Eye-tracking techniques are widely used to analyze user behavior. While eye-trackers collect valuable quantitative data, the results are often described in a qualitative manner due to the lack of a model that interprets the gaze trajectories generated by routine tasks, such as reading or comparing two products. The aim of this work is to propose a new quantitative way to analyze gaze trajectories (scanpaths) using machine learning. We conducted a within-subjects study (N = 30) testing six different tasks that simulated specific user behaviors in web sites (attentional, comparing two images, reading in different contexts, and free surfing). We evaluated the scanpath results with three different classifiers (long short-term memory recurrent neural network—LSTM, random forest, and multilayer perceptron neural network—MLP) to discriminate between tasks. The results revealed that it is possible to classify and distinguish between the 6 different web behaviors proposed in this study based on the user’s scanpath. The classifier that achieved the best results was the LSTM, with a 95.7% accuracy. To the best of our knowledge, this is the first study to provide insight about MLP and LSTM classifiers to discriminate between tasks. In the discussion, we propose practical implications of the study results.
6 December 2022 in Computers in Biology and Medicine
This paper describes an ensemble feature identification algorithm called SEQENS, and measures its capability to identify the relevant variables in a case-control study using a genetic expression microarray dataset. SEQENS uses Sequential Feature Search on multiple sample splitting to select variables showing stronger relation with the target, and a variable relevance ranking is finally produced. Although designed for feature identification, SEQENS could also serve as a basis for feature selection (classifier optimisation). Cliff, a ranking evaluation metric is also presented and used to assess the feature identification algorithms when a groundtruth of relevant variables is available. To test performance, three types of synthetic groundtruths emulating fictitious diseases are generated from ten randomly chosen variables following different target pattern distributions using the E-MTAB-3732 dataset. Several sample-to-dimensionality ratios ranging from 300 to 3,000 observations and 854 to 54,675 variables are explored. SEQENS is compared with other feature selection or identification state-of-the-art methods. On average, the proposed algorithm identifies better the relevant genes and exhibits a stronger stability. The algorithm is available to the community.
1 August 2019 in Computer Methods and Programs in Biomedicine
Unplanned hospital readmissions are a severe and recurrent problem that affects all health systems. Estimating the risk of being readmitted the following days after discharge is difficult since many heterogeneous factors can influence this. The extensive work concerning this problem proposes solutions mostly based on classification machine-learning models. Survival analysis methods could make a better match with the assessment of readmission risk and are yet to become well-established in this field. We compare different statistical and machine learning survival analysis models trained with right-censored all-cause hospital admission data with covariates available at the moment of discharge. The main focus is on tree-ensemble regression methods based on the assumption of proportional hazards. These models are more thoroughly evaluated at a 30-day time period after discharge, although the actual prediction could be set to any time up to 90 days. The mean performance obtained by each of the proposed survival models ranges from 0.707 to 0.716 C-Index and 0.709 to 0.72 ROC-AUC at a 30-day time period after discharge. The model with the lower performance on both metrics was Cox Proportional Hazards, while the model marking the upper end on both ranges is an XGBoost Regression model with a Cox objective function. Our findings indicate that survival models perform well addressing the hospital readmission problem, machine-learning models getting the edge over statistical methods. There seems to be an improvement over classification models when attempting to predict at a 30-day period since discharge, perhaps due to a better handling of cases nearing the 30-day boundary. Some preprocessing steps, such as limiting the observation period to 90 days after discharge, are also highlighted since they resulted in a performance boost.
Background and Objective: The main objective in this paper is to validate a machine-learning model trained to predict the 90-day risk of complications for patients with Acute Myeloid Leukemia using variables available at diagnosis. This is a first fundamental step towards the development of a tool that could help physicians in their therapeutic decisions. Methods: 266 patients and 36 variables form the training dataset collected by Hospital 12 de Octubre (Madrid, Spain). The external test cohort provided by Instituto de Investigación Sanitaria La Fe (Valencia, Spain) contains 162 observations. An XGBoost model was trained with one dataset and validated with the other. Additionally, the features were ranked by permutation importance and compared with the ELN 2022 risk classification by genetics at initial diagnosis. Results: The model was evaluated with the training cohort using leave-one-out cross-validation, reaching a ROC-AUC of 0.85. By setting the functioning point that maximises Youden’s index, 3 out of 4 patients with complications and 84 out of 100 in remission are correctly classified. The model was validated with external data collected in a different hospital, achieving 0.7 ROC-AUC. At the best functioning point, almost 6 out of 10 patients with complications and 8 out of 10 patients in remission are correctly classified. Ranking the variables by descending importance, the top four are, in order: age, white-blood-cells count, Gender, and TP53. The list exhibits good coherence with the ELN 2022 risk classification. Conclusions: The model achieves performances that suggest it could be used as a therapeutical decision support tool. Important variables are coherent with ELN 2022 risk classification. Further work is needed to understand the reasons for the drop in test performance. The 90-day model should be supplemented by others that predict the risk of complications at six months or one year.