Study Objective: Machine-learning algorithms allow improved prediction of sepsis syndromes in the emergency department (ED), using data from electronic medical records. Transfer learning, a new subfield of machine learning, allows generalizability of an algorithm across clinical sites. We aim to validate the Artificial Intelligence Sepsis Expert for the prediction of delayed septic shock in a cohort of patients treated in the ED and demonstrate the feasibility of transfer learning to improve external validity at a second site.

Methods: This was an observational cohort study using data from greater than 180,000 patients from 2 academic medical centers between 2014 and 2019, using multiple definitions of sepsis. The Artificial Intelligence Sepsis Expert algorithm was trained with 40 input variables at the development site to predict delayed septic shock (occurring greater than 4 hours after ED triage) at various prediction windows. We then validated the algorithm at a second site, using transfer learning to demonstrate generalizability of the algorithm.

Results: We identified 9,354 patients with severe sepsis, of whom 723 developed septic shock at least 4 hours after triage. The Artificial Intelligence Sepsis Expert algorithm demonstrated excellent area under the receiver operating characteristic curve (>0.8) at 8 and 12 hours for the prediction of delayed septic shock. Transfer learning significantly improved the test characteristics of the Artificial Intelligence Sepsis Expert algorithm and yielded comparable performance at the validation site.

Conclusion: The Artificial Intelligence Sepsis Expert algorithm accurately predicted the development of delayed septic shock. The use of transfer learning allowed significantly improved external validity and generalizability at a second site. Future prospective studies are indicated to evaluate the clinical utility of this model.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8554871PMC
http://dx.doi.org/10.1016/j.annemergmed.2020.11.007DOI Listing

Publication Analysis

Top Keywords

septic shock
24
transfer learning
20
artificial intelligence
20
intelligence sepsis
20
sepsis expert
20
delayed septic
16
expert algorithm
16
emergency department
8
sepsis
8
prediction delayed
8

Similar Publications

Febrile neutropenia is a major complication in patients with acute leukemia or those undergoing hematopoietic stem cell transplantation (HSCT). Understanding patient characteristics and susceptibility patterns in febrile neutropenia is essential for appropriate antimicrobial therapy. First-line agents should have Pseudomonas aeruginosa coverage, but with the increase in multi-drug resistant organisms, ceftazidime-avibactam has emerged as a new therapeutic option.

View Article and Find Full Text PDF

Background: Invasive fungal infections have been reported as complications with significant mortality and morbidity in patients hospitalized with COVID-19. This study aimed to evaluate the clinical characteristics and outcomes of candidaemia patients with COVID-19 and to investigate the association between COVID-19 and mortality in candidaemia patients.

Methods: This retrospective study included candidaemia patients aged 18 years or older admitted to four university-affiliated tertiary hospitals in South Korea between January 1, 2020, and December 31, 2022.

View Article and Find Full Text PDF

Background: Robotic-assisted bariatric surgery is growing rapidly. The optimal approach to minimize complications remains unclear.

Objective: Assess robot utilization and compare 30-day outcomes for laparoscopic and robotic primary sleeve gastrectomy (SG) and Roux-en-Y gastric bypass (RYGB) using the Metabolic and Bariatric Surgery Accreditation and Quality Improvement Program (MBSAQIP) database.

View Article and Find Full Text PDF

Brentuximab vedotin (BV)-bendamustine (90 or 120 mg/m2 day 1 and 2) every 28 days is an effective treatment for relapsed/refractory Hodgkin lymphoma (R/R HL) but associated to high toxicity especially for elderly patients. We conducted in St Louis Hospital, Paris, between 2015 and 2021 a retrospective single-center analysis of 44 patients with R/R HL treated with one-day BV-bendamustine (120 mg/m2) every 21 days. Sixteen percent of patients were ≥ 60 years old (yo).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!