We investigated the accuracy and completeness of four large language model (LLM) artificial intelligence tools. Most LLMs provided acceptable answers to commonly asked infection prevention questions (accuracy 98.9%, completeness 94.6%). The use of LLMs to supplement infection prevention consults should be further explored.

For adult patients with Staphylococcus aureus bacteremia (SAB), Infectious Diseases consultation (IDC) significantly lowers mortality and recurrence rate. Our systematic review and meta-analysis demonstrate that IDC is also associated with significantly lower mortality in children with SAB. Analysis of the impact of IDC on pediatric recurrence rates revealed moderate heterogeneity.

Background: Artificial intelligence (AI) tools have demonstrated success in US medical licensing examinations; however, their utility in infection prevention and control (IPC) remains unknown. Methods: The program of hospital epidemiology handles consultation calls and records each question and answer. Using 2022 data, we selected 31 frequently asked questions. We utilized four AI tools, including Chat GPT-3.5 and 4.0, Bing AI, and OpenEvidence, to generate answers. We predefined scales (Table 1) to capture responses by three reviewers, including two hospital epidemiologists and one infection preventionist. The mean score of ≥ 3 and ≥ 4 was considered acceptable in accuracy and completeness, respectively. We reported the percentage of responses with acceptable accuracy and completeness out of assessed questions for each category. Results: Among 31 questions, 16 were associated with isolation duration, 9 with healthcare personnel (HCP) exposure, 4 with cleaning contaminated rooms, and 2 with patient exposure. Regarding accuracy, most AI tools performed worse in questions about isolation duration, ranging between 75% and 93.8%. All AI tools, except OpenEvidence, had a 100% accuracy rate for HCP and patient exposure. All AI tools had a 100% accuracy rate for contaminated room handling. The highest overall acceptable accuracy rate was observed in Chat GPT-3.5. Regarding completeness, most AI tools performed worse in questions about isolation duration, ranging between 44% and 75%. All AI tools, except OpenEvidence, had a 100% completeness rate for contaminated rooms and patient exposure. The highest overall acceptable completeness rate was observed in Bing AI (Table 2). Conclusions: All AI tools provided reasonable answers to commonly asked IPC-related questions, although, there were variations among different tools used. AI could be used to supplement the infection control program, especially if resources are limited.

Defaulting the order for peripherally inserted central catheters (PICCs) placement to single lumen increased proportion of single-lumen insertions over total insertions from 42/126 (33%) to 57/104 (51)%. Single-lumen PICCs had a nonsignificant lower rate of central line-associated bloodstream infection compared to double-lumen PICCs.

Of the 2,668 patients admitted with coronavirus disease 2019 (COVID-19), 4% underwent prolonged isolation for >20 days. Reasons for extended isolation were inconsistent with Centers for Disease Control and Prevention (CDC) guidelines in 25% of these patients and were questionable in 54% due to an ongoing critically ill condition at day 20 without CDC-defined immunocompromised status.

We describe the association between job roles and coronavirus disease 2019 (COVID-19) among healthcare personnel. A wide range of hazard ratios were observed across job roles. Medical assistants had higher hazard ratios than nurses, while attending physicians, food service workers, laboratory technicians, pharmacists, residents and fellows, and temporary workers had lower hazard ratios.

We describe COVID-19 cases among nonphysician healthcare personnel (HCP) by work location. The proportion of HCP with coronavirus disease 2019 (COVID-19) was highest in the emergency department and lowest among those working remotely. COVID-19 and non–COVID-19 units had similar proportions of HCP with COVID-19 (13%). Cases decreased across all work locations following COVID-19 vaccination.

Background: Scabies is a contagious dermatosis caused by human mites, (Sarcoptes scabei, variant hominis). In crusted (Norwegian) scabies, the burden of mite infestation is higher and up to 2 million per person, facilitating easy skin-to-skin transmission and nosocomial transmission. We describe a case of undiagnosed crusted scabies and subsequent transmission to employees in our hospital. Methods: A 90-year-old female was admitted to our 636-bed, nonprofit, academic hospital for 22 days prior to diagnosis of crusted scabies by skin scraping. The patient was admitted to 2 different medical-surgical wards and the medical intensive care unit. We collected healthcare worker (HCW) demographics, including department of service, age, sex, pregnancy, and breastfeeding status in those who were at risk of exposure. We interviewed HCWs at 2 time points and collected information related to infestation, allergies to treatment, acceptance of empiric treatment, and whether employee was furloughed. Results: On initial screening, 20 of 124 at-risk HCWs had symptoms (Fig.). Most had a “new onset raised red rash or new pimple like rash (not on face), or linear rash” and 4 had “new onset uncontrollable itching.” All 124 HCWs were contacted 28 days later. One HCW that had not been compliant with prophylaxis became symptomatic and was diagnosed with scabies by dermatology. Of the remaining 20 HCWs, 3 were still having symptoms (2 had itching and 1 had a rash and a scrape performed by dermatology with confirmation of mites). All 3 were retreated with ivermectin. Overall, 21 of 124 exposed HCWs were ultimately symptomatic. Conclusions: During a 22-day admission of an undiagnosed and unisolated elderly patient with crusted scabies, the scabies mite was transmitted to 21 HCWs for an acquisition rate of 17%. Persistence of symptoms after treatment with permethrin occurred in 14%. The infectivity of this disease necessitates early recognition and infection control measures.

Funding: None

Disclosures: None