scholarly journals Evaluating Adoption, Impact, and Factors Driving Adoption for TREWS, a Machine Learning-Based Sepsis Alerting System

2021 ◽  
Author(s):  
Katharine E Henry ◽  
Roy Adams ◽  
Cassandra Parent ◽  
Anirudh Sridharan ◽  
Lauren Johnson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Warning System ◽  
Clinical Decision ◽  
Related Factors ◽  
Support Tools ◽  
Alerting System ◽  
Risk Patients ◽  
Provider Knowledge ◽  
Clinical Decision Support Tools

Machine learning-based clinical decision support tools for sepsis create opportunities to identify at-risk patients and initiate treatments earlier, an important step in improving sepsis outcomes. Increasing use of such systems means quantifying and understanding provider adoption is critical. Using real-time provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System) deployed at five hospitals over a two-year period (469,419 screened patient encounters, 9,805 (2.1%) of which were retrospectively identified as having sepsis), we found high adoption rates (89% of alerts were evaluated by a physician or advanced practice provider) and an association between use of the tool and earlier treatment of sepsis patients (1.85 (95% CI: 1.66 - 2.00) hour reduction in median time to first antibiotics order). Further, we found that provider-related factors had the strongest association with alert adoption and that case complexity and atypical presentation were associated with dismissal of alerts on sepsis patients. Beyond improving the performance of the system, efforts to improve adoption should focus on provider knowledge, experience, and perceptions of the system.

scholarly journals 72. Improving Antibiotic Prescribing in Interventional Radiology Using Clinical Decision Support Tools to Assess Penicillin Allergies

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S54-S54
Author(s):  
Vidya Atluri ◽  
Paula Marsland ◽  
Luke M Johnson ◽  
Rupali Jain ◽  
Paul Pottinger ◽  
...  
Keyword(s):  
Interventional Radiology ◽  
Decision Support ◽  
Clinical Decision Support ◽  
Clinical Decision ◽  
Prophylactic Antibiotics ◽  
Decision Support Tools ◽  
First Line ◽  
Support Tools ◽  
History Of ◽  
Clinical Decision Support Tools

Abstract Background Patients labeled with penicillin allergies often receive alternative antibiotics, leading to increased cost, higher risk of adverse events, and decreased efficacy of procedural prophylaxis. However, most of those patients can tolerate a cephalosporin. University of Washington Medical Center – Montlake (UWMC-ML) Interventional Radiology (IR) frequently administer a pre-procedure prophylactic cephalosporin. We worked with the clinicians in IR to develop tools to allow them to better assess penicillin allergies, make the most appropriate antibiotic choice, and update the patient’s allergy documentation. Methods We identified all patients who underwent procedures in IR between 2017–2019. Chart review was done to determine the procedures performed, patient demographic information, allergies, allergy documentation, and prophylactic antibiotics received. In May 2020 we implemented new Clinical Decision Support tools, including an online assessment app (https://tinyurl.com/IRPCNAllAssess) and handouts to guide antibiotic decision making to clinicians in IR. Results From 2017 to 2019, 381 patients underwent 958 procedures in IR. Of those, 379 patients underwent 496 procedures for which the recommended first line choice for antibiotic prophylaxis is a cephalosporin. Of patients who received pre-procedure prophylactic antibiotics for those procedures, 15.9% [n=11] of patients with penicillin allergies received the first line antibiotic, compared to 89.9% [n=319] of patients without a reported penicillin allergy. Since implementation, the online app has been used to evaluate 9 patients, of whom 8 had penicillin allergies. All 8 patients safely received the first line antibiotic (3 were delabeled, 4 reported a history of mild reactions, and 1 reported a history of an immediate IgE mediated response to penicillin but safely received cefazolin). Conclusion IR evaluates hundreds of patients who may receive prophylactic antibiotics each year. By providing tools to assess penicillin allergies, we were able to improve both their prescribing and de-label patients which will provide a much broader impact on their care than on just their current procedure. Our free tool can be accessed at the website above, and we will demonstrate in person. Disclosures All Authors: No reported disclosures

Effect of a Real-Time Risk Score on 30-day Readmission Reduction in Singapore

2021 ◽  
Vol 12 (02) ◽  
pp. 372-382
Author(s):  
Christine Xia Wu ◽  
Ernest Suresh ◽  
Francis Wei Loong Phng ◽  
Kai Pik Tai ◽  
Janthorn Pakdeethai ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Real Time ◽  
Risk Score ◽  
Patient Specific ◽  
Learning Models ◽  
Medicine Department ◽  
High Risk Patients ◽  
Risk Patients ◽  
Machine Learning Models

Abstract Objective To develop a risk score for the real-time prediction of readmissions for patients using patient specific information captured in electronic medical records (EMR) in Singapore to enable the prospective identification of high-risk patients for enrolment in timely interventions. Methods Machine-learning models were built to estimate the probability of a patient being readmitted within 30 days of discharge. EMR of 25,472 patients discharged from the medicine department at Ng Teng Fong General Hospital between January 2016 and December 2016 were extracted retrospectively for training and internal validation of the models. We developed and implemented a real-time 30-day readmission risk score generation in the EMR system, which enabled the flagging of high-risk patients to care providers in the hospital. Based on the daily high-risk patient list, the various interfaces and flow sheets in the EMR were configured according to the information needs of the various stakeholders such as the inpatient medical, nursing, case management, emergency department, and postdischarge care teams. Results Overall, the machine-learning models achieved good performance with area under the receiver operating characteristic ranging from 0.77 to 0.81. The models were used to proactively identify and attend to patients who are at risk of readmission before an actual readmission occurs. This approach successfully reduced the 30-day readmission rate for patients admitted to the medicine department from 11.7% in 2017 to 10.1% in 2019 (p < 0.01) after risk adjustment. Conclusion Machine-learning models can be deployed in the EMR system to provide real-time forecasts for a more comprehensive outlook in the aspects of decision-making and care provision.

scholarly journals Model-Informed Precision Dosing: Background, Requirements, Validation, Implementation, and Forward Trajectory of Individualizing Drug Therapy

2021 ◽  
Vol 61 (1) ◽  
pp. 225-245 ◽  
Author(s):  
Adam S. Darwich ◽  
Thomas M. Polasek ◽  
Jeffrey K. Aronson ◽  
Kayode Ogungbenro ◽  
Daniel F.B. Wright ◽  
...  
Keyword(s):  
Drug Therapy ◽  
Current Knowledge ◽  
Clinical Care ◽  
Clinical Decision ◽  
Decision Support Tools ◽  
Support Tools ◽  
Drug Regulations ◽  
The Common ◽  
Clinical Decision Support Tools ◽  
Practical Validation

Model-informed precision dosing (MIPD) has become synonymous with modern approaches for individualizing drug therapy, in which the characteristics of each patient are considered as opposed to applying a one-size-fits-all alternative. This review provides a brief account of the current knowledge, practices, and opinions on MIPD while defining an achievable vision for MIPD in clinical care based on available evidence. We begin with a historical perspective on variability in dose requirements and then discuss technical aspects of MIPD, including the need for clinical decision support tools, practical validation, and implementation of MIPD in health care. We also discuss novel ways to characterize patient variability beyond the common perceptions of genetic control. Finally, we address current debates on MIPD from the perspectives of the new drug development, health economics, and drug regulations.

scholarly journals 1475. Understanding Prescribing Practices for Uncomplicated Urinary Tract Infections (UTIs) in the Primary Care Setting: A Pilot Study

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S538-S538
Author(s):  
Mark Pinkerton ◽  
Jahnavi Bongu ◽  
Aimee James ◽  
Michael Durkin
Keyword(s):  
Primary Care ◽  
Urinary Tract ◽  
Urinary Tract Infections ◽  
Clinical Decision ◽  
Primary Care Providers ◽  
Care Providers ◽  
Prescribing Practices ◽  
Support Tools ◽  
Tract Infections ◽  
Clinical Decision Support Tools

Abstract Background Uncomplicated urinary tract infections (UTIs) should be treated empirically with a short course of narrow-spectrum antibiotics. However, many clinicians order unnecessary tests and treat with long courses of antibiotics. The objective of this study was to understand how internists clinically approach UTIs. Methods We conducted semi-structured qualitative interviews of community primary care providers (n = 15) and internal medicine residents (n = 15) in St. Louis, Missouri from 2018 to 2019 to explore why clinical practices deviate from evidence-based guidelines. Interviews were transcribed, de-identified, and coded by two independent researchers using NVivo qualitative software. A Likert scale was used to evaluate preferences for possible interventions. Results Several common themes emerged. Both providers and residents ordered urine tests to “confirm” presence of urinary tract infections. Antibiotic prescriptions were often based on historical practice and anecdotal experience. Providers were more comfortable treating over the phone than residents and tended to prescribe longer courses of antibiotics. Both providers and residents voiced frustrations with guidelines being difficult to easily incorporate due to length and extraneous information. Preferences for receiving and incorporating guidelines into practice varied. Both groups felt benchmarking would improve prescribing practices, but had reservations about implementation. Pragmatic clinical decision support tools were favored by providers, with residents preferring order sets and attendings preferring nurse triage algorithms. Conclusion Misconceptions regarding urinary tract infection management were common among residents and community primary care providers. Multifaceted interventions that include provider education, synthesis of guidelines, and pragmatic clinical decision support tools are needed to improve antibiotic prescribing and diagnostic testing; optimal interventions to improve UTI management may vary based on provider training level. Disclosures All authors: No reported disclosures.

Sign in / Sign up

Export Citation Format

Share Document