69 research outputs found
Interview with Constantin Aliferis
No full textConstantin Aliferis received an MD degree from Athens University in Greece in 1990, and an MS in 1994 and PhD in 1998 in Intelligent Systems from the University of Pittsburgh. After completing his PhD, Aliferis returned to Greece to complete two years of mandatory military service. At the same time he served as a research associate in epidemiology at Athens University. In 2000, Randy Miller and William Stead recruited Aliferis to Vanderbilt University to serve as an assistant professor of biomedical informatics and founding director of Vanderbilt University’s MS/PhD Program in Biomedical Informatics. While at Vanderbilt, Aliferis was founding director of the Discovery Systems Laboratory (2001-2008), faculty member at the Vanderbilt-Ingram Cancer Center (2000-2008), assistant professor of cancer biology (2005-2008), assistant professor of computer science (2007-2008), and assistant professor of biostatistics (2007-2008). In October 2008, Aliferis was recruited to New York University to serve as founding director of NYU’s Center for Health Informatics and Bioinformatics, Director of the Biomedical Informatics Core of NYU’s Clinical and Translational Science Institute, and associate professor of pathology (with tenure); positions he held until left NYU in June 2015. While at NYU, Aliferis also held the following positions: associate professor, computational biology program, Sackler Institute of Graduate Biomedical Studies (2009-2015); scientific director, Best Practices Integrative Informatics Consulting Core (2009-2015); scientific director, High Performance Computing Facility (2009-2015); founding director, NYU PhD Program in Biomedical Informatics (2011-2015); director, Biomedical Informatics Shared Resource of the Cancer Institute (2012-2015); and faculty, NYU Center for Data Science (2013-2015). In June 2015, Aliferis was recruited to the University of Minnesota. At the University of Minnesota, he holds the positions of professor and director of the Institute for Health Informatics, and the first University of Minnesota chief research informatics officer, heading the Clinical and Translational Institute Biomedical Informatics program. Aliferis will also build and lead a Big Data Analytics Unit for MHealth (collectively the Academic Health Center, Fairview Health Systems, and University of Minnesota Physicians) and carry the title of chief analytics officer.
Dr. Aliferis’ research is focused on high dimensional modeling and analysis designed to transform biomedical data into novel actionable scientific knowledge. His three key areas of broad interest are (a) use of advanced informatics and analytics to accelerate and enhance the sophistication, volume, quality, and reproducibility of scientific research; (b) quality and cost improvements of healthcare using Big Data approaches; and (c) precision medicine.
Dr. Aliferis was elected as a fellow of the American College of Medical Informatics in 2007.Constantin Aliferis begins by discussing his educational background, including his early interest in biomedical and health informatics. He describes the main focus of his research since graduate school, which has included machine learning and the analysis of complex and high-dimensional data sets; scientometrics and informatics retrieval; and model building, analysis, and knowledge discovery across a variety of disease domains. Aliferis goes on to briefly discuss his tenure at Vanderbilt University, followed by a more detailed discussion of his tenure at New York University. Next, Aliferis offers his definition of precision medicine. The remainder of the interview focuses on health informatics at the University of Minnesota. Aliferis describes his vision for the Institute for Health Informatics, reflects on the strong backing provided by the leadership of the University and the University’s Academic Health Center to support this vision, and offers his perspective on the future of the field of biomedical and health informatics.Aliferis, Constantin F.; Tobbell, Dominique. (2015). Interview with Constantin Aliferis. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/173663
Nashville, Tennessee Approved,
No full textTo my beloved and infinitely supportive wife, Kristina, and to my parents: my mother, Elena Feofilova, and my father, Roman Statnikov ii ACKNOWLEDGEMENTS First of all, I would like to acknowledge my academic advisors, Dr. Constantin F. Aliferis and Dr. Ioannis Tsamardinos, for their contribution to my Master’s project. In addition, I am grateful to Dr. Aliferis for introducing me to the fields of Biomedical Informatics and Machine Learning; training me both a researcher and as a professional scientific programmer; and setting up a framework for my future research and career development. I am also indebted to Dr. Tsamardinos for providing me with excellent technical and scientific ideas that are relevant for my professional and scientific growth. I would also like to thank everybody with whom I had pleasure to work during this project. In particular, I would to express my gratitude to Dr. Douglas P. Hardin and Dr. Shawn Levy who being members of my Master’s committee contributed not only to this project, but also to the journal manuscript based on this work. I would like to acknowledge all Biomedical Informatics faculty and graduate students for their countless contributions to the success of this project. Finally, I am forever indebted to my wife, Kristina Statnikova, for her understanding, endless patience and encouragement. This project would not be possible without her support. iii TABLE OF CONTENTS DEDICATION............................................................................................................................................... i
Developing Computer-generated PubMed Queries for Identifying Drug-Drug Interaction Content in MEDLINE
No full textDeveloping Computer-generated PubMed Queries for Identifying Drug-Drug Interaction Content in MEDLINE
No full textUnwanted drug-drug interactions endanger millions of patients each year and burden families and the hospital system with escalating costs. Computer-based alerting systems are designed to prevent these interactions, yet the knowledge bases that support these systems often contain incomplete, clinically insignificant, and inaccurate drug information that can contribute to false alerts and wasted time. It may be possible to improve the content of these drug interaction databases by facilitating access to new or underused sources of drug-drug interaction information. The National Library of Medicine's MEDLINE database represents a respected source of peer-reviewed biomedical citations that would serve as a valuable source of information if the relevant articles could be pinpointed effectively and efficiently. This research compared the classification capabilities of human-generated and computer-generated Boolean queries as methods for locating articles about drug interactions. Two manual queries were assembled by medical librarians specializing in MEDLINE searches, and three computer-based queries were developed using a decision tree modeled on Support Vector Machine output. All five queries were tested on a corpus of manually-labeled positive and negative drug-drug interaction citations. Overall, the study showed that computer-generated queries derived from automated classification techniques have the potential to perform at least as well as manual queries in identifying drug-drug interaction articles in MEDLINE
Automatic Cancer Diagnostic Decision Support System for Gene Expression Domain
No full textThe success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (Gene Expression Model Selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. After the system was built, we performed a preliminary evaluation of the system with 5 new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org
Analysis and computational dissection of molecular signature multiplicity.
No full textMolecular signatures are computational or mathematical models created to diagnose disease and other phenotypes and to predict clinical outcomes and response to treatment. It is widely recognized that molecular signatures constitute one of the most important translational and basic science developments enabled by recent high-throughput molecular assays. A perplexing phenomenon that characterizes high-throughput data analysis is the ubiquitous multiplicity of molecular signatures. Multiplicity is a special form of data analysis instability in which different analysis methods used on the same data, or different samples from the same population lead to different but apparently maximally predictive signatures. This phenomenon has far-reaching implications for biological discovery and development of next generation patient diagnostics and personalized treatments. Currently the causes and interpretation of signature multiplicity are unknown, and several, often contradictory, conjectures have been made to explain it. We present a formal characterization of signature multiplicity and a new efficient algorithm that offers theoretical guarantees for extracting the set of maximally predictive and non-redundant signatures independent of distribution. The new algorithm identifies exactly the set of optimal signatures in controlled experiments and yields signatures with significantly better predictivity and reproducibility than previous algorithms in human microarray gene expression datasets. Our results shed light on the causes of signature multiplicity, provide computational tools for studying it empirically and introduce a framework for in silico bioequivalence of this important new class of diagnostic and personalized medicine modalities
Algorithms for discovery of multiple Markov boundaries: application to the molecular signature multiplicity problem
No full textAlgorithms for discovery of multiple Markov boundaries: application to the molecular signature multiplicity problem
No full textAlgorithms for discovery of a Markov boundary from data constitute one of the most important recent developments in machine learning, primarily because they offer a principled solution to the variable/feature selection problem and give insight about local causal structure. Even though there is always a single Markov boundary of the response variable in faithful distributions, distributions with violations of the intersection property may have multiple Markov boundaries. Such distributions are abundant in practical data-analytic applications, and there are several reasons why it is important to induce all Markov boundaries from such data. However, there are currently no practical algorithms that can provably accomplish this task. To this end, I propose a novel generative algorithm (termed TIE*) that can discover all Markov boundaries from data. The generative algorithm can be instantiated to discover Markov boundaries independent of data distribution. I prove correctness of the generative algorithm and provide several admissible instantiations. The new algorithm is then applied to identify the set of maximally predictive and non-redundant molecular signatures. TIE* identifies exactly the set of true signatures in simulated distributions and yields signatures with significantly better predictivity and reproducibility than prior algorithms in human microarray gene expression datasets. The results of this thesis also shed light on the causes of molecular signature multiplicity phenomenon
Effects of environment, genetics and data analysis pitfalls in an esophageal cancer genome-wide association study.
No full textThe development of new high-throughput genotyping technologies has allowed fast evaluation of single nucleotide polymorphisms (SNPs) on a genome-wide scale. Several recent genome-wide association studies employing these technologies suggest that panels of SNPs can be a useful tool for predicting cancer susceptibility and discovery of potentially important new disease loci.In the present paper we undertake a careful examination of the relative significance of genetics, environmental factors, and biases of the data analysis protocol that was used in a previously published genome-wide association study. That prior study reported a nearly perfect discrimination of esophageal cancer patients and healthy controls on the basis of only genetic information. On the other hand, our results strongly suggest that SNPs in this dataset are not statistically linked to the phenotype, while several environmental factors and especially family history of esophageal cancer (a proxy to both environmental and genetic factors) have only a modest association with the disease.The main component of the previously claimed strong discriminatory signal is due to several data analysis pitfalls that in combination led to the strongly optimistic results. Such pitfalls are preventable and should be avoided in future studies since they create misleading conclusions and generate many false leads for subsequent research
- …
