Predicting sepsis-related mortality and ICU admissions from telephone triage information of patients presenting to out-of-hours GP cooperatives with acute infections: A cohort study of linked routine care databases

• Published in: PloS one Vol. 18; no. 12; p. e0294557
• Main Authors: Loots, Feike J, Smits, Marleen, Jenniskens, Kevin, Leeuwenberg, Artuur M, Giesen, Paul H J, Ramerman, Lotte, Verheij, Robert, van Zanten, Arthur R H, Venekamp, Roderick P
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.12.2023; Public Library of Science (PLoS)
• Subjects: Antibiotics; Biology and Life Sciences; Care and treatment; Cohort analysis; Complaints; Computer and Information Sciences; Cooperatives; Diagnosis; Dyspnea; Evaluation; Family medicine; Hospitals; Infection; Infections; Learning algorithms; Machine learning; Medical research; Medicine; Medicine and Health Sciences; Medicine, Experimental; Mortality; Netherlands; Neural networks; Patient admissions; Patient outcomes; Patients; Physical Sciences; Physicians (General practice); Practice; Prediction models; Primary care; Probability learning; Regression analysis; Regression models; Research and Analysis Methods; Sepsis; Statistical analysis; Subgroups; Triage (Medicine); Netherlands
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0294557

General practitioners (GPs) often assess patients with acute infections. It is challenging for GPs to recognize patients needing immediate hospital referral for sepsis while avoiding unnecessary referrals. This study aimed to predict adverse sepsis-related outcomes from telephone triage information of patients presenting to out-of-hours GP cooperatives. A retrospective cohort study using linked routine care databases from out-of-hours GP cooperatives, general practices, hospitals and mortality registration. We included adult patients with complaints possibly related to an acute infection, who were assessed (clinic consultation or home visit) by a GP from a GP cooperative between 2017-2019. We used telephone triage information to derive a risk prediction model for sepsis-related adverse outcome (infection-related ICU admission within seven days or infection-related death within 30 days) using logistic regression, random forest, and neural network machine learning techniques. Data from 2017 and 2018 were used for derivation and from 2019 for validation. We included 155,486 patients (median age of 51 years; 59% females) in the analyses. The strongest predictors for sepsis-related adverse outcome were age, type of contact (home visit or clinic consultation), patients considered ABCD unstable during triage, and the entry complaints"general malaise", "shortness of breath" and "fever". The multivariable logistic regression model resulted in a C-statistic of 0.89 (95% CI 0.88-0.90) with good calibration. Machine learning models performed similarly to the logistic regression model. A "sepsis alert" based on a predicted probability >1% resulted in a sensitivity of 82% and a positive predictive value of 4.5%. However, most events occurred in patients receiving home visits, and model performance was substantially worse in this subgroup (C-statistic 0.70). Several patient characteristics identified during telephone triage of patients presenting to out-of-hours GP cooperatives were associated with sepsis-related adverse outcomes. Still, on a patient level, predictions were not sufficiently accurate for clinical purposes.