Applying machine learning methods to avalanche forecasting

Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Machine learning for spatial environmental data. Theory, applications and software

The book presents the state of the art in machine learning algorithms (artificial neural networks of different architectures, support vector machines, etc.) as applied to the classification and mapping of spatially distributed environmental data. Basic geostatistical algorithms are presented as well. New trends in machine learning and their application to spatial data are given, and real case studies based on environmental and pollution data are carried out. The book provides a CD-ROM with the Machine Learning Office software, including sample sets of data, that will allow both students and researchers to put the concepts rapidly to practice.

Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

Environmental data mining and modeling based on machine learning algorithms and geostatistics

The paper presents some contemporary approaches to spatial environmental data analysis. The main topics are concentrated on the decision-oriented problems of environmental spatial data mining and modeling: valorization and representativity of data with the help of exploratory data analysis, spatial predictions, probabilistic and risk mapping, development and application of conditional stochastic simulation models. The innovative part of the paper presents integrated/hybrid model-machine learning (ML) residuals sequential simulations-MLRSS. The models are based on multilayer perceptron and support vector regression ML algorithms used for modeling long-range spatial trends and sequential simulations of the residuals. NIL algorithms deliver non-linear solution for the spatial non-stationary problems, which are difficult for geostatistical approach. Geostatistical tools (variography) are used to characterize performance of ML algorithms, by analyzing quality and quantity of the spatially structured information extracted from data with ML algorithms. Sequential simulations provide efficient assessment of uncertainty and spatial variability. Case study from the Chernobyl fallouts illustrates the performance of the proposed model. It is shown that probability mapping, provided by the combination of ML data driven and geostatistical model based approaches, can be efficiently used in decision-making process. (C) 2003 Elsevier Ltd. All rights reserved.

Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Acute Eosinophilic and Neutrophilic Pneumonia following Transarterial Chemoembolization with Drug-Eluting Beads Loaded with Doxorubicin for Hepatocellular Carcinoma: A Case Report.

At an intermediate or advanced stage, i.e. stage B or C, based on the Barcelona Clinic Liver Cancer classification of hepatocellular carcinoma (HCC), transarterial chemoembolization (TACE) may be offered as a treatment of palliative intent. We report the case of a patient suffering from acute respiratory distress syndrome after TACE with drug-eluting beads loaded with doxorubicin for HCC. To our knowledge, this is the first case described where a bronchoalveolar lavage was performed, and where significant levels of alveolar eosinophilia and neutrophilia were evident, attributed to a pulmonary toxicity of doxorubicin following liver chemoembolization. © 2014 S. Karger AG, Basel.

Continuous Sunitinib treatment in patients with advanced hepatocellular carcinoma: a Swiss Group for Clinical Cancer Research (SAKK) and Swiss Association for the Study of the Liver (SASL) multicenter phase II trial (SAKK 77/06).

BACKGROUND: Sunitinib (SU) is a multitargeted tyrosine kinase inhibitor with antitumor and antiangiogenic activity. The objective of this trial was to demonstrate antitumor activity of continuous SU treatment in patients with hepatocellular carcinoma (HCC). PATIENTS AND METHODS: Key eligibility criteria included unresectable or metastatic HCC, no prior systemic anticancer treatment, measurable disease, and Child-Pugh class A or mild Child-Pugh class B liver dysfunction. Patients received 37.5 mg SU daily until progression or unacceptable toxicity. The primary endpoint was progression-free survival at 12 weeks (PFS12). RESULTS: Forty-five patients were enrolled. The median age was 63 years; 89% had Child-Pugh class A disease and 47% had distant metastases. PFS12 was rated successful in 15 patients (33%; 95% confidence interval, 20%-47%). Over the whole trial period, one complete response and a 40% rate of stable disease as the best response were achieved. The median PFS duration, disease stabilization duration, time to progression, and overall survival time were 1.5, 2.9, 1.5, and 9.3 months, respectively. Grade 3 and 4 adverse events were infrequent. None of the 33 deaths were considered drug related. CONCLUSION: Continuous SU treatment with 37.5 mg daily is feasible and has moderate activity in patients with advanced HCC and mild to moderately impaired liver dysfunction. Under this trial design (>13 PFS12 successes), the therapy is considered promising. This is the first trial describing the clinical effects of continuous dosing of SU in HCC patients on a schedule that is used in an ongoing, randomized, phase III trial in comparison with the current treatment standard, sorafenib (ClinicalTrials.gov identifier, NCT00699374).

Prospective randomized study of doxorubicin-eluting-bead embolization in the treatment of hepatocellular carcinoma: results of the PRECISION V study.

Transcatheter arterial chemoembolization (TACE) offers a survival benefit to patients with intermediate hepatocellular carcinoma (HCC). A widely accepted TACE regimen includes administration of doxorubicin-oil emulsion followed by gelatine sponge-conventional TACE. Recently, a drug-eluting bead (DC Bead) has been developed to enhance tumor drug delivery and reduce systemic availability. This randomized trial compares conventional TACE (cTACE) with TACE with DC Bead for the treatment of cirrhotic patients with HCC. Two hundred twelve patients with Child-Pugh A/B cirrhosis and large and/or multinodular, unresectable, N0, M0 HCCs were randomized to receive TACE with DC Bead loaded with doxorubicin or cTACE with doxorubicin. Randomization was stratified according to Child-Pugh status (A/B), performance status (ECOG 0/1), bilobar disease (yes/no), and prior curative treatment (yes/no). The primary endpoint was tumor response (EASL) at 6 months following independent, blinded review of MRI studies. The drug-eluting bead group showed higher rates of complete response, objective response, and disease control compared with the cTACE group (27% vs. 22%, 52% vs. 44%, and 63% vs. 52%, respectively). The hypothesis of superiority was not met (one-sided P = 0.11). However, patients with Child-Pugh B, ECOG 1, bilobar disease, and recurrent disease showed a significant increase in objective response (P = 0.038) compared to cTACE. DC Bead was associated with improved tolerability, with a significant reduction in serious liver toxicity (P < 0.001) and a significantly lower rate of doxorubicin-related side effects (P = 0.0001). TACE with DC Bead and doxorubicin is safe and effective in the treatment of HCC and offers a benefit to patients with more advanced disease.

Naturally acquired MAGE-A10- and SSX-2-specific CD8+ T cell responses in patients with hepatocellular carcinoma.

Immunotherapy is being proposed to treat patients with hepatocellular carcinoma (HCC). However, more detailed knowledge on tumor Ag expression and specific immune cells is required for the preparation of highly targeted vaccines. HCC express a variety of tumor-specific Ags, raising the question whether CTL specific for such Ags exist in HCC patients. Indeed, a recent study revealed CTLs specific for two cancer-testis (CT) Ags (MAGE-A1 and MAGE-A3) in tumor infiltrating lymphocytes of HCC patients. Here we assessed the presence of T cells specific for additional CT Ags: MAGE-A10, SSX-2, NY-ESO-1, and LAGE-1, which are naturally immunogenic as demonstrated in HLA-A2(+) melanoma patients. In two of six HLA-A2(+) HCC patients, we found that MAGE-A10- and/or SSX-2-specific CD8(+) T cells naturally responded to the disease, because they were enriched in tumor lesions but not in nontumoral liver. Isolated T cells specifically and strongly killed tumor cells in vitro, providing evidence that these CTL were selected in vivo for high avidity Ag recognition. Therefore, besides melanoma, HCC is the second solid human tumor with clear evidence for in vivo tumor recognition by T cells, providing the rational for specific immunotherapy, based on immunization with CT Ags such as MAGE-A10 and SSX-2.

Comparative genetic analyses point to HCP5 as susceptibility locus for HCV-associated hepatocellular carcinoma.

BACKGROUND & AIMS: Recently, genetic variations in MICA (lead single nucleotide polymorphism [SNP] rs2596542) were identified by a genome-wide association study (GWAS) to be associated with hepatitis C virus (HCV)-related hepatocellular carcinoma (HCC) in Japanese patients. In the present study, we sought to determine whether this SNP is predictive of HCC development in the Caucasian population as well. METHODS: An extended region around rs2596542 was genotyped in 1924 HCV-infected patients from the Swiss Hepatitis C Cohort Study (SCCS). Pair-wise correlation between key SNPs was calculated both in the Japanese and European populations (HapMap3: CEU and JPT). RESULTS: To our surprise, the minor allele A of rs2596542 in proximity of MICA appeared to have a protective impact on HCC development in Caucasians, which represents an inverse association as compared to the one observed in the Japanese population. Detailed fine-mapping analyses revealed a new SNP in HCP5 (rs2244546) upstream of MICA as strong predictor of HCV-related HCC in the SCCS (univariable p=0.027; multivariable p=0.0002, odds ratio=3.96, 95% confidence interval=1.90-8.27). This newly identified SNP had a similarly directed effect on HCC in both Caucasian and Japanese populations, suggesting that rs2244546 may better tag a putative true variant than the originally identified SNPs. CONCLUSIONS: Our data confirms the MICA/HCP5 region as susceptibility locus for HCV-related HCC and identifies rs2244546 in HCP5 as a novel tagging SNP. In addition, our data exemplify the need for conducting meta-analyses of cohorts of different ethnicities in order to fine map GWAS signals.

Genetic Analyses Reveal a Role for Vitamin D Insufficiency in HCV-Associated Hepatocellular Carcinoma Development.

BACKGROUND: Vitamin D insufficiency has been associated with the occurrence of various types of cancer, but causal relationships remain elusive. We therefore aimed to determine the relationship between genetic determinants of vitamin D serum levels and the risk of developing hepatitis C virus (HCV)-related hepatocellular carcinoma (HCC). METHODOLOGYPRINCIPAL FINDINGS: Associations between CYP2R1, GC, and DHCR7 genotypes that are determinants of reduced 25-hydroxyvitamin D (25[OH]D3) serum levels and the risk of HCV-related HCC development were investigated for 1279 chronic hepatitis C patients with HCC and 4325 without HCC, respectively. The well-known associations between CYP2R1 (rs1993116, rs10741657), GC (rs2282679), and DHCR7 (rs7944926, rs12785878) genotypes and 25(OH)D3 serum levels were also apparent in patients with chronic hepatitis C. The same genotypes of these single nucleotide polymorphisms (SNPs) that are associated with reduced 25(OH)D3 serum levels were found to be associated with HCV-related HCC (P = 0.07 [OR = 1.13, 95% CI = 0.99-1.28] for CYP2R1, P = 0.007 [OR = 1.56, 95% CI = 1.12-2.15] for GC, P = 0.003 [OR = 1.42, 95% CI = 1.13-1.78] for DHCR7; ORs for risk genotypes). In contrast, no association between these genetic variations and liver fibrosis progression rate (P>0.2 for each SNP) or outcome of standard therapy with pegylated interferon-α and ribavirin (P>0.2 for each SNP) was observed, suggesting a specific influence of the genetic determinants of 25(OH)D3 serum levels on hepatocarcinogenesis. CONCLUSIONSSIGNIFICANCE: Our data suggest a relatively weak but functionally relevant role for vitamin D in the prevention of HCV-related hepatocarcinogenesis.

Portal vein embolization with N-butyl cyanoacrylate before partial hepatectomy in patients with hepatocellular carcinoma and underlying cirrhosis or advanced fibrosis.

PURPOSE: To describe the safety, complications, and liver regeneration associated with the left liver after embolization of the right portal vein (PV) in patients with hepatocellular carcinoma (HCC) developed in the setting of advanced liver fibrosis and cirrhosis. MATERIALS AND METHODS: Forty patients (31 men, nine women; mean age, 62 years) with HCC underwent PV embolization over a 4-year period. Embolization was performed from a left PV percutaneous access with use of n-butyl cyanoacrylate (NBCA) mixed with iodized oil. Computed tomography (CT) volumetry was performed before and 1 month after PV embolization to measure the left lobe volume as well as the functional liver ratio defined by the ratio between the left lobe and the total liver volume minus tumoral volume. PV pressure and liver enzyme levels were compared before and 1 month after the procedure and complications were registered. Factors potentially affecting regeneration (age, sex, diabetes, chemoembolization, functional liver ratio before PV embolization, and Knodell histologic score) were evaluated by one-way and stepwise regression analysis. RESULTS: PV embolization could be achieved successfully in all cases. Two patients had partial PV thrombosis on the 1-month follow-up CT and two patients developed transient ascites after PV embolization. The left lobe volume increase was 41% +/- 32% after PV embolization and the functional liver ratio increased from 28% +/- 10% to 36% +/- 10% (P < .0001). Hypertrophy of the left lobe was greater in patients with a low functional liver ratio before PV embolization and those with an F3 fibrosis score. Other factors had no influence on left lobe regeneration. CONCLUSION: PV embolization with use of NBCA is feasible in patients with advanced fibrosis and cirrhosis. Hypertrophy of the left lobe of the liver after PV embolization has a statistically significant correlation with lower functional liver ratio and lower degrees of fibrosis.

A randomized phase II trial of a drug eluting bead in the treatment of hepatocellular carcinoma by transcatheter arterial chemoembolization

Background: Transcatheter arterial chemoembolization (TACE) has been shown to offer a survival benefit for patients with intermediate-stage hepatocellular carcinoma (HCC). A widely accepted TACE regimen includes the administration of a doxorubicin-in-oil emulsion followed by gelatine sponge particles. Recently, a drug-eluting bead (DEB) has been developed to enhance drug delivery to the tumor and reduce its systemic availability. Purpose of this randomized trial was to compare conventional TACE with DEB-TACE for the treatment of intermediate-stage HCC in patients with cirrhosis. Methods: Two hundred and twelve patients (185 males and 27 females; mean age, 67 years) with Child-Pugh A or B liver cirrhosis and large and/or multinodular, unresectable HCC were randomized to receive DEB-TACE (DC Bead; Biocompatibles, UK) uploaded with doxorubicin or conventional TACE with doxorubicin, lipiodol, and gelatin sponge particles. Randomization was stratified according to Child Pugh status (A or B), performance status (ECOG 0 or 1), bilobar disease (yes or no) and prior curative treatment (yes or no). Tumor response at 6 months was the primary study endpoint. An independent, blinded review of magnetic resonance imaging studies was conducted to assess tumor response according to amended RECIST criteria. Results: DEB-TACE with doxorubicin showed a higher rate of complete response, objective response and disease control compared with conventional TACE (27% vs 22%; 52% vs 44%; and 63% vs 52%, respectively; p>0.05). Patients with Child Pugh B, ECOG 1, bilobar disease and recurrence following curative treatment showed a significant increase in objective response (p=0.038) compared to the control. There was a marked reduction in serious liver toxicity in patients treated with DEB-TACE. The rate of doxorubicin related side effects was significantly lower (p=0.0001) in the DEB-TACE group compared with the conventional TACE group. Conclusions: DEB-TACE with doxorubicin is safe and effective in the treatment of intermediate-stage HCC and may offer benefit to patients with more advanced disease.