Estimating the impact of bias in causal epidemiological studies: the case of health outcomes following assisted reproduction.

Researchers interested in causal questions must deal with two sources of error: random error (random deviation from the true mean value of a distribution), and bias (systematic deviance from the true mean value due to extraneous factors). For some causal questions, randomization is not feasible, and observational studies are necessary. Bias poses a substantial threat to the validity of observational research and can have important consequences for health policy developed from the findings. The current piece describes bias and its sources, outlines proposed methods to estimate its impacts in an observational study, and demonstrates how these methods may be used to inform debate on the causal relationship between medically assisted reproduction (MAR) and health outcomes, using cancer as an example. In doing so, we aim to enlighten researchers who work with observational data, especially regarding the health effects of MAR and infertility, on the pitfalls of bias, and how to address them. We hope that, in combination with the provided example, we can convince readers that estimating the impact of bias in causal epidemiologic research is not only important but necessary to inform the development of robust health policy and clinical practice recommendations.

The Australian Health Care Homes trial: quality of care and patient outcomes. A propensity score-matched cohort study.

OBJECTIVE: To assess the impact of the Health Care Homes (HCH) primary health care initiative on quality of care and patient outcomes. DESIGN, SETTING: Quasi-experimental, matched cohort study; analysis of general practice data extracts and linked administrative data from ten Australian primary health networks, 1 October 2017 - 30 June 2021. PARTICIPANTS: People with chronic health conditions (practice data extracts: 9811; linked administrative data: 10 682) enrolled in the HCH 1 October 2017 - 30 June 2019; comparison groups of patients receiving usual care (1:1 propensity score-matched). INTERVENTION: Participants were involved in shared care planning, provided enhanced access to team care, and encouraged to seek chronic condition care at the HCH practice where they were enrolled. Participating practices received bundled payments based on clinical risk tier. MAIN OUTCOME MEASURES: Access to care, processes of care, diabetes-related outcomes, hospital service use, risk of death. RESULTS: During the first twelve months after enrolment, the mean numbers of general practitioner encounters (rate ratio, 1.14; 95% confidence interval [CI], 1.11-1.17) and Medicare Benefits Schedule claims for allied health services (rate ratio, 1.28; 95% CI, 1.24-1.33) were higher for the HCH than the usual care group. Annual influenza vaccinations (relative risk, 1.20; 95% CI, 1.17-1.22) and measurements of blood pressure (relative risk, 1.09; 95% CI, 1.08-1.11), blood lipids (relative risk, 1.19; 95% CI, 1.16-1.21), glycated haemoglobin (relative risk, 1.06; 95% CI, 1.03-1.08), and kidney function (relative risk, 1.13; 95% CI, 1.11-1.15) were more likely in the HCH than the usual care group during the twelve months after enrolment. Similar rate ratios and relative risks applied in the second year. The numbers of emergency department presentations (rate ratio, 1.09; 95% CI, 1.02-1.18) and emergency admissions (rate ratio, 1.13; 95% CI, 1.04-1.22) were higher for the HCH group during the first year; other differences in hospital use were not statistically significant. Differences in glycaemic and blood pressure control in people with diabetes in the second year were not statistically significant. By 30 June 2021, 689 people in the HCH group (6.5%) and 646 in the usual care group (6.1%) had died (hazard ratio, 1.07; 95% CI, 0.96-1.20). CONCLUSIONS: The HCH program was associated with greater access to care and improved processes of care for people with chronic diseases, but not changes in diabetes-related outcomes, most measures of hospital use, or risk of death.

Factors associated with cardiac implantable electronic device-related infections, New South Wales, 2016-21: a retrospective cohort study.

OBJECTIVES: To quantify the rate of cardiac implantable electronic device (CIED)-related infections and to identify risk factors for such infections. DESIGN: Retrospective cohort study; analysis of linked hospital admissions and mortality data. SETTING, PARTICIPANTS: All adults who underwent CIED procedures in New South Wales between 1 January 2016 and 30 June 2021 (public hospitals) or 30 June 2020 (private hospitals). MAIN OUTCOME MEASURES: Proportions of patients hospitalised with CIED-related infections (identified by hospital record diagnosis codes); risk of CIED-related infection by patient, device, and procedural factors. RESULTS: Of 37 675 CIED procedures (23 194 men, 63.5%), 500 were followed by CIED-related infections (median follow-up, 24.9 months; interquartile range, 11.2-40.8 months), including 397 people (1.1%) within twelve months of their procedures, and 186 of 10 540 people (2.5%) at high risk of such infections (replacement or upgrade procedures; new cardiac resynchronisation therapy with defibrillator, CRT-D). The overall infection rate was 0.50 (95% confidence interval [CI], 0.45-0.54) per 1000 person-months; it was highest during the first month after the procedure (5.60 [95% CI, 4.89-6.42] per 1000 person-months). The risk of CIED-related infection was greater for people under 65 years of age than for those aged 65-74 years (adjusted hazard ratio [aHR], 1.71; 95% CI, 1.32-2.23), for people with CRT-D devices than for those with permanent pacemakers (aHR, 1.46; 95% CI, 1.02-2.08), for people who had previously undergone CIED procedures (two or more v none: aHR, 1.51; 95% CI, 1.02-2.25) or had CIED-related infections (aHR, 11.4; 95% CI, 8.34-15.7), or had undergone concomitant cardiac surgery (aHR, 1.62; 95% CI, 1.10-2.39), and for people with atrial fibrillation (aHR, 1.33; 95% CI, 1.11-1.60), chronic kidney disease (aHR, 1.54; 95% CI, 1.27-1.87), chronic obstructive pulmonary disease (aHR, 1.37; 95% CI, 1.10-1.69), or cardiomyopathy (aHR 1.60; 95% CI, 1.25-2.05). CONCLUSIONS: Knowledge of risk factors for CIED-related infections can help clinicians discuss them with their patients, identify people at particular risk, and inform decisions about device type, upgrades and replacements, and prophylactic interventions.

Risk for Congenital Anomalies in Children Conceived With Medically Assisted Fertility Treatment : A Population-Based Cohort Study.

BACKGROUND: More than 2 million children are conceived annually using assisted reproductive technologies (ARTs), with a similar number conceived using ovulation induction and intrauterine insemination (OI/IUI). Previous studies suggest that ART-conceived children are at increased risk for congenital anomalies (CAs). However, the role of underlying infertility in this risk remains unclear, and ART clinical and laboratory practices have changed drastically over time, particularly there has been an increase in intracytoplasmic sperm injection (ICSI) and cryopreservation. OBJECTIVE: To investigate the role of underlying infertility and fertility treatment on CA risks in the first 2 years of life. DESIGN: Propensity score-weighted population-based cohort study. SETTING: New South Wales, Australia. PARTICIPANTS: 851 984 infants (828 099 singletons and 23 885 plural children) delivered between 2009 and 2017. MEASUREMENTS: Adjusted risk difference (aRD) in CAs of infants conceived through fertility treatment compared with 2 naturally conceived (NC) control groups-those with and without a parental history of infertility (NC-infertile and NC-fertile). RESULTS: The overall incidence of CAs was 459 per 10 000 singleton births and 757 per 10 000 plural births. Compared with NC-fertile singleton control infants (n = 747 018), ART-conceived singleton infants (n = 31 256) had an elevated risk for major genitourinary abnormalities (aRD, 19.0 cases per 10 000 births [95% CI, 2.3 to 35.6]); the risk remained unchanged (aRD, 22 cases per 10 000 births [CI, 4.6 to 39.4]) when compared with NC-infertile singleton control infants (n = 36 251) (that is, after accounting for parental infertility), indicating that ART remained an independent risk. After accounting for parental infertility, ICSI in couples without male infertility was associated with an increased risk for major genitourinary abnormalities (aRD, 47.8 cases per 10 000 singleton births [CI, 12.6 to 83.1]). There was some suggestion of increased risk for CAs after fresh embryo transfer, although estimates were imprecise and inconsistent. There were no increased risks for CAs among OI/IUI-conceived infants (n = 13 574). LIMITATIONS: This study measured the risk for CAs only in those children who were born at or after 20 weeks' gestation. Observational study design precludes causal inference. Many estimates were imprecise. CONCLUSION: Patients should be counseled on the small increased risk for genitourinary abnormalities after ART, particularly after ICSI, which should be avoided in couples without problems of male infertility. PRIMARY FUNDING SOURCE: Australian National Health and Medical Research Council.

Incidence and Predictors of Readmissions to Non-Index Hospitals After Transcatheter Aortic Valve Implantation in the Contemporary Era in New South Wales, Australia.

BACKGROUND: In Australia, transcatheter aortic valve implantation (TAVI) is only performed in a limited number of specialised metropolitan centres, many of which are private hospitals, making it likely that TAVI patients who require readmission will present to another (non-index) hospital. It is important to understand the impact of non-index readmission on patient outcomes and healthcare resource utilisation. METHOD: We analysed linked hospital and death records for residents of New South Wales, Australia, aged ≥18 years, who had an emergency readmission within 90 days following a TAVI procedure in 2013-2022. Mixed-effect, multi-level logistic regression models were used to evaluate predictors of non-index readmission, and associations between non-index readmission and readmission length of stay, 90-day mortality, and 1-year mortality. RESULTS: Of 4,198 patients (mean age, 82.7 years; 40.6% female) discharged alive following TAVI, 933 (22.2%) were readmitted within 90 days of discharge. Over three-quarters (76.0%) of those readmitted returned to a non-index hospital, with no significant difference in readmission principal diagnosis between index hospital and non-index hospital readmissions. Among readmitted patients, independent predictors of non-index readmission included: residence in regional or remote areas, lower socio-economic status, having a pre-procedure transfer, and a private index hospital. Readmission length of stay (median, 4 days), 90-day mortality (adjusted odds ratio [OR] 1.04, 95% confidence interval [CI] 0.56-1.96) and 1-year mortality (adjusted OR 1.01, 95% CI 0.64-1.58) were similar between index and non-index readmissions. CONCLUSIONS: Non-index readmission following TAVI was highly prevalent but not associated with increased mortality or healthcare utilisation. Our results are reassuring for TAVI patients in regional and remote areas with limited access to return to index TAVI hospitals.

Predicting Adverse Outcomes Following Catheter Ablation Treatment for Atrial Flutter/Fibrillation.

BACKGROUND & AIM: To develop prognostic survival models for predicting adverse outcomes after catheter ablation treatment for non-valvular atrial fibrillation (AF) and/or atrial flutter (AFL). METHODS: We used a linked dataset including hospital administrative data, prescription medicine claims, emergency department presentations, and death registrations of patients in New South Wales, Australia. The cohort included patients who received catheter ablation for AF and/or AFL. Traditional and deep survival models were trained to predict major bleeding events and a composite of heart failure, stroke, cardiac arrest, and death. RESULTS: Out of a total of 3,285 patients in the cohort, 177 (5.3%) experienced the composite outcome-heart failure, stroke, cardiac arrest, death-and 167 (5.1%) experienced major bleeding events after catheter ablation treatment. Models predicting the composite outcome had high-risk discrimination accuracy, with the best model having a concordance index >0.79 at the evaluated time horizons. Models for predicting major bleeding events had poor risk discrimination performance, with all models having a concordance index <0.66. The most impactful features for the models predicting higher risk were comorbidities indicative of poor health, older age, and therapies commonly used in sicker patients to treat heart failure and AF and AFL. DISCUSSION: Diagnosis and medication history did not contain sufficient information for precise risk prediction of experiencing major bleeding events. Predicting the composite outcome yielded promising results, but future research is needed to validate the usefulness of these models in clinical practice. CONCLUSIONS: Machine learning models for predicting the composite outcome have the potential to enable clinicians to identify and manage high-risk patients following catheter ablation for AF and AFL proactively.

Have We Been Underestimating Modifiable Dementia Risk? An Alternative Approach for Calculating the Combined Population Attributable Fraction for Modifiable Dementia Risk Factors.

Estimating the fraction of dementia cases in a population attributable to a risk factor or combination of risk factors (the population attributable fraction (PAF)) informs the design and choice of dementia risk-reduction activities. It is directly relevant to dementia prevention policy and practice. Current methods employed widely in the dementia literature to combine PAFs for multiple dementia risk factors assume a multiplicative relationship between factors and rely on subjective criteria to develop weightings for risk factors. In this paper we present an alternative approach to calculating the PAF based on sums of individual risk. It incorporates individual risk factor interrelationships and enables a range of assumptions about the way in which multiple risk factors will combine to affect dementia risk. Applying this method to global data demonstrates that the previous estimate of 40% is potentially too conservative an estimate of modifiable dementia risk and would necessitate subadditive interaction between risk factors. We calculate a plausible conservative estimate of 55.7% (95% confidence interval: 55.2, 56.1) based on additive risk factor interaction.

Long-Term Outcomes Following Elective Repair of Intact Abdominal Aortic Aneurysms: A Comparison Between Open Surgical and Endovascular Repair Using Linked Administrative and Clinical Registry Data.

OBJECTIVE: Compare long-term mortality, secondary intervention and secondary rupture following elective endovascular aneurysm repair (EVAR) and open surgical repair (OSR). BACKGROUND: EVAR has surpassed OSR as the most common procedure used to repair abdominal aortic aneurysm (AAA), but evidence regarding long-term outcomes is inconclusive. METHODS: We included patients in linked clinical registry and administrative data undergoing EVAR or OSR for intact AAA between January 2010 and June 2019. We used an inverse probability of treatment-weighted survival analysis to compare all-cause mortality, cause-specific mortality, secondary interventions and secondary rupture, and evaluate the impact of secondary interventions and secondary rupture on all-cause mortality. RESULTS: The study included 3460 EVAR and 427 OSR patients. Compared to OSR, the EVAR all-cause mortality rate was lower in the first 30 days [adjusted hazard ratio (HR) = 0.22, 95% confidence interval (CI) 0.140.33], but higher between 1 and 4 years (HR = 1.29, 95% CI 1.12-1.48) and after 4years (HR = 1.41, 95% CI 1.23-1.63). Secondary intervention rates were higher over the first 30 days (HR = 2.26, 95% CI 1.11-4.59), but lower between 1 and 4years (HR = 0.59, 95% CI 0.48-0.74). Secondary aortic intervention rates were higher across the entire follow-up period (HR = 2.52, 95% CI 2.06-3.07). Secondary rupture rates did not differ significantly (HR = 1.06, 95% CI 0.73-1.55). All-cause mortality beyond 1 year remained significantly higher for EVAR after adjusting for any secondary interventions, or secendary rupture. CONCLUSIONS: EVAR has an early survival benefit compared to OSR. However, elevated long-term mortality and higher rates of secondary aortic interventions and subsequent aneurysm repair suggest that EVAR may be a less durable method of aortic aneurysm exclusion.

Long-term Mortality and Reintervention After Endovascular and Open Abdominal Aortic Aneurysm Repairs in Australia, Germany, and the United States.

OBJECTIVE: To examine long-term outcomes after endovascular (EVAR) and open repairs (OAR) for intact abdominal aortic aneurysms in Australia, Germany, and the United States, using a unified study design. BACKGROUND: Similarities and differences in long-term outcomes after EVAR versus OAR across countries remained unclear, given differences in designs across existing studies. METHODS: We identified patients aged >65 years undergoing intact abdominal aortic aneurysm repairs during 2010-2017/2018. We compared long-term patient mortality and reintervention after EVAR and OAR using Kaplan-Meier analyses and Cox regressions. Propensity score matching was performed within each country to adjust for differences in baseline patient characteristics between procedure groups. RESULTS: We included 3311, 4909, and 145363 patients from Australia, Germany, and the United States, respectively. The median patient age was 76 to 77 years, and most patients were males (77%-84%). Patient mortality was lower after EVAR than OAR within the first 60 days and became similar at 3-year follow-up (Australia 14.7% vs 16.5%, Germany 18.2% vs 19.7%, United States: 24.4% vs 24.4%). At the end of follow-up, patient mortality after EVAR was higher than OAR in Australia [ hazard ratio (HR) 95% CI: 1.21 (0.96-1.54)] but similar to OAR in Germany [HR 95% CI: 0.92 (0.80-1.07)] and the United States [HR 95% CI: 1.02 (0.99-1.05)]. The risk of reintervention after EVAR was more than twice that after OAR in Australia [HR 95% CI: 2.60 (1.09-6.15)], Germany [HR 95% CI: 4.79 (2.56-8.98)], and the United States [HR 95% CI: 2.67 (2.38-3.00)]. The difference in reintervention risk appeared early in German and United States patients. CONCLUSIONS: This multinational study demonstrated important similarities in long-term outcomes after EVAR versus OAR across 3 countries. Variation in long-term mortality and reintervention comparisons indicates possible differences in patient profiles, surveillance, and best medical therapy across countries.

Editor's Choice - Comparison of Outcomes for Major Contemporary Endograft Devices Used for Endovascular Repair of Intact Abdominal Aortic Aneurysms.

OBJECTIVE: To compare rates of mortality, rupture, and secondary intervention following endovascular repair (EVAR) of intact abdominal aortic aneurysms (AAA) using contemporary endograft devices from three major manufacturers. METHODS: This was a retrospective cohort study using linked clinical registry (Australasian Vascular Audit) and all payer administrative data. Patients undergoing EVAR for intact AAA between 2010 and 2019 in New South Wales, Australia were identified. Rates of all cause death, secondary rupture, and secondary intervention (subsequent aneurysm repair; other secondary aortic intervention) were compared for patients treated with Cook, Medtronic, and Gore standard devices. Inverse probability of treatment weighted proportional hazards and competing risk regression were used to adjust for patient, clinical, and aneurysm characteristics, using Cook as the referent device. RESULTS: This study identified 2 874 eligible EVAR patients, with a median follow up of 4.1 (maximum 9.5) years. Mortality rates were similar for patients receiving different devices (ranging between 7.0 and 7.3 per 100 person years). There was no statistically significant difference between devices in secondary rupture rates, which ranged between 0.4 and 0.5 per 100 person years. Patients receiving Medtronic and Gore devices tended to have higher crude rates of subsequent aneurysm repair (1.5 per 100 person years) than patients receiving Cook devices (0.8 per 100 person years). This finding remained in the adjusted analysis, but was only statistically significant for Medtronic devices (HR 1.57, 95% CI 1.02 - 2.47; HR 1.73, 95% CI 0.94 - 3.18, respectively). CONCLUSION: Major endograft devices have similar overall long term safety profiles. However, there may be differences in rates of secondary intervention for some devices. This may reflect endograft durability, or patient selection for different devices based on aneurysm anatomy. Continuous comparative assessments are needed to guide evidence for treatment decisions across the range of available devices.

Real-world evidence on the association between cardiac implantable electronic device infection and all-cause mortality.

AIMS: An infection following cardiac implantable electronic device (CIED) procedure is a serious complication, but its association with all-cause mortality is inconsistent across observational studies. To quantify the association between CIED infection and all-cause mortality in a large, contemporary cohort from New South Wales, Australia. METHODS AND RESULTS: This retrospective cohort study used linked hospital and mortality data and included all patients aged >18 years who underwent a CIED procedure between July 2017 and September 2022. Cardiac implantable electronic device infection was defined by the presence of relevant diagnosis codes. Cox regression to estimate adjusted hazard ratios (aHRs) with 95% confidence intervals (CIs) for the association of CIED infection with mortality, at 1-year, and at the end of follow-up, with CIED infection included as a time-dependent variable, and other potential risk factors for mortality included as fixed covariates. We followed 37,750 patients with CIED procedures {36% female, mean age [standard deviation (SD)] 75.8 [12.7] years}, and 487 (1.3%) CIED infections were identified. We observed 5771 (15.3%) deaths during an average follow-up of 25.2 (SD 16.8) months. Compared with no infection group, patients with CIED infection had a higher Kaplan-Meier mortality rate (19.4 vs. 6.8%) and adjusted hazard of mortality (aHR 2.73, 95% CI 2.10-3.54) at 12 months post-procedure. These differences were attenuated but still remained significant at the end of follow-up (aHR 1.83, 95% CI 1.52-2.19). CONCLUSION: In a complete, state-wide cohort of CIED patients, infection was associated with higher risks of both short-term and long-term mortality.

In-hospital outcomes by insurance type among patients undergoing percutaneous coronary interventions for acute myocardial infarction in New South Wales public hospitals.

BACKGROUND: International evidence suggests patients receiving cardiac interventions experience differential outcomes by their insurance status. We investigated outcomes of in-hospital care according to insurance status among patients admitted in public hospitals with acute myocardial infarction (AMI) undergoing percutaneous coronary intervention (PCI). METHODS: We conducted a cohort study within the Australian universal health care system with supplemental private insurance. Using linked hospital and mortality data, we included patients aged 18 + years admitted to New South Wales public hospitals with AMI and undergoing their first PCI from 2017-2020. We measured hospital-acquired complications (HACs), length of stay (LOS) and in-hospital mortality among propensity score-matched private and publicly funded patients. Matching was based on socio-demographic, clinical, admission and hospital-related factors. RESULTS: Of 18,237 inpatients, 30.0% were privately funded. In the propensity-matched cohort (n = 10,630), private patients had lower rates of in-hospital mortality than public patients (odds ratio: 0.59, 95% CI: 0.45-0.77; approximately 11 deaths avoided per 1,000 people undergoing PCI procedures). Mortality differences were mostly driven by STEMI patients and those from major cities. There were no significant differences in rates of HACs or average LOS in private, compared to public, patients. CONCLUSION: Our findings suggest patients undergoing PCI in Australian public hospitals with private health insurance experience lower in-hospital mortality compared with their publicly insured counterparts, but in-hospital complications are not related to patient health insurance status. Our findings are likely due to unmeasured confounding of broader patient selection, socioeconomic differences and pathways of care (e.g. access to emergency and ambulatory care; delays in treatment) that should be investigated to improve equity in health outcomes.

Elective spinal surgery in New South Wales adults, 2001-20, by procedure funding type: a cross-sectional study.

OBJECTIVE: To investigate elective rates of spinal fusion, decompression, and disc replacement procedures for people with degenerative conditions, by funding type (public, private, workers' compensation). DESIGN, SETTING: Cross-sectional study; analysis of hospitals admissions data extracted from the New South Wales Admitted Patient Data Collection. PARTICIPANTS: All adults who underwent elective spinal surgery (spinal fusion, decompression, disc replacement) in NSW, 1 July 2001 - 30 June 2020. MAIN OUTCOME MEASURES: Crude and age- and sex-adjusted procedure rates, by procedure, funding type, and year; annual change in rates, 2001-20, expressed as incidence rate ratios (IRRs). RESULTS: During 2001-20, 155 088 procedures in 129 525 adults were eligible for our analysis: 53 606 fusion, 100 225 decompression, and 1257 disc replacement procedures. The privately funded fusion procedure rate increased from 26.6 to 109.5 per 100 000 insured adults (per year: IRR, 1.06; 95% confidence interval [CI], 1.05-1.07); the workers' compensation procedure rate increased from 6.1 to 15.8 per 100 000 covered adults (IRR, 1.04; 95% CI, 1.01-1.06); the publicly funded procedure rate increased from 5.6 to 12.4 per 100 000 adults (IRR, 1.03; 95% CI, 1.01-1.06), and from 10.5 to 22.1 per 100 000 adults without hospital cover private health insurance (IRR, 1.03; 95% CI, 1.01-1.05). The privately funded decompression procedure rate increased from 93.4 to 153.6 per 100 000 people (IRR, 1.02; 95% CI, 1.01-1.03); the workers' compensation procedure rate declined from 19.7 to 16.7 per 100 000 people (IRR, 0.98; 95% CI, 0.96-0.99), and the publicly funded procedure rate did not change significantly. The privately funded disc replacement procedure rate increased from 6.2 per million in 2010-11 to 38.4 per million people in 2019-20, but did not significantly change for the other two funding groups. The age- and sex-adjusted rates for privately and publicly funded fusion and decompression procedures were similar to the crude rates. CONCLUSIONS: Privately funded spinal surgery rates continue to be larger than for publicly funded procedures, and they have also increased more rapidly. These differences may indicate that some privately funded procedures are unnecessary, or that the number of publicly funded procedures does not reflect clinical need.

Continuous time recurrent neural networks: Overview and benchmarking at forecasting blood glucose in the intensive care unit.

OBJECTIVE: Blood glucose measurements in the intensive care unit (ICU) are typically made at irregular intervals. This presents a challenge in choice of forecasting model. This article gives an overview of continuous time autoregressive recurrent neural networks (CTRNNs) and evaluates how they compare to autoregressive gradient boosted trees (GBT) in forecasting blood glucose in the ICU. METHODS: Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations through incorporating continuous evolution of the hidden states between observations. This is achieved using a neural ordinary differential equation (ODE) or neural flow layer. In this manuscript, we give an overview of these models, including the varying architectures that have been proposed to account for issues such as ongoing medical interventions. Further, we demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting using electronic medical record and simulated data and compare with GBT and linear models. RESULTS: The experiments confirm that addition of a neural ODE or neural flow layer generally improves the performance of autoregressive recurrent neural networks in the irregular measurement setting. However, several CTRNN architecture are outperformed by a GBT model (Catboost), with only a long short-term memory (LSTM) and neural ODE based architecture (ODE-LSTM) achieving comparable performance on probabilistic forecasting metrics such as the continuous ranked probability score (ODE-LSTM: 0.118 ± 0.001; Catboost: 0.118 ± 0.001), ignorance score (0.152 ± 0.008; 0.149 ± 0.002) and interval score (175 ± 1; 176 ± 1). CONCLUSION: The application of deep learning methods for forecasting in situations with irregularly measured time series such as blood glucose shows promise. However, appropriate benchmarking by methods such as GBT approaches (plus feature transformation) are key in highlighting whether novel methodologies are truly state of the art in tabular data settings.

Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV.

OBJECTIVE: Clinical data's confidential nature often limits the development of machine learning models in healthcare. Generative adversarial networks (GANs) can synthesise realistic datasets, but suffer from mode collapse, resulting in low diversity and bias towards majority demographics and common clinical practices. This work proposes an extension to the classic GAN framework that includes a variational autoencoder (VAE) and an external memory mechanism to overcome these limitations and generate synthetic data accurately describing imbalanced class distributions commonly found in clinical variables. METHODS: The proposed method generated a synthetic dataset related to antiretroviral therapy for human immunodeficiency virus (ART for HIV). We evaluated it based on five metrics: (1) accurately representing imbalanced class distribution; (2) the realism of the individual variables; (3) the realism among variables; (4) patient disclosure risk; and (5) the utility of the generated dataset for developing downstream machine learning models. RESULTS: The proposed method overcomes the issue of mode collapse and generates a synthetic dataset that accurately describes imbalanced class distributions commonly found in clinical variables. The generated data has a patient disclosure risk of 0.095%, lower than the 9% threshold stated by Health Canada and the European Medicines Agency, making it suitable for distribution to the research community with high security. The generated data also has high utility, indicating the potential of the proposed method to enable the development of downstream machine learning algorithms for healthcare applications using synthetic data. CONCLUSION: Our proposed extension to the classic GAN framework, which includes a VAE and an external memory mechanism, represents a promising approach towards generating synthetic data that accurately describe imbalanced class distributions commonly found in clinical variables. This method overcomes the limitations of GANs and creates more realistic datasets with higher patient cohort diversity, facilitating the development of downstream machine learning algorithms for healthcare applications.

Population-wide contribution of medically assisted reproductive technologies to overall births in Australia: temporal trends and parental characteristics.

STUDY QUESTION: In a country with supportive funding for medically assisted reproduction (MAR) technologies, what is the proportion of MAR births over-time? SUMMARY ANSWER: In 2017, 6.7% of births were conceived by MAR (4.8% ART and 1.9% ovulation induction (OI)/IUI) with a 55% increase in ART births and a stable contribution from OI/IUI births over the past decade. WHAT IS KNOWN ALREADY: There is considerable global variation in utilization rates of ART despite a similar infertility prevalence worldwide. While the overall contribution of ART to national births is known in many countries because of ART registries, very little is known about the contribution of OI/IUI treatment or the socio-demographic characteristics of the parents. Australia provides supportive public funding for all forms of MAR with no restrictions based on male or female age, and thus provides a unique setting to investigate the contribution of MAR to national births as well as the socio-demographic characteristics of parents across the different types of MAR births. STUDY DESIGN, SIZE, DURATION: This is a novel population-based birth cohort study of 898 084 births using linked ART registry data and administrative data including birth registrations, medical services, pharmaceuticals, hospital admissions and deaths. Birth (a live or still birth of at least one baby of ≥400 g birthweight or ≥20 weeks' gestation) was the unit of analysis in this study. Multiple births were considered as one birth in our analysis. PARTICIPANTS/MATERIALS, SETTING, METHODS: This study included a total of 898 084 births (606 488 mothers) in New South Wales and the Australian Capital Territory, Australia 2009-2017. We calculated the prevalence of all categories of MAR-conceived births over the study period. Generalized estimating equations were used to examine the association between parental characteristics (parent's age, parity, socio-economic status, maternal country of birth, remoteness of mother's dwelling, pre-existing medical conditions, smoking, etc.) and ART and OI/IUI births relative to naturally conceived births. MAIN RESULTS AND THE ROLE OF CHANCE: The proportion of MAR births increased from 5.1% of all births in 2009 to 6.7% in 2017, representing a 30% increase over the decade. The proportion of OI/IUI births remained stable at around 2% of all births, representing 32% of all MAR births. Over the study period, ART births conceived by frozen embryo-transfer increased nearly 3-fold. OI/IUI births conceived using clomiphene citrate decreased by 39%, while OI/IUI births conceived using letrozole increased 56-fold. Overall, there was a 55% increase over the study period in the number of ART-conceived births, rising to 56% of births to mothers aged 40 years and older. In 2017, almost one in six births (17.6%) to mothers aged 40 years and over were conceived using ART treatment. Conversely, the proportion of OI/IUI births was similar across different mother's age groups and remained stable over the study period. ART children, but not OI/IUI children, were more likely to have parents who were socio-economically advantaged compared to naturally conceived children. For example, compared to naturally conceived births, ART births were 16% less likely to be born to mothers who live in the disadvantaged neighbourhoods after accounting for other covariates (adjusted relative risk (aRR): 0.84 [95% CI: 0.81-0.88]). ART- or OI/IUI-conceived children were 25% less likely to be born to immigrant mothers than births after natural conception (aRR: 0.75 [0.74-0.77]). LIMITATIONS, REASONS FOR CAUTION: The social inequalities that we observed between the parents of children born using ART and naturally conceived children may not directly reflect disparities in accessing fertility care for individuals seeking treatment. WIDER IMPLICATIONS OF THE FINDINGS: With the ubiquitous decline in fertility rates around the world and the increasing trend to delay childbearing, this population-based study enhances our understanding of the contribution of different types of MARs to population profiles among births in high-income countries. The parental socio-demographic characteristics of MAR-conceived children differ significantly from naturally conceived children and this highlights the importance of accounting for such differences in studies investigating the health and development of MAR-conceived children. STUDY FUNDING/COMPETING INTEREST(S): This study was funded through Australian National Health and Medical Research Council (NHMRC) grant: APP1127437. G.M.C. is an employee of The University of New South Wales (UNSW) and Director of the National Perinatal Epidemiology and Statistics Unit (NPESU), UNSW. The NPESU manages the Australian and New Zealand Assisted Reproduction Database with funding support from the Fertility Society of Australia and New Zealand. C.V. is an employee of The University of New South Wales (UNSW), Director of Clinical Research of IVFAustralia, Member of the Board of the Fertility Society of Australia and New Zealand, and Member of Research Committee of School of Women's and Children's Health, UNSW. C.V. reports grants from Australian National Health and Medical Research Council (NHMRC), and Merck KGaA. C.V. reports consulting fees, and payment or honoraria for lectures, presentations, speakers, bureaus, manuscript, writing or educational events or attending meeting or travel from Merck, Merck Sparpe & Dohme, Ferring, Gedon-Richter and Besins outside this submitted work. C.V. reported stock or stock options from Virtus Health Limited outside this submitted work. R.J.N. is an employee of The University of Adelaide, and Chair DSMC for natural therapies trial of The University of Hong Kong. R.J.N. reports grants from NHMRC. R.J.N. reports lecture fees and support for attending or travelling for lecture from Merck Serono which is outside this submitted work. L.R.J. is an employee of The UNSW and Foundation Director of the Centre for Big Data Research in Health at UNSW Sydney. L.R.J. reports grants from NHMRC. The other co-authors have no conflict of interest. TRIAL REGISTRATION NUMBER: N/A.

The impact of re-opening the international border on COVID-19 hospitalisations in Australia: a modelling study.

OBJECTIVE: To estimate the numbers of COVID-19-related hospitalisations in Australia after re-opening the international border. DESIGN: Population-level deterministic compartmental epidemic modelling of eight scenarios applying various assumptions regarding SARS-CoV-2 transmissibility (baseline R0 = 3.5 or 7.0), vaccine rollout speed (slow or fast), and scale of border re-opening (mean of 2500 or 13 000 overseas arrivals per day). SETTING: Simulation population size, age structure, and age-based contact rates based on recent estimates for the Australian population. We assumed that 80% vaccination coverage of people aged 16 years or more was reached in mid-October 2021 (fast rollout) or early January 2022 (slow rollout). MAIN OUTCOME MEASURES: Numbers of people admitted to hospital with COVID-19, December 2021 - December 2022. RESULTS: In scenarios assuming a highly transmissible SARS-CoV-2 variant (R0  = 7.0), opening the international border on either scale was followed by surges in both infections and hospitalisations that would require public health measures beyond mask wearing and social distancing to avoid overwhelming the health system. Reducing the number of hospitalisations to manageable levels required several cycles of additional social and mobility restrictions. CONCLUSIONS: If highly transmissible SARS-CoV-2 variants are circulating locally or overseas, large and disruptive COVID-19 outbreaks will still be possible in Australia after 80% of people aged 16 years or more have been vaccinated. Continuing public health measures to restrict the spread of disease are likely to be necessary throughout 2022.

Differences in the pre-hospital management of women and men with stroke by emergency medical services in New South Wales.

OBJECTIVES: To examine whether pre-hospital emergency medical service care differs for women and men subsequently admitted to hospital with stroke. DESIGN, SETTING, PARTICIPANTS: Population-based cohort study; analysis of linked Admitted Patient Data Collection and NSW Ambulance data for people admitted to New South Wales hospitals with a principal diagnosis of stroke at separation, 1 July 2005 - 31 December 2018. MAIN OUTCOME MEASURES: Emergency medical service assessments, protocols, and management for patients subsequently diagnosed with stroke, by sex. RESULTS: Of 202 231 people hospitalised with stroke (mean age, 73 [SD, 14] years; 98 599 women [51.0%]), 101 357 were conveyed to hospital by ambulance (50.1%). A larger proportion of women than men travelled by ambulance (52.4% v 47.9%; odds ratio [OR], 1.09; 95% CI, 1.07-1.11), but time between the emergency call and emergency department admission was similar for both sexes. The likelihood of being assessed as having a stroke (adjusted OR [aOR], 0.97; 95% CI, 0.93-1.01) or subarachnoid haemorrhage (aOR, 1.22; 95% CI, 0.73-2.03) was similar for women and men, but women under 70 years of age were less likely than men to be assessed as having a stroke (aOR, 0.89; 95% CI, 0.82-0.97). Women were more likely than men to be assessed by paramedics as having migraine, other headache, anxiety, unconsciousness, hypertension, or nausea. Women were less likely than men to be managed according to the NSW Ambulance pre-hospital stroke care protocol (aOR, 0.95; 95% CI, 0.92-0.97), but the likelihood of basic pre-hospital care was similar for both sexes (aOR, 1.01; 95% CI, 0.99-1.04). CONCLUSION: Our large population-based study identified sex differences in pre-hospital management by emergency medical services of women and men admitted to hospital with stroke. Paramedics should receive training that improves the recognition of stroke symptoms in women.

De-identifying Australian hospital discharge summaries: An end-to-end framework using ensemble of deep learning models.

Electronic Medical Records (EMRs) contain clinical narrative text that is of great potential value to medical researchers. However, this information is mixed with Personally Identifiable Information (PII) that presents risks to patient and clinician confidentiality. This paper presents an end-to-end de-identification framework to automatically remove PII from Australian hospital discharge summaries. Our corpus included 600 hospital discharge summaries which were extracted from the EMRs of two principal referral hospitals in Sydney, Australia. Our end-to-end de-identification framework consists of three components: (1) Annotation: labelling of PII in the 600 hospital discharge summaries using five pre-defined categories: person, address, date of birth, individual identification number, phone/fax number; (2) Modelling: training six named entity recognition (NER) deep learning base-models on balanced and imbalanced datasets; and evaluating ensembles that combine all six base-models, the three base-models with the best F1 scores and the three base-models with the best recall scores respectively, using token-level majority voting and stacking methods; and (3) De-identification: removing PII from the hospital discharge summaries. Our results showed that the ensemble model combined using the stacking Support Vector Machine (SVM) method on the three base-models with the best F1 scores achieved excellent results with a F1 score of 99.16% on the test set of our corpus. We also evaluated the robustness of our modelling component on the 2014 i2b2 de-identification dataset. Our ensemble model, which uses the token-level majority voting method on all six base-models, achieved the highest F1 score of 96.24% at strict entity matching and the highest F1 score of 98.64% at binary token-level matching compared to two state-of-the-art methods. The end-to-end framework provides a robust solution to de-identifying clinical narrative corpuses safely. It can easily be applied to any kind of clinical narrative documents.

Hierarchical label-wise attention transformer model for explainable ICD coding.

International Classification of Diseases (ICD) coding plays an important role in systematically classifying morbidity and mortality data. In this study, we propose a hierarchical label-wise attention Transformer model (HiLAT) for the explainable prediction of ICD codes from clinical documents. HiLAT firstly fine-tunes a pretrained Transformer model to represent the tokens of clinical documents. We subsequently employ a two-level hierarchical label-wise attention mechanism that creates label-specific document representations. These representations are in turn used by a feed-forward neural network to predict whether a specific ICD code is assigned to the input clinical document of interest. We evaluate HiLAT using hospital discharge summaries and their corresponding ICD-9 codes from the MIMIC-III database. To investigate the performance of different types of Transformer models, we develop ClinicalplusXLNet, which conducts continual pretraining from XLNet-Base using all the MIMIC-III clinical notes. The experiment results show that the F1 scores of the HiLAT + ClinicalplusXLNet outperform the previous state-of-the-art models for the top-50 most frequent ICD-9 codes from MIMIC-III. Visualisations of attention weights present a potential explainability tool for checking the face validity of ICD code predictions.