Eye-LRCN: A Long-Term Recurrent Convolutional Network for Eye Blink Completeness Detection.

Computer vision syndrome causes vision problems and discomfort mainly due to dry eye. Several studies show that dry eye in computer users is caused by a reduction in the blink rate and an increase in the prevalence of incomplete blinks. In this context, this article introduces Eye-LRCN, a new eye blink detection method that also evaluates the completeness of the blink. The method is based on a long-term recurrent convolutional network (LRCN), which combines a convolutional neural network (CNN) for feature extraction with a bidirectional recurrent neural network that performs sequence learning and classifies the blinks. A Siamese architecture is used during CNN training to overcome the high-class imbalance present in blink detection and the limited amount of data available to train blink detection models. The method was evaluated on three different tasks: blink detection, blink completeness detection, and eye state detection. We report superior performance to the state-of-the-art methods in blink detection and blink completeness detection, and remarkable results in eye state detection.

Analysis of clinical prognostic variables for Chronic Lymphocytic Leukemia decision-making problems.

INTRODUCTION: Chronic Lymphocytic Leukemia (CLL) is a disease with highly heterogeneous clinical course. A key goal is the prediction of patients with high risk of disease progression, which could benefit from an earlier or more intense treatment. In this work we introduce a simple methodology based on machine learning methods to help physicians in their decision making in different problems related to CLL. MATERIAL AND METHODS: Clinical data belongs to a retrospective study of a cohort of 265 Caucasians who were diagnosed with CLL between 1997 and 2007 in Hospital Cabueñes (Asturias, Spain). Different machine learning methods were applied to find the shortest list of most discriminatory prognostic variables to predict the need of Chemotherapy Treatment and the development of an Autoimmune Disease. RESULTS: Autoimmune disease occurrence was predicted with very high accuracy (>90%). Autoimmune disease development is currently an unpredictable severe complication of CLL. Chemotherapy Treatment has been predicted with a lower accuracy (80%). Risk analysis showed that the number of false positives and false negatives are well balanced. CONCLUSIONS: Our study highlights the importance of prognostic variables associated with the characteristics of platelets, reticulocytes and natural killers, which are the main targets of the autoimmune haemolytic anemia and immune thrombocytopenia for autoimmune disease development, and also, the relevance of some clinical variables related with the immune characteristics of CLL patients that are not taking into account by current prognostic markers for predicting the need of chemotherapy. Because of its simplicity, this methodology could be implemented in spreadsheets.

Disease liability prediction from large scale genotyping data using classifiers with a reject option.

Genome-wide association studies (GWA) try to identify the genetic polymorphisms associated with variation in phenotypes. However, the most significant genetic variants may have a small predictive power to forecast the future development of common diseases. We study the prediction of the risk of developing a disease given genome-wide genotypic data using classifiers with a reject option, which only make a prediction when they are sufficiently certain, but in doubtful situations may reject making a classification. To test the reliability of our proposal, we used the Wellcome Trust Case Control Consortium (WTCCC) data set, comprising 14,000 cases of seven common human diseases and 3,000 shared controls.

Explaining the genetic basis of complex quantitative traits through prediction models.

The functional characterization of genes involved in many complex traits (phenotypes) of plants, animals, or humans can be studied from a computational point of view using different tools. We propose prediction--from the machine learning point of view--to search for the genetic basis of these traits. However, trying to predict an exact value of a phenotype can be too difficult to obtain a confident model, but predicting an approximation, in the form of an interval of values, can be easier. We shall see that trustable and useful models can be obtained from this relaxed formulation. These predictors may be built as extensions of conventional classifiers or regressors. Although the prediction performance in both cases are similar, we show that, from the classification field, it is straightforward to obtain a principled and scalable method to select a reduced set of features in these genetic learning tasks. We conclude by comparing the results so achieved in a real-world data set of barley plants with those obtained with state-of-the-art methods used in the biological literature.

Predicting the probability of survival in intensive care unit patients from a small number of variables and training examples.

OBJECTIVE: Survival probability predictions in critically ill patients are mainly used to measure the efficacy of intensive care unit (ICU) treatment. The available models are functions induced from data on thousands of patients. Eventually, some of the variables used for these purposes are not part of the clinical routine, and may not be registered in some patients. In this paper, we propose a new method to build scoring functions able to make reliable predictions, though functions whose induction only requires records from a small set of patients described by a few variables. METHODS: We present a learning method based on the use of support vector machines (SVM), and a detailed study of its prediction performance, in different contexts, of groups of variables defined according to the source of information: monitoring devices, laboratory findings, and demographic and diagnostic features. RESULTS: We employed a data set collected in general ICUs at 10 units of hospitals in Spain, 6 of which include coronary patients, while the other 4 do not treat coronary diseases. The total number of patients considered in our study was 2501, 19.83% of whom did not survive. Using these data, we report a comparison between the SVM method proposed here with other approaches based on logistic regression (LR), including a second-level recalibration of release III of the acute physiology and chronic health evaluation (APACHE, a scoring system commonly used in ICUs) induced from the available data. The SVM method significantly outperforms them all from a statistical point of view. Comparison with the commercial version of APACHE III shows that the SVM scores are slightly better when working with data sets of more than 500 patients. CONCLUSIONS: From a practical point of view, the implications of the research reported here may be helpful to address the construction of cheap and reliable prediction systems in accordance with the peculiarities of ICUs and kinds of patients.