Data mining critical care data: SSRIs and mortality in ICU

September 30, 2014 − by Suzanne Elvidge − in Big data, Big data in research, Data analytics, Data mining, Healthcare big data analysis − No Comments

Patients in ICU (intensive care units) are particularly vulnerable, and any clues to ways of improving their outcomes are important. Mined data from patient records suggests that previous use of certain drugs could have an effect on outcomes for patients, showing that having access to large databases of medical records could help doctors better diagnose and treat patients.

“Historically, there has been no system to capture, store and share the massive amount of information generated during patient care. Giving providers easy access to a national or international database of information gathered during the practice of medicine would transform health care”, says Dr. David J. Stone of the departments of anaesthesiology and neurosurgery and the Center for Wireless Health at the University of Virginia.

Selective serotonin reuptake inhibitors (SSRIs) are the most commonly prescribed antidepressants, but they have been linked with haemorrhage, stroke, and increased death rates. A team of US researchers, including from the University of Virginia, used data mining to search the publicly available Multiparameter Intelligent Monitoring in Intensive Care (MIMIC) 2.6 database, analysing 14,709 patient records (2471 in the SSRI/SNRI group and 12,238 in the control group) for in-hospital mortality. The data was published in CHEST.

The analysis showed that patients’ use of SSRIs or SNRIs (serotonin-norepinephrine reuptake inhibitors) before admission were linked with significantly increases in death in hospital. In particular, the risk was highest in patients with acute coronary syndrome, and in patients admitted to the cardiac surgery recovery unit. The death rate appeared to increase with higher levels of serotonin inhibition.

“Although our study looked at the impact of specific drugs on a particular type of patient, it has broad importance. It demonstrated the general systems solution of how data mining can benefit health care,” Stone said. “By leveraging the knowledge gained from caring for individuals, the medical community will be able to provide better care and outcomes to all patients.”

Post a Comment

Your email address will not be published. Required fields are marked *