Azade Tabaie1, Evan W Orenstein2, Shamim Nemati3, Rajit K Basu2, Swaminathan Kandaswamy2, Gari D Clifford4, Rishikesan Kamaleswaran4. 1. Department of Biomedical Informatics, Emory School of Medicine, Atlanta, GA, USA. Electronic address: azade.tabaie@emory.edu. 2. Department of Pediatrics, Emory University School of Medicine, Atlanta, GA, USA. 3. Department of Biomedical Informatics, University of California San Diego, San Diego, CA, USA. 4. Department of Biomedical Informatics, Emory School of Medicine, Atlanta, GA, USA; Department of Biomedical Engineering, Georgia Institute of Technology and Emory School of Medicine, Atlanta, GA, USA.
Abstract
BACKGROUND: Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care. METHODS: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train machine learning models (XGBoost and ElasticNet) to predict the occurrence of PSI 8 h prior to clinical suspicion. Prediction for PSI was benchmarked against PRISM-III. RESULTS: Our model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI = [0.82, 0.85]), sensitivity of 0.73 [0.69, 0.74], and positive predictive value (PPV) of 0.36 [0.34, 0.36]. The PRISM-III conversely achieved a lower sensitivity of 0.19 [0.16, 0.22] and PPV of 0.30 [0.26, 0.34] at a cut-off of ≥ 10. The features with the most impact on the PSI prediction were maximum diastolic blood pressure prior to PSI prediction (mean SHAP = 3.4), height (mean SHAP = 3.2), and maximum temperature prior to PSI prediction (mean SHAP = 2.6). CONCLUSION: A machine learning model using common features in the electronic medical records can predict the onset of serious infections in children with central venous lines at least 8 h prior to when a clinical team drew a blood culture.
BACKGROUND: Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care. METHODS: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train machine learning models (XGBoost and ElasticNet) to predict the occurrence of PSI 8 h prior to clinical suspicion. Prediction for PSI was benchmarked against PRISM-III. RESULTS: Our model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI = [0.82, 0.85]), sensitivity of 0.73 [0.69, 0.74], and positive predictive value (PPV) of 0.36 [0.34, 0.36]. The PRISM-III conversely achieved a lower sensitivity of 0.19 [0.16, 0.22] and PPV of 0.30 [0.26, 0.34] at a cut-off of ≥ 10. The features with the most impact on the PSI prediction were maximum diastolic blood pressure prior to PSI prediction (mean SHAP = 3.4), height (mean SHAP = 3.2), and maximum temperature prior to PSI prediction (mean SHAP = 2.6). CONCLUSION: A machine learning model using common features in the electronic medical records can predict the onset of serious infections in children with central venous lines at least 8 h prior to when a clinical team drew a blood culture.
Authors: Scott M Lundberg; Gabriel Erion; Hugh Chen; Alex DeGrave; Jordan M Prutkin; Bala Nair; Ronit Katz; Jonathan Himmelfarb; Nisha Bansal; Su-In Lee Journal: Nat Mach Intell Date: 2020-01-17
Authors: Marlene R Miller; Michael Griswold; J Mitchell Harris; Gayane Yenokyan; W Charles Huskins; Michele Moss; Tom B Rice; Debra Ridling; Deborah Campbell; Peter Margolis; Stephen Muething; Richard J Brilli Journal: Pediatrics Date: 2010-01-11 Impact factor: 7.124
Authors: Chanu Rhee; Raymund Dantes; Lauren Epstein; David J Murphy; Christopher W Seymour; Theodore J Iwashyna; Sameer S Kadri; Derek C Angus; Robert L Danner; Anthony E Fiore; John A Jernigan; Greg S Martin; Edward Septimus; David K Warren; Anita Karcz; Christina Chan; John T Menchaca; Rui Wang; Susan Gruber; Michael Klompas Journal: JAMA Date: 2017-10-03 Impact factor: 56.272
Authors: Chanu Rhee; Sameer Kadri; Susan S Huang; Michael V Murphy; Lingling Li; Richard Platt; Michael Klompas Journal: Infect Control Hosp Epidemiol Date: 2015-11-03 Impact factor: 3.254
Authors: Sidney Le; Jana Hoffman; Christopher Barton; Julie C Fitzgerald; Angier Allen; Emily Pellegrini; Jacob Calvert; Ritankar Das Journal: Front Pediatr Date: 2019-10-11 Impact factor: 3.418