Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Dec 4, 2020
Date Accepted: Jul 5, 2021
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Geospatial Analysis to Understand Pediatric Surgery Cancellation
ABSTRACT
Background:
Day-of-surgery cancellation (DoSC) represents a substantial wastage of hospital resources, and can cause significant distress and inconvenience to patients and families. Cancellation is reported to impact between 2% and 20% of the 50 million procedures performed annually in American hospitals. Up to 85% of cancellations may be amenable to modification of patients’ and/or families’ behaviors. However, factors underlying DoSC and barriers experienced by families (e.g., low education, poor transportation access) are not well understood.
Objective:
This study aimed to conduct a geospatial analysis of patient-specific variables from electronic health records (EHR) of Cincinnati Children’s Hospital Medical Center (CCHMC) and of Texas Children’s Hospital (TCH), as well as linked socioeconomic factors measured at the census tract level, to understand potential underlying contributors to pediatric surgery cancellation.
Methods:
The study populations were pediatric patients with scheduled surgeries at CCHMC and TCH. A five-year dataset was extracted from the CCHMC EHR; addresses were then geocoded. An equivalent set of data over 5.7 years was extracted from the TCH EHR. Case-based data related to patients’ prior healthcare utilization and scheduling behaviors were aggregated at the census tract level. Community-level variables were extracted from the American Community Survey as surrogates for patients’ socioeconomic and minority status as well as markers of surrounding context. Leveraging the selected variables, we built spatial models to understand variation in DoSC rates across census tracts. The findings were compared to those of non-spatial generalized linear regression (GLM) and deep learning models. Model performance was evaluated by root mean squared error (RMSE) using nested ten-fold cross-validation. Feature importance was measured by computing increment of RMSE when a single variable was shuffled within the dataset.
Results:
Data collection procedures yielded a set of 463 census tracts (DoSC rates: [1.2%, 12.5%]) at CCHMC and 1,024 census tracts (DoSC rates: [3.0%, 12.2%]) at TCH. For CCHMC, an L2-normalized GLM achieved the best performance in predicting all-cause DoSC rate (RMSE: 1.299%; 95%CI: [1.210%, 1.387%]), but its gain over others, including spatial models, was marginal. For TCH, an L2-normalized GLM also performed best (RMSE: 1.305%; 95%CI: [1.257%, 1.352%]). All-cause cancellation at CCHMC was predicted most strongly by “previous ‘no show’”. As for community-level data, the proportion of African American inhabitants per census tract was consistently an important predictor. In the Texas area, the proportion of overcrowded households showed the strongest association with DoSC.
Conclusions:
Our findings suggest that geospatial analysis offers potential for use in targeting interventions towards census tracts at higher risk of cancellation. Our study also demonstrates the importance of home location, socioeconomic disadvantage and racial minority status to DoSC of children’s surgery. The success of future efforts to reduce cancellation may benefit from taking social, economic and cultural issues into account.
Citation
