Clinical Utility and Functionality of an Artificial Intelligence-Based App to Predict Mortality in COVID-19: Mixed Methods Analysis.

BACKGROUND: The artificial neural network (ANN) is an increasingly important tool in the context of solving complex medical classification problems. However, one of the principal challenges in leveraging artificial intelligence technology in the health care setting has been the relative inability to translate models into clinician workflow. OBJECTIVE: Here we demonstrate the development of a COVID-19 outcome prediction app that utilizes an ANN and assesses its usability in the clinical setting. METHODS: Usability assessment was conducted using the app, followed by a semistructured end-user interview. Usability was specified by effectiveness, efficiency, and satisfaction measures. These data were reported with descriptive statistics. The end-user interview data were analyzed using the thematic framework method, which allowed for the development of themes from the interview narratives. In total, 31 National Health Service physicians at a West London teaching hospital, including foundation physicians, senior house officers, registrars, and consultants, were included in this study. RESULTS: All participants were able to complete the assessment, with a mean time to complete separate patient vignettes of 59.35 (SD 10.35) seconds. The mean system usability scale score was 91.94 (SD 8.54), which corresponds to a qualitative rating of "excellent." The clinicians found the app intuitive and easy to use, with the majority describing its predictions as a useful adjunct to their clinical practice. The main concern was related to the use of the app in isolation rather than in conjunction with other clinical parameters. However, most clinicians speculated that the app could positively reinforce or validate their clinical decision-making. CONCLUSIONS: Translating artificial intelligence technologies into the clinical setting remains an important but challenging task. We demonstrate the effectiveness, efficiency, and system usability of a web-based app designed to predict the outcomes of patients with COVID-19 from an ANN.

Non-typhoidal salmonellosis presenting as acute calculus cholecystitis.

Non-typhoidal Salmonella spp.are Gram-negative bacilli, which typically cause a clinical picture of gastroenteritis and, less commonly, patients may become a chronic carrier of the pathogen within their gallbladder. We describe a rare clinical presentation of a non-typhoidal Salmonella spp. infection as acute calculus cholecystitis in an adult patient. Salmonella enterica subsp. Salamae (ST P4271) was grown from cholecystostomy fluid, and the patient subsequently underwent a laparoscopic cholecystectomy that demonstrated a necrotic gallbladder fundus. We advise that microbiological sampling of bile is essential, especially in the context of foreign travel, to detect unusual pathogens as in this case or common pathogens that may have unusual antimicrobial resistance. Given the necrotic gallbladder as in this case, we also advise that early cholecystectomy should be strongly considered in these patients.

Closed-Loop Control for Precision Antimicrobial Delivery: An In Silico Proof-of-Concept.

OBJECTIVE: Inappropriate dosing of patients with antibiotics is a driver of antimicrobial resistance, toxicity, and poor outcomes of therapy. In this paper, we investigate, in silico, the hypothesis that the use of a closed-loop control system could improve the attainment of pharmacokinetic-pharmacodynamic targets for antimicrobial therapy, where wide variations in target attainment have been reported. This includes patients in critical care, patients with renal disease, and patients with obesity. METHODS: The presented in silico study focuses on vancomycin delivery, a first line therapy for Methicillin-resistant Staphylococcus aureus (MRSA) that has serious side effects, including nephrotoxicity. For this purpose, an in silico platform for the simulation of pharmacokinetics of vancomycin agents was developed including 24 virtual noncritically ill-adult subjects obtained from routinely collected data from two prospective audits of vancomycin therapy. Intraday variability on renal clearance, sensor error, and infusion constraints were taken into account. Proportional integral derivative (PID) controller was chosen because of its simplicity of implementation and satisfactory performance. RESULTS: Even though significant intraday variability and sensor error were considered in the simulations, by assuming a minimum inhibitory concentration of 1 mg/l for MRSA, the proposed controller was able to reach the well-established therapeutic target of 24-h area under curve to minimum inhibitory concentration ratio equal to 400 $\text{mg} \cdot \text{h}\text{/}\text{l}$ for all the studied subjects, while staying significantly below toxic levels. CONCLUSION: A PID controller has the potential to precisely deliver a vancomycin therapy in a noncritically ill-adult population. SIGNIFICANCE: Closed-loop control for precision Vancomycin delivery can potentially reduce toxicity and poor therapeutic outcomes, as well as reduce antimicrobial resistance.

Obtaining antibiotics online from within the UK: a cross-sectional study.

Background: Improved antibiotic stewardship (AS) and reduced prescribing in primary care, with a parallel increase in personal internet use, could lead citizens to obtain antibiotics from alternative sources online. Objectives: A cross-sectional analysis was performed to: (i) determine the quality and legality of online pharmacies selling antibiotics to the UK public; (ii) describe processes for obtaining antibiotics online from within the UK; and (iii) identify resulting AS and patient safety issues. Methods: Searches were conducted for 'buy antibiotics online' using Google and Yahoo. For each search engine, data from the first 10 web sites with unique URL addresses were reviewed. Analysis was conducted on evidence of appropriate pharmacy registration, prescription requirement, whether antibiotic choice was 'prescriber-driven' or 'consumer-driven', and whether specific information was required (allergies, comorbidities, pregnancy) or given (adverse effects) prior to purchase. Results: Twenty unique URL addresses were analysed in detail. Online pharmacies evidencing their location in the UK ( n = 5; 25%) required a prescription before antibiotic purchase, and were appropriately registered. Online pharmacies unclear about the location they were operating from ( n = 10; 50%) had variable prescription requirements, and no evidence of appropriate registration. Nine (45%) online pharmacies did not require a prescription prior to purchase. For 16 (80%) online pharmacies, decisions were initially consumer-driven for antibiotic choice, dose and quantity. Conclusions: Wide variation exists among online pharmacies in relation to antibiotic practices, highlighting considerable patient safety and AS issues. Improved education, legislation, regulation and new best practice stewardship guidelines are urgently needed for online antibiotic suppliers.

Mapping the decision pathways of acute infection management in secondary care among UK medical physicians: a qualitative study.

BACKGROUND: The inappropriate use of antimicrobials drives antimicrobial resistance. We conducted a study to map physician decision-making processes for acute infection management in secondary care to identify potential targets for quality improvement interventions. METHODS: Physicians newly qualified to consultant level participated in semi-structured interviews. Interviews were audio recorded and transcribed verbatim for analysis using NVIVO11.0 software. Grounded theory methodology was applied. Analytical categories were created using constant comparison approach to the data and participants were recruited to the study until thematic saturation was reached. RESULTS: Twenty physicians were interviewed. The decision pathway for the management of acute infections follows a Bayesian-like step-wise approach, with information processed and systematically added to prior assumptions to guide management. The main emerging themes identified as determinants of the decision-making of individual physicians were (1) perceptions of providing 'optimal' care for the patient with infection by providing rapid and often intravenous therapy; (2) perceptions that stopping/de-escalating therapy was a senior doctor decision with junior trainees not expected to contribute; and (3) expectation of interactions with local guidelines and microbiology service advice. Feedback on review of junior doctor prescribing decisions was often lacking, causing frustration and confusion on appropriate practice within this cohort. CONCLUSION: Interventions to improve infection management must incorporate mechanisms to promote distribution of responsibility for decisions made. The disparity between expectations of prescribers to start but not review/stop therapy must be urgently addressed with mechanisms to improve communication and feedback to junior prescribers to facilitate their continued development as prudent antimicrobial prescribers.

A report on a rare case of Klebsiella ozaenae causing atrophic rhinitis in the UK.

Ozena is a chronic disease of the nasal cavity characterised by atrophy of the mucosa and bone caused by Klebsiella ozaenae. It is endemic to subtropical and temperate regions affecting the lower socio-economic group, usually the poor who live in unhygienic conditions. It is a rare disease in the UK. There is usually a delay in diagnosis due to unfamiliarity of the disease. A 25-year-old Nigerian migrant presented with nasal obstruction with purulent nasal discharge. Isolation of the bacterium was found from cultures of nasal discharge, crusting and tissue biopsies. She was treated successfully with ciprofloxacin. It is important to consider this rare condition in cases of nasal obstruction even in non-endemic areas especially with the advances of modern travel.