WITHDRAWN: Relevance Based Prediction: A Transparent, Non-Artificial Intelligence, Mathematical Solution to Personalized Opioid Treatment
- 1The Johns Hopkins University School of Medicine
Abstract
Accurate prediction of individual medical outcomes is essential for optimizing treatment allocation amid rising costs, coverage denials, and limited clinical resources. Traditional predictive models, including regression and neural networks, rely on average effects and cannot tailor predictions to the specific circumstances of individual cases. We present relevance-based prediction (RBP), a model-free method that predicts outcomes as weighted averages of observed cases, with weights determined by a rigorously defined measure of relevance. Unlike model-based methods that rely on fixed calibrated parameters, RBP revisits the original data for each prediction and customizes both the cases and variables used. Applied to opioid treatment, RBP provides case-specific insights unavailable from conventional models, including how each prior case informs a prediction, how each variable affects its reliability and value, and how reliable the prediction is before it is made. These individualized insights may prevent misleading average-based decisions and reduce harmful or suboptimal treatment.
Related
- Athlete-AI: a multi-modal artificial intelligence framework for personalized athlete monitoring and injury risk forecasting
- From digital reminders to artificial intelligence–enabled understanding: can personalized treatment predictions improve therapeutic adherence?
- Personalized Remote Patient Management in Heart Failure : From Implanted Hemodynamic Monitoring Toward an Artificial Intelligence-Supported Adaptive Care Cycle.
- Artificial intelligence chatbots provide inadequately transparent and readable patient information on triangular fibrocartilage complex injuries: a cross-sectional study
- Artificial Intelligence in Chronic Rhinosinusitis: From Molecular Profiling to Personalized Clinical Management—A Systematic Review
BibTeX
@misc{robinson2026withdrawn,
title = {{WITHDRAWN: Relevance Based Prediction: A Transparent, Non-Artificial Intelligence, Mathematical Solution to Personalized Opioid Treatment}},
author = {C. L. Robinson and D. Turkington and L. Lee and M. Kritzman and R. J. Yong},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.07.26359966},
url = {https://www.medrxiv.org/content/10.64898/2026.08.07.26359966v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - WITHDRAWN: Relevance Based Prediction: A Transparent, Non-Artificial Intelligence, Mathematical Solution to Personalized Opioid Treatment
AU - C. L. Robinson
AU - D. Turkington
AU - L. Lee
AU - M. Kritzman
AU - R. J. Yong
PY - 2026
DA - 2026/08/07
PB - medRxiv
DO - 10.64898/2026.08.07.26359966
UR - https://www.medrxiv.org/content/10.64898/2026.08.07.26359966v2
AB - Accurate prediction of individual medical outcomes is essential for optimizing treatment allocation amid rising costs, coverage denials, and limited clinical resources. Traditional predictive models, including regression and neural networks, rely on average effects and cannot tailor predictions to the specific circumstances of individual cases. We present relevance-based prediction (RBP), a model-free method that predicts outcomes as weighted averages of observed cases, with weights determined by a rigorously defined measure of relevance. Unlike model-based methods that rely on fixed calibrated parameters, RBP revisits the original data for each prediction and customizes both the cases and variables used. Applied to opioid treatment, RBP provides case-specific insights unavailable from conventional models, including how each prior case informs a prediction, how each variable affects its reliability and value, and how reliable the prediction is before it is made. These individualized insights may prevent misleading average-based decisions and reduce harmful or suboptimal treatment.
ER -