The medical record for a neuro-oncology patient is complex, consisting of typically a large number of both text and imaging data. It includes descriptions of prior observations, interpretations, and interventions which need to be integrated into decisions regarding current patient care. An appropriate review of a patient's medical record often requires that a physician review multiple clinical documents while mentally noting issues related to what the findings were, the chronology of events, spatial/temporal patterns of disease progression, the effects of interventions, and the possible causal lines of explanation of observed findings. Additionally, imaging data and imaging- derived conclusions are poorly integrated into patient care and management decisions. The physician also needs to filter out those pieces of information not related to the current clinical context of care. Given the time constraints, data complexity and data volume associated with chronic patient cases, an appropriate review of a patient's chart is in reality rarely performed. Additionally, the lack of tools for formalizing the representation of the accounts of current and prior cases impedes the development of clinical databases that can be ultimately used to learn patterns of disease. This proposal addresses the development of a system for facilitating the review of clinical patient data intended to promote an orderly process of medical problem understanding and care.
The specific aims of the proposal are summarized as follows: 1) Development of a backend tool to facilitate the structured representation of observations, events, and inferences stated within medical reports. 2) Development of an application interface for visualizing, navigating, and editing structured patient data. 3) Evaluation of the effectiveness of the application in the domain of neuro-oncology. Relation to public health. If the goals of this proposal can be realized, neuro-oncologist should be able to more easily seek desired patient data and detect patterns of evidence as compared to the current mode of operation (HIS, RIS, PACS). The structuring tools should lead to improvements in the quality of clinical research databases.
Medical records for neuro-oncology patients are difficult to review due to volume and complexity of information. A novel system for partitioning data along the information axes of space, time, existence, and causality is proposed to improve navigation and assimilation of data within the medical record.
| Garcia-Gathright, Jean I; Matiasz, Nicholas J; Adame, Carlos et al. (2018) Evaluating Casama: Contextualized semantic maps for summarization of lung cancer studies. Comput Biol Med 92:55-63 |
| Garcia-Gathright, Jean I; Matiasz, Nicholas J; Garon, Edward B et al. (2016) Toward patient-tailored summarization of lung cancer literature. IEEE EMBS Int Conf Biomed Health Inform 2016:449-452 |
| Garcia-Gathright, Jean I; Oh, Andrea; Abarca, Phillip A et al. (2015) Representing and extracting lung cancer study metadata: study objective and study design. Comput Biol Med 58:63-72 |
| Pearl, Judea (2014) Interpretation and identification of causal mediation. Psychol Methods 19:459-81 |
| Pearl, Judea (2014) Reply to commentary by Imai, Keele, Tingley, and Yamamoto concerning causal mediation analysis. Psychol Methods 19:488-92 |
| Tong, Maurine; Hsu, William; Taira, Ricky K (2013) A formal representation for numerical data presented in published clinical trial reports. Stud Health Technol Inform 192:856-60 |
| Hsu, William; Speier, William; Taira, Ricky K (2012) Automated extraction of reported statistical analyses: towards a logical representation of clinical trial literature. AMIA Annu Symp Proc 2012:350-9 |
| Pearl, Judea (2012) The causal mediation formula--a guide to the assessment of pathways and mechanisms. Prev Sci 13:426-36 |
| Hsu, William; Taira, Ricky K; El-Saden, Suzie et al. (2012) Context-based electronic health record: toward patient specific healthcare. IEEE Trans Inf Technol Biomed 16:228-34 |
| Speier, William; Iglesias, Juan E; El-Kara, Leila et al. (2011) Robust skull stripping of clinical glioblastoma multiforme data. Med Image Comput Comput Assist Interv 14:659-66 |
Showing the most recent 10 out of 18 publications
