Results
Automated surveillance of healthcare-associated infections using an artificial intelligence algorithm.
Healthcare-associated infections (HAIs) are among hospitals' most common adverse events. In a cohort study, we used artificial intelligence (AI) algorithms for infection surveillance. The model correctly detected 67 out of 73 patients with IAHs. The final model reached an area under the receiver operation curve (ROC-AUC) of 90.27%; specificity of 78.86%; sensitivity of 88.57%. Respiratory infections had the best results (ROC-AUC ≥93.47%).
Learn More
Coronavirus Disease 2019 (Covid-19): Transmission events in school professionals: a Brazilian prospective cohort.
From October to December 2020, we followed a prospective cohort of 315 professionals and 768 students from three schools in Porto Alegre and the metropolitan region regarding the transmission of Sars-Cov-2. In the period, schools were in hybrid mode (with students in person and at a distance). The schools have gone through a process of reviewing their protocols. Through the robot-ISA application, professionals and students were monitored for the presence of symptoms. Professionals who had symptoms were evaluated on the same day by an infectious diseases physician. There were 3,229 responses from professionals to the ISA robot. Fifty-five professionals reported symptoms. Of these, seven professionals (2.2% of the total) were positive. The presence of fever, tiredness and more than five symptoms correlated with positivity for Sars-cov-2. There was no work-related transmission event among school professionals.
Learn More
Management of antimicrobials by telemedicine in a community hospital in southern Brazil
The tele-stewardship program was implemented in a 50-bed community hospital 575 km away. The intervention began in May 2011. During the four months, 81 prescription evaluations were carried out. The rate of the adequacy of prescriptions rose from 36% to 60% in the fourth month of work. Adherence to the recommendations of specialists by remote medical professionals was 100%. The study showed that telemedicine tools could be applied over long distances, with excellent adherence, in community hospitals in Brazil, where access to specialists is more complicated.
Learn More
Intervention study before and after Qualis services at the Alto Vale Regional Hospital
From May 2014 to April 2016, a quasi-experimental study in a 220-bed hospital showed that a tele-stewardship intervention reduced the consumption of antimicrobials such as quinolones, first-generation cephalosporins, vancomycin, and polymyxins. On the other hand, it increased the consumption of amoxicillin+clavulanate and cefuroxime. The adequacy of choices for antimicrobials rose from 51% to 84%, which significantly impacted the reduction of bacterial resistance, especially Carbapenem-resistant Acinetobacter spp.. In addition, there was a reduction in antimicrobial spending in the order of R$109,730.00 (monthly average) before to R$ 89,723.00 (savings of 20 thousand reais monthly).
Learn More
Using Machine Learning to Reduce Burden on Infection Control Staff
Surveillance of health care–associated infection (HAI) is the foundation of infection control and one of the first steps in infection prevention. Traditionally, however, surveillance is performed by infection control professionals (ICPs) who manually review patients’ records, searching for defined criteria. Such an approach leaves room for subjective interpretation, resulting in low interrater reliability. Moreover, depending on the surveillance method used — for instance, a search based on antimicrobial results — it may have low sensitivity. In Brazil, leaders at Tacchini Hospital and Qualis, a startup that offers infection control advisory and antimicrobial stewardship, have developed a machine-learning–algorithm robot that has been demonstrated to be a reliable tool for identifying patients with HAIs using a semiautomated method. The performance of this infection surveillance assistant (ISA) robot shows optimal sensitivity, specificity, accuracy, and negative predictive values, and the precision (positive predictive value) is acceptable. The ISA robot identified more patients with HAIs than did the infection control manual surveillance reference. The time spent on patient review was also reduced compared with that spent on manual surveillance. The robot detected HAI in one of every two or three patients reviewed in the interface. The years of the Covid-19 pandemic have highlighted the problem of the shortage of health care professionals, including ICPs. Tacchini Hospital and Qualis aim to increase infection control efficiency, enabling these professionals to spend more time on inpatient wards, implementing care bundles, than handling office activities, such as manual surveillance. In this study, the authors describe the implementation of semiautomated surveillance in a single center, but expanding themodel for different patient scenarios and multiple centers should be the future for external validation of machine-learning surveillance. Such models have the potential for generalization because they do not depend only on xed rules for HAI classi cation, but they can also learn from data sets in different patient population settings.
SAIBA MAIS
Hospital-acquired infections surveillance: The machine-learning algorithm mirrors National Healthcare Safety Network definitions
Background: Surveillance of hospital-acquired infections (HAIs) is the foundation of infection control. Machine learning (ML) has been demonstrated to be a valuable tool for HAI surveillance. We compared manual surveillance with a supervised, semiautomated, ML method, and we explored the types of infection and features of importance depicted by the model.