Searching the Resource Information Network
Are you sure you want to leave this community? Leaving the community will revoke any permissions you have been granted in this community.
Deep learning algorithms have achieved human-equivalent performance in image recognition. However, the majority of clinical data within electronic health records is inherently in a non-image format. Therefore, creating visual representations of clinical data could facilitate using cutting-edge deep learning models for predicting outcomes such as in-hospital mortality, while enabling clinician interpretability. The objective of this study was to develop a framework that first transforms longitudinal patient data into visual timelines and then utilizes deep learning to predict in-hospital mortality.
Pubmed ID: 31365580
Publication data is provided by the National Library of Medicine ® and PubMed ®. Data is retrieved from PubMed ® on a weekly schedule. For terms and conditions see the National Library of Medicine Terms and Conditions.
NIGMS supports basic biomedical research that is not targeted to specific diseases. NIGMS funds studies on genes, proteins, and cells, as well as on fundamental processes like communication within and between cells, how our bodies use energy, and how we respond to medicines. The results of this research increase our understanding of life and lay the foundation for advances in disease diagnosis, treatment, and prevention. NIGMS also supports research training programs that produce the next generation of biomedical scientists, and it has special programs to encourage underrepresented minorities to pursue biomedical research careers. The National Institute of General Medical Sciences (NIGMS) primarily supports research that lays the foundation for advances in disease diagnosis, treatment, and prevention. The Institute's research training programs help provide the next generation of scientists. Each year, NIGMS-supported scientists make many advances in understanding fundamental life processes. In the course of answering basic research questions, these investigators increase our knowledge about the mechanisms and pathways involved in certain diseases. Institute grantees also develop important new tools and techniques, some of which have medical applications. In recognition of the significance of their work, a number of NIGMS grantees have received the Nobel Prize and other high scientific honors. At any given time, NIGMS supports approximately 4,700 research grants—approximately 11 percent of the grants funded by NIH as a whole. NIGMS also supports approximately 26 percent of the trainees who receive assistance from NIH. NIGMS also supports approximately 25% of the trainees who receive assistance from NIH. The Institute places great emphasis on supporting investigator-initiated research grants. It funds a limited number of research center grants in selected fields, including structural genomics, trauma and burn research, and systems biology. In addition, NIGMS supports several important scientific resources, including the NIGMS Human Genetic Cell Repository and the Protein Data Bank.
View all literature mentions