Search All Research Studies
AHRQ Research Studies Date
AHRQ Research Studies
Sign up: AHRQ Research Studies Email updates
Research Studies is a monthly compilation of research articles funded by AHRQ or authored by AHRQ researchers and recently published in journals or newsletters.
Results1 to 4 of 4 Research Studies Displayed
Shi J, Hurdle JF, Johnson SA
Natural language processing for the surveillance of postoperative venous thromboembolism.
The objective of the study was to develop a portal natural language processing approach to aid in the identification of postoperative venous thromboembolism events from free-text clinical notes. The investigators concluded that accurate surveillance of postoperative venous thromboembolism may be achieved using natural language processing on clinical notes in 2 independent health care systems. They indicated that these findings suggest natural language processing may augment manual chart abstraction for large registries such as National Surgical Quality Improvement Program.
Citation: Shi J, Hurdle JF, Johnson SA . Natural language processing for the surveillance of postoperative venous thromboembolism. Surgery 2021 Oct;170(4):1175-82. doi: 10.1016/j.surg.2021.04.027..
Keywords: Blood Clots, Health Information Technology (HIT), Quality Improvement, Quality of Care, Surgery, Adverse Events
Zhu Y, Simon GJ, Wick EC
Applying machine learning across sites: external validation of a surgical site infection detection algorithm.
Surgical complications have tremendous consequences and costs. Complication detection is important for quality improvement, but traditional manual chart review is burdensome. Automated mechanisms are needed to make this more efficient. The purpose of the study was to understand the generalizability of a machine learning algorithm between sites; automated surgical site infection (SSI) detection algorithms developed at one center were tested at another distinct center.
Citation: Zhu Y, Simon GJ, Wick EC . Applying machine learning across sites: external validation of a surgical site infection detection algorithm. J Am Coll Surg 2021 Jun;232(6):963-71.e1. doi: 10.1016/j.jamcollsurg.2021.03.026..
Keywords: Healthcare-Associated Infections (HAIs), Surgery, Adverse Events, Diagnostic Safety and Quality, Electronic Health Records (EHRs), Health Information Technology (HIT), Quality Improvement, Quality of Care
Aasen DM, Bronsert Rozeboom, PD
Relationships between predischarge and postdischarge infectious complications, length of stay, and unplanned readmissions in the ACS NSQIP database.
This study looked at the relationships between predischarge and postdischarge infectious complications, length of stay, and unplanned hospital readmissions after surgery. Data from the American College of Surgeons National Surgical Quality Improvement database from 2012 to 2017 across nine surgical specialties was used to analyze 30-day postoperative infectious complications including sepsis, surgical site infections, pneumonia, and urinary tract infections. Postoperative infectious complications were identified in 5.2% of cases, of which 59.8% were postdischarge. The specific postdischarge complications identified were 73.4% of surgical site infections, 34.9% of sepsis cases, 26.5% of pneumonia cases, and 53.2% of urinary tract infections. These postoperative infections were associated with an increased risk of readmission. Most infections were diagnosed postdischarge. The trend towards shorter length of stays postoperation also contribute to the increase in infections detected after discharge and the rate of unplanned related postoperative readmissions.
Citation: Aasen DM, Bronsert Rozeboom, PD . Relationships between predischarge and postdischarge infectious complications, length of stay, and unplanned readmissions in the ACS NSQIP database. Surgery 2021 Feb;169(2):325-32. doi: 10.1016/j.surg.2020.08.009..
Keywords: Hospital Readmissions, Adverse Events, Healthcare-Associated Infections (HAIs), Infectious Diseases, Quality Improvement, Quality of Care, Surgery
Marshall TL, Ipsaro AJ, Le M
Increasing physician reporting of diagnostic learning opportunities.
This study investigated methods to improve physician reporting of diagnostic errors at the pediatric division of a hospital. In that pediatric hospital medicine (PHM) division only 1 diagnostic-related safety event was reported in the preceding 4 years. The authors aimed to improve attending physician reporting of suspected diagnostic errors from 0 to 2 per 100 PHM patient admissions within 6 months. The improvement team used the Model for Improvement and used the term diagnostic learning opportunity (DLO) with clinicians as opposed to diagnostic error to lessen the stigma. They developed an electronic reporting form and encouraged its use through reminders, scheduled reflection time, and monthly progress reports. Over the course of 13 weeks, there was an increase from 0 to 1.6 per patient admission reports files. Most events (66%) were true diagnostic errors.
Citation: Marshall TL, Ipsaro AJ, Le M . Increasing physician reporting of diagnostic learning opportunities. Pediatrics 2021 Jan;147(1). doi: 10.1542/peds.2019-2400..
Keywords: Children/Adolescents, Diagnostic Safety and Quality, Medical Errors, Adverse Events, Patient Safety, Hospitals, Quality Improvement, Quality of Care