Forward Feature Selection Procedure Research Articles

Informative Power Evaluation of Clinical Parameters to Predict Initial Therapeutic Response in Patients with Advanced Pleural Mesothelioma: A Machine Learning Approach.

Malignant pleural mesothelioma (MPM) is a rare neoplasm whose early diagnosis is challenging and systemic treatments are generally administered as first line in the advanced disease stage. The initial clinical response may represent a useful parameter in terms of identifying patients with a better long-term outcome. In this report, the initial therapeutical response in 46 patients affected with advanced/unresectable pleural mesothelioma was investigated. The initial therapeutic response was assessed by CT scan and clinical examination after 2–3 treatment cycles. Our preliminary evaluation shows that the group of patients treated with regimens including antiangiogenetics and/or immunotherapy had a significantly better initial response as compared to patients only treated with standard chemotherapy, exhibiting a disease control rate (DCR) of 100% (95% IC, 79.40–100%) and 80.0% (95% IC, 61.40–92.30%), respectively. Furthermore, the therapeutic response was correlated with the disease stage, blood leukocytes and neutrophils, high albumin serum levels, and basal body mass index (BMI). Specifically, the patients with disease stage III showed a DCR of 95.7% (95% IC, 78.1–99.9%), whereas for disease stage IV the DCR decreased to 66.7% (95% IC, 34.9–9.1%). Moreover, a better initial response was observed in patients with a higher BMI, who reached a DCR of 96.10% (95% IC, 80.36–99.90%). Furthermore, in order to evaluate in the predictive power of the collected features a multivariate way, we report the preliminary results of a machine learning model for predicting the initial therapeutic response. We trained a state-of-the-art algorithm combined to a sequential forward feature selection procedure. The model reached a median AUC value, accuracy, sensitivity, and specificity of 77.0%, 75%, 74.8%, and 83.3%, respectively. The features with greater informational power were gender, histotype, BMI, smoking habits, packs/year, and disease stage. Our preliminary data support the possible favorable correlation between innovative treatments and therapeutic response in patients with unresectable/advanced pleural mesothelioma. The small sample size does not allow concrete conclusions to be drawn; nevertheless, this work is the basis of an ongoing study that will also involve radiomics in a larger dataset.

Machine learning for suicide risk prediction in children and adolescents with electronic health records

Accurate prediction of suicide risk among children and adolescents within an actionable time frame is an important but challenging task. Very few studies have comprehensively considered the clinical risk factors available to produce quantifiable risk scores for estimation of short- and long-term suicide risk for pediatric population. In this paper, we built machine learning models for predicting suicidal behavior among children and adolescents based on their longitudinal clinical records, and determining short- and long-term risk factors. This retrospective study used deidentified structured electronic health records (EHR) from the Connecticut Children’s Medical Center covering the period from 1 October 2011 to 30 September 2016. Clinical records of 41,721 young patients (10–18 years old) were included for analysis. Candidate predictors included demographics, diagnosis, laboratory tests, and medications. Different prediction windows ranging from 0 to 365 days were adopted. For each prediction window, candidate predictors were first screened by univariate statistical tests, and then a predictive model was built via a sequential forward feature selection procedure. We grouped the selected predictors and estimated their contributions to risk prediction at different prediction window lengths. The developed predictive models predicted suicidal behavior across all prediction windows with AUCs varying from 0.81 to 0.86. For all prediction windows, the models detected 53–62% of suicide-positive subjects with 90% specificity. The models performed better with shorter prediction windows and predictor importance varied across prediction windows, illustrating short- and long-term risks. Our findings demonstrated that routinely collected EHRs can be used to create accurate predictive models for suicide risk among children and adolescents.

Agricultural crop discrimination in a heterogeneous low-mountain range region based on multi-temporal and multi-sensor satellite data

Crop type information such as its location and spatial distribution is relevant for agricultural planning and decision making about food sustainability and security. This information can be obtained through the analysis of images obtained through optical satellite remote sensing. Activities such as accurate discrimination of crops require dense time-series of satellite data which can capture the diverse crop phenology. However, given the presence of clouds at important periods of crops’ development, the required time-series is impossible to obtain from just one optical satellite sensor. The Harmonized Landsat and Sentinel-2 (HLS) project by NASA provides fused data from both Operational Land Imager and Multispectral Instrument optical sensors of Landsat and Sentinel systems respectively. The present study used a multi-temporal HLS data and a target-oriented cross-validation (TOV) modelling approach with random forest algorithm to discriminate 13 crop types. 15 phenological metrics derived from time-series HLS data, together with 48 spectral and 2 topographic information were used as predictors in the model. A forward feature selection (FFS) procedure of the TOV was used to improve the classification model. 16 predictors comprising of spectral, phenological and topographic information were selected as useful for the crop discrimination. An independent accuracy assessment of the final model based on the selected predictors by the FFS procedure resulted in an overall accuracy of 76%. While most of the crop classes, achieved higher producer’s and user’s accuracies (>80%), the discrimination accuracies of potato, summer oat and winter triticale were comparatively low (<60%). Based on the outcome of the FFS, three models consisting of different predictor combinations, were further developed to ascertain the contribution of the predictors. A comparison of the models showed that the addition of phenological metrics increased the discrimination performance of the model as a whole and for cereals in particular. However, the inclusion of the topographic information did not have any significant effect on the overall model performance. Therefore, future crop type discrimination research in areas with similar terrain characteristics like Northern Hesse should reconsider the use of topographic predictors. Overall, our findings depict that the TOV modelling approach based on multi-temporal and multi-sensor data is promising for effective, accurate and practical crop type discrimination.

Multi-domain features for reducing false positives in automated detection of clustered microcalcifications in digital breast tomosynthesis.

In digital breast tomosynthesis (DBT) imaging, a microcalcification (MC) cluster may span across different slices and blurring exists in the out-of-focus slices. We developed a radiomics approach to extract features from focus slice and combine multiple spatial domains to reduce false positives (FPs) in an automated pipeline of detecting MC clusters. We performed a retrospective study on a cohort of 290 Chinese women patients with a total of 580 DBT volumes. We developed an automated MC detection pipeline that consists of two stages: an initial detection to identify a set of MC candidates that may include many FPs, followed by a radiomics-based classification model to identify and reduce the FPs. We extract both two-dimensional (2D) and three-dimensional (3D) radiomics features from multiple spatial domains, including a focus slice, projection image, and tomographic volume. A linear discriminant classifier was used coupled with a sequential forward feature selection procedure. The free-response operating characteristics (FROC) curve and partial area under the FROC curve (pAUC) in the FP rate range of 0 to 2 per DBT volume were used to evaluate the model's performance. At a sensitivity of 90%, the FP rate was reduced from 1.3 to 0.2 per DBT volume after applying the multi-domain-based classification on the initial detections. The multi-domain yielded a significantly higher pAUC compared to the initial detection (increase of pAUC=0.2278, P<0.0001), focus slice (increase of pAUC=0.0345, P=0.0152), project image (increase of pAUC=0.1043, P<0.0001), and tomographic volume (increase of pAUC=0.0791, P=0.0032). The radiomic features extracted from the three domains may provide complementary information and their integration can significantly reduce FPs in automated detection of MCs in DBT volumes on a large Chinese women population.

Early Findings on Functional Connectivity Correlates of Behavioral Outcomes of Brain-Computer Interface Stroke Rehabilitation Using Machine Learning.

The primary goal of this work was to apply data-driven machine learning regression to assess if resting state functional connectivity (rs-FC) could estimate measures of behavioral domains in stroke subjects who completed brain-computer interface (BCI) intervention for motor rehabilitation. The study cohort consisted of 20 chronic-stage stroke subjects exhibiting persistent upper-extremity motor deficits who received the intervention using a closed-loop neurofeedback BCI device. Over the course of this intervention, resting state functional MRI scans were collected at four distinct time points: namely, pre-intervention, mid-intervention, post-intervention and 1-month after completion of intervention. Behavioral assessments were administered outside the scanner at each time-point to collect objective measures such as the Action Research Arm Test, Nine-Hole Peg Test, and Barthel Index as well as subjective measures including the Stroke Impact Scale. The present analysis focused on neuroplasticity and behavioral outcomes measured across pre-intervention, post-intervention and 1-month post-intervention to study immediate and carry-over effects. Rs-FC, changes in rs-FC within the motor network and the behavioral measures at preceding stages were used as input features and behavioral measures and associated changes at succeeding stages were used as outcomes for machine-learning-based support vector regression (SVR) models. Potential clinical confounding factors such as age, gender, lesion hemisphere, and stroke severity were included as additional features in each of the regression models. Sequential forward feature selection procedure narrowed the search for important correlates. Behavioral outcomes at preceding time-points outperformed rs-FC-based correlates. Rs-FC and changes associated with bilateral primary motor areas were found to be important correlates of across several behavioral outcomes and were stable upon inclusion of clinical variables as well. NIH Stroke Scale and motor impairment severity were the most influential clinical variables. Comparatively, linear SVR models aided in evaluation of contribution of individual correlates and seed regions while non-linear SVR models achieved higher performance in prediction of behavioral outcomes.

A Sensor System for Automatic Detection of Food Intake Through Non-Invasive Monitoring of Chewing

Objective and automatic sensor systems to monitor ingestive behavior of individuals arise as a potential solution to replace inaccurate method of self-report. This paper presents a simple sensor system and related signal processing and pattern recognition methodologies to detect periods of food intake based on non-invasive monitoring of chewing. A piezoelectric strain gauge sensor was used to capture movement of the lower jaw from 20 volunteers during periods of quiet sitting, talking and food consumption. These signals were segmented into non-overlapping epochs of fixed length and processed to extract a set of 250 time and frequency domain features for each epoch. A forward feature selection procedure was implemented to choose the most relevant features, identifying from 4 to 11 features most critical for food intake detection. Support vector machine classifiers were trained to create food intake detection models. Twenty-fold cross-validation demonstrated per-epoch classification accuracy of 80.98% and a fine time resolution of 30 s. The simplicity of the chewing strain sensor may result in a less intrusive and simpler way to detect food intake. The proposed methodology could lead to the development of a wearable sensor system to assess eating behaviors of individuals.

Classification of infectious diseases based on chemiluminescent signatures of phagocytes in whole blood

Despite medical advances, infectious diseases are still a major cause of mortality and morbidity, disability and socio-economic upheaval worldwide. Early diagnosis, appropriate choice and immediate initiation of antibiotic therapy can greatly affect the outcome of any kind of infection. Phagocytes play a central role in the innate immune response of the organism to infection. They comprise the first-line of defense against infectious intruders in our body, being able to produce large quantities of reactive oxygen species, which can be detected by means of chemiluminescence (CL). The data preparation approach implemented in this work corresponds to a dynamic assessment of phagocytic respiratory burst localization in a luminol-enhanced whole blood CL system. We have previously applied this approach to the problem of identifying various intra-abdominal pathological processes afflicting peritoneal dialysis patients in the Nephrology department and demonstrated 84.6% predictive accuracy with the C4.5 decision-tree algorithm. In this study, we apply the CL-based approach to a larger sample of patients from two departments (Nephrology and Internal Medicine) with the aim of finding the most effective and interpretable feature sets and classification models for a fast and accurate identification of several infectious diseases. Whole blood samples were collected from 78 patients (comprising 115 instances) with respiratory infections, infections associated with renal replacement therapy and patients without infections. CL kinetic parameters were calculated for each case, which was assigned into a specific clinical group according to the available clinical diagnostics. Feature selection wrapper and filter methods were applied to remove the irrelevant and redundant features and to improve the predictive performance of disease classification algorithms. Three data mining algorithms, C4.5 (J48) decision tree, support vector machines and naive Bayes classifier were applied for inducing disease classification models and their performance in classifying three clinical groups was evaluated by 10 runs of a stratified 10-fold cross-validation. The results demonstrate that the predictive power of the best models obtained with the three evaluated algorithms after feature selection was found to be in the range of 63.38 ± 2.18-70.68 ± 1.43%. The highest disease classification accuracy was reached by C4.5, which also provides the most informative model in the form of a decision tree, and the lowest accuracy was obtained with naive Bayes. The feature selection method attaining the best classification performance was the wrapper method in forward direction. Moreover, the classification models exposed biological patterns specific to the clinical states and the predictive features selected were found to be characteristic of a specific disorder. Based on these encouraging results, we believe that the CL-based data pre-processing approach combined with the wrapper forward feature selection procedure and the C4.5 decision-tree algorithm has a clear potential to become a fast, informative, and sensitive tool for predictive diagnostics of infectious diseases in clinics.

Information-theoretic feature selection for functional data classification

The classification of functional or high-dimensional data requires to select a reduced subset of features among the initial set, both to help fighting the curse of dimensionality and to help interpreting the problem and the model. The mutual information criterion may be used in that context, but it suffers from the difficulty of its estimation through a finite set of samples. Efficient estimators are not designed specifically to be applied in a classification context, and thus suffer from further drawbacks and difficulties. This paper presents an estimator of mutual information that is specifically designed for classification tasks, including multi-class ones. It is combined to a recently published stopping criterion in a traditional forward feature selection procedure. Experiments on both traditional benchmarks and on an industrial functional classification problem show the added value of this estimator.

Mining complex genotypic features for predicting HIV-1 drug resistance

Human immunodeficiency virus type 1 (HIV-1) evolves in human body, and its exposure to a drug often causes mutations that enhance the resistance against the drug. To design an effective pharmacotherapy for an individual patient, it is important to accurately predict the drug resistance based on genotype data. Notably, the resistance is not just the simple sum of the effects of all mutations. Structural biological studies suggest that the association of mutations is crucial: even if mutations A or B alone do not affect the resistance, a significant change might happen when the two mutations occur together. Linear regression methods cannot take the associations into account, while decision tree methods can reveal only limited associations. Kernel methods and neural networks implicitly use all possible associations for prediction, but cannot select salient associations explicitly. Our method, itemset boosting, performs linear regression in the complete space of power sets of mutations. It implements a forward feature selection procedure where, in each iteration, one mutation combination is found by an efficient branch-and-bound search. This method uses all possible combinations, and salient associations are explicitly shown. In experiments, our method worked particularly well for predicting the resistance of nucleotide reverse transcriptase inhibitors (NRTIs). Furthermore, it successfully recovered many mutation associations known in biological literature. http://www.kyb.mpg.de/bs/people/hiroto/iboost/. Supplementary data are available at Bioinformatics online.