Melissa A Davis1, Balaji Rao1, Paul A Cedeno1, Atin Saha1, Vahe M Zohrabian2. 1. Department of Radiology and Biomedical Imaging ,Yale School of Medicine, Yale University, New Haven, CT 06520. 2. Department of Radiology and Biomedical Imaging ,Yale School of Medicine, Yale University, New Haven, CT 06520.. Electronic address: vahe.zohrabian@gmail.com.
Abstract
OBJECTIVE: The timely reporting of critical results in radiology is paramount to improved patient outcomes. Artificial intelligence has the ability to improve quality by optimizing clinical radiology workflows. We sought to determine the impact of a United States Food and Drug Administration-approved machine learning (ML) algorithm, meant to mark computed tomography (CT) head examinations pending interpretation as higher probability for intracranial hemorrhage (ICH), on metrics across our healthcare system. We hypothesized that ML is associated with a reduction in report turnaround time (RTAT) and length of stay (LOS) in emergency department (ED) and inpatient populations. MATERIALS AND METHODS: An ML algorithm was incorporated across CT scanners at imaging sites in January 2018. RTAT and LOS were derived for reports and patients between July 2017 and December 2017 prior to implementation of ML and compared to those between January 2018 and June 2018 after implementation of ML. A total of 25,658 and 24,996 ED and inpatient cases were evaluated across the entire healthcare system before and after ML, respectively. RESULTS: RTAT decreased from 75 to 69 minutes (P <0.001) at all facilities in the healthcare system. At the level 1 trauma center specifically, RTAT decreased from 67 to 59 minutes (P <0.001). ED LOS decreased from 471 to 425 minutes (P <0.001) for patients without ICH, and from 527 to 491 minutes for those with ICH (P = 0.456). Inpatient LOS decreased from 18.4 to 15.8 days for those without ICH (P = 0.001) and 18.1 to 15.8 days for those with ICH (P = 0.02). CONCLUSION: We demonstrated that utilization of ML was associated with a statistically significant decrease in RTAT. There was also a significant decrease in LOS for ED patients without ICH, but not for ED patients with ICH. Further evaluation of the impact of such tools on patient care and outcomes is needed.
OBJECTIVE: The timely reporting of critical results in radiology is paramount to improved patient outcomes. Artificial intelligence has the ability to improve quality by optimizing clinical radiology workflows. We sought to determine the impact of a United States Food and Drug Administration-approved machine learning (ML) algorithm, meant to mark computed tomography (CT) head examinations pending interpretation as higher probability for intracranial hemorrhage (ICH), on metrics across our healthcare system. We hypothesized that ML is associated with a reduction in report turnaround time (RTAT) and length of stay (LOS) in emergency department (ED) and inpatient populations. MATERIALS AND METHODS: An ML algorithm was incorporated across CT scanners at imaging sites in January 2018. RTAT and LOS were derived for reports and patients between July 2017 and December 2017 prior to implementation of ML and compared to those between January 2018 and June 2018 after implementation of ML. A total of 25,658 and 24,996 ED and inpatient cases were evaluated across the entire healthcare system before and after ML, respectively. RESULTS: RTAT decreased from 75 to 69 minutes (P <0.001) at all facilities in the healthcare system. At the level 1 trauma center specifically, RTAT decreased from 67 to 59 minutes (P <0.001). ED LOS decreased from 471 to 425 minutes (P <0.001) for patients without ICH, and from 527 to 491 minutes for those with ICH (P = 0.456). Inpatient LOS decreased from 18.4 to 15.8 days for those without ICH (P = 0.001) and 18.1 to 15.8 days for those with ICH (P = 0.02). CONCLUSION: We demonstrated that utilization of ML was associated with a statistically significant decrease in RTAT. There was also a significant decrease in LOS for ED patients without ICH, but not for ED patients with ICH. Further evaluation of the impact of such tools on patient care and outcomes is needed.
Authors: Muhannad Seyam; Thomas Weikert; Alexander Sauter; Alex Brehm; Marios-Nikos Psychogios; Kristine A Blackham Journal: Radiol Artif Intell Date: 2022-02-09
Authors: Malvika Sharma; Carl Savage; Monika Nair; Ingrid Larsson; Petra Svedberg; Jens M Nygren Journal: J Med Internet Res Date: 2022-10-05 Impact factor: 7.076