Data collected from intensive care units could be used to guide decision-making in real-time, but instead have often led to overwhelmed clinicians trying to uncover the signal buried in the noise. This data deluge is particularly challenging when the data are delayed, as this can lead to events being incorrectly seen as simultaneous or even out of order. Patients' health also changes at different time scales such as due to a new medication or circadian rhythms. Thus as doctors attempt to integrate the many signals to understand a patient's status, their health is a moving target. To transform the data into actionable knowledge, it is also not enough to find correlations. We must be sure that the patterns we find are truly causal to avoid treating symptoms instead of a disease or launching unsuccessful clinical trials. Our prior work, though, has found that ICU data streams can in fact be used to gain insight into recovery from stroke. In particular, we revealed that nonconvulsive seizures may be related to poor outcomes in patients with subarachnoid hemorrhage (SAH). Unlike epileptic seizures, which have a sudden onset, these seizures begin gradually, making them difficult to detect automatically. Further, many SAH patients in our study were unconscious on admission, and it is difficult to frequently and reliably assess consciousness. Therefore while progress has been made, two key barriers to using ICU data to guide treatment are a) a lack of methods for finding gradual changes in a patient's state (which could be used to alert clinicians) and b) finding causal relationships with uncertain data (where the cause may be documented as happening after the effect). To address these challenges, our specific aims are 1) to develop methods for finding timing uncertainty for each variable and using this in causal inference, 2) to develop real-time methods for finding when things change, and 3) to apply these to find when stroke patients have seizures or changes in consciousness, so these can be quickly identified and treated. We propose that by learning the reasons for errors in data, and by developing methods that specifically model their uncertain and changing nature, we will enable better use of large-scale observational biomedical data for real-time treatment decisions.

Public Health Relevance

Big data may aid in developing more precise, individualized, interventions for patients in the ICU, but it is challenging for clinicians to integrate a large number of complex signals in real-time. Our work may improve this by learning when major changes are happening (such as regaining consciousness) and identifying errors in the data. In applying the methods to data from stroke patients, we aim to quickly detect seizures and the effects of medications, leading to better treatment.

Agency
National Institute of Health (NIH)
Institute
National Library of Medicine (NLM)
Type
Research Project (R01)
Project #
5R01LM011826-06
Application #
9494683
Study Section
Biomedical Library and Informatics Review Committee (BLR)
Program Officer
Sim, Hua-Chuan
Project Start
2013-06-01
Project End
2020-05-31
Budget Start
2018-06-01
Budget End
2019-05-31
Support Year
6
Fiscal Year
2018
Total Cost
Indirect Cost
Name
Stevens Institute of Technology
Department
Biostatistics & Other Math Sci
Type
Biomed Engr/Col Engr/Engr Sta
DUNS #
064271570
City
Hoboken
State
NJ
Country
United States
Zip Code
Morris, Nicholas A; Robinson, David; Schmidt, J Michael et al. (2018) Hunt-Hess 5 subarachnoid haemorrhage presenting with cardiac arrest is associated with larger volume bleeds. Resuscitation 123:71-76
Zheng, Min; Claassen, Jan; Kleinberg, Samantha (2018) Automated Identification of Causal Moderators in Time-Series Data. Proc Mach Learn Res 92:4-22
Reznik, Michael E; Mahta, Ali; Schmidt, J Michael et al. (2018) Duration of Agitation, Fluctuations of Consciousness, and Associations with Outcome in Patients with Subarachnoid Hemorrhage. Neurocrit Care 29:33-39
Witsch, Jens; Frey, Hans-Peter; Schmidt, J Michael et al. (2017) Electroencephalographic Periodic Discharges and Frequency-Dependent Brain Tissue Hypoxia in Acute Brain Injury. JAMA Neurol 74:301-309
Hum, R Stanley; Kleinberg, Samantha (2017) Replicability, Reproducibility, and Agent-based Simulation of Interventions. AMIA Annu Symp Proc 2017:959-968
Reznik, Michael E; Schmidt, J Michael; Mahta, Ali et al. (2017) Agitation After Subarachnoid Hemorrhage: A Frequent Omen of Hospital Complications Associated with Worse Outcomes. Neurocrit Care 26:428-435
Mikell, Charles B; Dyster, Timothy G; Claassen, Jan (2016) Invasive seizure monitoring in the critically-Ill brain injury patient: Current practices and a review of the literature. Seizure 41:201-5
Claassen, Jan; Rahman, Shah Atiqur; Huang, Yuxiao et al. (2016) Causal Structure of Brain Physiology after Brain Injury from Subarachnoid Hemorrhage. PLoS One 11:e0149878
Claassen, Jan; Velazquez, Angela; Meyers, Emma et al. (2016) Bedside quantitative electroencephalography improves assessment of consciousness in comatose subarachnoid hemorrhage patients. Ann Neurol 80:541-53
Heintzman, Nathaniel; Kleinberg, Samantha (2016) Using uncertain data from body-worn sensors to gain insight into type 1 diabetes. J Biomed Inform 63:259-268

Showing the most recent 10 out of 11 publications