Health information management : journal of the Health Information Management Association of Australia最新文献

Background: Artificial intelligence (AI) transforms healthcare data collection, analysis, and application, making AI proficiency a growing necessity across health professions.ObjectiveThis study aimed to examine the influence of demographic factors on AI literacy among Health Information (HI) professionals, identify key knowledge gaps and inform workforce-aligned training recommendations.

Method: This mixed-methods study analysed convenience-sampled survey data on AI literacy among HI professionals. Quantitative responses were examined with descriptive statistics, t-tests, Analysis of Variance (ANOVA), Spearman rank-order correlation, linear regression, geospatial analysis and a random forest to examine AI knowledge across demographic groups. The one qualitative open-ended response was analysed with latent Dirichlet allocation (LDA) topic modelling to identify themes.ResultsA total of 128 valid responses were analysed, including 22 participants who completed the technical knowledge section and 48 who responded to the open-ended question on AI education. Higher educational attainment and geographic location significantly predicted greater general AI literacy. However, no significant associations were found between AI literacy (general or technical) and age group, possession of non-health informatics credentials or prior AI experience. The cross-validated Random Forest models were assessed with and without oversampling. Accuracy was identical across both models (0.95), indicating that the overall prediction correctness of low versus high AI literacy was not affected by oversampling. The oversampled model had a superior ability to detect the minority class, making it more suitable for imbalanced classification tasks where recall is critical.

Conclusion: This study identified several important knowledge gaps on the influence of demographic factors on AI literacy, which informs workforce-aligned training recommendations. These findings underscore the need for competency-based education to strengthen AI readiness within the health information workplace.Implications for health information management practice:The thematic analysis demonstrated the urgent need for AI knowledge, training and literacy for HI professionals and students. Themes from the LDA topic modelling informed the development of AI educational frameworks, structured into domains, subdomains and specific components of educational competencies. With multidisciplinary collaboration and further research, standardised AI core competencies for HI professionals could be created, validated by experts and adopted across educational programs to improve AI literacy in the HI field.

Background: This study shares insights from clinical trialists who have conducted investigator-initiated trials that have linked trial data to administrative data, focusing on the challenges and facilitators of this approach.

Objective: To provide recommendations for evaluating the feasibility and suitability of using administrative data in clinical trials.

Method: A convergent parallel mixed-methods study was conducted, surveying Australian clinical trialists and operations staff. Participants could opt-in to in-depth interviews. Survey data were analysed using descriptive statistics, while thematic analysis was applied to interview data, with findings integrated during interpretation.

Results: Four main themes and 10 sub-themes were identified as critical when evaluating the suitability of administrative data for clinical trials: (i) "trial management considerations" covers operational factors like budgeting, timelines and staffing; (ii) "assessing burdens vs. gains" encourages weighing up the research benefits with the additional operational and consent considerations; (iii) "data preparation and analysis" addresses the processes involved in preparing and analysing data for linkage between trial and administrative datasets; and (iv) "training and support" emphasises the need for researcher support when using linked data.

Conclusion: Researchers should carefully evaluate the feasibility of using administrative data, considering costs, required skills, timelines and data accuracy. They must also be prepared for delays due to data request processes, participant consent requirements and the mandated use of data access platforms. Early planning can mitigate later complexities.Implications for health information management practice:This study highlights the value of health information managers in clinical research, particularly in managing electronic health records and clinical coding. Their expertise in these areas, as well as in data governance and system architecture, can support clinical trials that link to administrative data.

Background: Automated clinical coding can use statistical or artificial intelligence-based technology to transform unstructured clinical data into clinical codes. These processes have the potential to enhance the quality and accuracy of data collections, save resources and accelerate research.

Objective: To evaluate the use of automated clinical coding in the United Kingdom (UK) and European cancer registries.

Method: An online electronic survey was formulated to evaluate the use and user opinion of automation within cancer registries. The survey was distributed to members of the United Kingdom and Ireland Association of Cancer Registry and the European cancer registries. Data analysis was performed using Microsoft Excel 2015^® version 15.13.3 in order to summarise the results.

Results: Twenty-three of the 117 cancer registries responded to the distributed survey; 15 (12.8%) cancer registries used automation within their registry, mainly in the form of natural language processing or machine learning. Most of the sampled registries (73.3%) used these technologies to automate data collection from pathology reports; 87% of respondents reported automation as efficient; and 26.1% reported improved data quality; 12 (52.1%) of cancer registries still manually checked all the automations; and 17 (74%) respondents believed that the algorithms for difficult tasks require further development.

Conclusion: Various computer-based algorithms have been used for automated clinical coding in the UK and European cancer registries in the past few decades; however, to date there are no published data to validate its use. Further research and development of these technologies is needed to ensure external validity and maximise the potential use within other cancer registries globally.Implications for health information management practice:It is clear that while automation can be advantageous in areas of clinical coding, the role of the "human" (HIMs and clinical coders) in coding and classifying registry data, and in overseeing the transition, will be required for some time yet.

Background: Robust population health surveillance is required to monitor trends in prevalence in congenital anomalies (CA) and to detect emerging threats to human development. All eight Australian states and territories are mandated to report CA data to national authorities. Objectives: (i) Compare Australian congenital anomaly registers (CARs) across jurisdictions; (ii) measure research utilisation of Australian CAR data. Method: We conducted a documentary analysis of publicly available online information on Australian CARs and performed a scoping review of peer-reviewed research published from 1980 to 2024 that utilised CAR data. Results: Five Australian states/territories possessed an established CAR; three practiced active surveillance, and three included mandatory reporting. Age of child inclusion criteria ranged from birth episode to 6 years. Most states/territories classified CAs according to the International Classification of Diseases 10th Revision Australian Modification (ICD-10-AM). There was inconsistency in scope, data sources, method of ascertainment, data linkage processes, data availability, reporting requirements and data quality. The scoping review identified 83 peer-reviewed publications using CAR data. The majority of publications originated from three states/territories and included key CAR staff as authors. Only one state/territory CAR consistently published research over the 44-year review period. Conclusion: There are major methodological inconsistencies among Australian CARs, undermining the interpretability and quality of nationally reported CA data. More standardisation and resourcing are required to maximise the research and policy value of Australian CARs. Implications for health information management practice: Urgent attention to data management practices, harmonisation across jurisdictions and resourcing are required to safeguard the sustainability and value of Australian CARs.

Background: The Australian Childhood Immunisation Register (ACIR), established in 1996, captures details of vaccinations given to children aged <7 years, expanded in 2016 to the whole-of-life Australian Immunisation Register (AIR). Objective: Overview of ACIR/AIR, how health information captured is managed and how AIR data facilitate insights into vaccination reporting trends. Method: The authors, with 58 years of collective experience in analysing and interpreting ACIR/AIR data, reviewed formal and grey literature relevant to ACIR/AIR and their operation and use. We analysed AIR data to document how data transmission to AIR and vaccination provider settings has evolved. Results: We describe policy and program changes instrumental to the ACIR-AIR expansion, AIR data fields, methodology for measuring population-level vaccination coverage, and ways data are used for: monitoring and evaluation of immunisation programs; public health surveillance; linked data analyses; vaccine effectiveness studies and other research. We show evidence of changing vaccination landscape including increasing trends in electronic data transmission (e.g. proportion of vaccinations given to children aged <10 years and notified to ACIR/AIR using practice management software increased from 56% in 2014 to 89% in 2023) and increase in vaccinations given in pharmacies (e.g. proportion of influenza vaccinations given to adults aged 20-64 years in pharmacies increased from 0.9% in 2017 to 26.9% in 2023). Conclusion: The AIR has been instrumental in monitoring and evaluating the reach and impact of Australia's publicly funded immunisation programs across the life course. Implications for health information management practice: Health information managers working with vaccination data contribute to the AIR through data management and upload to the AIR.

Background: Blood transfusion is a common medical intervention. For patients with acute critical bleeding, large volume "massive" transfusion (MT) is required, and is potentially life-saving. However, the evidence-base for transfusion practice, particularly for critical bleeding/MT management, is relatively weak, and has confounded the development of clinical best practice recommendations.

Aim: The aim was to address this evidence gap by building the Australian and New Zealand Massive Transfusion Registry (ANZ-MTR). We describe how data collection, standardisation and interoperability of data sourced from multiple electronic information systems are managed, and share the lessons learned.

Innovation: The ANZ-MTR is a database of routine electronic hospital admission information, laboratory test results, transfusion records and outcomes of adults (18 years and older) who have received a MT for any cause of acute critical bleeding, including trauma, major surgery, obstetric or gastrointestinal haemorrhage. Source data are provided by participating hospitals and are harmonised by the registry. Since its launch in 2011, the ANZ-MTR has captured over 9200 MT episodes from 29 hospitals.What can be learned from this case:Effective communication with all custodians of the source data has been fundamental to the success of the registry. A preeminent outcome of this success is the current expansion of the registry to become the National Transfusion Dataset, which will capture comprehensive data for all transfusions.Implications for health information management practice:The ANZ-MTR illustrates that complex and varied arrays of routinely collected clinical and hospital administrative data from multiple electronic information systems can be consolidated into a resource-rich clinical database.

Background: Clinical registries are long-term observational data collections relating to specific medical conditions, procedures, devices or health services. Objective: To assess current characteristics and outputs of clinical registries in Australia. Method: A cross-sectional survey design of Australian clinical registries listed on the Australian Commission on Safety and Quality in Health Care (ACSQHC) register as of 21 September 2023. Results: Of 107 clinical registries on the ACSQHC register that were contacted, 64 (60%) participated in the survey. Of these, 37 (58%) had been active for ⩾10 years, 38 (59%) were medical clinical registries and 35 (57%) received government funding. Clinical registry activities included research (92%), quality improvement (81%) and epidemiological monitoring (68%). Data were commonly patient-identifiable (64%) and collected by clinicians/staff (81%). A majority (55%) had real-time data available to contributing hospitals. Clinical registry outputs included providing data to researchers (97%), publications (83%), annual reports (69%) and site benchmarked reports (64%). Over half informed quality improvement activities (60%), monitored adherence to guidelines (59%) or informed policy or service planning (52%). Nearly half-supported clinical trials (49%), while one-fifth had integrated with government data frameworks. Conclusion: Australian clinical registries monitor health system performance across a breadth of clinical areas. A majority undertake regular public and hospital reporting and inform other quality improvement activities. Implications for health information management practice: Clinical registries interact with hospitals regarding their data collection and reporting activities. Health information management specialists have an important role in maximising registry data quality and therefore value to a wide variety of stakeholders.

Background: Haemophilia is a lifelong and chronic disease that has adverse consequences for the patient. The haemophilia registry is a key tool for managing this disease.

Objective: The present study aimed to design a minimum dataset for developing a registry system for haemophilia.

Method: This study was conducted in two stages. In the first stage, in order to conduct a scoping review, PubMed, Scopus and Web of Science databases were searched using relevant keywords up to 4 July 2025. The study selection process was based on the PRISMA guidelines, and finally, 40 articles were included. In the second stage, the data items retrieved from the studies were evaluated and consulted by 14 haematology specialists through a questionnaire. The minimum data items for haemophilia registry were confirmed based on the level of agreement of the participants (more than 75%), and descriptive statistics were used for data analysis, which was performed using the SPSS software (IBM Corp., Armonk, NY, USA).

Results: The initial minimum data items for the haemophilia registry system were extracted from 40 studies. These items included 77 items in 4 main categories: demographic data (21 items), laboratory data (32 items), clinical data (21 items) and adverse outcomes (3 items). Finally, these data items were validated by 14 haematology specialists. In the final dataset, 58 items, distributed across 4 categories, achieved an agreement of more than 75%, comprising 8 demographic items, 28 laboratory items, 17 clinical items and 3 adverse outcome items.

Conclusion: Registries record different data according to their purposes. The importance of this work lies in providing a minimum dataset for registering haemophilia patients in Iran, which can help improve the quality of care, facilitate future research and align with international registry systems for bleeding diseases. Therefore, the findings of this study provide a basis for designing, implementing and improving the haemophilia registry system in Iran.Implications for health information management practice:The findings of this study provide a strong foundation for designing and implementing a National Haemophilia Registry in Iran. This system will standardise and integrate data, prevent duplicate records and enhance treatment planning. It will also support epidemiological and clinical research with links to international databases, while improving patient care, follow-up and reducing complications. Overall, it can help align Iran with global standards for managing bleeding disorders.

Context: The Norwegian Health Archives Registry (NHAR) is a national initiative dedicated to digitising, centralising, and providing access to historical full-text patient health records (PHRs) for research purposes. Established in 2019, NHAR includes PHRs from the deceased population in Norway's specialist healthcare services, offering a unique long-term data source for future research. NHAR has now digitised 1.7 million paper-based PHRs, covering medical history dating back to 1875. The registry is now expanding to include digital-born PHRs.

Aim: This article describes NHAR's innovation potential as a health registry, its data management processes, and the integration of artificial intelligence (AI) tools to facilitate data management and research in compliance with strict health data regulations.

Practice innovation: NHAR's data value chain includes structured metadata acquisition, large-scale digitisation and secure data delivery for research. The workflow includes a custom optical character recognition (OCR) tool tailored to Norwegian medical terminology, concept-based search tools for unstructured clinical full text and robust strategies for long-term data management. A novel AI-based de-identification system automatically detects and masks personal identifiers in digitised PHRs.

Lessons learned: Despite these innovations, challenges persist in processing handwritten and historical PHRs due to OCR limitations and language-specific complexities. Key challenges include improving data quality, enhancing OCR accuracy and refining AI tools for information retrieval, data extraction and de-identification.

Conclusion: NHAR offers significant potential for interdisciplinary research across various medical fields.Implications for health information management practice:NHAR establishes a foundation for secure access to historical health data and introduces advanced data management strategies to facilitate future research.