Category: Statistics

Biometrics. 2024 Jul 1;80(3):ujae078. doi: 10.1093/biomtc/ujae078.

ABSTRACT

Interval-censored failure time data frequently arise in various scientific studies where each subject experiences periodical examinations for the occurrence of the failure event of interest, and the failure time is only known to lie in a specific time interval. In addition, collected data may include multiple observed variables with a certain degree of correlation, leading to severe multicollinearity issues. This work proposes a factor-augmented transformation model to analyze interval-censored failure time data while reducing model dimensionality and avoiding multicollinearity elicited by multiple correlated covariates. We provide a joint modeling framework by comprising a factor analysis model to group multiple observed variables into a few latent factors and a class of semiparametric transformation models with the augmented factors to examine their and other covariate effects on the failure event. Furthermore, we propose a nonparametric maximum likelihood estimation approach and develop a computationally stable and reliable expectation-maximization algorithm for its implementation. We establish the asymptotic properties of the proposed estimators and conduct simulation studies to assess the empirical performance of the proposed method. An application to the Alzheimer’s Disease Neuroimaging Initiative (ADNI) study is provided. An R package ICTransCFA is also available for practitioners. Data used in preparation of this article were obtained from the ADNI database.

PMID:39177025 | DOI:10.1093/biomtc/ujae078

Cancer Med. 2024 Aug;13(16):e70032. doi: 10.1002/cam4.70032.

ABSTRACT

The large real-world EHR dataset Flatiron has shown that race was not significantly associated with poorer survival in patients with DLBCL. Medicaid insurance status was significantly associated with poorer overall survival and time to second-line therapy or death due to any cause in patients with DLBCL aged <65 years.

PMID:39177019 | DOI:10.1002/cam4.70032

Euro Surveill. 2024 Aug;29(34). doi: 10.2807/1560-7917.ES.2024.29.34.2400139.

ABSTRACT

BackgroundIn 2022, a global monkeypox virus (MPXV) clade II epidemic occurred mainly among men who have sex with men. Until early 1980s, European smallpox vaccination programmes were part of worldwide smallpox eradication efforts. Having received smallpox vaccine > 20 years ago may provide some cross-protection against MPXV.AimTo assess the effectiveness of historical smallpox vaccination against laboratory-confirmed mpox in 2022 in Europe.MethodsEuropean countries with sufficient data on case vaccination status and historical smallpox vaccination coverage were included. We selected mpox cases born in these countries during the height of the national smallpox vaccination campaigns (latest 1971), male, with date of onset before 1 August 2022. We estimated vaccine effectiveness (VE) and corresponding 95% CI for each country using logistic regression as per the Farrington screening method. We calculated a pooled estimate using a random effects model.ResultsIn Denmark, France, the Netherlands and Spain, historical smallpox vaccination coverage was high (80-90%) until the end of the 1960s. VE estimates varied widely (40-80%, I2 = 82%), possibly reflecting different booster strategies. The pooled VE estimate was 70% (95% CI: 23-89%).ConclusionOur findings suggest residual cross-protection by historical smallpox vaccination against mpox caused by MPXV clade II in men with high uncertainty and heterogeneity. Individuals at high-risk of exposure should be offered mpox vaccination, following national recommendations, regardless of prior smallpox vaccine history, until further evidence becomes available. There is an urgent need to conduct similar studies in sub-Saharan countries currently affected by the MPXV clade I outbreak.

PMID:39176988 | DOI:10.2807/1560-7917.ES.2024.29.34.2400139

Euro Surveill. 2024 Aug;29(34). doi: 10.2807/1560-7917.ES.2024.29.34.2300503.

ABSTRACT

BackgroundVaccine uptake differs between social groups. Mobile vaccination units (MV-units) were deployed in the Netherlands by municipal health services in neighbourhoods with low uptake of COVID-19 vaccines.AimWe aimed to evaluate the impact of MV-units on vaccine uptake in neighbourhoods with low vaccine uptake.MethodsWe used the Dutch national-level registry of COVID-19 vaccinations (CIMS) and MV-unit deployment registrations containing observations in 253 neighbourhoods where MV-units were deployed and 890 contiguous neighbourhoods (total observations: 88,543 neighbourhood-days). A negative binomial regression with neighbourhood-specific temporal effects using splines was used to study the effect.ResultsDuring deployment, the increase in daily vaccination rate in targeted neighbourhoods ranged from a factor 2.0 (95% confidence interval (CI): 1.8-2.2) in urbanised neighbourhoods to 14.5 (95% CI: 11.6-18.0) in rural neighbourhoods. The effects were larger in neighbourhoods with more voters for the Dutch conservative Reformed Christian party but smaller in neighbourhoods with a higher proportion of people with non-western migration backgrounds. The absolute increase in uptake over the complete intervention period ranged from 0.22 percentage points (95% CI: 0.18-0.26) in the most urbanised neighbourhoods to 0.33 percentage point (95% CI: 0.28-0.37) in rural neighbourhoods.ConclusionDeployment of MV-units increased daily vaccination rate, particularly in rural neighbourhoods, with longer travel distance to permanent vaccination locations. This public health intervention shows promise to reduce geographic and social health inequalities, but more proactive and long-term deployment is required to identify its potential to substantially contribute to overall vaccination rates at country level.

PMID:39176986 | DOI:10.2807/1560-7917.ES.2024.29.34.2300503

Drug Alcohol Rev. 2024 Aug 23. doi: 10.1111/dar.13933. Online ahead of print.

ABSTRACT

INTRODUCTION: More evidence for patterns of healthcare utilisation and associated costs among people receiving opioid agonist therapy (OAT) is needed. We investigated primary and secondary healthcare usage and costs among methadone and buprenorphine recipients in England.

METHODS: We conducted a cohort study using the Clinical Practice Research Datalink GOLD and Aurum databases of patients who were prescribed OAT between 1 January 2007 and 31 July 2019. The cohort was linked to Hospital Episode Statistics admitted patient care, outpatient and emergency department data, neighbourhood- and practice-level Index of Multiple Deprivation quintiles and mortality records. Negative binomial regression models were applied to estimate weighted rate ratios (wRR) of healthcare utilisation. Total and mean costs were calculated using Unit Costs of Health and Social Care and the National Healthcare Service Payment by Results National Tariffs.

RESULTS: Among 12,639 patients observed over 39,016 person-years, we found higher rate of hospital admissions (wRR 1.18; 1.08-1.28) among methadone compared with buprenorphine recipients. The commonest hospital discharge diagnoses among methadone patients were infectious diseases (19.2%), mental and behavioural disorders (17.0%) and drug-related poisoning (16.5%); the three commonest among buprenorphine patients were mental and behavioural diseases (21.5%), endocrine (13.8%) and genitourinary system diseases (13.1%). Methadone patients had similar mean costs compared with buprenorphine patients (cost difference: £539.01; 432.11-1006.69).

DISCUSSION AND CONCLUSIONS: Differences in healthcare utilisation frequency for methadone versus buprenorphine recipients were observed. The differences in associated costs were mainly driven by hospital admissions. These findings offer valuable insights for optimising care strategies and resource allocation for OAT recipients.

PMID:39176979 | DOI:10.1111/dar.13933

Stud Health Technol Inform. 2024 Aug 22;316:1069-1073. doi: 10.3233/SHTI240595.

ABSTRACT

This comparative study examines the transition from isolated registries to a consolidated data-centric approach at University Hospital Schleswig-Holstein, focusing on migrating the Atrioventricular Valve Intervention Registry (AVIR) from REDCap to a Medical Data Integration Center based openEHR registry. Through qualitative analysis, we identify key disparities and strategic decisions guiding this transition. While REDCap has historical utility, its limitations in automated data integration and traceability highlight the advantages of a data-centric approach, which include streamlined data (integration) management at a single-point-of-truth based on e.g., centralized consent management. Our findings lay the groundwork for the AVIR project and a proof-of-concept data-centric registry, reflecting a broader industry trend towards data-centric healthcare initiatives.

PMID:39176974 | DOI:10.3233/SHTI240595

Stud Health Technol Inform. 2024 Aug 22;316:1038-1042. doi: 10.3233/SHTI240588.

ABSTRACT

The effective management of human resources in nursing is fundamental to ensuring high-quality care. The necessary staffing levels can be derived from the nursing-related health status. Our approach is based on the use of artificial intelligence (AI) and machine learning (ML) to recognize key workload-driving predictors from routine data in the first step and derive recommendations for staffing levels in the second step. The precedent analysis was a multi-center study with data provided by three hospitals. The SPI (Self Care Index = sum score of 10 functional/cognitive items of the epaAC (epaAC = nursing assessment tool for AcuteCare (abbreviated from the German-language effiziente Pflege-Analyse AcuteCare))) was identified as a strong predictor of nursing workload. The SPI alone explains the variance in minutes with an adjusted R2 of 40% to 66%. With the addition of further predictors such as “fatigue” or “pain intensity”, the adjusted R2 can be increased by up to 17%. The resulting model can be used as a foundation for data-based personnel controlling using AI-based prediction models.

PMID:39176968 | DOI:10.3233/SHTI240588

Stud Health Technol Inform. 2024 Aug 22;316:993-997. doi: 10.3233/SHTI240577.

ABSTRACT

Healthcare processes are complex and involve uncertainties to influence the service quality and health of patients. Patient transportation takes place between the hospitals or between the departments within the hospital (i.e., Inter- or Intra-Hospital Transportation respectively). The focus of our paper is route planning for transporting patients within the hospital. The route planning task is complex due to multiple factors such as regulations, fairness considerations (i.e., balanced workload amongst transporters), and other dynamic factors (i.e., transport delays, wait times). Transporters perform the physical transportation of patients within the hospital. In principle, each job allocation respects the transition time between the subsequent jobs. The primary objective was to determine the feasible number of transporters, and then generate the route plan for all determined transporters by distributing all transport jobs (i.e., from retrospective data) within each shift. Secondary objectives are to minimize the sum of total travel time and sum of total idle time of all transporters and minimize the deviations in total travel time amongst transporters. Our method used multi-staged Local Search Metaheuristics to attain the primary objective. Metaheuristics incorporate Mixed Integer Linear Programming to allocate fairly the transport jobs by formulating optimization constraints with bounds for satisfying the secondary objectives. The obtained results using formulated optimization constraints represent better efficacy in multi-objective route planning of Intra-Hospital Transportation of patients.

PMID:39176958 | DOI:10.3233/SHTI240577

Stud Health Technol Inform. 2024 Aug 22;316:929-933. doi: 10.3233/SHTI240563.

ABSTRACT

Predictive modeling holds a large potential in clinical decision-making, yet its effectiveness can be hindered by inherent data imbalances in clinical datasets. This study investigates the utility of synthetic data for improving the performance of predictive modeling on realistic small imbalanced clinical datasets. We compared various synthetic data generation methods including Generative Adversarial Networks, Normalizing Flows, and Variational Autoencoders to the standard baselines for correcting for class underrepresentation on four clinical datasets. Although results show improvement in F1 scores in some cases, even over multiple repetitions, we do not obtain statistically significant evidence that synthetic data generation outperforms standard baselines for correcting for class imbalance. This study challenges common beliefs about the efficacy of synthetic data for data augmentation and highlights the importance of evaluating new complex methods against simple baselines.

PMID:39176944 | DOI:10.3233/SHTI240563

Stud Health Technol Inform. 2024 Aug 22;316:868-872. doi: 10.3233/SHTI240549.

ABSTRACT

This study investigates the forecasting of cardiovascular mortality trends in Greece’s elderly population. Utilizing mortality data from 2001 to 2020, we employ two forecasting models: the Autoregressive Integrated Moving Average (ARIMA) and Facebook’s Prophet model. Our study evaluates the efficacy of these models in predicting cardiovascular mortality trends over 2020-2030. The ARIMA model showcased predictive accuracy for the general and male population within the 65-79 age group, whereas the Prophet model provided better forecasts for females in the same age bracket. Our findings emphasize the need for adaptive forecasting tools that accommodate demographic-specific characteristics and highlight the role of advanced statistical methods in health policy planning.

PMID:39176930 | DOI:10.3233/SHTI240549