Predictive Planning
Introducing Predictive Planning
from Oncospace
Oncospace Predictive Planning uses a machine learning model based on thousands of clinical treatment plans to derive achievable, best-practice, dosimetric goals for plan optimization and evaluation.
“Predicting achievable dose objectives in Oncospace before we start radiation therapy planning will remove the guesswork that slows us down.
We can begin with the end in mind and take confidence that the final plans will meet the high quality we expect.”
Questions Remain
With all the technology, talent, and know-how in a radiation oncology practice, questions still remain
- What impact will my decisions have on this patient’s plan?
- How do I know errors are being found and corrected?
- How do I know this is what the physician wants?
- How do I mitigate risks in the practice?
- How do I effectively protect the hospital network and patient data while ensuring user performance?
Predictive Planning turns questions into confidence.
What impact will my decisions have on this patient’s plan?
- Examine a range of predictions from “Best Achievable” to “Typically Achievable”
- Determine the most appropriate planning strategy
- Set patient specific clinical goals and planning objectives
How do I know errors are being found and corrected?
- Create or customize pre-defined templates of clinical goals, prescriptions, and delivery methods
- Correct contour and prescription anomalies
- Avoid unrealistic clinical goals and planning objectives
How do I know this is what the physician wants?
- Access a shared resource detailing physician defined, patient specific, planning requirements
- Drive planning with clear, prediction* defined objectives, clinical goals, prescriptions, and delivery methods
- Compare TPS results to clinical goals and predictions
Previous
Next
How do I mitigate risks in the practice?
- Modernize Pinnacle archive data: accessible for retreatments and continuity of care
- Minimize “Time on TPS” with predicted* achievable plan optimization objectives at the start
- Ensure consistency across users and locations with a common, robust prediction model
How do I effectively protect the hospital network and patient data while ensuring user performance?
- Built cloud-first on Microsoft Azure
- Perform PHI de-identification prior to secure cloud upload with On-premises component
- ISO/IEC 27001/SOC II Certification (Pending)