Oncospace
K242748Oncospace, Inc. · cleared 2025-04-11 · product code MUJ · Radiology
Premarket evidence — what FDA accepted
source quote (p.7)
“The Oncospace subject device is a software-only medical device that performs the same functions as the Oncospace predicate device. The following verification and validation testing results (performance data) support the substantial equivalence determination. Since this is a software-only medical device that does not control other devices the performance data does not include biocompatibility, electrical safety, electromagnetic compatibility, mechanical, acoustic, or animal testing.”
source quote (p.5)
“The software includes locked machine learning algorithms. The Oncospace software includes an algorithm for transforming non-standardized OAR names used by treatment planners to standardized names defined by AAPM Task Group 263. This matching process primarily uses a table of synonyms that is updated as matches are made during use of the product, as well as a Natural Language Processing (NLP) model that attempts to match plan names not already in the synonym table.”
source quote (p.5)
“The software includes locked machine learning algorithms. Note: The subject device algorithms, and any future algorithm updates, are locked prior to clinical use.”
source quote (p.10)
“The verification tests met all system requirements and acceptance criteria which address clinical, standard user interface, and cybersecurity requirements for the Oncospace device.”
Validation studies (5)
Retrospective clinical
n=18 patients · 1 site(s)
endpoints: plan quality as represented by mean organ-at-risk (OAR) dose sparing; target coverage
Retrospective clinical
n=20 patients · 1 site(s)
endpoints: plan quality as represented by mean organ-at-risk (OAR) dose sparing; target coverage
Retrospective clinical
n=17 patients · 1 site(s)
endpoints: plan quality as represented by mean organ-at-risk (OAR) dose sparing; target coverage
Retrospective clinical
n=17 patients · 1 site(s)
endpoints: plan quality as represented by mean organ-at-risk (OAR) dose sparing; target coverage
Standalone
n=221 other
endpoints: macro-averaged F1 score; accuracy; correctly matched structure names
Reported performance (2 observations)
source quote (p.13)
“During 5-fold cross-validation all models achieved a validation macro-averaged F1 score above 0.92”
source quote (p.13)
“and accuracy above 96% for classifying previously unseen terms.”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
- recall_reason_pattern
Software/algorithm-related recall in product code MUJ (Philips Medical Systems (Cleveland) Inc, initiated 2025-08-05): "Due to a software issue, there is a potential image error of the Region of Interest for expansion/contraction for HFP (Head First Prone), FFS (Feet First Supine) and FFP (Feet Firs" Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:97049
- recall_reason_pattern
Software/algorithm-related recall in product code MUJ (Philips Medical Systems (Cleveland) Inc, initiated 2025-07-17): "Due to software issue, Radiation Therapy Planning system may provide incorrect dataset calculations when performing the "Stopping Power Ratio" (SPR) ," Recalling firm is another firm in the same product code.
first seen 2026-07-08 · recall res_event_number:97309
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).