Forecasting daily emergency department arrivals using high-dimensional multivariate data: a feature selection approach.

BACKGROUND AND OBJECTIVE: Emergency Department (ED) overcrowding is a chronic international issue that is associated with adverse treatment outcomes. Accurate forecasts of future service demand would enable intelligent resource allocation that could alleviate the problem. There has been continued academic interest in ED forecasting but the number of used explanatory variables has been low, limited mainly to calendar and weather variables. In this study we investigate whether predictive accuracy of next day arrivals could be enhanced using high number of potentially relevant explanatory variables and document two feature selection processes that aim to identify which subset of variables is associated with number of next day arrivals. Performance of such predictions over longer horizons is also shown. METHODS: We extracted numbers of total daily arrivals from Tampere University Hospital ED between the time period of June 1, 2015 and June 19, 2019. 158 potential explanatory variables were collected from multiple data sources consisting not only of weather and calendar variables but also an extensive list of local public events, numbers of website visits to two hospital domains, numbers of available hospital beds in 33 local hospitals or health centres and Google trends searches for the ED. We used two feature selection processes: Simulated Annealing (SA) and Floating Search (FS) with Recursive Least Squares (RLS) and Least Mean Squares (LMS). Performance of these approaches was compared against autoregressive integrated moving average (ARIMA), regression with ARIMA errors (ARIMAX) and Random Forest (RF). Mean Absolute Percentage Error (MAPE) was used as the main error metric. RESULTS: Calendar variables, load of secondary care facilities and local public events were dominant in the identified predictive features. RLS-SA and RLS-FA provided slightly better accuracy compared ARIMA. ARIMAX was the most accurate model but the difference between RLS-SA and RLS-FA was not statistically significant. CONCLUSIONS: Our study provides new insight into potential underlying factors associated with number of next day presentations. It also suggests that predictive accuracy of next day arrivals can be increased using high-dimensional feature selection approach when compared to both univariate and nonfiltered high-dimensional approach. Performance over multiple horizons was similar with a gradual decline for longer horizons. However, outperforming ARIMAX remains a challenge when working with daily data. Future work should focus on enhancing the feature selection mechanism, investigating its applicability to other domains and in identifying other potentially relevant explanatory variables.

ClothFace: A Batteryless RFID-Based Textile Platform for Handwriting Recognition.

This paper introduces a prototype of ClothFace technology, a battery-free textile-based handwriting recognition platform that includes an e-textile antenna and a 10 × 10 array of radio frequency identification (RFID) integrated circuits (ICs), each with a unique ID. Touching the textile platform surface creates an electrical connection from specific ICs to the antenna, which enables the connected ICs to be read with an external UHF (ultra-haigh frequency) RFID reader. In this paper, the platform is demonstrated to recognize handwritten numbers 0-9. The raw data collected by the platform are a sequence of IDs from the touched ICs. The system converts the data into bitmaps and their details are increased by interpolating between neighboring samples using the sequential information of IDs. These images of digits written on the platform can be classified, with enough accuracy for practical use, by deep learning. The recognition system was trained and tested with samples from six volunteers using the platform. The real-time number recognition ability of the ClothFace technology is demonstrated to work successfully with a very low error rate. The overall recognition accuracy of the platform is 94.6% and the accuracy for each digit is between 91.1% and 98.3%. As the solution is fully passive and gets all the needed energy from the external RFID reader, it enables a maintenance-free and cost-effective user interface that can be integrated into clothing and into textiles around us.

Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects.

Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer's disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance imaging (MRI)-based method for predicting the MCI-to-AD conversion from one to three years before the clinical diagnosis. First, we developed a novel MRI biomarker of MCI-to-AD conversion using semi-supervised learning and then integrated it with age and cognitive measures about the subjects using a supervised learning algorithm resulting in what we call the aggregate biomarker. The novel characteristics of the methods for learning the biomarkers are as follows: 1) We used a semi-supervised learning method (low density separation) for the construction of MRI biomarker as opposed to more typical supervised methods; 2) We performed a feature selection on MRI data from AD subjects and normal controls without using data from MCI subjects via regularized logistic regression; 3) We removed the aging effects from the MRI data before the classifier training to prevent possible confounding between AD and age related atrophies; and 4) We constructed the aggregate biomarker by first learning a separate MRI biomarker and then combining it with age and cognitive measures about the MCI subjects at the baseline by applying a random forest classifier. We experimentally demonstrated the added value of these novel characteristics in predicting the MCI-to-AD conversion on data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. With the ADNI data, the MRI biomarker achieved a 10-fold cross-validated area under the receiver operating characteristic curve (AUC) of 0.7661 in discriminating progressive MCI patients (pMCI) from stable MCI patients (sMCI). Our aggregate biomarker based on MRI data together with baseline cognitive measurements and age achieved a 10-fold cross-validated AUC score of 0.9020 in discriminating pMCI from sMCI. The results presented in this study demonstrate the potential of the suggested approach for early AD diagnosis and an important role of MRI in the MCI-to-AD conversion prediction. However, it is evident based on our results that combining MRI data with cognitive test results improved the accuracy of the MCI-to-AD conversion prediction.

Automatic detection of changes in the dynamics of delayed stochastic gene networks and in vivo production of RNA molecules in Escherichia coli.

MOTIVATION: Production and degradation of RNA and proteins are stochastic processes, difficulting the distinction between spurious fluctuations in their numbers and changes in the dynamics of a genetic circuit. An accurate method of change detection is key to analyze plasticity and robustness of stochastic genetic circuits. RESULTS: We use automatic change point detection methods to detect non-spurious changes in the dynamics of delayed stochastic models of gene networks at run time. We test the methods in detecting changes in mean and noise of protein numbers, and in the switching frequency of a genetic switch. We also detect changes, following genes' silencing, in the dynamics of a model of the core gene regulatory network of Saccharomyces cerevisiae with 328 genes. Finally, from images, we determine when RNA molecules tagged with fluorescent proteins are first produced in Escherichia coli. Provided prior knowledge on the time scale of the changes, the methods detect them accurately and are robust to fluctuations in protein and RNA levels. AVAILABILITY: Simulator: www.cs.tut.fi/~sanchesr/SGN/SGNSim.html CONTACT: andre.ribeiro@tut.fi SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Computational framework for simulating fluorescence microscope images with cell populations.

Fluorescence microscopy combined with digital imaging constructs a basic platform for numerous biomedical studies in the field of cellular imaging. As the studies relying on analysis of digital images have become popular, the validation of image processing methods used in automated image cytometry has become an important topic. Especially, the need for efficient validation has arisen from emerging high-throughput microscopy systems where manual validation is impractical. We present a simulation platform for generating synthetic images of fluorescence-stained cell populations with realistic properties. Moreover, we show that the synthetic images enable the validation of analysis methods for automated image cytometry and comparison of their performance. Finally, we suggest additional usage scenarios for the simulator. The presented simulation framework, with several user-controllable parameters, forms a versatile tool for many kinds of validation tasks, and is freely available at http://www.cs.tut.fi/sgn/csb/simcep.

Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia.

We present a comparative split-half resampling analysis of various data driven feature selection and classification methods for the whole brain voxel-based classification analysis of anatomical magnetic resonance images. We compared support vector machines (SVMs), with or without filter based feature selection, several embedded feature selection methods and stability selection. While comparisons of the accuracy of various classification methods have been reported previously, the variability of the out-of-training sample classification accuracy and the set of selected features due to independent training and test sets have not been previously addressed in a brain imaging context. We studied two classification problems: 1) Alzheimer's disease (AD) vs. normal control (NC) and 2) mild cognitive impairment (MCI) vs. NC classification. In AD vs. NC classification, the variability in the test accuracy due to the subject sample did not vary between different methods and exceeded the variability due to different classifiers. In MCI vs. NC classification, particularly with a large training set, embedded feature selection methods outperformed SVM-based ones with the difference in the test accuracy exceeding the test accuracy variability due to the subject sample. The filter and embedded methods produced divergent feature patterns for MCI vs. NC classification that suggests the utility of the embedded feature selection for this problem when linked with the good generalization performance. The stability of the feature sets was strongly correlated with the number of features selected, weakly correlated with the stability of classification accuracy, and uncorrelated with the average classification accuracy.

Insight to Nanoparticle Size Analysis-Novel and Convenient Image Analysis Method Versus Conventional Techniques.

The aim of this paper is to introduce a new image analysis program "Nanoannotator" particularly developed for analyzing individual nanoparticles in transmission electron microscopy images. This paper describes the usefulness and efficiency of the program when analyzing nanoparticles, and at the same time, we compare it to more conventional nanoparticle analysis techniques. The techniques which we are concentrating here are transmission electron microscopy (TEM) linked with different image analysis methods and X-ray diffraction techniques. The developed program appeared as a good supplement to the field of particle analysis techniques, since the traditional image analysis programs suffer from the inability to separate the individual particles from agglomerates in the TEM images. The program is more efficient, and it offers more detailed morphological information of the particles than the manual technique. However, particle shapes that are very different from spherical proved to be problematic also for the novel program. When compared to X-ray techniques, the main advantage of the small-angle X-ray scattering (SAXS) method is the average data it provides from a very large amount of particles. However, the SAXS method does not provide any data about the shape or appearance of the sample.

Robust detection of periodic time series measured from biological systems.

BACKGROUND: Periodic phenomena are widespread in biology. The problem of finding periodicity in biological time series can be viewed as a multiple hypothesis testing of the spectral content of a given time series. The exact noise characteristics are unknown in many bioinformatics applications. Furthermore, the observed time series can exhibit other non-idealities, such as outliers, short length and distortion from the original wave form. Hence, the computational methods should preferably be robust against such anomalies in the data. RESULTS: We propose a general-purpose robust testing procedure for finding periodic sequences in multiple time series data. The proposed method is based on a robust spectral estimator which is incorporated into the hypothesis testing framework using a so-called g-statistic together with correction for multiple testing. This results in a robust testing procedure which is insensitive to heavy contamination of outliers, missing-values, short time series, nonlinear distortions, and is completely insensitive to any monotone nonlinear distortions. The performance of the methods is evaluated by performing extensive simulations. In addition, we compare the proposed method with another recent statistical signal detection estimator that uses Fisher's test, based on the Gaussian noise assumption. The results demonstrate that the proposed robust method provides remarkably better robustness properties. Moreover, the performance of the proposed method is preferable also in the standard Gaussian case. We validate the performance of the proposed method on real data on which the method performs very favorably. CONCLUSION: As the time series measured from biological systems are usually short and prone to contain different kinds of non-idealities, we are very optimistic about the multitude of possible applications for our proposed robust statistical periodicity detection method.

Flow Cytometry-Based Classification in Cancer Research: A View on Feature Selection.

In this paper, we study the problem of feature selection in cancer-related machine learning tasks. In particular, we study the accuracy and stability of different feature selection approaches within simplistic machine learning pipelines. Earlier studies have shown that for certain cases, the accuracy of detection can easily reach 100% given enough training data. Here, however, we concentrate on simplifying the classification models with and seek for feature selection approaches that are reliable even with extremely small sample sizes. We show that as much as 50% of features can be discarded without compromising the prediction accuracy. Moreover, we study the model selection problem among the ℓ 1 regularization path of logistic regression classifiers. To this aim, we compare a more traditional cross-validation approach with a recently proposed Bayesian error estimator.

Quantitative analysis of dynamic association in live biological fluorescent samples.

Determining vesicle localization and association in live microscopy may be challenging due to non-simultaneous imaging of rapidly moving objects with two excitation channels. Besides errors due to movement of objects, imaging may also introduce shifting between the image channels, and traditional colocalization methods cannot handle such situations. Our approach to quantifying the association between tagged proteins is to use an object-based method where the exact match of object locations is not assumed. Point-pattern matching provides a measure of correspondence between two point-sets under various changes between the sets. Thus, it can be used for robust quantitative analysis of vesicle association between image channels. Results for a large set of synthetic images shows that the novel association method based on point-pattern matching demonstrates robust capability to detect association of closely located vesicles in live cell-microscopy where traditional colocalization methods fail to produce results. In addition, the method outperforms compared Iterated Closest Points registration method. Results for fixed and live experimental data shows the association method to perform comparably to traditional methods in colocalization studies for fixed cells and to perform favorably in association studies for live cells.

Bioprocess data mining using regularized regression and random forests.

BACKGROUND: In bioprocess development, the needs of data analysis include (1) getting overview to existing data sets, (2) identifying primary control parameters, (3) determining a useful control direction, and (4) planning future experiments. In particular, the integration of multiple data sets causes that these needs cannot be properly addressed by regression models that assume linear input-output relationship or unimodality of the response function. Regularized regression and random forests, on the other hand, have several properties that may appear important in this context. They are capable, e.g., in handling small number of samples with respect to the number of variables, feature selection, and the visualization of response surfaces in order to present the prediction results in an illustrative way. RESULTS: In this work, the applicability of regularized regression (Lasso) and random forests (RF) in bioprocess data mining was examined, and their performance was benchmarked against multiple linear regression. As an example, we used data from a culture media optimization study for microbial hydrogen production. All the three methods were capable in providing a significant model when the five variables of the culture media optimization were linearly included in modeling. However, multiple linear regression failed when also the multiplications and squares of the variables were included in modeling. In this case, the modeling was still successful with Lasso (correlation between the observed and predicted yield was 0.69) and RF (0.91). CONCLUSION: We found that both regularized regression and random forests were able to produce feasible models, and the latter was efficient in capturing the non-linearity in the data. In this kind of a data mining task of bioprocess data, both methods outperform multiple linear regression.

Leukemia prediction using sparse logistic regression.

We describe a supervised prediction method for diagnosis of acute myeloid leukemia (AML) from patient samples based on flow cytometry measurements. We use a data driven approach with machine learning methods to train a computational model that takes in flow cytometry measurements from a single patient and gives a confidence score of the patient being AML-positive. Our solution is based on an [Formula: see text] regularized logistic regression model that aggregates AML test statistics calculated from individual test tubes with different cell populations and fluorescent markers. The model construction is entirely data driven and no prior biological knowledge is used. The described solution scored a 100% classification accuracy in the DREAM6/FlowCAP2 Molecular Classification of Acute Myeloid Leukaemia Challenge against a golden standard consisting of 20 AML-positive and 160 healthy patients. Here we perform a more extensive validation of the prediction model performance and further improve and simplify our original method showing that statistically equal results can be obtained by using simple average marker intensities as features in the logistic regression model. In addition to the logistic regression based model, we also present other classification models and compare their performance quantitatively. The key benefit in our prediction method compared to other solutions with similar performance is that our model only uses a small fraction of the flow cytometry measurements making our solution highly economical.

Effects of latanoprost in iris bioidentification.

PURPOSE: Bioidentification is becoming increasingly important in everyday life. One of the most widespread methods of bioidentification is based on the structure of the iris. Iris photography has several advantages as an identification method: it is relatively simple and effective; it is non-invasive, and it is comparatively inexpensive. However, some medical conditions may change the appearance of the iris. This paper discusses the effects of latanoprost-induced pigmentation changes in iris bioidentification. METHODS: The study is based on four extreme cases of latanoprost-induced pigmentation changes. Iris photographs in these patients during treatment are compared with pretreatment photographs. The comparison is carried out with iris recognition software developed by our research group based on the principles of Daugman's well-known IrisCode. The system was evaluated with 595 iris comparisons. RESULTS: Iris photographs showing latanoprost-induced pigmentation changes were correctly matched with pretreatment photographs of the same irises with an error probability similar to that for matching equivalent pairs of photographs in intact eyes. CONCLUSIONS: Our results indicate that the pigmentation changes studied do not seem to have a significant effect on the standard identification algorithm.

Three-dimensional digital image analysis of immunostained neurons in thick tissue sections.

Detection and three dimensional reconstruction of cell structures from brightfield microscopy video clips using digital image processing algorithms is presented. While the confocal microscopy offers an efficient technique for three dimensional measurements, extensive and repeated measurements are still often better to be performed using permanent staining and brightfield microscopy. By processing of brightfield microscopy videos using automated and efficient digital image processing algorithms, the tedious task of manual analysis can be avoided. Our two-stage algorithm is applied for 1) cell soma detection and 2) identification of the 3D structure of entire neurons. To verify the results, we present 3D reconstructions of the detected cells.