Search
Now showing items 1-10 of 25
CANCERCELLNET: A COMPUTATIONAL PLATFORM TO EVALUATE THE TRANSCRIPTIONAL FIDELITY OF CANCER MODELS
(Johns Hopkins University, 2020-05-11)
Cancer cell lines, patient derived xenografts and genetically engineered mouse models provide valuable platforms for researchers to investigate tumor biology and to identify therapies. The extent of similarity between ...
Translating Machine Learning into Clinical Practice: Lessons from Development to Deployment
(Johns Hopkins University, 2020-02-19)
With the recent widespread availability of electronic health record data, there are new opportunities to apply data-driven methods to clinical problems. This has led to increasing numbers of publications proposing and ...
Topics at the interface of optimization and statistics
(Johns Hopkins University, 2020-07-22)
Optimization has been an important tool in statistics for a long time. For example, the problem of parameter estimation in a statistical model, either by maximizing a likelihood function or using least squares approach, ...
Machine Learning Methods for the Accelerated Global Structural Optimization of Thiolate-Protected Gold Nanoclusters
(Johns Hopkins University, 2020-10-28)
Modern computational chemistry techniques allow for the calculation of a wide set of material properties at the level of quantum physics, but such calculations require as input the atomic structure of the material in ...
Focal Impaired Awareness Seizure Detection Using a Smartwatch
(Johns Hopkins University, 2020-08-12)
Epileptic seizures are commonly classified as either generalized (originating simultaneously in cortical neurons across the entire brain) or focal (originating in a subpopulation of cortical neurons in a focal brain region). ...
Development and Validation of Traumatic Brain Injury Outcome Prognosis Model and Identification of Novel Quantitative Data-Driven Endotypes
(Johns Hopkins University, 2020-08-11)
The practical application of machine learning in medicine has been a budding field of study to take advantage of the patient data available to better understand human physiology. This area of study primarily focuses on the ...
Using Machine Learning and Computational Methods to Elucidate Therapeutic Response in Immuno-Oncology Clinical Trials
(Johns Hopkins University, 2021-03-26)
Checkpoint inhibitor (CPI) immunotherapies can produce remarkable patient responses, even in the context of late stage malignancies. While these drugs are efficacious for some patients, clinical responses are observed in ...
INTEGRATING USABILITY WITH TASK PERFORMANCE FOR SHARED AUTONOMY
(Johns Hopkins University, 2021-05-03)
As robots become more complex, the degrees-of-freedom (DoF) for controlling them is rapidly outpacing the degrees-of-control that can be supplied by humans via conventional interfaces. In practice, this is making it more ...
Predicting splicing regulation with learning methods
(Johns Hopkins University, 2021-07-12)
Alternative splicing is an important post-transcriptional process that serves to increase the diversity of proteins in different tissues and developmental stages, and its dysregulation is often associated with diseases. ...
Multiscale Statistical Hypothesis Testing for k-Sample Graph Inference
(Johns Hopkins University, 2021-05-13)
A connectome is a map of the structural and/or functional connections in the brain. This information-rich representation has the potential to transform our understanding of the relationship between patterns in brain ...