Unmet Need
Bone is the third most frequent site of tumor metastasis; it is estimated that 280,000 patients in the United States are living with symptomatic bone metastasis (SBM). Currently, physicians use their intuition and subjective experience with patients suffering from bone metastasis to make survival predictions that guide treatment decisions. Due to the variability of symptoms and status from patient to patient, decision making processes may suffer from uncertainty. Consequently, this uncertainty may have a detrimental effect on patient communication and the ability to determine the best course of treatment. Therefore, there is a need to mitigate uncertainty and allow physicians to communicate more accurate predictions and treatment decisions through the advancement of survival estimations. The disclosed technology aims to address this limitation with a web-based machine-learning platform that can improve the accuracy in survival estimations for patients with SBM; thus, improving the decision-making process.
Technology Overview
Researchers at Johns Hopkins University have designed a novel platform to assist physicians that deal with symptomatic bone metastasis in patients. More specifically, the technology intends to improve the accuracy of survival estimations in patients using prognostic factors. The unique platform incorporates a machine-learning model that allows medical professionals to enter patient-specific factors, and consequently render a survival prediction based on the information. The disclosed technology has the potential to ameliorate the prognosis and treatment options for patients with bone metastasis.
Stage of Development
Source code is developed and data that supports the technology is available. A demo version of the BMETS platform is available (https://nomogram-demo2.alcorn.dayflower.io/).
Publications
Alcorn SR, et al. Int J Radiat Oncol Biol Phys, S0360-3016(20)31147-0, 2020
