Machine learning in clinical practice: Evaluation of an artificial intelligence tool after implementation.

OBJECTIVE: Artificial intelligence (AI) has gradually found its way into healthcare, and its future integration into clinical practice is inevitable. In the present study, we evaluate the accuracy of a novel AI algorithm designed to predict admission based on a triage note after clinical implementation. This is the first of such studies to investigate real-time AI performance in the emergency setting. METHODS: The novel AI algorithm that predicts admission using a triage note was translated into clinical practice and integrated within St Vincent's Hospital Melbourne's electronic emergency patient management system. The data were collected from 1 January 2021 to 17 August 2022 to evaluate the diagnostic accuracy of the AI system after implementation. RESULTS: A total of 77 125 ED presentations were included. The live AI algorithm has a sensitivity of 73.1% (95% confidence interval 72.5-73.8), specificity of 74.3% (73.9-74.7), positive predictive value of 50% (49.6-50.4) and negative predictive value of 88.7% (88.5-89) with a total accuracy of 74% (73.7-74.3). The accuracy of the system was at the lowest for admission to psychiatric units (34%) and at the highest for gastroenterology and medical admission (84% and 80%, respectively). CONCLUSION: Our study showed the diagnostic evaluation of a real-time AI clinical decision-support tool became less accurate than the original. Although real-time sensitivity and specificity of the AI tool was still acceptable as a decision-support tool in the ED, we propose that continuous training and evaluation of AI-enabled clinical support tools in healthcare are conducted to ensure consistent accuracy and performance to prevent inadvertent consequences.

Attitudes and regard for specific medical conditions among Australian emergency medicine clinicians.

OBJECTIVE: To quantify the attitude ED clinicians hold towards patients presenting with different medical conditions, including a novel pandemic condition. METHODS: A cross-sectional study of emergency doctors and nurses utilising the Medical Condition Regard Scale (MCRS); a validated tool used to capture the bias and emotions of clinicians towards individual medical conditions. The five conditions presented to participants each represent a classical medical, complex medical, psychiatric/substance use, somatoform and a novel medical condition. RESULTS: One hundred and ninety-six clinicians were included in the study including 116 nurses and 80 doctors. Concerning each condition, both medical and nursing staff demonstrated the highest regard for a classical medical condition (58 ± 5 and 57 ± 6, respectively). Significantly different from the classical medical condition, the lowest MCRS scores were for the somatoform condition (36 ± 10) for emergency doctors and the substance use condition (39 ± 11) for emergency nurses. Regard for a novel condition (i.e., COVID-19 infection) was comparably high among both cohorts. CONCLUSION: Emergency doctors and nurses generally hold lower regard for complex medical conditions with behavioural components, including substance use disorders and somatoform conditions.

Epidemiology, clinical presentations and outcome of patients presenting to the emergency department after a COVID-19 vaccination: An observational study.

OBJECTIVE: The World Health Organization declared the COVID-19 pandemic on 11 March 2020. In 2021, several vaccines were provisionally approved to reduce the risk of transmission and hospitalisation of COVID-19 infection. A surge in COVID-19 vaccination was seen between August and October 2021 in Victoria, Australia. We hypothesised this led to an increase in ED presentations. METHODS: Patients in the present study were adults who presented to the ED within 21 days of receiving a dose of a COVID-19 vaccine between 11 August 2021 and 14 November 2021. All cases underwent chart reviews to extract epidemiological features, clinical presentations, ED assessments, investigations and disposition. RESULTS: Notably, 968 patients were included in the study, comprising 6.1% of all ED presentations during the study period. The median age was 31 years. 82.9% of patients were younger than 45 years. 20.1% of patients arrived by ambulance. Chest pain was the most common presenting complaint (43.6%), followed by headache (10.3%) and palpitations (8.2%). The most common investigations were a full blood examination (73.5%), an ECG (63.8%) and serum troponin (49.1%). 64.8% of patients were directly discharged home and 22.1% were sent home after a short stay admission. Only 2.2% of patients were admitted to the hospital. CONCLUSION: A majority of patients who presented to the ED after their COVID vaccinations were young and discharged home after the initial assessment. These presentations have significantly increased the workload in prehospital settings and EDs, contributing to increased investigation usage, ED treatment space occupancy, and increased costs to the health system.

The Australian drug harms ranking study.

BACKGROUND/AIM: The aim of the current study was to review drug harms as they occur in Australia using the Multi-criteria Decision Analysis (MCDA) methodology adopted in earlier studies in other jurisdictions. METHOD: A facilitated workshop with 25 experts from across Australia, was held to score 22 drugs on 16 criteria: 9 related to harms that a drug produces in the individual and 7 to harms to others. Participants were guided by facilitators through the methodology and principles of MCDA. In open discussion, each drug was scored on each criterion. The criteria were then weighted using a process of swing weighting. Scoring was captured in MCDA software tool. RESULTS: MCDA modelling showed the most harmful substances to users were fentanyls (part score 50), heroin (part score 45) and crystal methamphetamine (part score 42). The most harmful substances to others were alcohol (part score 41), crystal methamphetamine (part score 24) and cigarettes/tobacco (part score 14). Overall, alcohol was the most harmful drug when harm to users and harm to others was combined. A supplementary analysis took into consideration the prevalence of each substance in Australia. Alcohol was again ranked the most harmful substance overall, followed by cigarettes, crystal methamphetamine, cannabis, heroin and pharmaceutical opioids. CONCLUSIONS: The results of this study make an important contribution to the emerging international picture of drug harms. They highlight the persistent and pervasive harms caused by alcohol. Policy implications and recommendations are discussed. Policies to reduce harm from alcohol and methamphetamine should be a priority.

Intravenous midazolam-droperidol combination, droperidol or olanzapine monotherapy for methamphetamine-related acute agitation: subgroup analysis of a randomized controlled trial.

AIM: To examine the efficacy and safety of (1) midazolam-droperidol versus droperidol and (2) midazolam-droperidol versus olanzapine for methamphetamine-related acute agitation. DESIGN AND SETTING: A multi-centre, randomized, double-blind, controlled, clinical trial was conducted in two Australian emergency departments, between October 2014 and September 2015. PARTICIPANTS: Three hundred and sixty-one patients, aged 18-65 years, requiring intravenous medication sedation for acute agitation, were enrolled into this study. We report the results of a subgroup of 92 methamphetamine-affected patients. INTERVENTION AND COMPARATOR: Patients were assigned randomly to receive either an intravenous bolus of midazolam 5 mg-droperidol 5 mg combined, droperidol 10 mg or olanzapine 10 mg. Two additional doses were administered, if required: midazolam 5 mg, droperidol 5 mg or olanzapine 5 mg, respectively. MEASUREMENTS: The primary outcome was the proportion of patients sedated adequately at 10 minutes. Odds ratios with 95% confidence intervals (ORs, 95% CI) were estimated. FINDINGS: The baseline characteristics of patients in the three groups were similar. At 10 minutes, significantly more patients in the midazolam-droperidol group [29 of 34 (85.3%)] were sedated adequately compared with the droperidol group [14 of 30 (46.7%), OR = 6.63, 95% CI = 2.02-21.78] or with the olanzapine group [14 of 28 (50.0%), OR 5.80, 95% CI = 1.74-19.33]. The number of patients who experienced an adverse event (AE) in the midazolam-droperidol, droperidol and olanzapine groups was seven of 34, two of 30 and six of 28, respectively. The most common AE was oxygen desaturation. CONCLUSION: A midazolam-droperidol combination appears to provide more rapid sedation of patients with methamphetamine-related acute agitation than droperidol or olanzapine alone.

Midazolam-Droperidol, Droperidol, or Olanzapine for Acute Agitation: A Randomized Clinical Trial.

STUDY OBJECTIVE: We aim to determine the most efficacious of 3 common medication regimens for the sedation of acutely agitated emergency department (ED) patients. METHODS: We undertook a randomized, controlled, double-blind, triple-dummy, clinical trial in 2 metropolitan EDs between October 2014 and August 2015. Patients aged 18 to 65 years and requiring intravenous medication sedation for acute agitation were enrolled and randomized to an intravenous bolus of midazolam 5 mg-droperidol 5 mg, droperidol 10 mg, or olanzapine 10 mg. Two additional doses were administered, if required: midazolam 5 mg, droperidol 5 mg, or olanzapine 5 mg. The primary outcome was the proportion of patients adequately sedated at 10 minutes. RESULTS: Three hundred forty-nine patients were randomized to the 3 groups. Baseline characteristics were similar across the groups. Ten minutes after the first dose, significantly more patients in the midazolam-droperidol group were adequately sedated compared with the droperidol and olanzapine groups: differences in proportions 25.0% (95% confidence interval [CI] 12.0% to 38.1%) and 25.4% (95% CI 12.7% to 38.3%), respectively. For times to sedation, the differences in medians between the midazolam-droperidol group and the droperidol and olanzapine groups were 6 (95% CI 3 to 8) and 6 (95% CI 3 to 7) minutes, respectively. Patients in the midazolam-droperidol group required fewer additional doses or alternative drugs to achieve adequate sedation. The 3 groups' adverse event rates and lengths of stay did not differ. CONCLUSION: Midazolam-droperidol combination therapy is superior, in the doses studied, to either droperidol or olanzapine monotherapy for intravenous sedation of the acutely agitated ED patient.

Patient perceptions of privacy infringements in an emergency department.

OBJECTIVE: To identify the nature, severity, impact, frequency and risk factors for patient perceived privacy infringements in the ED of St Vincent's Health Melbourne with 32,000 emergency attendances per annum. METHODS: Patients 18 years and older attending emergency over a 2-week period were offered a nine-item questionnaire using a Likert scale. A privacy incident was defined as: (i) overhearing medical or personal information; (ii) being overheard; (iii) having private body parts exposed or (iv) seeing others' body parts. Differences between demographic, emergency environment, length of stay and other factors suspected of affecting patient privacy were quantified. RESULTS: From 1169 emergency presentations, 235 patients returned questionnaires, with 105 of these (45%) reporting a total of 159 privacy incidents. Seventy-eight patients (33%, 95% CI 28-36%) reported a definite privacy incident and 81 (35%, 95% CI 29-37%) reported a probable privacy incident. Ninety-six patients (41%, 95% CI 35-47%) reported overhearing other patient's conversations with the staff whereas 36 (15%, 95% CI 11-21%) felt their conversations with staff were overheard by others. Twenty-seven patients (11%, 95% CI 6-14%) experienced or observed inappropriate exposure of private body parts. Ten patients (4%, 95% CI 2-7%) changed or withheld information from staff because they felt others may overhear it and two refused part of their physical examination because they felt they may be seen by inappropriate people. Twenty-four patients (10%, 95% CI 6-14%) did not have their expectations of privacy met. The longer a patient was in emergency the greater the number of privacy incidents they experienced (Spearman correlation P < 0.01). Patients in walled cubicles experienced fewer privacy incidents than those in curtained cubicles (P < 0.05). CONCLUSIONS: Patient privacy incidents occur frequently in an ED, risk factors being length of stay and absence of a walled cubicle. Patients who have their conversations overheard are more likely to withhold information from staff and less likely to have had their expectations of privacy met.