Kristian Svendsen

Aim: In this review, we investigated how Machine Learning (ML) was utilized to predict all-cause somatic hospital admissions and readmissions in adults. Methods: We searched eight databases (PubMed, Embase, Web of Science, CINAHL, ProQuest, OpenGrey, WorldCat, and MedNar) from their inception date to October 2023, and included records that predicted all-cause somatic hospital admissions and readmissions of adults using ML methodology. We used the CHARMS checklist for data extraction, PROBAST for bias and applicability assessment, and TRIPOD for reporting quality. Results: We screened 7,543 studies of which 163 full-text records were read and 116 met the review inclusion criteria. Among these, 45 predicted admission, 70 predicted readmission, and one study predicted both. There was a substantial variety in the types of datasets, algorithms, features, data preprocessing steps, evaluation, and validation methods. The most used types of features were demographics, diagnoses, vital signs, and laboratory tests. Area Under the ROC curve (AUC) was the most used evaluation metric. Models trained using boosting tree-based algorithms often performed better compared to others. ML algorithms commonly outperformed traditional regression techniques. Sixteen studies used Natural language processing (NLP) of clinical notes for prediction, all studies yielded good results. The overall adherence to reporting quality was poor in the review studies. Only five percent of models were implemented in clinical practice. The most frequently inadequately addressed methodological aspects were: providing model interpretations on the individual patient level, full code availability, performing external validation, calibrating models, and handling class imbalance. Conclusion: This review has identified considerable concerns regarding methodological issues and reporting quality in studies investigating ML to predict hospitalizations. To ensure the acceptability of these models in clinical settings, it is crucial to improve the quality of future studies.

Emergency departments (EDs) handle urgent medical needs for a diverse population. Medication errors and adverse drug events pose safety risks in the ED. Clinical pharmacists, experts in medication use, play a crucial role in identifying and optimizing medication therapy. The aim of this study was to investigate how clinical pharmacists introduced into the ED interdisciplinary teams distribute their work time. In a time and motion study, we used the Work Observation Method By Activity Timing (WOMBAT) to observe pharmacists in two Norwegian EDs. The pragmatic approach allowed pharmacists to adapt to ED personnel and patient needs. The pharmacists spent 41.8% of their work time on medication-related tasks, especially those linked to medication reconciliation, including documenting medication-related issues (16.2%), reading and retrieving written information (9.6%), and obtaining oral information about medication use from patients (9.5%). The remaining time was spent on non-medication-related tasks (41.8%), and on standby and movement (17.4%). In conclusion, ED pharmacists spent 42% of their work time on medication-related tasks, predominantly medication reconciliation. Their relatively new role in the interdisciplinary team may have limited their broader clinical impact. Relative to other ED healthcare professionals, ED pharmacists’ goal remains to ensure accurate patient medication lists and appropriate medication use.

Background: Medication lists prepared in the emergency department (ED) form the basis for diagnosing and treating patients during hospitalization. Since incomplete medication information may lead to patient harm, it is crucial to obtain a correct and complete medication list at hospital admission. In this cross-sectional retrospective study we wanted to explore medication information completeness in admission notes from Norwegian EDs and investigate which factors were associated with level of completeness. Methods: Medication information was assessed for completeness by applying five evaluation criteria; generic name, formulation, dose, frequency, and indication for use. A medication completeness score in percent was calculated per medication, per admission note and per criterion. Quantile regression analysis was applied to investigate which variables were associated with medication information completeness. Results: Admission notes for patients admitted between October 2018 and September 2019 and using at least one medication were included. A total of 1,080 admission notes, containing 8,604 medication orders, were assessed. The individual medications had a mean medication completeness score of 88.1% (SD 16.4), while admission notes had a mean medication completeness score of 86.3% (SD 16.2). Over 90% of all individual medications had information about generic name, formulation, dose and frequency stated, while indication for use was only present in 60%. The use of an electronic tool to prepare medication information had a significantly strong positive association with completeness. Hospital visit within the last 30 days, the patient’s living situation, number of medications in use, and which hospital the patient was admitted to, were also associated with information completeness. Conclusions: Medication information completeness in admission notes was high, but potential for improvement regarding documentation of indication for use was identified. Applying an electronic tool when preparing admission notes in EDs seems crucial to safeguard completeness of medication information.

The global prevalence of infections caused by extended-spectrum β-lactamase-producing Enterobacterales (ESBL-E) is increasing, and for Escherichia coli , observations indicate that this is partly driven by community-onset cases. The ESBL-E population structure in the community is scarcely described, and data on risk factors for carriage are conflicting. Here, we report the prevalence and population structure of fecal ESBL-producing E. coli and Klebsiella pneumoniae (ESBL-Ec/Kp) in a general adult population, examine risk factors, and compare carriage isolates with contemporary clinical isolates. Fecal samples obtained from 4,999 participants (54% women) ≥40 years in the seventh survey of the population-based Tromsø Study, Norway (2015, 2016), were screened for ESBL-Ec/Kp. In addition, we included 118 ESBL-Ec clinical isolates from the Norwegian surveillance program in 2014. All isolates were whole-genome sequenced. Risk factors associated with carriage were analyzed using multivariable logistic regression. ESBL-Ec gastrointestinal carriage prevalence was 3.3% [95% confidence interval (CI) 2.8%–3.9%, no sex difference] and 0.08% (0.02%–0.20%) for ESBL-Kp. For ESBL-Ec, travel to Asia was the only independent risk factor (adjusted odds ratio 3.46, 95% CI 2.18–5.49). E. coli ST131 was most prevalent in both collections. However, the ST131 proportion was significantly lower in carriage (24%) versus clinical isolates (58%, P < 0.001). Carriage isolates were genetically more diverse with a higher proportion of phylogroup A (26%) than clinical isolates (5%, P < 0.001), indicating that ESBL gene acquisition occurs in a variety of E. coli lineages colonizing the gut. STs commonly related to extraintestinal infections were more frequent in clinical isolates also carrying a higher prevalence of antimicrobial resistance, which could indicate clone-associated pathogenicity. IMPORTANCE: ESBL-Ec and ESBL-Kp are major pathogens in the global burden of antimicrobial resistance. However, there is a gap in knowledge concerning the bacterial population structure of human ESBL-Ec/Kp carriage isolates in the community. We have examined ESBL-Ec/Kp isolates from a population-based study and compared these to contemporary clinical isolates. The large genetic diversity of carriage isolates indicates frequent ESBL gene acquisition, while those causing invasive infections are more clone dependent and associated with a higher prevalence of antibiotic resistance. The knowledge of factors associated with ESBL carriage helps to identify patients at risk to combat the spread of resistant bacteria within the healthcare system. Particularly, previous travel to Asia stands out as a major risk factor for carriage and should be considered in selecting empirical antibiotic treatment in critically ill patients.

Background Emergency department (ED) pharmacists reduce medication errors and improve quality of medication use. Patient perceptions and experiences with ED pharmacists have not been studied. The aim of this study was to explore patients’ perceptions of and experiences with medication-related activities in the ED, with and without an ED pharmacist present. Methods We conducted 24 semistructured individual interviews with patients admitted to one ED in Norway, 12 before and 12 during an intervention, where pharmacists performed medication-related tasks close to patients and in collaboration with ED staff. Interviews were transcribed and analysed applying thematic analysis. Results From our five developed themes, we identified that: (1) Our informants had low awareness and few expectations of the ED pharmacist, both with and without the pharmacist present. However, they were positive to the ED pharmacist. (2) Our informants expressed a variation of trust in the healthcare system, healthcare professionals and electronic systems, though the majority expressed a high level of trust. They believed that their medication list was automatically updated and assumed to get the correct medication. (3) Some informants felt responsible to have an overview of their medication use, while others expressed low interest in taking responsibility regarding their medication. (4) Some informants did not want involvement from healthcare professionals in medication administration, while others expressed no problems with giving up control. (5) Medication information was important for all informants to feel confident in medication use, but the need for information differed. Conclusion Despite being positive to pharmacists, it did not seem important to our informants who performed the medication-related tasks, as long as they received the help they needed. The degree of trust, responsibility, control and information varied among ED patients. These dimensions can be applied by healthcare professionals to tailor medication-related activities to patients’ individual needs.

The global prevalence of infections caused by ESBL-producing Enterobacterales (ESBL-E) is increasing and for Escherichia coli observations indicate that this is partly driven by community-onset cases. The ESBL-E population structure in the community is scarcely described and data on risk factors for carriage are conflicting. Here, we report the prevalence and population structure of fecal ESBL-producing E. coli and Klebsiella pneumoniae (ESBL-Ec/Kp) in a general adult population, examine risk factors, and compare carriage isolates with contemporary clinical isolates. Fecal samples obtained from 4999 participants (54% women) ≥40 years in the seventh survey of the population-based Tromsø Study, Norway (2015-2016) were screened for ESBL-Ec/Kp. In addition, we included 118 ESBL-Ec clinical isolates from the Norwegian surveillance program in 2014. All isolates were whole-genome sequenced. Risk factors associated with carriage were analyzed using multivariable logistic regression. ESBL-Ec gastrointestinal carriage prevalence was 3.3% (95% CI 2.8-3.9%, no sex difference) and 0.08% (0.02-0.20%) for ESBL-Kp. For ESBL-Ec, travel to Asia was the only independent risk factor (AOR 3.47, 95% CI 2.18-5.51). E. coli ST131 was most prevalent in both collections. However, the ST131 proportion was significantly lower in carriage (24%) vs. clinical isolates (58%, pE. coli lineages colonizing the gut. STs commonly related to extra-intestinal infections were more frequent in clinical isolates also carrying a higher prevalence of antimicrobial resistance, which could indicate clone associated pathogenicity. Importance: ESBL-producing E. coli (ESBL-Ec) and K. pneumoniae (ESBL-Kp) are major pathogens in the global burden of antimicrobial resistance. However, there is a gap in knowledge concerning the bacterial population structure of human ESBL-Ec/Kp carriage isolates in the community. We have examined ESBL-Ec/Kp isolates from a population-based study and compared these to contemporary clinical isolates. The large genetic diversity of carriage isolates indicates frequent ESBL gene acquisition, while those causing invasive infections are more clone dependent and associated with a higher prevalence of antibiotic resistance. The knowledge of factors associated with ESBL carriage helps to identify patients at risk to combat the spread of resistant bacteria within the healthcare system. Particularly, previous travel to Asia stands out as a major risk factor for carriage and should be considered in selecting empirical antibiotic treatment in critically ill patients.