Predicting ophthalmic clinic non-attendance using machine learning: Development and validation of models using
Finley Breeze1, Ruhella R Hossain1,2, Michael Mayo3
1Department of Ophthalmology, University of Auckland, Auckland, New Zealand.
Clinical & Experimental Ophthalmology
|October 27, 2023
Summary
Machine learning accurately predicts ophthalmic clinic non-attendance using basic data, offering a cost-effective alternative to current strategies. This can improve healthcare access and reduce inequities in New Zealand.
Area of Science:
- Ophthalmology
- Health Informatics
- Machine Learning
Background:
- Ophthalmic clinic non-attendance in New Zealand leads to poor health outcomes, inequities, and significant costs.
- Current strategies to improve attendance are expensive and ineffective.
Purpose of the Study:
- To develop and validate machine learning models for accurate prediction of ophthalmic clinic non-attendance.
Main Methods:
- A retrospective observational study analyzed 3.1 million appointments from New Zealand public ophthalmology clinics (2009-2018).
- XGBoost and logistic regression models were trained and optimized using repeated ten-fold cross-validation on demographic and clinic-related variables.
- Models trained on regional data subsets were compared to a nationwide model.
Main Results:
- XGBoost models trained on regional data achieved the highest predictive performance (mean AUROC 0.764).
- XGBoost outperformed logistic regression (mean AUROC 0.756, p=0.002).
- Region-specific models performed better than a single nationwide model (mean AUROC 0.754, p=0.04).
Conclusions:
- Machine learning models can effectively predict ophthalmic clinic non-attendance using readily available data.
- Further research into implementing these algorithms in scheduling and public health interventions is warranted.
Related Concept Videos
01:18Steps in Outbreak Investigation
135
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
135
01:03Prediction Intervals
2.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.3K