Combination of machine learning algorithms with natural language processing may increase the probability of bacteremia detection in the emergency department: A retrospective, big-data analysis of 94,482 patients.

Background: Prompt diagnosis of bacteremia in the emergency department (ED) is of utmost importance. Nevertheless, the average time to first clinical laboratory finding range from 1 to 3 days. Alongside a myriad of scoring systems for occult bacteremia prediction, efforts for applying artificial intelligence (AI) in this realm are still preliminary. In the current study we combined an AI algorithm with a Natural Language Processing (NLP) algorithm that would potentially increase the yield extracted from clinical ED data. Methods: This study involved adult patients who visited our emergency department and at least one blood culture was taken to rule out bacteremia. Using both tabular and free text data, we built an ensemble model that leverages XGBoost for structured data, and logistic regression (LR) on a word-analysis technique called bag-of-words (BOW) Term Frequency-Inverse Document Frequency (TF-IDF), for textual data. All algorithms were designed in order to predict the risk for bacteremia with ED patients whose blood cultures were sent to the laboratory. Results: The study cohort comprised 94,482 individuals, of whom 52% were males. The prevalence of bacteremia in the entire cohort was 9.7%. The model trained on the tabular data yielded an area under the curve (AUC) of 73.7% for XGBoost, while the LR that was trained on the free text achieved an AUC of 71.3%. After checking a range of weights, the best combination was for 55% weight on the XGBoost prediction and 45% weight on the LR prediction. The final model prediction yielded an AUC of 75.6%. Conclusion: Harnessing artificial intelligence to the task of bacteremia surveillance in the ED settings by a combination of both free text and tabular data analysis improved predictive performance compared to using tabular data alone. We recommend that future AI applications based on our findings should be assimilated into the clinical routines of ED physicians.

Atrial fibrillation in young hospitalized patients: Clinical characteristics, predictors of new onset, and outcomes.

BACKGROUND: Atrial fibrillation (AF) in young adults is an uncommon and not well studied entity. METHODS: Consecutive patients aged 18-45 years admitted to internal or cardiology services in a large tertiary medical center (January 1, 2009 through December 31, 2019) were included. Clinical, electrocardiographic, and echocardiographic data were compared between patients with and without AF at baseline. Predictors of new-onset AF in the young were identified using multivariate Cox regression model among patients free of baseline AF. RESULTS: Final cohort included 16,432 patients with median age of 34 (IQR 26-41) years of whom 8914 (56 %) were men. Patients with AF at baseline (N = 366; 2 %) were older, more likely to be men, and had higher proportion of comorbidities and electrocardiographic conduction disorders. Male sex, increased age, obesity, heart failure, congenital heart disease (CHD) and the presence of left or right bundle branch block were all independently associated with baseline AF in a multivariate model (p < 0.001 for all). Sub-analysis of 10,691 (98 %) patients free of baseline AF identified 85 cases of new-onset AF during a median follow up of 3.5 (IQR 1.5-6.5) years. Multivariate model identified increased age, heart failure, and CHD as independent predictors of new-onset AF. Finally, the CHARGE-AF risk score outperformed the CHA2DS2-VASc score in AF prediction [AUC of ROC 0.75 (0.7-0.8) vs. 0.56 (0.48-0.65)]. CONCLUSIONS: AF among hospitalized young adults is not rare. Screening for new-onset AF in young post hospitalization patients may be guided by specific clinical predictors and the CHARGE-AF risk score.