Early diagnosis of candidemia with explainable machine learning on automatically extracted laboratory and microbiological data: results of the AUTO-CAND project.

BACKGROUND: Candidemia is associated with a heavy burden of morbidity and mortality in hospitalized patients. The availability of blood culture results could require up to 48-72 h after blood draw; thus, early treatment decisions are made in the absence of a definite diagnosis. METHODS: In this retrospective study, we assessed the performance of different supervised machine learning algorithms for the early differential diagnosis of candidemia and bacteremia in adult patients on a large dataset automatically extracted within the AUTO-CAND project. RESULTS: Overall, 12,483 episodes of candidemia (1275; 10%) or bacteremia (11,208; 90%) were included in the analysis. A random forest classifier achieved the best diagnostic performance for candidemia, with sensitivity 0.98 and specificity 0.65 on the training set (true skill statistic [TSS] = 0.63) and sensitivity 0.74 and specificity 0.57 on the test set (TSS = 0.31). Then, the random classifier was trained in the subgroup of patients with available serum ß-D-glucan (BDG) and procalcitonin (PCT) values by exploiting the feature ranking learned in the entire dataset. Although no statistically significant differences were observed from the performance measures obtained by employing BDG and PCT alone, the performance measures of the classifier that included the features selected in the entire dataset, plus BDG and PCT, were the highest in most cases. CONCLUSIONS: Random forest classifiers trained on large datasets of automatically extracted data have the potential to improve current diagnostic algorithms for candidemia. However, further development through implementation of automatically extracted clinical features may be necessary to achieve crucial improvements.

Use of antibiotics in hospitalized patients with COVID-19: evolving concepts in a highly dynamic antimicrobial stewardship scenario.

INTRODUCTION: Excessive use of antibiotics has been frequently reported in hospitalized patients with COVID-19 worldwide, compared to the actual number of bacterial co-infections or super-infections. AREAS COVERED: In this perspective, we discuss the current literature on the use of antibiotics and antimicrobial stewardship interventions in hospitalized patients with COVID-19. A search was conducted in PubMed up to March 2023. EXPERT OPINION: The COVID-19 pandemic has witnessed an excessive use of antibiotics in hospitals worldwide, especially before the advent of COVID-19 vaccination, although according to the most recent data there is still an important disproportion between the prevalence of antibiotic use and that of proven bacterial coinfection or superinfections. An important reduction in the prevalence of antibiotic use in COVID-19 patients reported in the literature, from 70-100% to 50-60%, has been observed after successful vaccination campaigns, likely related to the reduced median disease severity of hospitalized COVID-19 patients and some successful interventions of antimicrobial and diagnostic stewardship. However, the disproportion between antibiotic use and the prevalence of bacterial infections (4-6%) is still uncomfortable from an antimicrobial stewardship perspective and requires further attention.

Validation of an Automated System for the Extraction of a Wide Dataset for Clinical Studies Aimed at Improving the Early Diagnosis of Candidemia.

There is increasing interest in assessing whether machine learning (ML) techniques could further improve the early diagnosis of candidemia among patients with a consistent clinical picture. The objective of the present study is to validate the accuracy of a system for the automated extraction from a hospital laboratory software of a large number of features from candidemia and/or bacteremia episodes as the first phase of the AUTO-CAND project. The manual validation was performed on a representative and randomly extracted subset of episodes of candidemia and/or bacteremia. The manual validation of the random extraction of 381 episodes of candidemia and/or bacteremia, with automated organization in structured features of laboratory and microbiological data resulted in ≥99% correct extractions (with confidence interval < ±1%) for all variables. The final automatically extracted dataset consisted of 1338 episodes of candidemia (8%), 14,112 episodes of bacteremia (90%), and 302 episodes of mixed candidemia/bacteremia (2%). The final dataset will serve to assess the performance of different ML models for the early diagnosis of candidemia in the second phase of the AUTO-CAND project.

Monkeypox outbreak in Genoa, Italy: Clinical, laboratory, histopathologic features, management, and outcome of the infected patients.

Since May 2022, multiple human Monkeypox cases were identified in nonendemic countries, mainly among men who have sex with men. We aimed to report the features, clinical course, management, and outcome of the Monkeypox cases diagnosed in the Dermatology and Infectious Disease Units of the San Martino Hospital, Genoa, Italy. We performed an observational study of the Monkeypox cases diagnosed from July 1 until August 31, 2022, collecting clinical, laboratory, and histological data. We studied 16 Monkeypox-infected men (14 homosexual, 2 bisexual) with a median age of 37 years. Three were HIV-infected. All patients reported multiple sexual partners and/or unprotected sex in the 2 weeks before the diagnosis. Most patients had prodromal signs/symptoms before the appearance of the skin/mucosal eruption, consisting of erythematous papules/vesicles/pustules in the anogenital area, which tended to erode evolving into crusts and ulcers. Lesions were often associated with local and/or systemic symptoms. Histopathology showed overlapping features in all cases: epidermal ulceration and dermal inflammatory infiltrate consisting of lymphocytes and neutrophils with an interstitial and perivascular/peri-adnexal pattern and endothelial swelling. Concomitant sexually transmitted infections (STIs) (gonococcal/nongonococcal proctitis and anal high-risk human papillomavirus [HR-HPV] infection) were frequent. Four patients were hospitalized, and one received specific treatment. The overall outcome was good. At the follow-up visit, three patients presented skin scars. Our series confirms the features of the current Monkeypox outbreak; however, different from other studies, we found a considerable rate of concomitant STIs, such as anal HR-HPV infection, that should be kept in mind because this persistent infection is the main cause of anal cancers.

Nasal monkeypox virus infection successfully treated with cidofovir in a patient newly diagnosed with HIV.

Monkeypox (MPXV) usually causes a mild and self-limited infection. To date there are no data about cidofovir for the treatment for MPXV in humans. We report a case of a 25 years-old Brazilian man with a concurrent diagnosis of acute HIV (human immunodeficiency virus) infection, primary syphilis and MPXV infection with a nasal lesion successfully treated with intravenous cidofovir.

Reactivation of Herpes Simplex Virus Type 1 (HSV-1) Detected on Bronchoalveolar Lavage Fluid (BALF) Samples in Critically Ill COVID-19 Patients Undergoing Invasive Mechanical Ventilation: Preliminary Results from Two Italian Centers.

Reactivation of herpes simplex virus type 1 (HSV-1) has been described in critically ill patients with coronavirus disease 2019 (COVID-19) pneumonia. In the present two-center retrospective experience, we primarily aimed to assess the cumulative risk of HSV-1 reactivation detected on bronchoalveolar fluid (BALF) samples in invasively ventilated COVID-19 patients with worsening respiratory function. The secondary objectives were the identification of predictors for HSV-1 reactivation and the assessment of its possible prognostic impact. Overall, 41 patients met the study inclusion criteria, and 12/41 patients developed HSV-1 reactivation (29%). No independent predictors of HSV-1 reactivation were identified in the present study. No association was found between HSV-1 reactivation and mortality. Eleven out of 12 patients with HSV-1 reactivation received antiviral therapy with intravenous acyclovir. In conclusion, HSV-1 reactivation is frequently detected in intubated patients with COVID-19. An antiviral treatment in COVID-19 patients with HSV-1 reactivation and worsening respiratory function might be considered.