Differences

This shows you the differences between two versions of the page.

--- research [2018/05/02 17:59]
shyam [Precision medicine and personalized modeling]
+++ research [2019/03/03 19:35]
shyam [Data mining and causal discovery from biomedical data]
@@ Line 39: / Line 39: @@
-==== Precision medicine and personalized modeling ====
+==== Precision medicine and patient-specific modeling ====
 {{ wiki:allofus.png?200x0}}
@@ Line 48: / Line 48: @@
 The University of Pittsburgh is funded as one of the Healthcare Provider Organizations for the national **All of Us Research Program**, which is a historic effort to gather data from 1 million people living in the United States. The goal of the program is to revolutionize how disease is prevented and treated based on individual differences in lifestyle, environment and genetics. Along with [[http://www.health.pitt.edu/people/steven-e-reis|Steven E. Reis]] and [[http://www.upmc.com/media/experts/Pages/oscar-c-marroquin.aspx|Oscar Marroquin]], I am a PD/PI on the **All of Us Pennsylvania** project that will enroll and collect data and bio specimens for 120,000 individuals for the All of Us Research Program.
-In predictive modeling in medicine, the typical paradigm consists of learning a single model from a database of individuals, which is then applied to predict outcomes for any future individual. Such a model is called a population-wide model because it is intended to be applied to an entire population of future individuals. In contrast, personalized modeling focuses on learning models that are tailored to the characteristics of the individual at hand. Personalized models that are optimized to perform well for a specific individual are likely to have better predictive performance than the typical population-wide models that are optimized to have good predictive performance on average on all future individuals. Moreover, personalized models can identify features such as genomic factors that are specific for an individual thus enabling precision medicine. This work is in collaboration with [[http://www.dbmi.pitt.edu/person/gregory-cooper-md-phd|Gregory F. Cooper]] (at the University of Pittsburgh). The areas of focus include:
+In predictive modeling in medicine, the typical paradigm consists of learning a single model from a database of individuals, which is then applied to predict outcomes for any future individual. Such a model is called a population-wide model because it is intended to be applied to an entire population of future individuals. In contrast, patient-specific modeling focuses on learning models that are tailored to the characteristics of the individual at hand. Patient-specific models that are optimized to perform well for a specific individual are likely to have better predictive performance than the typical population-wide models that are optimized to have good predictive performance on average on all future individuals. Moreover, patient-specific models can identify features such as genomic factors that are specific for an individual thus enabling precision medicine. This work is in collaboration with [[http://www.dbmi.pitt.edu/person/gregory-cooper-md-phd|Gregory F. Cooper]] (at the University of Pittsburgh). The areas of focus include:
-  * development of Bayesian and information-theoretic methods for learning personalized models from clinical and genomic data, and
+  * development of Bayesian and information-theoretic methods for learning patient-specific models from clinical and genomic data, and
   * application of personalized modeling to risk assessment, diagnosis, prognosis and selection of therapy.
@@ Line 76: / Line 76: @@
 Development and application of causal discovery machine learning methods to biomedical data including large-scale electronic medical record data is important for uncovering casual relations in these data. This work is in collaboration with [[http://www.dbmi.pitt.edu/person/gregory-cooper-md-phd|Gregory F. Cooper]] and [[http://www.mdphd.pitt.edu/students/eric-strobl|Eric Strobl]] and is funded by a [[https://projectreporter.nih.gov/project_info_description.cfm?aid=8935874|U54 grant from NHGRI]], NIH.
-Surging use of social media1 has resulted in unprecedented opportunities for examination of complex social and behavioral phenomena. We are developing  machine learning infoveillance tools to study cancer communication in Twitter data. This work is in collaboration with This work is in collaboration with [[https://www.dom.pitt.edu/dgim/faculty_info.aspx/Primack4945|Brian Primack]] and is funded by a [[https://projectreporter.nih.gov/project_info_details.cfm?aid=950346|R01 grant from NCI]], NIH.
+Surging use of social media has resulted in unprecedented opportunities for examination of complex social and behavioral phenomena. We are developing  machine learning infoveillance tools to study cancer communication in Twitter data. This work is in collaboration with This work is in collaboration with [[https://www.dom.pitt.edu/dgim/faculty_info.aspx/Primack4945|Brian Primack]] and is funded by a [[https://projectreporter.nih.gov/project_info_details.cfm?aid=950346|R01 grant from NCI]], NIH.
 The areas of focus include: