Using Historical Information of Patients for Prior Authorization Learning

Farias, Karoline de M.; Neto, Pedro; Santana, A. M.; Neto, Ranulfo Bezerra

doi:10.1109/bracis.2019.00110

Cited by 5 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This dynamic learning mechanism enables the model to quickly adapt to the evolving landscape of requests, providing the preauthorization process with increased adaptability and responsiveness. Furthermore, the proposed approach enables real-time prediction and effectively tackles the issue of Previous studies on medical preauthorization in health insurance [31][32] relied on traditional machine-learning methods. Although the proposed approach shows potential, it is important to note that previous studies exhibited higher performance than the initial performance of the proposed model, and this could be attributed to the limited amount of labeled data used to train it.…”

Section: Resultsmentioning

confidence: 99%

Advancing Preauthorization Task in Healthcare: An Application of Deep Active Incremental Learning for Medical Text Classification

Salau,

Agwu Nwojo,

Mahamat Boukar

et al. 2023

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

This study presents a novel approach to medical text classification using a deep active incremental learning model, aiming to improve the automation of the preauthorization process in medical health insurance. By automating decision-making for request approval or denial through text classification techniques, the primary focus is on real-time prediction, utilization of limited labeled data, and continuous model improvement. The proposed approach combines a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network with active learning, using uncertainty sampling to facilitate expert-based sample selection and online learning for continuous updates. The proposed model demonstrates improved predictive accuracy over a baseline Long Short-Term Memory (LSTM) model. Through active learning iterations, the proposed model achieved a 4% improvement in balanced accuracy over 100 iterations, underscoring its efficiency in continuous refinement using limited labeled data.

show abstract

Section: Resultsmentioning

confidence: 99%