1
|
Liang L, Hou J, Uno H, Cho K, Ma Y, Cai T. Semi-supervised approach to event time annotation using longitudinal electronic health records. Lifetime Data Anal 2022; 28:428-491. [PMID: 35753014 PMCID: PMC10044535 DOI: 10.1007/s10985-022-09557-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/16/2021] [Accepted: 05/13/2022] [Indexed: 06/15/2023]
Abstract
Large clinical datasets derived from insurance claims and electronic health record (EHR) systems are valuable sources for precision medicine research. These datasets can be used to develop models for personalized prediction of risk or treatment response. Efficiently deriving prediction models using real world data, however, faces practical and methodological challenges. Precise information on important clinical outcomes such as time to cancer progression are not readily available in these databases. The true clinical event times typically cannot be approximated well based on simple extracts of billing or procedure codes. Whereas, annotating event times manually is time and resource prohibitive. In this paper, we propose a two-step semi-supervised multi-modal automated time annotation (MATA) method leveraging multi-dimensional longitudinal EHR encounter records. In step I, we employ a functional principal component analysis approach to estimate the underlying intensity functions based on observed point processes from the unlabeled patients. In step II, we fit a penalized proportional odds model to the event time outcomes with features derived in step I in the labeled data where the non-parametric baseline function is approximated using B-splines. Under regularity conditions, the resulting estimator of the feature effect vector is shown as root-n consistent. We demonstrate the superiority of our approach relative to existing approaches through simulations and a real data example on annotating lung cancer recurrence in an EHR cohort of lung cancer patients from Veteran Health Administration.
Collapse
Affiliation(s)
- Liang Liang
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA, USA
| | - Jue Hou
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA, USA
| | - Hajime Uno
- Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA, USA
| | - Kelly Cho
- Massachusetts Veterans Epidemiology Research and Information Center, US Department of Veteran Affairs, Boston, MA, USA
- Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Yanyuan Ma
- Department of Statistics, Penn State University, University Park, PA, Boston, USA
| | - Tianxi Cai
- Department of Biostatistics, Harvard T. H. Chan School of Public Health, Boston, MA, USA.
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
2
|
Kaleel M, Torrisi M, Mooney C, Pollastri G. PaleAle 5.0: prediction of protein relative solvent accessibility by deep learning. Amino Acids 2019; 51:1289-96. [PMID: 31388850 DOI: 10.1007/s00726-019-02767-6] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2019] [Accepted: 07/29/2019] [Indexed: 10/26/2022]
Abstract
Predicting the three-dimensional structure of proteins is a long-standing challenge of computational biology, as the structure (or lack of a rigid structure) is well known to determine a protein's function. Predicting relative solvent accessibility (RSA) of amino acids within a protein is a significant step towards resolving the protein structure prediction challenge especially in cases in which structural information about a protein is not available by homology transfer. Today, arguably the core of the most powerful prediction methods for predicting RSA and other structural features of proteins is some form of deep learning, and all the state-of-the-art protein structure prediction tools rely on some machine learning algorithm. In this article we present a deep neural network architecture composed of stacks of bidirectional recurrent neural networks and convolutional layers which is capable of mining information from long-range interactions within a protein sequence and apply it to the prediction of protein RSA using a novel encoding method that we shall call "clipped". The final system we present, PaleAle 5.0, which is available as a public server, predicts RSA into two, three and four classes at an accuracy exceeding 80% in two classes, surpassing the performances of all the other predictors we have benchmarked.
Collapse
|
3
|
Kalbfleisch JD. Discussion of "Survival models and health sequences" by Walter Dempsey and Peter McCullagh. Lifetime Data Anal 2018; 24:585-587. [PMID: 30008054 DOI: 10.1007/s10985-018-9439-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/12/2018] [Accepted: 06/28/2018] [Indexed: 06/08/2023]
Abstract
This is a discussion of the paper by Dempsey and McCullagh.
Collapse
Affiliation(s)
- John D Kalbfleisch
- Department of Biostatistics, University of Michigan, 1415 Washington Heights, Ann Arbor, MI, 48109, USA.
| |
Collapse
|
4
|
Kamalabadi F, Qin J, Harding BJ, Iliou D, Makela JJ, Meier RR, England SL, Frey HU, Mende SB, Immel TJ. Inferring Nighttime Ionospheric Parameters With the Far Ultraviolet Imager Onboard the Ionospheric Connection Explorer. Space Sci Rev 2018; 214:70. [PMID: 33795893 PMCID: PMC8011574 DOI: 10.1007/s11214-018-0502-9] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/11/2017] [Accepted: 03/30/2018] [Indexed: 06/02/2023]
Abstract
The Ionospheric Connection Explorer (ICON) Far Ultraviolet (FUV) imager, ICON FUV, will measure altitude profiles of OI 135.6 nm emissions to infer nighttime ionospheric parameters. Accurate estimation of the ionospheric state requires the development of a comprehensive radiative transfer model from first principles to quantify the effects of physical processes on the production and transport of the 135.6 nm photons in the ionosphere including the mutual neutralization contribution as well as the effect of resonant scattering by atomic oxygen and pure absorption by oxygen molecules. This forward model is then used in conjunction with a constrained optimization algorithm to invert the anticipated ICON FUV line-of-sight integrated measurements. In this paper, we describe the connection between ICON FUV measurements and the nighttime ionosphere, along with the approach to inverting the measured emission profiles to derive the associated O+ profiles from 150-450 km in the nighttime ionosphere that directly reflect the electron density in the F-region of the ionosphere.
Collapse
Affiliation(s)
- Farzad Kamalabadi
- Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, 1308 West Main Street, Urbana, IL 61801
| | | | | | | | | | | | | | | | | | | |
Collapse
|
5
|
Abstract
While assistive robot technology is quickly progressing, several challenges remain to make this technology truly usable and useful for humans. One of the aspects that is particularly important is in defining control protocols that allow both the human and the robot technology to contribute to the best of their abilities. In this paper we propose a framework for the collaborative control of a smart wheelchair designed for individuals with mobility impairments. Our approach is based on a decision-theoretic model of control, and accepts commands from both the human user and robot controller. We use a Partially Observable Markov Decision Process to optimize the collaborative action choice, which allows the system to take into account uncertainty in the user intent, in the command and in the environment. The system is deployed and validated on the SmartWheeler platform, and experiments with 8 users show the improvement in usability and navigation efficiency that are achieved with this form of collaborative control.
Collapse
Affiliation(s)
- Mahmoud Ghorbel
- Department of Electrical Engineering, Polytechnique Montréal, Canada
| | - Joelle Pineau
- School of Computer Science, McGill University, Canada
| | - Richard Gourdeau
- Department of Electrical Engineering, Polytechnique Montreal,Canada
| | | | | |
Collapse
|
6
|
Raouafi NE, Patsourakos S, Pariat E, Young PR, Sterling A, Savcheva A, Shimojo M, Moreno-Insertis F, DeVore CR, Archontis V, Török T, Mason H, Curdt W, Meyer K, Dalmasse K, Matsui Y. Solar Coronal Jets: Observations, Theory, and Modeling. Space Sci Rev 2016; 201:1-53. [PMID: 32908324 PMCID: PMC7477949 DOI: 10.1007/s11214-016-0260-5] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Chromospheric and coronal jets represent important manifestations of ubiquitous solar transients, which may be the source of significant mass and energy input to the upper solar atmosphere and the solar wind. While the energy involved in a jet-like event is smaller than that of "nominal" solar flares and Coronal Mass Ejections (CMEs), jets share many common properties with these major phenomena, in particular, the explosive magnetically driven dynamics. Studies of jets could, therefore, provide critical insight for understanding the larger, more complex drivers of the solar activity. On the other side of the size-spectrum, the study of jets could also supply important clues on the physics of transients close or at the limit of the current spatial resolution such as spicules. Furthermore, jet phenomena may hint to basic process for heating the corona and accelerating the solar wind; consequently their study gives us the opportunity to attack a broad range of solar-heliospheric problems.
Collapse
Affiliation(s)
- N. E. Raouafi
- The Johns Hopkins University Applied Physics Laboratory, Laurel, MD 20723, USA
| | - S. Patsourakos
- Department of Physics, University of Ioannina, Ioannina, Greece
| | - E. Pariat
- LESIA, Observatoire de Paris, Meudon, France
| | - P. R. Young
- College of Science, George Mason University, Fairfax, VA, USA. NASA/Goddard Space Flight Center, Code 671, Greenbelt, MD 20771, USA
| | - A. Sterling
- NASA/Marshall Space Flight Center, Huntsville, Alabama, USA
| | - A. Savcheva
- Harvard-Smithsonian Center for Astrophysics, Cambridge, MA, USA
| | - M. Shimojo
- National Astronomical Observatory of Japan, Mitaka, Tokyo, Japan
| | | | - C. R. DeVore
- Heliophysics Science Division, NASA Goddard Space Flight Center, Greenbelt, MD, USA
| | - V. Archontis
- School of Mathematics and Statistics, University of St. Andrews, St. Andrews, UK
| | - T. Török
- Predictive Science Inc., 9990 Mesa Rim Rd., Ste. 170, San Diego, CA 92121, USA
| | - H. Mason
- DAMTP, Centre for Mathematical Sciences, University of Cambridge, Cambridge, UK
| | - W. Curdt
- Max-Planck-Institut für Sonnensystemforschung, Göttingen, Germany
| | - K. Meyer
- Division of Computing and Mathematics, Abertay University, Dundee, UK
| | - K. Dalmasse
- LESIA, Observatoire de Paris, Meudon, France
- CISL/HAO, NCAR, P.O. Box 3000, Boulder, CO 80307-3000, USA
| | - Y. Matsui
- Department of Earth and Planetary Science, University of Tokyo, Tokyo, Japan
| |
Collapse
|