Survival Prediction Model for Palliative Bone Metastasis Radiotherapy


This tool can be used at the time of consultation for palliative radiotherapy to symptomatic bone metastases in order to estimate patient survival time following consultation. Providers can enter values for the patient, disease, and treatment variables listed below, and a predicted survival plot will be displayed, based on the Bone Metastases Ensemble Trees for Survival (BMETS) machine learning model (publication pending).

Briefly, the BMETS model was built using a database of 397 patients seen in Radiation Oncology consultation for symptomatic bone metastasis at the Johns Hopkins Hospital between 2007 and 2013. Each patient’s chart was retrospectively reviewed to collect demographic, disease, and treatment information felt to be potentially useful in predicting survival. His or her actual survival time following consultation was documented. The BMETS model was then built using a random survival forests algorithm to predict survival time following consultation based on 27 patient-specific characteristics.

Enter your patient’s information below. If a value is unknown, leave the entry blank or unselected. Values marked with Required Field are required fields.



Age (yrs):

White blood cell count within 1 month of consultation: in µL (reference range 4500-1100)

in µL (reference range 1100-4800)

    (use yyyy-mm-dd format if text in Safari or IE)

Gender: Male Female

Race: White African American Asian Other

Primary cancer site: Required Field
Breast Prostate Leukemias Lung Other

Required Field

Please select all bone sites that will be treated with palliative radiotherapy at this time: Question Icon
Spine Extremity Hip/Pelvis Chest Wall Skull

How many separate bone fields are currently being treated? Question Icon

If site(s) of current radiotherapy include the spine, is there definite radiologic evidence of nerve root, spinal canal, or spinal cord involvement within the spine field(s)?
Yes No Not applicable Imaging unavailable

If site(s) of current radiotherapy include the hip/pelvis, is there definite radiologic evidence of nerve root, spinal canal, or spinal cord involvement within the hip/pelvic field(s)?
Yes No Not applicable Imaging unavailable

Was there prior surgery at any of the current sites of palliative radiotherapy?
Yes No

Are there other NON-BONE sites of metastatic disease that are going to be treated concurrently (in non-contiguous fields)? Question Icon
None Brain Lungs Other

Is the patient admitted at the hospital (inpatient)? Question Icon
Yes No

Is the patient currently taking steroid medication?
Yes No

Is the patient currently taking opioid pain medication?
Yes No

What was the most recent type of systemic therapy delivered? Question Icon
None IV Oral Hormonal

Did the patient receive systemic therapy in the past 1 month?
Yes No

Does the patient report any weight loss within the past 6 months?
Yes No

Please select all radiologically-confirmed sites of metastases other than the current site of palliative radiation. Question Icon
Brain Lung Liver Adrenal glands
Lymph nodes Soft tissue Other bone Other sites not specified

The BMETS model is intended to help health care providers when estimating survival time for patients. The BMETS model is not intended to be a substitute for medical evaluation, advice, or treatment and should only be used in the context of a clinical discussion with a qualified health care provider. While the model is calibrated to be as accurate as possible across patients, the predicted survival time may underestimate or overestimate an individual patient’s actual survival time. This model has undergone internal and limited external validation procedures. However, given the range of clinical presentations and the rapidly changing nature of health care, the model may produce inaccurate or outdated predictions for specific patients. Particular caution should be used when applying these data to patient populations that vary significantly from the source population described in the primary manuscript. As such, health care providers should use their own clinical discretion when interpreting these results for individual patients. The Johns Hopkins University School of Medicine (JHUSOM) expressly disclaims all representations and warranties related to the BMETS model, including representations and warranties of accuracy, fitness for use, reliability, validity, or non-infringement of third party intellectual property rights. JHUSOM does not save user information or other data entered into this web platform. By accepting these terms of use, you are agreeing that JHUSOM will not be liable for health care decisions or outcomes rendered from the use of the BMETS model.

I understand these limitations and agree to proceed
I do not agree to proceed





The interactive orange plot above demonstrates the predicted survival curve within the 12 months following radiation oncology consultation for the specific patient based on the characteristics selected above. The blue curves demonstrate the predicted survival for all other patients with symptomatic bone metastases in the BMETS database, arranged from lowest (dark blue) to highest (light blue) predicted survival. These blue curves are displayed for comparison purposes and to demonstrate the effective prediction limits of BMETS. NOTE: The plot displaying the patient’s predicted survival reflects a predicted value from the BMETS model. While the model is calibrated to be as accurate as possible across all patients within the prediction limits, the predicted survival time may underestimate or overestimate an individual patient’s actual survival time. PLEASE EXERCISE PARTICULAR CAUTION when interpreting specific survival probability values that fall close to or outside of the blue curves, as such values may be outside of the BMETS prediction limits. Specifically outside of these prediction limits, the model tends to overestimate true survival among patients with very low BMETS-predicted survival probabilities at shorter survival times and may underestimate true survival among patients with higher BMETS-predicted survival probabilities at long survival times.

Click here for a tutorial on using and interpreting output for the predicted survival plot..


© 2020 The Johns Hopkins University