Diagnostic suspicion bias and machine learning: Breaking the awareness deadlock for sepsis detection.

Many early warning algorithms are downstream of clinical evaluation and diagnostic testing, which means that they may not be useful when clinicians fail to suspect illness and fail to order appropriate tests. Depending on how such algorithms handle missing data, they could even indicate "low risk" simply because the testing data were never ordered. We considered predictive methodologies to identify sepsis at triage, before diagnostic tests are ordered, in a busy Emergency Department (ED). One algorithm used "bland clinical data" (data available at triage for nearly every patient). The second algorithm added three yes/no questions to be answered after the triage interview. Retrospectively, we studied adult patients from a single ED between 2014-16, separated into training (70%) and testing (30%) cohorts, and a final validation cohort of patients from four EDs between 2016-2018. Sepsis was defined per the Rhee criteria. Investigational predictors were demographics and triage vital signs (downloaded from the hospital EMR); past medical history; and the auxiliary queries (answered by chart reviewers who were blinded to all data except the triage note and initial HPI). We developed L2-regularized logistic regression models using a greedy forward feature selection. There were 1164, 499, and 784 patients in the training, testing, and validation cohorts, respectively. The bland clinical data model yielded ROC AUC's 0.78 (0.76-0.81) and 0.77 (0.73-0.81), for training and testing, respectively, and ranged from 0.74-0.79 in four hospital validation. The second model which included auxiliary queries yielded 0.84 (0.82-0.87) and 0.83 (0.79-0.86), and ranged from 0.78-0.83 in four hospital validation. The first algorithm did not require clinician input but yielded middling performance. The second showed a trend towards superior performance, though required additional user effort. These methods are alternatives to predictive algorithms downstream of clinical evaluation and diagnostic testing. For hospital early warning algorithms, consideration should be given to bias and usability of various methods.

External validation of GO-FAR 2 calculator for outcomes after in-hospital cardiac arrest with comparison to GO-FAR and trial of expanded applications.

Aim: Externally validate the GO-FAR 2 tool for predicting survival with good neurologic function after in-hospital cardiac arrest with comparison to the original GO-FAR tool. Additionally, we collected qualitative descriptors and performed exploratory analyses with various levels of neurologic function and discharge destination. Methods: Retrospective chart review of all patients who underwent in-hospital resuscitation after cardiac arrest during the calendar years 2016-2019 in our institution (n = 397). GO-FAR and GO-FAR 2 scores were calculated based on information available in the medical record at the time of hospital admission. Cerebral performance category (CPC) scores at the time of admission and discharge were assessed by chart review. Results: The GO-FAR 2 score accurately predicted outcomes in our study population with a c-statistic of 0.625. The original GO-FAR score also had accurate calibration with a stronger c-statistic of 0.726. The GO-FAR score had decreased predictive value for lesser levels of neurologic function (c-statistic 0.56 for alive at discharge) and discharge destination (0.69). Descriptors of functional status by CPC score were collected. Conclusion: Our findings support the validity of the GO-FAR and GO-FAR 2 tools as published, but the c-statistics suggest modest predictive discrimination. We include functional descriptors of CPC outcomes to aid clinicians in using these tools. We propose that information about expected outcomes could be valuable in shared decision-making conversations.

Phlegmasia cerulea dolens causing compartment syndrome.

BACKGROUND: Phlegmasia cerulea dolens (PCD) is a rare condition characterized by a severely swollen, cyanotic, blue extremity due to a large proximal (iliofemoral) deep venous thrombosis extending into the collateral veins. Mortality in PCD ranges 20-40%. Due to severely compromised venous drainage, compartment pressures can rapidly increase 16-fold within 6 h, but rarely result in arterial compromise. CASE REPORT: We present a case of a middle-aged woman with no prior history of deep venous thrombosis, with a blue swollen left leg in intractable severe pain unresponsive to 3 doses of hydromorphone. Her pain was successfully alleviated with IV Lidocaine. Patient was found to have phlegmasia cerulea dolens resulting in compartment syndrome of her left leg. Although the patient initially had no motor function, after catheter-directed thrombolysis and emergent thrombectomy, she regained her motor function and made a full recovery. WHY SHOULD AN EMERGENCY PHYSICIAN BE AWARE OF THIS?: Phlegmasia cerulea dolens complicated by severe compartment syndrome is a rare entity. Prompt recognition and treatment are necessary to prevent irreversible limb ischemia and associated morbidity and mortality. IV Lidocaine may be considered as an option for analgesia for such patients.

Validation of a 'Usual Care' Model for Vasopressor Initiation in a Cohort of Emergency Department Patients with Sepsis.

Usual care regarding vasopressor (VP) initiation is ill-defined. We aimed to further validate a quantitative model for usual care in the Emergency Department (ED) regarding the timing of VP initiation in sepsis. We retrospectively studied a cohort of adult critically-ill ED patients who also received antibiotics in the ED. We applied a multivariable model previously developed from another patient cohort which distinguishes between time points at which patients were or were not subsequently started on a continuous VP infusion. The model has six independently significant predictors (respiratory rate, Glasgow Coma Scale score, systolic blood pressure, SpO2, administered intravenous fluids, and elapsed time). The outcome was initiation of VP infusion, either within the ED or within 6 hours after leaving the ED. We applied the model to all time points, beginning when all model input parameters were first available for a given patient, and ending when either VP were first started, or the patient left the ED. Out of 55,963 adult ED patients during the two-year study interval, we identified 1,629 who met our inclusion criteria. The area under the receiver operating characteristic curve was 0.81 for all patients, and 0.72 for the subset with at least one hypotensive blood pressure measurement. At a model threshold with sensitivity and specificity 0.74 and 0.74, respectively, the median advance detection time was 170.5 minutes (IQR 53 - 363).