A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients

The aim of the study was to build a machine learning-based predictive model to discriminate between hospitalized patients at low risk and high risk of bloodstream infection (BSI). A Data Mart including all patients hospitalized between January 2016 and December 2019 with suspected BSI was built. Multivariate logistic regression was applied to develop a clinically interpretable machine learning predictive model. The model was trained on 2016-2018 data and tested on 2019 data. A feature selection based on a univariate logistic regression first selected candidate predictors of BSI. A multivariate logistic regression with stepwise feature selection in five-fold cross-validation was applied to express the risk of BSI. A total of 5660 hospitalizations (4026 and 1634 in the training and the validation subsets, respectively) were included. Eleven predictors of BSI were identified. The performance of the model in terms of AUROC was 0.74. Based on the interquartile predicted risk score, 508 (31.1%) patients were defined as being at low risk, 776 (47.5%) at medium risk, and 350 (21.4%) at high risk of BSI. Of them, 14.2% (72/508), 30.8% (239/776), and 64% (224/350) had a BSI, respectively. The performance of the predictive model of BSI is promising. Computational infrastructure and machine learning models can help clinicians identify people at low risk for BSI, ultimately supporting an antibiotic stewardship approach.

Epidemiology, time course, and risk factors for hospital-acquired bloodstream infections in a cohort of 14,884 patients before and during the COVID-19 pandemic

OBJECTIVE

COVID-19 pandemic has changed in-hospital care and was linked to superimposed infections. Here, we described epidemiology and risk factors for hospital-acquired bloodstream infections (HA-BSIs), before and during COVID-19 pandemic.

METHODS

This retrospective, observational, single-center real-life study included 14,884 patients admitted to hospital wards and intensive care units (ICUs) with at least one blood culture, drawn 48 h after admission, either before (pre-COVID, N = 7382) or during pandemic (N = 7502, 1203 COVID-19+ and 6299 COVID-19-).

RESULTS

Two thousand two hundred and forty-five HA-BSI were microbiologically confirmed in 14,884 patients (15.1%), significantly higher among COVID-19+ (22.9%; ptrend < .001). COVID-19+ disclosed a significantly higher mortality rate (33.8%; p < .001) and more ICU admissions (29.7%; p < .001). Independent HAI-BSI predictors were: COVID-19 (OR: 1.43, 95%CI: 1.21-1.69; p < .001), hospitalization length (OR: 1.04, 95%CI: 1.03-1.04; p < .001), ICU admission (OR: 1.38, 95%CI: 1.19-1.60; p < .001), neoplasms (OR:1.48, 95%CI: 1.34-1.65; p < .001) and kidney failure (OR: 1.81, 95%CI: 1.61-2.04; p < .001). Of note, HA-BSI IRs for Acinetobacter spp. (0.16 × 100 patient-days) and Staphylococcus aureus (0.24 × 100 patient-days) peaked during the interval between first and second pandemic waves in our National context.

CONCLUSIONS

Patients with HA-BSI admitted before and during pandemic substantially differed. COVID-19 represented a risk factor for HA-BSI, though not confirmed in the sole pandemic period. Some etiologies emerged between pandemic waves, suggesting potential COVID-19 long-term effect on HA-BSIs.

Incidence of bloodstream infections due to multidrug-resistant pathogens in ordinary wards and intensive care units before and during the COVID-19 pandemic: a real-life, retrospective observational study

PURPOSE

SARS-COV-2 pandemic led to antibiotic overprescription and unprecedented stress on healthcare systems worldwide. Knowing the comparative incident risk of bloodstream infection due to multidrug-resistant pathogens in COVID ordinary wards and intensive care-units may give insights into the impact of COVID-19 on antimicrobial resistance.

METHODS

Single-center observational data extracted from a computerized dataset were used to identify all patients who underwent blood cultures from January 1, 2018 to May 15, 2021. Pathogen-specific incidence rates were compared according to the time of admission, patient's COVID status and ward type.

RESULTS

Among 14,884 patients for whom at least one blood culture was obtained, a total of 2534 were diagnosed with HA-BSI. Compared to both pre-pandemic and COVID-negative wards, HA-BSI due to S. aureus and Acinetobacter spp. (respectively 0.3 [95% CI 0.21-0.32] and 0.11 [0.08-0.16] new infections per 100 patient-days) showed significantly higher incidence rates, peaking in the COVID-ICU setting. Conversely, E. coli incident risk was 48% lower in COVID-positive vs COVID-negative settings (IRR 0.53 [0.34-0.77]). Among COVID + patients, 48% (n = 38/79) of S. aureus isolates were resistant to methicillin and 40% (n = 10/25) of K. pneumoniae isolates were resistant to carbapenems.

CONCLUSIONS

The data presented here indicate that the spectrum of pathogens causing BSI in ordinary wards and intensive care units varied during the pandemic, with the greatest shift experienced by COVID-ICUs. Antimicrobial resistance of selected high-priority bacteria was high in COVID positive settings.

Fetlock Joint Angle Pattern and Range of Motion Quantification Using Two Synchronized Wearable Inertial Sensors per Limb in Sound Horses and Horses with Single Limb Naturally Occurring Lameness

Fetlock joint angle (FJA) pattern is a sensitive indicator of lameness. The first aim of this study is to describe a network of inertial measurement units system (IMUs) for quantifying FJA simultaneously in all limbs. The second aim is to evaluate the accuracy of IMUs for quantifying the sagittal plane FJA overground in comparison to bi-dimensional (2-D) optical motion capture (OMC). 14 horses (7 free from lameness and 7 lame) were enrolled and analyzed with both systems at walk and trot on a firm surface. All enrolled horses were instrumented with 8 IMUs (a pair for each limb) positioned at the dorsal aspect of the metacarpal/metatarsal bone and pastern and acquiring data at 200 Hz. Passive markers were glued on the center of rotation of carpus/tarsus, fetlock, and distal interphalangeal joint, and video footages were captured at 60 Hz and digitalized for OMC acquisition. The IMU system accuracy was reported as Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (PCC). The Granger Causality Test (GCT) and the Bland−Altman analysis were computed between the IMUs and OMC patterns to determine the agreement between the two systems. The proposed IMU system was able to provide FJAs in all limbs using a patented method for sensor calibration and related algorithms. Fetlock joint range of motion (FJROM) variability of three consecutive strides was analyzed in the population through 3-way ANOVA. FJA patterns quantified by IMUs demonstrated high accuracy at the walk (RMSE 8.23° ± 3.74°; PCC 0.95 ± 0.03) and trot (RMSE 9.44° ± 3.96°; PCC 0.96 ± 0.02) on both sound (RMSE 7.91° ± 3.19°; PCC 0.97 ± 0.03) and lame horses (RMSE 9.78° ± 4.33°; PCC 0.95 ± 0.03). The two systems’ measurements agreed (mean bias around 0) and produced patterns that were in temporal agreement in 97.33% of the cases (p < 0.01). The main source of variability between left and right FJROM in the population was the presence of lameness (p < 0.0001) and accounted for 28.46% of this total variation. IMUs system accurately quantified sagittal plane FJA at walk and trot in both sound and lame horses.