Objectives: In the era of increasing antimicrobial resistance, the need for early identification and prompt treatment of multi-drug-resistant infections is crucial for achieving favorable outcomes in critically ill patients. As traditional microbiological susceptibility testing requires at least 24 hours, automated machine learning (AutoML) techniques could be used as clinical decision support tools to predict antimicrobial resistance and select appropriate empirical antibiotic treatment. Methods: An antimicrobial susceptibility dataset of 11,496 instances from 499 patients admitted to the internal medicine wards of a public hospital in Greece was processed by using Microsoft Azure AutoML to evaluate antibiotic susceptibility predictions using patients’ simple demographic characteristics, as well as previous antibiotic susceptibility testing, without any concomitant clinical data. Furthermore, the balanced dataset was also processed using the same procedure. The datasets contained the attributes of sex, age, sample type, Gram stain, 44 antimicrobial substances, and the antibiotic susceptibility results. Results: The stack ensemble technique achieved the best results in the original and balanced dataset with an area under the curve-weighted metric of 0.822 and 0.850, respectively. Conclusions Implementation of AutoML for antimicrobial susceptibility data can provide clinicians useful information regarding possible antibiotic resistance and aid them in selecting appropriate empirical antibiotic therapy by taking into consideration the local antimicrobial resistance ecosystem.

Objectives: In the era of increasing antimicrobial resistance, the need for early identification and prompt treatment of multi-drug-resistant infections is crucial for achieving favorable outcomes in critically ill patients. As traditional microbiological susceptibility testing requires at least 24 hours, automated machine learning (AutoML) techniques could be used as clinical decision support tools to predict antimicrobial resistance and select appropriate empirical antibiotic treatment. Methods: An antimicrobial susceptibility dataset of 11,496 instances from 499 patients admitted to the internal medicine wards of a public hospital in Greece was processed by using Microsoft Azure AutoML to evaluate antibiotic susceptibility predictions using patients’ simple demographic characteristics, as well as previous antibiotic susceptibility testing, without any concomitant clinical data. Furthermore, the balanced dataset was also processed using the same procedure. The datasets contained the attributes of sex, age, sample type, Gram stain, 44 antimicrobial substances, and the antibiotic susceptibility results. Results: The stack ensemble technique achieved the best results in the original and balanced dataset with an area under the curve-weighted metric of 0.822 and 0.850, respectively. Conclusions Implementation of AutoML for antimicrobial susceptibility data can provide clinicians useful information regarding possible antibiotic resistance and aid them in selecting appropriate empirical antibiotic therapy by taking into consideration the local antimicrobial resistance ecosystem.

The development of underground workspaces is a strategic effort towards healthy urban growth in cities with ever-increasing land scarcity. Despite the growth in underground workspaces, there is limited information regarding the impact of this environment on workers’ health. The Health Effects of Underground Workspaces (HEUW) study is a cohort study that was set up to examine the health effects of working in underground workspaces. In this paper, we describe the rationale for the study, study design, data collection, and baseline characteristics of participants. The HEUW study recruited 464 participants at baseline, of whom 424 (91.4%) were followed-up at 3 months and 334 (72.0%) at 12 months from baseline. We used standardized and validated questionnaires to collect information on socio-demographic and lifestyle characteristics, medical history, family history of chronic diseases, sleep quality, health-related quality of life, chronotype, psychological distress, occupational factors, and comfort levels with indoor environmental quality parameters. Clinical and anthropometric parameters including blood pressure, spirometry, height, weight, and waist and hip circumference were also measured. Biochemical tests of participants’ blood and urine samples were conducted to measure levels of glucose, lipids, and melatonin. We also conducted objective measurements of individuals’ workplace environment, assessing air quality, light intensity, temperature, thermal comfort, and bacterial and fungal counts. The findings this study will help to identify modifiable lifestyle and environmental parameters that are negatively affecting workers’ health. The findings may be used to guide the development of more health-promoting workspaces that attempt to negate any potential deleterious health effects from working in underground workspaces.