OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433.

Objective To create and validate a simple and transferable machine learning model from electronic health record data to accurately predict clinical deterioration in patients with covid-19 across institutions, through use of a novel paradigm for model development and code sharing. Design Retrospective cohort study. Setting One US hospital during 2015-21 was used for model training and internal validation. External validation was conducted on patients admitted to hospital with covid-19 at 12 other US medical centers during 2020-21. Participants 33 119 adults (≥18 years) admitted to hospital with respiratory distress or covid-19. Main outcome measures An ensemble of linear models was trained on the development cohort to predict a composite outcome of clinical deterioration within the first five days of hospital admission, defined as in-hospital mortality or any of three treatments indicating severe illness: mechanical ventilation, heated high flow nasal cannula, or intravenous vasopressors. The model was based on nine clinical and personal characteristic variables selected from 2686 variables available in the electronic health record. Internal and external validation performance was measured using the area under the receiver operating characteristic curve (AUROC) and the expected calibration error—the difference between predicted risk and actual risk. Potential bed day savings were estimated by calculating how many bed days hospitals could save per patient if low risk patients identified by the model were discharged early. Results 9291 covid-19 related hospital admissions at 13 medical centers were used for model validation, of which 1510 (16.3%) were related to the primary outcome. When the model was applied to the internal validation cohort, it achieved an AUROC of 0.80 (95% confidence interval 0.77 to 0.84) and an expected calibration error of 0.01 (95% confidence interval 0.00 to 0.02). Performance was consistent when validated in the 12 external medical centers (AUROC range 0.77-0.84), across subgroups of sex, age, race, and ethnicity (AUROC range 0.78-0.84), and across quarters (AUROC range 0.73-0.83). Using the model to triage low risk patients could potentially save up to 7.8 bed days per patient resulting from early discharge. Conclusion A model to predict clinical deterioration was developed rapidly in response to the covid-19 pandemic at a single hospital, was applied externally without the sharing of data, and performed well across multiple medical centers, patient subgroups, and time periods, showing its potential as a tool for use in optimizing healthcare resources.

Objective: To describe the incidence of systemic overlap and typical coronavirus disease 2019 (COVID-19) symptoms in healthcare personnel (HCP) following COVID-19 vaccination and association of reported symptoms with diagnosis of severe acute respiratory coronavirus virus 2 (SARS-CoV-2) infection in the context of public health recommendations regarding work exclusion. Design: This prospective cohort study was conducted between December 16, 2020, and March 14, 2021, with HCP who had received at least 1 dose of either the Pfizer-BioNTech or Moderna COVID-19 vaccine. Setting: Large healthcare system in New England. Interventions: HCP were prompted to complete a symptom survey for 3 days after each vaccination. Reported symptoms generated automated guidance regarding symptom management, SARS-CoV-2 testing requirements, and work restrictions. Overlap symptoms (ie, fever, fatigue, myalgias, arthralgias, or headache) were categorized as either lower or higher severity. Typical COVID-19 symptoms included sore throat, cough, nasal congestion or rhinorrhea, shortness of breath, ageusia and anosmia. Results: Among 64,187 HCP, a postvaccination electronic survey had response rates of 83% after dose 1 and 77% after dose 2. Report of ≥3 lower-severity overlap symptoms, ≥1 higher-severity overlap symptoms, or at least 1 typical COVID-19 symptom after dose 1 was associated with increased likelihood of testing positive. HCP with prior COVID-19 infection were significantly more likely to report severe overlap symptoms after dose 1. Conclusions: Reported overlap symptoms were common; however, only report of ≥3 low-severity overlap symptoms, at least 1 higher-severity overlap symptom, or any typical COVID-19 symptom were associated with infection. Work-related restrictions for overlap symptoms should be reconsidered.

Objective:To describe an investigation into 5 clinical cases of carbapenem-resistant Acinetobacter baumannii (CRAB).Design:Epidemiological investigation supplemented by whole-genome sequencing (WGS) of clinical and environmental isolates.Setting:A tertiary-care academic health center in Boston, Massachusetts.Patients or participants:Individuals identified with CRAB clinical infections.Methods:A detailed review of patient demographic and clinical data was conducted. Clinical isolates underwent phenotypic antimicrobial susceptibility testing and WGS. Infection control practices were evaluated, and CRAB isolates obtained through environmental sampling were assessed by WGS. Genomic relatedness was measured by single-nucleotide polymorphism (SNP) analysis.Results:Four clinical cases spanning 4 months were linked to a single index case; isolates differed by 1–7 SNPs and belonged to a single cluster. The index patient and 3 case patients were admitted to the same room prior to their development of CRAB infection, and 2 case patients were admitted to the same room within 48 hours of admission. A fourth case patient was admitted to a different unit. Environmental sampling identified highly contaminated areas, and WGS of 5 environmental isolates revealed that they were highly related to the clinical cluster.Conclusions:We report a cluster of highly resistant Acinetobacter baumannii that occurred in a burn ICU over 5 months and then spread to a separate ICU. Two case patients developed infections classified as community acquired under standard epidemiological definitions, but WGS revealed clonality, highlighting the risk of burn patients for early-onset nosocomial infections. An extensive investigation identified the role of environmental reservoirs.

No abstract