William Speier

Cost Implications of New Treatments for Advanced Colorectal Cancer

Since 1996, 6 new drugs have been introduced for the treatment of metastatic colorectal cancer. Although they are promising, these drugs frequently are given in the palliative and are much more expensive than older treatments. The objective of the current study was to measure the cost implications of treatment with sequential regimens that include chemotherapy and/or monoclonal antibodies.

Natural Language Processing with Dynamic Classification Improves P300 Speller Accuracy and Bit Rate

The P300 speller is an example of a brain-computer interface that can restore functionality to victims of neuromuscular disorders. Although the most common application of this system has been communicating language, the properties and constraints of the linguistic domain have not to date been exploited when decoding brain signals that pertain to language. We hypothesized that combining the standard stepwise linear discriminant analysis with a Naive Bayes classifier and a trigram language model would increase the speed and accuracy of typing with the P300 speller. With integration of natural language processing, we observed significant improvements in accuracy and 40-60% increases in bit rate for all six subjects in a pilot study. This study suggests that integrating information about the linguistic domain can significantly improve signal classification.

The effects of stimulus timing features on P300 speller performance

OBJECTIVE Despite numerous examinations of factors affecting P300 speller performance, the impact of stimulus presentation parameters remains incompletely understood. This study examines the effects of four distinct stimulus presentation parameters (stimulus-off time [ISI(∗)], interstimulus interval [ISI], flash duration, and flash-duration:ISI ratio) on the accuracy and efficiency of the P300 speller performance. METHODS EEG data from a 32-electrode set were recorded from six subjects using a row-column paradigm of the speller task and analyzed offline. RESULTS P300 speller accuracy is affected by the number of trial repetitions (F(14,354) = 69.002, p < 0.0001), as expected. In addition, longer ISI and ISI(∗) times resulted in higher accuracy and characters per minute [CPM] rates. Subsets of the entire group (i.e. good vs. poor performers) were compared to show consistency of performance trends despite great variance among subjects. Moreover, the same significant effects were observed whether using the entire 32-electrode dataset or the reduced 8-channel set described by Sharbrough et al. (1991). CONCLUSIONS Despite variability in user performance, both ISI(∗) and ISI can affect P300 speller performance. SIGNIFICANCE P300 system optimization must consider critical stimulus timing features including ISI(∗) and ISI. Further characterization of the impact of these timing features in online experiments is warranted and the differential effect on accuracy and CPM should be more comprehensively explored.

Integrating Language Information With a Hidden Markov Model to Improve Communication Rate in the P300 Speller

The P300 speller is a common brain-computer interface (BCI) application designed to communicate language by detecting event related potentials in a subjects electroencephalogram (EEG) signal. Information about the structure of natural language can be valuable for BCI communication systems, but few attempts have been made to incorporate this domain knowledge into the classifier. In this study, we treat BCI communication as a hidden Markov model (HMM) where hidden states are target characters and the EEG signal is the visible output. Using the Viterbi algorithm, language information can be incorporated in classification and errors can be corrected automatically. This method was first evaluated offline on a dataset of 15 healthy subjects who had a significant increase in bit rate from a previously published naïve Bayes approach and an average 32% increase from standard classification with dynamic stopping. An online pilot study of five healthy subjects verified these results as the average bit rate achieved using the HMM method was significantly higher than that using the naïve Bayes and standard methods. These findings strongly support the integration of domain-specific knowledge into BCI classification to improve system performance and accuracy.

Improved P300 speller performance using electrocorticography, spectral features, and natural language processing

OBJECTIVE The P300 speller is a system designed to restore communication to patients with advanced neuromuscular disorders. This study was designed to explore the potential improvement from using electrocorticography (ECoG) compared to the more traditional usage of electroencephalography (EEG). METHODS We tested the P300 speller on two epilepsy patients with temporary subdural electrode arrays over the occipital and temporal lobes respectively. We then performed offline analysis to determine the accuracy and bit rate of the system and integrated spectral features into the classifier and used a natural language processing (NLP) algorithm to further improve the results. RESULTS The subject with the occipital grid achieved an accuracy of 82.77% and a bit rate of 41.02, which improved to 96.31% and 49.47 respectively using a language model and spectral features. The temporal grid patient achieved an accuracy of 59.03% and a bit rate of 18.26 with an improvement to 75.81% and 27.05 respectively using a language model and spectral features. Spatial analysis of the individual electrodes showed best performance using signals generated and recorded near the occipital pole. CONCLUSIONS Using ECoG and integrating language information and spectral features can improve the bit rate of a P300 speller system. This improvement is sensitive to the electrode placement and likely depends on visually evoked potentials. SIGNIFICANCE This study shows that there can be an improvement in BCI performance when using ECoG, but that it is sensitive to the electrode location.

A topic model of clinical reports

Clinical narrative in the medical record provides perhaps the most detailed account of a patients history. However, this information is documented in free-text, which makes it challenging to analyze. Efforts to index unstructured clinical narrative often focus on identifying predefined concepts from clinical terminologies. Less studied is the problem of analyzing the text as a whole to create temporal indices that capture relationships between learned clinical events. Topic models provide a method for analyzing large corpora of text to discover semantically related clusters of words. This work presents a topic model tailored to the clinical reporting environment that allows for individual patient timelines. Results show the model is able to identify patterns of clinical events in a cohort of brain cancer patients.

Integrating language models into classifiers for BCI communication: a review.

OBJECTIVE The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. APPROACH The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models. MAIN RESULTS Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation. SIGNIFICANCE Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.

Evaluating topic model interpretability from a primary care physician perspective

BACKGROUND AND OBJECTIVE Probabilistic topic models provide an unsupervised method for analyzing unstructured text. These models discover semantically coherent combinations of words (topics) that could be integrated in a clinical automatic summarization system for primary care physicians performing chart review. However, the human interpretability of topics discovered from clinical reports is unknown. Our objective is to assess the coherence of topics and their ability to represent the contents of clinical reports from a primary care physicians point of view. METHODS Three latent Dirichlet allocation models (50 topics, 100 topics, and 150 topics) were fit to a large collection of clinical reports. Topics were manually evaluated by primary care physicians and graduate students. Wilcoxon Signed-Rank Tests for Paired Samples were used to evaluate differences between different topic models, while differences in performance between students and primary care physicians (PCPs) were tested using Mann-Whitney U tests for each of the tasks. RESULTS While the 150-topic model produced the best log likelihood, participants were most accurate at identifying words that did not belong in topics learned by the 100-topic model, suggesting that 100 topics provides better relative granularity of discovered semantic themes for the data set used in this study. Models were comparable in their ability to represent the contents of documents. Primary care physicians significantly outperformed students in both tasks. CONCLUSION This work establishes a baseline of interpretability for topic models trained with clinical reports, and provides insights on the appropriateness of using topic models for informatics applications. Our results indicate that PCPs find discovered topics more coherent and representative of clinical reports relative to students, warranting further research into their use for automatic summarization.

Robust skull stripping of clinical Glioblastoma multiforme data

Skull stripping is the first step in many neuroimaging analyses and its success is critical to all subsequent processing. Methods exist to skull strip brain images without gross deformities, such as those affected by Alzheimers and Huntingtons disease. However, there are no techniques for extracting brains affected by diseases that significantly disturb normal anatomy. Glioblastoma multiforme (GBM) is such a disease, as afflicted individuals develop large tumors that often require surgical resection. In this paper, we extend the ROBEX skull stripping method to extract brains from GBM images. The proposed method uses a shape model trained on healthy brains to be relatively insensitive to lesions inside the brain. The brain boundary is then searched for potential resection cavities using adaptive thresholding and the Random Walker algorithm corrects for leakage into the ventricles. The results show significant improvement over three popular skull stripping algorithms (BET, BSE and HWA) in a dataset of 48 GBM cases.

Prevalence of Coronary Artery Disease Evaluated by Coronary CT Angiography in Women with Mammographically Detected Breast Arterial Calcifications

To assess the correlation between breast arterial calcifications (BAC) on digital mammography and the extent of coronary artery disease (CAD) diagnosed with dual source coronary computed tomography angiography (CTA) in a population of women both symptomatic and asymptomatic for coronary artery disease. 100 consecutive women (aged 34 – 86 years) who underwent both coronary CTA and digital mammography were included in the study. Health records were reviewed to determine the presence of cardiovascular risk factors such as hypertension, hyperlipidemia, diabetes mellitus, and smoking. Digital mammograms were reviewed for the presence and degree of BAC, graded in terms of severity and extent. Coronary CTAs were reviewed for CAD, graded based on the extent of calcified and non-calcified plaque, and the degree of major vessel stenosis. A four point grading scale was used for both coronary CTA and mammography. The overall prevalence of positive BAC and CAD in the studied population were 12% and 29%, respectively. Ten of the 12 patients with moderate or advanced BAC on mammography demonstrated moderate to severe CAD as determined by coronary CTA. For all women, the positive predictive value of BAC for CAD was 0.83 and the negative predictive value was 0.78. The presence of BAC on mammography appears to correlate with CAD as determined by coronary CTA (Spearman’s rank correlation coefficient = 0.48, p<.000001). Using logistic regression, the inclusion of BAC as a feature in CAD predication significantly increased classification results (p=0.04).