE) guidelines, also collecting clinical and demographic variables. Outcomes of the study were detection of relevant findings and new diagnosis of malignancy at EGD. The accuracy of the following clinical strategies and predictive rules was compared: (i) ASGE appropriateness guidelines (indicated vs. not indicated), (ii) simplified rule (>or=45 years or alarm features vs. <45 years without alarm features), (iii) logistic regression model, and (iv) ANN models.
A total of 8,252 patients were enrolled in 57 centers. Overall, 3,803 (46%) relevant findings and 132 (1.6%) new malignancies were detected. Sensitivity, specificity, and area under the receiver-operating characteristic curve (AUC) of the simplified rule were similar to that of the ASGE guidelines for both relevant findings (82%/26%/0.55 vs. 88%/27%/0.52) and cancer (97%/22%/0.58 vs. 98%/20%/0.58). Both logistic regression and ANN models seemed to be substantially more accurate in predicting new cases of malignancy, with an AUC of 0.82 and 0.87, respectively.
A simple predictive rule based on age and alarm features is similarly effective to the more complex ASGE guidelines in selecting patients for EGD. Regression and ANN models may be useful in identifying a relatively small subgroup of patients at higher risk of cancer.
The American Journal of Gastroenterology 12/2009; 105(6):1327-37. DOI:10.1038/ajg.2009.675 · 10.76 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: To investigate the role of artificial neural networks in predicting the presence of thyroid disease in atrophic body gastritis patients.
A dataset of 29 input variables of 253 atrophic body gastritis patients was applied to artificial neural networks (ANNs) using a data optimisation procedure (standard ANNs, T&T-IS protocol, TWIST protocol). The target variable was the presence of thyroid disease.
Standard ANNs obtained a mean accuracy of 64.4% with a sensitivity of 69% and a specificity of 59.8% in recognizing atrophic body gastritis patients with thyroid disease. The optimization procedures (T&T-IS and TWIST protocol) improved the performance of the recognition task yielding a mean accuracy, sensitivity and specificity of 74.7% and 75.8%, 78.8% and 81.8%, and 70.5% and 69.9%, respectively. The increase of sensitivity of the TWIST protocol was statistically significant compared to T&T-IS.
This study suggests that artificial neural networks may be taken into consideration as a potential clinical decision-support tool for identifying ABG patients at risk for harbouring an unknown thyroid disease and thus requiring diagnostic work-up of their thyroid status.
World Journal of Gastroenterology 01/2008; 14(4):563-8. DOI:10.3748/wjg.14.563 · 2.37 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: To assess the role of genetic polymorphisms in venous thrombosis events (VTE) using Artificial Neural Networks (ANNs), a model for solving non-linear problems frequently associated with complex biological systems, due to interactions between biological, genetic and environmental factors.
A database was generated from a case-control study of venous thrombosis, using 238 patients and 211 controls. The database of 64 variables included age, gender and a panel of 62 genetic variants. Three different ANNs were compared, with logistic regression for the accuracy of predicting cases and controls.
ANNs yielded a better performance than the logistic regression algorithm. Indeed, through ANNs models, the 62 variables related to genetic variants were first reduced to a set of 9, and then of 3 (MTHFR 677 C/T, FV arg506gln, ICAM1 gly214arg).
The findings of this study illustrate the power of ANN in evaluating multifactorial data, and show that the different sensitivities of the models of elaboration are related to the characteristics of the data. This may contribute to a better understanding of the role played by genetic polymorphisms in VTE, and help to define, if possible, a test panel of genetic variants to estimate an individual's probability of developing the disease.
Annals of Human Genetics 12/2005; 69(Pt 6):693-706. DOI:10.1111/j.1529-8817.2005.00206.x · 2.21 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: To investigate whether ANNs and LDA could recognize patients with ABG in a database, containing only clinical and biochemical variables, of a pool of patients with and without ABG, by selecting the most predictive variables and by reducing input data to the minimum.
Data was collected from 350 consecutive outpatients (263 with ABG, 87 with non-atrophic gastritis and/or celiac disease [controls]). Structured questionnaires with 22 items (anagraphic, anamnestic, clinical, and biochemical data) were filled out for each patient. All patients underwent gastroscopy with biopsies. ANNs and LDA were applied to recognize patients with ABG. Experiment 1: random selection on 37 variables, experiment 2: optimization process on 30 variables, experiment 3: input data reduction on 8 variables, experiment 4: use of only clinical input data on 5 variables, and experiment 5: use of only serological variables.
In experiment 1, overall accuracies of ANNs and LDA were 96.6% and 94.6%, respectively, for predicting patients with ABG. In experiment 2, ANNs and LDA reached an overall accuracy of 98.8% and 96.8%, respectively. In experiment 3, overall accuracy of ANNs was 98.4%. In experiment 4, overall accuracies of ANNs and LDA were, respectively, 91.3% and 88.6%. In experiment 5, overall accuracies of ANNs and LDA were, respectively, 97.7% and 94.5%.
This preliminary study suggests that advanced statistical methods, not only ANNs, but also LDA, may contribute to better address bioptic sampling during gastroscopy in a subset of patients in whom ABG may be suspected on the basis of aspecific gastrointestinal symptoms or non-digestive disorders.
World Journal of Gastroenterology 11/2005; 11(37):5867-73. · 2.37 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Previous studies have shown that in platelets of mild Alzheimer Disease (AD) patients there are alterations of specific APP forms, paralleled by alteration in expression level of both ADAM 10 and BACE when compared to control subjects. Due to the poor linear relation among each key-element of beta-amyloid cascade and the target diagnosis, the use of systems able to afford non linear tasks, like artificial neural networks (ANNs), should allow a better discriminating capacity in comparison with classical statistics.
To evaluate the accuracy of ANNs in AD diagnosis.
37 mild-AD patients and 25 control subjects were enrolled, and APP, ADM10 and BACE measures were performed. Fifteen different models of feed-forward and complex-recurrent ANNs (provided by Semeion Research Centre), based on different learning laws (back propagation, sine-net, bi-modal) were compared with the linear discriminant analysis (LDA).
The best ANN model correctly identified mild AD patients in the 94% of cases and the control subjects in the 92%. The corresponding diagnostic performance obtained with LDA was 90% and 73%.
This preliminary study suggests that the processing of biochemical tests related to beta-amyloid cascade with ANNs allows a very good discrimination of AD in early stages, higher than that obtainable with classical statistics methods.
Journal of Translational Medicine 08/2005; 3(1):30. DOI:10.1186/1479-5876-3-30 · 3.93 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: This paper aims to present a specific optimized experimental protocol (EP) for classification and/or prediction problems. The neuro-evolutionary algorithms on which it is based and its application with two selected real cases are described in detail. The first application addresses the problem of classifying the functional (FD) or organic (OD) forms of dyspepsia; the second relates to the problem of predicting the 6-month follow-up outcome of dyspeptic patients treated by helicobacter pylori (HP) eradication therapy.
The database built by the multicentre observational study, performed in Italy by the NUD-look Study Group, provided the material studied: a collection of data from 861 patients with previously uninvestigated dyspepsia, being referred for upper gastrointestinal endoscopy to 42 Italian Endoscopic Services. The proposed EP makes use of techniques based on advanced neuro-evolutionary systems (NESs) and is structured in phases and steps. The use of specific input selection (IS) and training and testing (T and T) techniques together with genetic doping (GenD) algorithm is described in detail, as well as the steps taken in the two benchmark and optimization protocol phases.
In terms of accuracy results, a value of 79.64% was achieved during optimization, with mean benchmark values of 64.90% for the linear discriminant analysis (LDA) and 68.15% for the multi layer perceptron (MLP), for the classification task. A value of 88.61% was achieved during optimization for the prediction task, with mean benchmark values of 49.32% for the LDA and 70.05% for the MLP.
The proposed EP has led to the construction of inductors that are viable and usable on medical data which is representative but highly not linear. In particular, for the classification problem, these new inductors may be effectively used on the basal examination data to support doctors in deciding whether to avoid endoscopic examinations; whereas, in the prediction problem, they may support doctors' decisions about the advisability of eradication therapy. In both cases the variables selected indicate the possibility of reducing the data collection effort and also of providing information that can be used for general investigations on symptom relevance.
Artificial Intelligence in Medicine 07/2005; 34(3):279-305. DOI:10.1016/j.artmed.2004.12.001 · 2.02 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Artificial neural networks (ANN) are modelling mechanisms that are highly flexible and adaptive to solve the non-linearity inherent in the relationship between symptoms and underlying pathology.
To assess the efficacy of ANN in achieving a diagnosis of gastro-oesophageal reflux disease (GORD) using oesophagoscopy or pH-metry as a diagnostic gold standard and discriminant analysis as a statistical comparator technique in a group of patients with typical GORD symptoms and with or without GORD objective findings (e.g. a positive oesophagoscopy or a pathological oesophageal pH-metry).
The sample of 159 cases (88 men, 71 women) presenting with typical symptoms of GORD, were subdivided on the basis of endoscopy and pH-metry results into two groups: GORD patients with or without oesophagitis, group 1 (N=103), and pH and endoscopy-negative patients in whom both examinations were negative, group 2 (N=56). A total of 101 different independent variables were collected: demographic information, medical history, generic health state and lifestyle, intensity and frequency of typical and atypical symptoms based on the Italian version of the Gastroesophageal Reflux Questionnaire (Mayo Clinic). The diagnosis was used as a dependent variable. Different ANN models were assessed.
Specific evolutionary algorithms selected 45 independent variables, concerning clinical and demographic features, as predictors of the diagnosis. The highest predictive performance was achieved by a 'back propagation' ANN, which was consistently 100% accurate in identifying the correct diagnosis compared with 78% obtained by traditional discriminant analysis.
On the basis of this preliminary work, the use of ANN seems to be a promising approach for predicting diagnosis without the need for invasive diagnostic methods in patients suffering from GORD symptoms.
European Journal of Gastroenterology & Hepatology 07/2005; 17(6):605-10. DOI:10.1097/00042737-200506000-00003 · 2.25 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Artificial neural networks (ANNs) are computer algorithms inspired by the highly interactive processing of the human brain. When exposed to complex data sets, ANNs can learn the mechanisms that correlate different variables and perform complex classification tasks.
A database, of 949 patients and 54 variables, was analysed to evaluate the capacity of ANNs to recognise patients with (VE+, n = 196) or without (VE-, n = 753) a history of vascular events on the basis of vascular risk factors (VRFs), carotid ultrasound variables (UVs) or both.
The performance of ANN was assessed by calculating the percentage of correct identifications of VE+ and VE- patients (sensitivity and specificity, respectively) and the prediction accuracy (weighted mean between sensitivity and specificity).
The results showed that ANNs can be trained to identify VE+ and VE- subjects more accurately than discriminant analyses. When VRFs and UVs were used as input variables, the prediction accuracies of the ANN providing the best results were 80.8% and 79.2%, respectively. The addition of gender, age, weight, height and body mass index to UVs increased accuracy of prediction to 83.0%. When the ANNs were allowed to choose the relevant input data automatically (I.S. system-Semeion), 37 variables were selected among 54, five of which were UVs. Using this set of variables as input data, the performance of the ANNs in the classification task reached a prediction accuracy of 85.0%. with the 92.0% correct classification of VE+ patients.
Artificial neural network technology is highly promising in the development of accurate diagnostic tools designed to recognize patients at high risk of cardiovascular diseases.
Annals of Medicine 02/2004; 36(8):630-40. DOI:10.1080/07853890410018880 · 3.89 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Data from several studies have pointed out the existence of a strong correlation between Alzheimer's disease (AD) neuropathology and cognitive state. However, because of their highly complex and nonlinear relationship, it has been difficult to develop a predictive model for individual patient classification through traditional statistical approaches. When exposed to complex data sets, artificial neural networks (ANNs) can recognize patterns, learn the relationship of different variables, and address classification tasks. To predict the results of postmortem brain examinations, we applied ANNs to the Nun Study data set, a longitudinal epidemiological study, which includes annual cognitive and functional evaluation. One hundred seventeen subjects from the study participated in this analysis. We determined how demographic data and the cognitive and functional variables of each subject during the last year of her life could predict the presence of brain pathology expressed as Braak stages, neurofibrillary tangles (NFTs) and neuritic plaques (NPs) count in the neocortex and hippocampus, and brain atrophy. The result of this analysis was then compared with traditional statistical models. ANNs proved to be better predictors than Linear Discriminant Analysis in all experimentations (+ approximately 10% in overall accuracy), especially when assembled in Artificial Organisms (+ approximately 20% in overall accuracy). Demographic, cognitive, and clinical variables were better predictors of tangles count in the neocortex and in the hippocampus when compared to NPs count. These findings strengthen the hypothesis that neurofibrillary pathology may represent the major anatomic substrate of the cognitive impairment found in AD.
[Show abstract][Hide abstract] ABSTRACT: The aim of this study was to evaluate the capability of improved artificial neural networks (ANN) and additional novel training methods in distinguishing between benign and malignant breast lesions in contrast-enhanced magnetic resonance-mammography (MRM). A total of 604 histologically proven cases of contrast-enhanced lesions of the female breast at MRI were analyzed. Morphological, dynamic and clinical parameters were collected and stored in a database. The data set was divided into several groups using random or experimental methods [Training & Testing (T&T) algorithm] to train and test different ANNs. An additional novel computer program for input variable selection was applied. Sensitivity and specificity were calculated and compared with a statistical method and an expert radiologist. After optimization of the distribution of cases among the training and testing sets by the T & T algorithm and the reduction of input variables by the Input Selection procedure a highly sophisticated ANN achieved a sensitivity of 93.6% and a specificity of 91.9% in predicting malignancy of lesions within an independent prediction sample set. The best statistical method reached a sensitivity of 90.5% and a specificity of 68.9%. An expert radiologist performed better than the statistical method but worse than the ANN (sensitivity 92.1%, specificity 85.6%). Features extracted out of dynamic contrast-enhanced MRM and additional clinical data can be successfully analyzed by advanced ANNs. The quality of the resulting network strongly depends on the training methods, which are improved by the use of novel training tools. The best results of an improved ANN outperform expert radiologists.
Medical Physics 09/2003; 30(9):2350-9. DOI:10.1118/1.1600871 · 2.64 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: To evaluate the accuracy of artificial neural networks compared with discriminant analysis in classifying positive and negative response to the cholinesterase inhibitor donepezil in a group of Alzheimer's disease (AD) patients.
Patients with mild to moderate AD consecutively admitted to a geriatric day hospital and treated with donepezil 5 mg/day.
Sixty-one older patients of both sexes with AD.
Accuracy in detecting subjects sensitive (responders) or not (nonresponders) to 3-month therapy with ANNs. The criterion standard for evaluation of efficacy was the scores of Alzheimer's Disease Assessment Scale-Cognitive portion and Clinician's Interview Based Impression of Change-plus scales.
ANNs were more effective in discriminating between responders and nonresponders than other advanced statistical methods, particularly linear discriminant analysis. The total accuracy in predicting the outcome was 92.59%.
ANNs appear to be a useful tool in detecting patient responsiveness to pharmacological treatment in AD.
Journal of the American Geriatrics Society 12/2002; 50(11):1857-60. DOI:10.1046/j.1532-5415.2002.50516.x · 4.57 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Artificial neural networks (ANNs) provide better solutions than linear discriminant analysis (LDA) to problems of classification and estimation involving a large number of non-homogeneous (categorical and metric) variables. In this study, we compared the ability of traditional LDA and a feed-forward back-propagation (FF-BP) ANN with self-momentum to predict pharmacological treatments received by intravenous drug users (IDUs) hospitalised for coexisting medical illness. When medical staff considered detoxification appropriate they usually suggested methadone (MET) and (or) benzodiazepines (BDZ). Given four different treatment options (MET, BDZ, MET+BDZ, no treatment) as dependent variables and 38 independent variables, the FF-BP ANN provided the best prediction of the consultant's decision (overall accuracy: 62.7%). It achieved the highest level of predictive accuracy for the BDZ option (90.5%), the lowest for no treatment (29.6), often misclassifying no treatment as BDZ. The LDA yielded a lower mean accuracy (50.3%). When the untreated group was excluded, ANN improved its absolute recognition rate by only 1.2% and the BDZ group remained the best predicted. In contrast, LDA improved its absolute recognition rate from 50.3 to 58.9%, maximum 65.7% for the BDZ group. In conclusion, the FF-BP ANN was more accurate than the statistical model (discriminant analysis) in predicting the pharmacological treatment of IDUs.
Artificial Intelligence in Medicine 02/2002; 24(1):37-49. DOI:10.1016/S0933-3657(01)00093-8 · 2.02 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Cellular Automata are usually considered the most efficient technology to understand the spatial logic of urban dynamics: they are inherently spatial, they are simple and computationally efficient and are able to represent a wide range of pattern and situations. Nevertheless the implementation of a CA requires the formulation of explicit spatial rules which represents the greatest limit of this approach. Whatever rich and complex the rules are, they don`t are able to capture satisfactorily the variety of the real processes. Recent developments in natural algorithms, and particularly in Artificial Neural Networks (ANN), allow to reverse the approach by learning the rules and the behaviours in urban land use dynamics directly from the Data Base, following a bottom-up process. The basic problem is to discover how and in to what extent the land use change of each cell i at time t+1 is determined by the neighbouring conditions (CA assumptions) or by other social, environmental, territorial features (i.e. political maps, planning rules) which where holding at the previous time t. Once the NN has learned the rules, it is able to predict the changes at time t+2 and following. In this paper we show and discuss the prediction capability of different architectures of supervised and unsupervised ANN. The Case study and Data Base concern the land use dynamics, between two temporal thresholds, in the South metropolitan area of Milan. The records have been randomly split in two sets which have been alternatively used in Training and in Testing phase in each ANN. The different ANNs performances have been evaluated with Statistical Functions. Finally, for the prediction, we have used the average of the prediction values of the 10 ANNs, and tested the results through the usual Statistical Functions.