Use of responsible artificial intelligence to predict health insurance claims in the USA using machine learning algorithms
importance 5/10
ai assisted
Artificial Intelligence in Healthcare health insurance stage: research
Problem
Predicting health insurance claims in the USA to improve claim processing and reduce insurance costs.
Why it matters
Better claim prediction could cut costs for insurers and speed healthcare payments.
What the AI did
Compared six ML algorithms (SVM, DT, RF, LR, XGBoost, KNN) for claim prediction with feature importance analysis.
Results
XGBoost and RF outperformed other algorithms with the highest R-squared values; exact value not stated in source.
Impact
Evidence shows XGBoost and RF best predicted claims; real-world savings or deployment not stated.
Record
| Venue | Exploration of Digital Health Technologies |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | A. N. M. Sajedul Alam, Victor R. Prybutok |
| Citations | 19 (OpenAlex, at import time) |
| References | 18 |
| Model or method | XGBoost, Random Forest (best performers) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.37349/edht.2024.00009 |
| Open access | diamond |
| Keywords | health insurance claims, XGBoost, random forest, machine learning, prediction, feature importance |
Importance rating
5
real but narrower advance
Better claim prediction could cut insurer costs and speed healthcare payments in the USA; abstract frames benefits as potential cost savings but provides no scale of impact.