Assessment of a Geriatric Evaluation and Management in the Home (GEMITH) Service at a Quaternary Hospital: A Retrospective Observational Study.

Background: The increasing aging population in Australia has created a higher demand for specialist geriatric services within hospitals. A Geriatric Evaluation and Management in the Home (GEMITH) service was implemented at a quaternary Queensland hospital. The GEMITH service was unique as it incorporated a specialist pharmacist into the multidisciplinary team. Objective: To determine the medication safety and quality impact of the GEMITH service by evaluating the type and clinical significance of specialist pharmacist interventions. Methods: This was retrospective observational study of clinical interventions made by the GEMITH pharmacist for patients admitted to the service between October 2020 to April 2021. All pharmacist interventions were rated for their clinical significance using the Society of Hospital Pharmacists of Australia (SHPA) risk classification system. The ratings were undertaken by a panel of three pharmacists that independently assessed the interventions, coming together for final discussion. A narrative analysis of the interventions were derived through group consensus. Results: There was a total of 119 admissions to the GEMITH service, with 132 clinical interventions made by the specialist geriatric pharmacist. The majority (47%) of interventions were considered as low risk interventions, although high- (21%) and extreme-risk (2%) interventions still occurred. The most common type of intervention (32%) involved medication reconciliation. Other intervention types included monitoring recommendations, dosing interventions, and deprescribing suggestions. Conclusion: Multiple clinical interventions were made by the GEMITH pharmacist, which prevented possible and significant medication-related harm. This demonstrated the quality impact of the specialist pharmacist in improving medication safety for geriatric patients.

Evaluating automated machine learning platforms for use in healthcare.

Objective: To describe development and application of a checklist of criteria for selecting an automated machine learning (Auto ML) platform for use in creating clinical ML models. Materials and Methods: Evaluation criteria for selecting an Auto ML platform suited to ML needs of a local health district were developed in 3 steps: (1) identification of key requirements, (2) a market scan, and (3) an assessment process with desired outcomes. Results: The final checklist comprising 21 functional and 6 non-functional criteria was applied to vendor submissions in selecting a platform for creating a ML heparin dosing model as a use case. Discussion: A team of clinicians, data scientists, and key stakeholders developed a checklist which can be adapted to ML needs of healthcare organizations, the use case providing a relevant example. Conclusion: An evaluative checklist was developed for selecting Auto ML platforms which requires validation in larger multi-site studies.

The adverse inpatient medication event and frailty (AIME-frail) risk prediction model.

BACKGROUND: Medication harm affects between 5 and 15% of hospitalised patients, with approximately half of the harm events considered preventable through timely intervention. The Adverse Inpatient Medication Event (AIME) risk prediction model was previously developed to guide a systematic approach to patient prioritisation for targeted clinician review, but frailty was not tested as a candidate predictor variable. AIM: To evaluate the predictive performance of an updated AIME model, incorporating a measure of frailty, when applied to a new multisite cohort of hospitalised adult inpatients. METHODS: A retrospective cohort study was conducted at two tertiary Australian hospitals on patients discharged between 1st January and April 31, 2020. Data were extracted from electronic medical records (EMRs) and clinical coding databases. Medication harm was identified using ICD-10 Y-codes and confirmed by senior pharmacist review of medical records. The Hospital Frailty Risk Score (HFRS) was calculated for each patient. Logistic regression analysis was used to construct a modified AIME model. Candidate variables of the original AIME model, together with new variables including HFRS were tested. Performance of the final model was reported using area under the curve (AUC) and decision curve analysis (DCA). RESULTS: A total of 4089 patient admissions were included, with a mean age ± standard deviation (SD) of 64 years (±19 years), 2050 patients (50%) were males, and mean HFRS was 6.2 (±5.9). 184 patients (4.5%) experienced one or more medication harm events during hospitalisation. The new AIME-Frail risk model incorporated 5 of the original variables: length of stay (LOS), anti-psychotics, antiarrhythmics, immunosuppressants, and INR greater than 3, as well as 5 new variables: HFRS, anticoagulants, antibiotics, insulin, and opioid use. The AUC was 0.79 (95% CI: 0.76-0.83) which was superior to the original model (AUC = 0.70, 95% CI: 0.65-0.74) with a sensitivity of 69%, specificity of 81%, positive predictive value of 0.14 (95% CI: 0.10-0.17) and negative predictive value of 0.98 (95% CI: 0.97-0.99). The DCA identified the model as having potential clinical utility between the probability thresholds of 0.05-0.4. CONCLUSION: The inclusion of a frailty measure improved the predictive performance of the AIME model. Screening inpatients using the AIME-Frail tool could identify more patients at high-risk of medication harm who warrant timely clinician review.

Exploring stakeholders' perspectives on antibiogram use, development, and implementation in residential aged care settings.

BACKGROUND: Knowledge of local antibiotic resistance data provided by antibiograms (cumulative-antimicrobial-susceptibility-tests) can assist prescribers to make appropriate empirical antibiotic choices. OBJECTIVE: This study explored the perceptions and knowledge of key stakeholders about the role of antibiograms in residential aged care facilities (RACF), and to understand barriers and enablers of antibiogram development and implementation in this setting. METHOD: Semi-structured interviews were conducted with aged-care health professionals ('end-users') and antibiogram content experts. This study was conducted in Queensland, Australia in 2023. Using qualitative techniques, framework thematic analysis was used to identify themes, which were mapped to the 'Integrated Promoting Action on Research Implementation in Health Services' framework constructs. RESULTS: Twenty interviews were conducted comprising of five 'content-experts' and fifteen 'end-users'. Five themes were identified which indicated lack of knowledge about how to use antibiograms, and its availability. Potential insufficient data was the primary issue identified by content experts with regards to feasibility of annual antibiograms. Pragmatic solutions were offered, such as pooling pathology data from facilities in the same geographical location, extending antibiogram data to two-or three-yearly, or utilising local hospital antibiograms. Presenting antibiogram data in a mode and format suiting preferences of individual users would encourage uptake and improve usability. Antimicrobial stewardship (AMS) champions and pharmacists were highlighted as drivers of educating and promoting antibiogram use. CONCLUSION: Clinicians recognised the potential role of antibiograms in improving empirical antibiotic prescribing choices. Establishing their baseline knowledge provides an essential starting point for the education needs of this group. This study provides practical recommendations regarding the presentation of antibiograms to ensure appropriate use and uptake as an AMS tool in RACFs. Pragmatic solutions suggested to overcome challenges of antibiogram development for RACFs should be applied and evaluated to determine feasibility of RACF-specific antibiograms.

Evidence-based Medication knowledge Brokers in Residential Aged CarE (EMBRACE): protocol for a helix-counterbalanced randomised controlled trial.

INTRODUCTION: Clinical practice guidelines recommend against the routine use of psychotropic medications in residential aged care facilities (RACFs). Knowledge brokers are individuals or groups who facilitate the transfer of knowledge into practice. The objective of this trial is to evaluate the effectiveness and cost-effectiveness of using knowledge brokers to translate Australia's new Clinical Practice Guidelines for the Appropriate Use of Psychotropic Medications in People Living with Dementia and in Residential Aged Care. METHODS AND ANALYSIS: The Evidence-based Medication knowledge Brokers in Residential Aged CarE (EMBRACE) trial is a helix-counterbalanced randomised controlled trial. The 12-month trial will be conducted in up to 19 RACFs operated by four Australian aged care provider organisations in Victoria, New South Wales, Western Australia and Queensland. RACFs will be randomised to receive three levels of implementation strategies (knowledge broker service, pharmacist-led quality use of medications education activities and distribution of the Guidelines and supporting materials) across three medication contexts (antipsychotics, benzodiazepines and antidepressants). Implementation strategies will be delivered by an embedded on-site aged care pharmacist working at a system level across each participating RACF. All RACFs will receive all implementation strategies simultaneously but for different medication contexts. The primary outcome will be a composite dichotomous measure of 6-month RACF-level concordance with Guideline recommendations and good practice statements among people using antipsychotics, benzodiazepines and antidepressants for changed behaviours. Secondary outcomes will include proportion of residents with Guideline concordant use of antipsychotics, benzodiazepines and antidepressants measured at the RACF-level and proportion of residents with psychotropic medication use, hospitalisation, falls, falls with injury, polypharmacy, quality of life, activities of daily living, medication incidents and behavioural incidents measured at the RACF-level. DISCUSSION: The EMBRACE trial investigates a novel guideline implementation strategy to improve the safe and effective use of psychotropic medications in RACFs. We anticipate that the findings will provide new information on the potential role of knowledge brokers for successful and cost-effective guideline implementation. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR): ACTRN12623001141639. Registered 6 November 2023 - retrospectively registered, https://www.anzctr.org.au/TrialSearch.aspx .

Clinical impact of antibiograms as an intervention to optimize antimicrobial prescribing and patient outcomes-A systematic review.

BACKGROUND: Antimicrobial stewardship (AMS) guidelines advocate for the use of antibiograms (cumulative antimicrobial susceptibility test data) as a tool to guide empirical antibiotic prescribing and inform local treatment guidelines. The objective of this review is to evaluate the effectiveness of antibiograms as an intervention to optimize antimicrobial prescribing and patient outcomes. METHODS: Embase, PubMed, CINAHL, and International Pharmacy Abstracts (IPA) databases were searched from inception until September 2022, to identify studies of antibiogram-related interventions in all health care settings. The National Institutes of Health Quality Assessment Tools were used to assess the methodological quality of the included studies. RESULTS: Of the 37 included studies, the majority of studies were conducted in the United States (n = 25) and in hospital settings (n = 27). All interventions were multifaceted and in 26 (70%) studies, facility-specific antibiograms could be considered as an integral component of the interventions. A positive impact on antibiotic consumption trends (17 studies), appropriateness of prescribing (16 studies), and cost of treatment (6 studies) was found, with minimal evidence for improvement in mortality, hospitalization, and resistance profiles. Due to the heterogeneity in study designs and outcomes, a meta-analysis was not performed. CONCLUSIONS: AMS interventions including antibiograms may improve antibiotic use, appropriateness, and costs. Multifaceted interventions were often used, which precludes drawing conclusions about the effectiveness of antibiograms alone as an AMS tool.

Impact of pharmacists during in-hospital resuscitation or medical emergency response events: A systematic review.

BACKGROUND: We sought to determine the impact of the presence of a pharmacist on medication and patient related outcomes during the emergency management of critically ill patients requiring resuscitation or medical emergency response team care in a hospital setting. METHODS: We conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of databases from January 1995 to April 2023 was conducted to identify studies of contemporary pharmacist practice. Results were extracted and analysed for included studies, those evaluating the impact of the presence of a pharmacist on medication and patient related outcomes during the emergency management of critically ill hospitalised patients requiring resuscitation or medical emergency response team care. To determine risk of bias, the Newcastle-Ottowa Quality Assessment scale was used for non-randomised studies and the Revised Cochrane risk-of-bias tool for randomised trials. RESULTS: Of 1345 studies identified, 54 were selected for full text review, and 30 were included in the final analysis. There were 29 cohort studies and one randomised controlled trial. The studies reported the impact of a pharmacist for a variety of patient presentations. The study team assigned each study to one of eight patient cohorts: acute stroke, cardiac arrest, rapid response calls, S-T segment elevation myocardial infarction, acute haemorrhage, major trauma resuscitation, sepsis and status epilepticus. The most frequently reported outcome, associated with a statistically significant benefit in 23 studies, was time to medication administration. Few studies reported a significant difference in patient outcome measures such as mortality. Only 8 of the 30 studies were assessed to have a low risk of bias. CONCLUSIONS: The results of this systematic review provide support for a beneficial impact of a pharmacist presence and intervention during resuscitation or medical emergency response team care, with significant improvements in outcomes such as time to initiation of time-critical medications, medication appropriateness and guideline compliance. However, studies were predominantly small and retrospective and were not powered to detect differences in patient related measures such as length of stay and mortality. Future research should investigate the clinical impacts of the pharmacist in ED resuscitation settings in controlled, prospective studies with robust sampling methods.

Experiences and learnings of pharmacists, students, and clinical assistants working collaboratively in a COVID-19 vaccination clinic: a qualitative study.

Background: The involvement of pharmacists and pharmacy clinical assistants (CAs) in hospital clinics has demonstrated benefits for improving medication safety and care delivery. Internationally, pharmacy staff played a crucial role in the safe storage, provision and administration of vaccines, as well as reinforcement of pharmacovigilance efforts during the COVID-19 pandemic. In Australia, healthcare providers collaborated to rapidly facilitate a phased COVID-19 vaccination program. The perspectives of the pharmacy team, including pharmacy students, involved in implementing novel health services are underexplored in the literature. Objective: To describe the key learnings in how a team of pharmacists, CAs and pharmacy students contributed to the COVID-19 vaccine service, and to explore their preparedness and experiences working at a vaccination clinic within a quaternary hospital. Method: This study involved semi-structured interviews with pharmacy students, CAs and pharmacists. All pharmacy staff who worked in the clinic were invited to participate in the study and a snowball strategy was used to maximise recruitment. The interviews were audio-recorded, transcribed, and analysed using inductive thematic techniques to identify major themes. Results: A total of 11 participants were interviewed including: four pharmacists, four CAs and three undergraduate students. Using thematic analysis, five main themes were identified: (1) Potential for student value and experiential learning; (2) Adaptive procedures and work practices in a rapidly changing environment; (3) Clear leadership, with role clarity, role expansion and interchangeability; (4) Supportive learning environment and (5) Stakeholder drivers for service delivery and to optimise societal benefit. These five themes often interacted with each other, highlighting the complexities of implementing and operating the service. Conclusions: The vaccine clinic service provided a novel and valuable opportunity for students, CAs, and pharmacists to work collaboratively, extending their scope of practice to contribute to better national health outcomes. Participants expressed their support for future initiatives involving pharmacy students and healthcare staff collaborating in hospital settings.

Evaluation of the Quality and Safety of Venous Thromboembolism Prophylaxis Among Gastroenterology Inpatients at a Tertiary Hospital in Australia.

Background and objective: Hospital acquired venous thromboembolisms (VTEs) are common and preventable. The Queensland Health VTE prophylaxis guidelines, developed in 2018, provide guidance for risk assessment, and prescribing of anticoagulation for prophylaxis and treatment of hospital inpatients. Currently, there are limited recommendations for gastroenterology patients. This study investigated the completion of VTE risk assessments, and the appropriateness of VTE prophylaxis regimens, in accordance with Queensland Health guidelines for gastroenterology patients. The quality and safety of VTE prophylaxis regimens was assessed based on their VTE risk and bleeding risk. Method: A retrospective study was conducted by obtaining a random sample of gastroenterology patients admitted to a tertiary Australian hospital, from 1st May 2019 and 1st May 2020, to determine the compliance of VTE risk assessment and thromboprophylaxis prescribing with state-wide VTE guidelines. The quality and safety of thromboprophylaxis was evaluated using the modified Caprini and HASBLED scores, and subsequent thromboprophylaxis-related complications. Results: Of the 94 patients reviewed, 68 did not have contraindications to thromboprophylaxis. Of these 68 patients, 32 (47%) had no VTE risk assessment recorded in their clinical records and were not prescribed any thromboprophylaxis during the hospitalization. There was no significant difference between thromboprophylaxis prescribing for patients with low VTE risk, compared to moderate to high VTE risk (P = .075). There was a trend for decrease in thromboprophylaxis prescribing as HASBLED bleeding risk score increased, and patients with moderate-high bleed risk were less likely to be prescribed thromboprophylaxis (P = .006). There were no thromboprophylaxis related complications identified. Conclusion: It is essential that all patients have a clearly documented risk assessment and are prescribed thromboprophylaxis according to best practice guidelines. The prescription of venous thromboembolism prophylaxis should continue to be individualized, with each patient assessed holistically.

Predicting Therapeutic Response to Unfractionated Heparin Therapy: Machine Learning Approach.

BACKGROUND: Unfractionated heparin (UFH) is an anticoagulant drug that is considered a high-risk medication because an excessive dose can cause bleeding, whereas an insufficient dose can lead to a recurrent embolic event. Therapeutic response to the initiation of intravenous UFH is monitored using activated partial thromboplastin time (aPTT) as a measure of blood clotting time. Clinicians iteratively adjust the dose of UFH toward a target, indication-defined therapeutic aPTT range using nomograms, but this process can be imprecise and can take ≥36 hours to achieve the target range. Thus, a more efficient approach is required. OBJECTIVE: In this study, we aimed to develop and validate a machine learning (ML) algorithm to predict aPTT within 12 hours after a specified bolus and maintenance dose of UFH. METHODS: This was a retrospective cohort study of 3019 patient episodes of care from January 2017 to August 2020 using data collected from electronic health records of 5 hospitals in Queensland, Australia. Data from 4 hospitals were used to build and test ensemble models using cross-validation, whereas data from the fifth hospital were used for external validation. We built 2 ML models: a regression model to predict the aPTT value after a UFH bolus dose and a multiclass model to predict the aPTT, classified as subtherapeutic (aPTT <70 seconds), therapeutic (aPTT 70-100 seconds), or supratherapeutic (aPTT >100 seconds). Modeling was performed using Driverless AI (H2O), an automated ML tool, and 17 different experiments were iteratively conducted to optimize model accuracy. RESULTS: In predicting aPTT, the best performing model was an ensemble with 4x LightGBM models with a root mean square error of 31.35 (SD 1.37). In predicting the aPTT class using a repurposed data set, the best performing ensemble model achieved an accuracy of 0.599 (SD 0.0289) and an area under the receiver operating characteristic curve of 0.735. External validation yielded similar results: root mean square error of 30.52 (SD 1.29) for the aPTT prediction model, and accuracy of 0.568 (SD 0.0315) and area under the receiver operating characteristic curve of 0.724 for the aPTT multiclassification model. CONCLUSIONS: To the best of our knowledge, this is the first ML model applied to intravenous UFH dosing that has been developed and externally validated in a multisite adult general medical and surgical inpatient setting. We present the processes of data collection, preparation, and feature engineering for replication.

Economic evaluation of antimicrobial stewardship in primary care: a systematic review and quality assessment.

BACKGROUND: Primary care accounts for 80%-90% of antimicrobial prescriptions, making this setting an important focus for antimicrobial stewardship (AMS) interventions. OBJECTIVES: To collate the findings and critically appraise the qualities of economic evaluation studies of AMS or related interventions aimed at reducing inappropriate antimicrobial prescribing in primary care. METHODS: A systematic review of economic evaluations of interventions aimed at reducing inappropriate antimicrobial prescribing in primary care was performed. Published literature were retrieved through a search of Medline, Embase, EconLit and Web of Science databases for the period 2010 to 2020. The quality of the studies was assessed using the Consensus on Health Economic Criteria checklist and Good Practice Guidelines for Decision-Analytic Modelling in Health Technology Assessment. RESULTS: Of the 2722 records identified, 12 studies were included in the review (8 trial-based and 4 modelled evaluations). The most common AMS interventions were communication skills training for health professionals and C-reactive protein point-of-care testing (CRP-POCT). Types of economic evaluations included in the review were cost-effectiveness (7 studies), cost-utility (1), cost-benefit (2), cost-effectiveness and cost-utility (1) and cost analysis (1). While six of the studies found AMS interventions to be cost-effective, the other six reported them as not cost-effective or inconclusive. The quality of the studies ranged from good to low. CONCLUSIONS: There were significant variations in cost-effectiveness of AMS interventions across studies and depending on the inclusion of cost components such as the cost of antimicrobial resistance. However, communication skills training and CRP-POCT were frequently cost-effective or cost-beneficial for reducing inappropriate antimicrobial prescribing.

Scoping Review of Studies Evaluating Frailty and Its Association with Medication Harm.

INTRODUCTION: Frailty is associated with an increased risk of death and morbid events. Frail individuals are known to have multiple comorbidities which are often associated with polypharmacy. Whilst a relationship between polypharmacy and frailty has been demonstrated, it is not clear if there is an independent relationship between frailty and medication harm. AIMS: This scoping review aimed to identify and critically appraise studies evaluating medication harm in patients with frailty. METHODS: PubMed, EMBASE, CINAHL and Cochrane databases were searched from inception until 1 February 2021 using key search terms that are synonymous with frailty (such as frail and frail elderly) and medication harm (such as adverse drug events and adverse drug reactions). To be included, studies must have identified medication harm as a primary or secondary outcome measure, and used a frailty assessment tool to determine frailty, or clearly defined how frailty was assessed. Data were narratively synthesised and presented in tables. The checklist from the Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies from the National Heart, Lung, and Blood Institute was used to assess the quality and risk of bias of studies that met the inclusion criteria. RESULTS: Of 2685 retrieved abstracts, 24 underwent full-text review and nine studies met the inclusion criteria. Three studies were retrospective cohort studies, and six were prospective observational studies. Six studies comprised two distinct groups of frail and non-frail individuals, and the remaining three studies evaluated medication harm in an entirely frail population. Seven studies used validated frailty tools such as the Clinical Frailty Scale, Fried Frailty Index, and Fried Frailty Phenotype. Two studies measured frailty using self-defined criteria. Overall, frail individuals were at risk of medication harm with rates ranging between 18.7 and 77% across the nine studies. However, whether frailty is an independent predictor of medication harm remains uncertain, as this was only evaluated in one study. The risk of bias assessment identified limitations in methods and reporting with all nine studies. CONCLUSION: This scoping review identified nine studies evaluating medication harm in frail patients. However, all were limited by the methodological quality and inadequate reporting of study factors. There are few high-quality studies that described a relationship between medication harm and frailty. More robust studies are required that examine the independent relationship between frailty and medication harm, after adjusting for all possible confounders and in particular polypharmacy.

A multimodal intervention to optimise antimicrobial use in residential aged care facilities (ENGAGEMENT): protocol for a stepped-wedge cluster randomised trial.

BACKGROUND: Inappropriate antibiotic use can cause harm and promote antimicrobial resistance, which has been declared a major health challenge by the World Health Organization. In Australian residential aged care facilities (RACFs), the most common indications for antibiotic prescribing are for infections of the urinary tract, respiratory tract and skin and soft tissue. Studies indicate that a high proportion of these prescriptions are non-compliant with best prescribing guidelines. To date, a variety of interventions have been reported to address inappropriate prescribing and overuse of antibiotics but with mixed outcomes. This study aims to identify the impact of a set of sustainable, multimodal interventions in residential aged care targeting three common infection types. METHODS: This protocol details a 20-month stepped-wedge cluster-randomised trial conducted across 18 RACFs (as 18 clusters). A multimodal multi-disciplinary set of interventions, the 'AMS ENGAGEMENT bundle', will be tailored to meet the identified needs of participating RACFs. The key elements of the intervention bundle include education for nurses and general practitioners, telehealth support and formation of an antimicrobial stewardship team in each facility. Prior to the randomised sequential introduction of the intervention, each site will act as its own control in relation to usual care processes for antibiotic use and stewardship. The primary outcome for this study will be antibiotic consumption measured using defined daily doses (DDDs). Cluster-level rates will be calculated using total occupied bed numbers within each RACF during the observation period as the denominator. Results will be expressed as rates per 1000 occupied bed days. An economic analysis will be conducted to compare the costs associated with the intervention to that of usual care. A comprehensive process evaluation will be conducted using the REAIM Framework, to enable learnings from the trial to inform sustainable improvements in this field. DISCUSSION: A structured AMS model of care, incorporating targeted interventions to optimise antimicrobial use in the RACF setting, is urgently needed and will be delivered by our trial. The trial will aim to empower clinicians, residents and families by providing a robust AMS programme to improve antibiotic-related health outcomes. TRIAL REGISTRATION: US National Library of Medicine Clinical Trials.gov ( NCT04705259 ). Prospectively registered in 12th of January 2021.

Evaluation of two European risk models for predicting medication harm in an Australian patient cohort.

PURPOSE: To externally evaluate the performance of two European risk prediction models, for identifying patients at high-risk of medication harm, in an Australian hospital setting. METHODS: This was a secondary analysis of a pre-existing cohort study described in a recently published study by Falconer et al. (Br J Clin Pharmacol 87(3):1512-1524, 2021) describing the development of a predictive risk model for inpatient medication harm. We retrospectively extracted relevant variables using the electronic health records of general medical and geriatric patients admitted to a quaternary hospital, in Brisbane, over 6 months from July to December 2017. This dataset was used to externally evaluate the two European models, The Brighton Adverse Drug Reaction Risk (BADRI) model by Tangiisuran et al. and a risk model developed by Trivalle et al. The variables were entered into both models and the patients' risk of medication harm was calculated, and compared with actual patient outcomes. Predictive performance was evaluated by measuring area under the receiver operative characteristic (AuROC) curves. RESULTS: The Australian patient cohort included 1982 patients (median age 74 years), of which 136 (7%) patients experienced ≥ 1 medication harm event(s). External evaluation of the two European models identified that both the BADRI and the Trivalle models had reduced predictive performance in an Australian patient cohort, compared with their original studies (AuROC of 0.63 [95% CI: 0.58-0.68] and 0.60 [95% CI: 0.55-0.65], respectively). CONCLUSION: Neither model demonstrated sufficient discrimination to warrant further evaluation in our local setting. This is likely a result of variations between the development and the validation cohorts, and the change in healthcare systems over time, and highlights the need for an up-to-date and context-specific risk prediction model.

Systematic review of machine learning models for personalised dosing of heparin.

AIM: To identify and critically appraise studies of prediction models, developed using machine learning (ML) methods, for determining the optimal dosing of unfractionated heparin (UFH). METHODS: Embase, PubMed, CINAHL, Web of Science, International Pharmaceutical Abstracts and IEEE Xplore databases were searched from inception to 31 January 2020 to identify relevant studies using key search terms synonymous with artificial intelligence or ML, 'prediction', 'dose', 'activated partial thromboplastin time (aPTT)' and 'UFH.' Studies had to have used ML methods for developing models that predicted optimal dose of UFH or target therapeutic aPTT levels in the hospital setting. The CHARMS Checklist was used to assess quality and risk of bias of included studies. RESULTS: Of 8393 retrieved abstracts, 61 underwent full text review and eight studies met inclusion criteria. Four studies described models for predicting aPTT, three studies described models predicting optimal dose of heparin during dialysis and one study described a model that used surrogate outcomes of clotting and bleeding to predict a therapeutic aPTT. Studies varied widely in reporting of study participants, feature characterisation and selection, handling of missing data, sample size calculations and the intended clinical application of the model. Only one study conducted an external validation and no studies evaluated model impacts in clinical practice. CONCLUSION: Studies of ML models for UFH dosing are few and none report a model ready for routine clinical use. Existing studies are limited by low methodological quality, inadequate reporting of study factors and absence of external validation and impact analysis.

The pharmacist informatician: providing an innovative model of care during the COVID-19 crisis.

OBJECTIVES: The global coronavirus pandemic has expedited digitisation in every industry, especially healthcare, and has highlighted the potential for informatics pharmacists to provide valuable input into crisis management. Informatics pharmacists can combine their clinical and information technology skills to help provide essential patient safety services related to medication management, procurement and analytics. The objective of this study was to determine the key opportunities for a pharmacist informatician to improve patient care and outcomes during the COVID-19 pandemic. METHODS: Fourteen expert informatics professionals involved in the provision of digital health in Queensland, Australia, were invited to participate in a brief semistructured interview. Transcripts were manually coded, through iterative readings of the text to identify participant responses related to opportunities for a pharmacist informatician to assist during COVID-19. Inductive thematic analysis as described by Braun and Clarke, was used to identify groups of text related to the provision of digital health, informatics and change of practice during a pandemic. The relevant codes were then grouped into themes to help answer the research question. KEY FINDINGS: Twelve experts agreed to participate, they included nine informatics pharmacists and three digital health experts from hospital and community. Two key themes and 13 codes related to enabling safer and more efficient workflow and use of data analytics to optimise care were identified. The first theme related to 'social distancing without compromising care' for example, by using the electronic capabilities of digital hospitals and telehealth services. The second theme related to the use of real-time data streaming to optimise patient flow and timely medication procurement and management. Examples of quotes from transcripts were used to provide context and answer the research question. CONCLUSIONS: The experts interviewed identified areas where informatics pharmacists have the potential to assist with maintaining high quality patient care during this pandemic, and in future disasters. Improving awareness, training, and the integration about informatics roles as a result of this global pandemic will likely assist with future patient management in the event of future disasters.

Development and validation of the Adverse Inpatient Medication Event model (AIME).

AIMS: Medication harm has negative clinical and economic consequences, contributing to hospitalisation, morbidity and mortality. The incidence ranges from 4 to 14%, of which up to 50% of events may be preventable. A predictive model for identifying high-risk inpatients can guide a timely and systematic approach to prioritisation. The aim of this study is to develop and internally validate a risk prediction model for prioritisation of hospitalised patients at risk of medication harm. METHODS: A retrospective cohort study was conducted in general medical and geriatric specialties at an Australian hospital over six months. Medication harm was identified using International Classification of Disease (ICD-10) codes and the hospital's incident database. Sixty-eight variables, including medications and laboratory results, were extracted from the hospital's databases. Multivariable logistic regression was used to develop the final risk model. Performance was evaluated using area under the receiver operative characteristic curve (AuROC) and clinical utility was determined using decision curve analysis. RESULTS: The study cohort included 1982 patients with median age 74 years, of which 136 (7%) experienced at least one adverse medication event(s). The model included: length of stay, hospital re-admission within 12 months, venous or arterial thrombosis and/or embolism, ≥ 8 medications, serum sodium < 126 mmol/L, INR > 3, anti-psychotic, antiarrhythmic and immunosuppressant medications, and history of medication allergy. Validation gave an AuROC of 0.70 (95% CI: 0.65-0.74). Decision curve analysis identified that the AIME may be clinically useful to help guide decision making in practice. CONCLUSION: We have developed a predictive model with reasonable performance. Future steps include external validation and impact evaluation.