Medicine and Health Sciences Commons^™

Data Mining The Functional Characterizations Of Proteins To Predict Their Cancer-Relatedness, Peter Revesz, Christopher Assi

School of Computing: Faculty Publications

This paper considers two types of protein data. First, data about protein function described in a number of ways, such as, GO terms and PFAM families. Second, data about whether individual proteins are experimentally associated with cancer by an anomalous elevation or lowering of their expressions within cancerous cells. We combine these two types of protein data and test whether the first type of data, that is, the functional descriptors, can predict the second type of data, that is, cancer-relatedness. By using data mining and machine learning, we derive a classifier algorithm that using only GO term and PFAM family …

Development Of A Diagnostic Test Set To Assess Agreement In Breast Pathology: Practical Application Of The Guidelines For Reporting Reliability And Agreement Studies (Grras), Natalia V. Oster, Patricia A. Carney, Kimberly H. Allison, Donald L. Weaver, Lisa Reisch, Gary Longton, Tracy Onega

Dartmouth Scholarship

Diagnostic test sets are a valuable research tool that contributes importantly to the validity and reliability of studies that assess agreement in breast pathology. In order to fully understand the strengths and weaknesses of any agreement and reliability study, however, the methods should be fully reported. In this paper we provide a step-by-step description of the methods used to create four complex test sets for a study of diagnostic agreement among pathologists interpreting breast biopsy specimens. We use the newly developed Guidelines for Reporting Reliability and Agreement Studies (GRRAS) as a basis to report these methods.

Scanning In Situ Spectroscopy Pplatform For Imaging Surgical Breast Tissue Specimens, Venkataramanan Krishnaswamy, Ashley M. Laughney, Wendy A. Wells, Keith D. Paulsen, Brian W. Pogue

Dartmouth Scholarship

A non-contact localized spectroscopic imaging platform has been developed and optimized to scan 1 x 1 cm² square regions of surgically resected breast tissue specimens with ~150-micron resolution. A color corrected, image-space telecentric scanning design maintained a consistent sampling geometry and uniform spot size across the entire imaging field. Theoretical modeling in ZEMAX allowed estimation of the spot size, which is equal at both the center and extreme positions of the field with ~5% variation across the designed waveband, indicating excellent color correction. The spot sizes at the center and an extreme field position were also measured experimentally using the …

Automated Point-Of-Care Image Processing Methodology For The Diagnosis Of Malaria, Michael B. Jorgensen

Master's Theses

Malaria has profoundly influenced human history for over four thousand years and despite numerous attempts at eradication, the prevention, diagnosis, and treatment of malaria have been largely ineffective. More than five hundred million people are affected by malaria every year resulting in over one million deaths. Drug resistance development by the parasite has diminished the effectiveness of numerous treatment options due, in part, to overtreatment of negative patients based on insufficient clinical algorithms and diagnostic methods. The goal of this research was to develop an image analysis algorithm to diagnose malaria with a high degree of sensitivity and specificity in …

A Dna Computer For Glioblastoma Multiforme Diagnosis And Drug Delivery, Sumaiya F. Hashmi

CMC Senior Theses

Glioblastoma multiforme (GBM) is a debilitating malignant brain tumor with expected patient survival of less than a year and limited responsiveness to most treatments, often requiring biopsy for diagnosis and invasive surgery for treatment. We propose a DNA computer system, consisting of input, computation, and output components, for diagnosis and treatment. The input component will detect the presence of three GBM biomarkers: vascular endothelial growth factor (VEGF), caveolin-1α (CAV), and B2 receptors. The computation component will include indicator segments for each of these genes, and ensure that output is only released if all the biomarkers are present. The output component …

A Machine Learning Approach To Diagnosis Of Parkinson’S Disease, Sumaiya F. Hashmi

CMC Senior Theses

I will investigate applications of machine learning algorithms to medical data, adaptations of differences in data collection, and the use of ensemble techniques.

Focusing on the binary classification problem of Parkinson’s Disease (PD) diagnosis, I will apply machine learning algorithms to a primary dataset consisting of voice recordings from healthy and PD subjects. Specifically, I will use Artificial Neural Networks, Support Vector Machines, and an Ensemble Learning algorithm to reproduce results from [MS12] and [GM09].

Next, I will adapt a secondary regression dataset of PD recordings and combine it with the primary binary classification dataset, testing various techniques to consolidate …