Dataset Information

Development and validation of a model to categorize cardiovascular cause of death using health administrative data.

ABSTRACT:

Study objective

Develop and evaluate a model that uses health administrative data to categorize cardiovascular (CV) cause of death (COD).

Design

Population-based cohort.

Setting

Ontario, Canada.

Participants

Decedents ≥ 40 years with known COD between 2008 and 2015 in the CANHEART cohort, split into derivation (2008 to 2012; n = 363,778) and validation (2013 to 2015; n = 239,672) cohorts.

Main outcome measures

Model performance. COD was categorized as CV or non-CV with ICD-10 codes as the gold standard. We developed a logistic regression model that uses routinely collected healthcare administrative to categorize CV versus non-CV COD. We assessed model discrimination and calibration in the validation cohort.

Results

The strongest predictors for CV COD were history of stroke, history of myocardial infarction, history of heart failure, and CV hospitalization one month before death. In the validation cohort, the c-statistic was 0.80, the sensitivity 0.75 (95 % CI 0.74 to 0.75) and the specificity 0.71 (95 % CI 0.70 to 0.71). In the primary prevention validation sub-cohort, the c-statistic was 0.81, the sensitivity 0.71 (95 % CI 0.70 to 0.71) and the specificity 0.75 (95 % CI 0.75 to 0.75) while in the secondary prevention sub-cohort the c-statistic was 0.74, the sensitivity 0.81 (95 % CI 0.81 to 0.82) and the specificity 0.54 (95 % CI 0.53 to 0.54).

Conclusion

Modelling approaches using health administrative data show potential in categorizing CV COD, though further work is necessary before this approach is employed in clinical studies.

SUBMITTER: Patel S

PROVIDER: S-EPMC10978408 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of a model to categorize cardiovascular cause of death using health administrative data.

Patel Sagar S Thompson Wade W Sivaswamy Atul A Khan Anam A Ferreira-Legere Laura L Lee Douglas S DS Abdel-Qadir Husam H Jackevicius Cynthia C Goodman Shaun S Farkouh Michael E ME Tu Karen K Kapral Moira K MK Wijeysundera Harindra C HC Tam Derrick D Austin Peter C PC Fang Jiming J Ko Dennis T DT Udell Jacob A JA

American heart journal plus : cardiology research and practice 20220916

<h4>Study objective</h4>Develop and evaluate a model that uses health administrative data to categorize cardiovascular (CV) cause of death (COD).<h4>Design</h4>Population-based cohort.<h4>Setting</h4>Ontario, Canada.<h4>Participants</h4>Decedents ≥ 40 years with known COD between 2008 and 2015 in the CANHEART cohort, split into derivation (2008 to 2012; n = 363,778) and validation (2013 to 2015; n = 239,672) cohorts.<h4>Main outcome measures</h4>Model performance. COD was categorized as CV or no ...[more]

PMID: 38558908

Similar Datasets

Project description:ImportanceSystems-level barriers to diabetes care could be improved with population health planning tools that accurately discriminate between high- and low-risk groups to guide investments and targeted interventions.ObjectiveTo develop and validate a population-level machine learning model for predicting type 2 diabetes 5 years before diabetes onset using administrative health data.Design, setting, and participantsThis decision analytical model study used linked administrative health data from the diverse, single-payer health system in Ontario, Canada, between January 1, 2006, and December 31, 2016. A gradient boosting decision tree model was trained on data from 1 657 395 patients, validated on 243 442 patients, and tested on 236 506 patients. Costs associated with each patient were estimated using a validated costing algorithm. Data were analyzed from January 1, 2006, to December 31, 2016.ExposuresA random sample of 2 137 343 residents of Ontario without type 2 diabetes was obtained at study start time. More than 300 features from data sets capturing demographic information, laboratory measurements, drug benefits, health care system interactions, social determinants of health, and ambulatory care and hospitalization records were compiled over 2-year patient medical histories to generate quarterly predictions.Main outcomes and measuresDiscrimination was assessed using the area under the receiver operating characteristic curve statistic, and calibration was assessed visually using calibration plots. Feature contribution was assessed with Shapley values. Costs were estimated in 2020 US dollars.ResultsThis study trained a gradient boosting decision tree model on data from 1 657 395 patients (12 900 257 instances; 6 666 662 women [51.7%]). The developed model achieved a test area under the curve of 80.26 (range, 80.21-80.29), demonstrated good calibration, and was robust to sex, immigration status, area-level marginalization with regard to material deprivation and race/ethnicity, and low contact with the health care system. The top 5% of patients predicted as high risk by the model represented 26% of the total annual diabetes cost in Ontario.Conclusions and relevanceIn this decision analytical model study, a machine learning model approach accurately predicted the incidence of diabetes in the population using routinely collected health administrative data. These results suggest that the model could be used to inform decision-making for population health planning and diabetes prevention.

Project description:BACKGROUND:Coding of underlying causes of death from death certificates is a process that is nowadays undertaken mostly by humans with potential assistance from expert systems, such as the Iris software. It is, consequently, an expensive process that can, in addition, suffer from geospatial discrepancies, thus severely impairing the comparability of death statistics at the international level. The recent advances in artificial intelligence, specifically the rise of deep learning methods, has enabled computers to make efficient decisions on a number of complex problems that were typically considered out of reach without human assistance; they require a considerable amount of data to learn from, which is typically their main limiting factor. However, the CépiDc (Centre d'épidémiologie sur les causes médicales de Décès) stores an exhaustive database of death certificates at the French national scale, amounting to several millions of training examples available for the machine learning practitioner. OBJECTIVE:This article investigates the application of deep neural network methods to coding underlying causes of death. METHODS:The investigated dataset was based on data contained from every French death certificate from 2000 to 2015, containing information such as the subject's age and gender, as well as the chain of events leading to his or her death, for a total of around 8 million observations. The task of automatically coding the subject's underlying cause of death was then formulated as a predictive modelling problem. A deep neural network-based model was then designed and fit to the dataset. Its error rate was then assessed on an exterior test dataset and compared to the current state-of-the-art (ie, the Iris software). Statistical significance of the proposed approach's superiority was assessed via bootstrap. RESULTS:The proposed approach resulted in a test accuracy of 97.8% (95% CI 97.7-97.9), which constitutes a significant improvement over the current state-of-the-art and its accuracy of 74.5% (95% CI 74.0-75.0) assessed on the same test example. Such an improvement opens up a whole field of new applications, from nosologist-level batch-automated coding to international and temporal harmonization of cause of death statistics. A typical example of such an application is demonstrated by recoding French overdose-related deaths from 2000 to 2010. CONCLUSIONS:This article shows that deep artificial neural networks are perfectly suited to the analysis of electronic health records and can learn a complex set of medical rules directly from voluminous datasets, without any explicit prior knowledge. Although not entirely free from mistakes, the derived algorithm constitutes a powerful decision-making tool that is able to handle structured medical data with an unprecedented performance. We strongly believe that the methods developed in this article are highly reusable in a variety of settings related to epidemiology, biostatistics, and the medical sciences in general.

Project description:BackgroundPeripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes.ObjectiveThe aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system.MethodsAn initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance.ResultsThe initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862.ConclusionsThe algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.

Dataset Information

Development and validation of a model to categorize cardiovascular cause of death using health administrative data.

Study objective

Design

Setting

Participants

Main outcome measures

Results

Conclusion

Publications

Development and validation of a model to categorize cardiovascular cause of death using health administrative data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets