Search

Background: Machine learning (ML) represents a powerful tool to capture relationships between molecular alterations and cancer types and to extract biological information. Here, we developed a plain ML model aimed at distinguishing cancer types based on genetic lesions, providing an additional tool to improve cancer diagnosis, particularly for tumors of unknown origin. Methods: TCGA data from 9,927 samples spanning 32 different cancer types were downloaded from cBioportal. A vector space model type data transformation technique was designed to build consistently homogeneous new datasets containing, as predictive features, calls for somatic point mutations and copy number variations at chromosome arm-level, thus allowing the use of the XGBoost classifier models. Considering the imbalance in the dataset, due to large difference in the number of cases for each tumor, two preprocessing strategies were considered: i) setting a percentage cut-off threshold to remove less represented cancer types, ii) dividing cancer types into different groups based on biological criteria and training a specific XGBoost model for each of them. The performance of all trained models was mainly assessed by the out-of-sample balanced accuracy (BACC) and the AUC scores. Results: The XGBoost classifier achieved the best performance (BACC 77%; AUC 97%) on a dataset containing the 10 most represented tumor types. Moreover, dividing the 18 most represented cancers into three different groups (endocrine-related carcinomas, other carcinomas and other cancers),such analysis models achieved 78%, 71% and 86% BACC, respectively, with AUC scores greater than 96%. In addition, the model capable of linking each group to a specific cancer type reached 81% BACC and 94% AUC. Overall, the diagnostic potential of our model was comparable/higher with respect to others already described in literature and based on similar molecular data and ML approaches. Conclusions: A boosted ML approach able to accurately discriminate different cancer types was developed. The methodology builds datasets simpler and more interpretable than the original data, while keeping enough information to accurately train standard ML models without resorting to sophisticated Deep Learning architectures. In combination with histopathological examinations, this approach could improve cancer diagnosis by using specific DNA alterations, processed by a replicable and easy-to-use automated technology. The study encourages new investigations which could further increase the classifier's performance, for example by considering more features and dividing tumors into their main molecular subtypes. [ABSTRACT FROM AUTHOR]

Forecasting volumes of incoming calls is the first step of the workforce planning process in call centers and represents a prominent issue from both research and industry perspectives. We investigate the application of Neural Networks to predict incoming calls 24 hours ahead. In particular, a Machine Learning deep architecture known as Echo State Network, is compared with a completely different rolling horizon shallow Neural Network strategy, in which the lack of recurrent connections is compensated by a careful input selection. The comparison, carried out on three different real world datasets, reveals better predictive performance for the shallow approach. The latter appears also more robust and less demanding, reducing the inference time by a factor of 2.5 to 4.5 compared to Echo State Networks. [ABSTRACT FROM AUTHOR]

In Europe, computation of displacement demand for seismic assessment of existing buildings is essentially based on a simplified formulation of the N2 method as prescribed by Eurocode 8 (EC8). However, a lack of accuracy of the N2 method in certain conditions has been pointed out by several studies. This paper addresses the assessment of effectiveness of the N2 method in seismic displacement demand determination in non-linear domain. The objective of this work is to investigate the accuracy of the N2 method through comparison with displacement demands computed using non-linear time-history analysis (NLTHA). Results show that the original N2 method may lead to overestimation or underestimation of displacement demand predictions. This may affect results of mechanical model-based assessment of seismic vulnerability at an urban scale. Hence, the second part of this paper addresses an improvement of the N2 method formula by empirical evaluation of NLTHA results based on EC8 ground-classes. This task is formulated as a mathematical programming problem in which coefficients are obtained by minimizing the overall discrepancy between NLTHA and modified formula results. Various settings of the mathematical programming problem have been solved using a global optimization metaheuristic. An extensive comparison between the original N2 method formulation and optimized formulae highlights benefits of the strategy. [ABSTRACT FROM AUTHOR]

The forecasts of electricity and heating demands are key inputs for the efficient design and operation of energy systems serving urban districts, buildings, and households. Their accuracy may have a considerable effect on the selection of the optimization approach and on the solution quality. In this work, we describe a supervised learning approach based on shallow Artificial Neural Networks to develop an accurate model for predicting the daily hourly energy consumption of an energy district 24 h ahead. Predictive models are generated for each one of the two considered energy types, namely electricity and heating. Single-layer feedforward neural networks are trained with the efficient and robust decomposition algorithm DEC proposed by Grippo et al. on a data set of historical data, including, among others, carefully selected information related to the hourly energy consumption of the energy district and the hourly weather data of the region where the district is located. Three different case studies are analyzed: a medium-size hospital located in the Emilia-Romagna Italian region, the whole Politecnico di Milano University campus, and a single building of a department belonging to the latter. The computational results indicate that the proposed method with enriched data inputs compares favorably with the benchmark forecasting and Machine Learning techniques, namely, ARIMA, Support Vector Regression and long short-term memory networks. [ABSTRACT FROM AUTHOR]

An accurate assessment of preoperative risk may improve use of hospital resources and reduce morbidity and mortality in high-risk surgical patients. This study aims at implementing an automated surgical risk calculator based on Artificial Neural Network technology to identify patients at risk for postoperative complications. We developed the new SUMPOT based on risk factors previously used in other scoring systems and tested it in a cohort of 560 surgical patients undergoing elective or emergency procedures and subsequently admitted to intensive care units, high-dependency units or standard wards. The whole dataset was divided into a training set, to train the predictive model, and a testing set, to assess generalization performance. The effectiveness of the Artificial Neural Network is a measure of the accuracy in detecting those patients who will develop postoperative complications. A total of 560 surgical patients entered the analysis. Among them, 77 patients (13.7%) suffered from one or more postoperative complications (PoCs), while 483 patients (86.3%) did not. The trained Artificial Neural Network returned an average classification accuracy of 90% in the testing set. Specifically, classification accuracy was 90.2% in the control group (46 patients out of 51 were correctly classified) and 88.9% in the PoC group (8 patients out of 9 were correctly classified). The Artificial Neural Network showed good performance in predicting presence/absence of postoperative complications, suggesting its potential value for perioperative management of surgical patients. Further clinical studies are required to confirm its applicability in routine clinical practice. [ABSTRACT FROM AUTHOR]