AMPREDICT PROsthetics-Predicting Prosthesis Mobility to Aid in Prosthetic Prescription and Rehabilitation Planning.
Daniel C Norvell, Mary Lou Thompson, Aaron Baraff and 7 others
PMID 36539174WHAT IT FOUND
A new model predicts 12-month mobility for first-time transtibial or transfemoral amputees using 23 electronic health record factors.
It best distinguishes household from community ambulation, helping clinicians match prosthetics to likely outcomes and set realistic patient goals.
Key findings
01The AMPREDICT PRO model uses 23 predictors from the electronic health record to estimate the probability of achieving specific mobility levels 12 months after prosthetic prescription.
02The model shows modest overall discrimination but performs well in distinguishing household ambulation from basic and advanced community ambulation.
03Predicted mobility outcomes vary by amputation level, with advanced community ambulation declining with age in all patients and with higher BMI specifically in transfemoral amputees.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study population was exclusively veterans, resulting in a very small number of women, which limits generalizability to civilian populations. The response rate for collecting mobility outcomes was 21%, though the authors note that non-responders were similar to responders. The model can only use data available at the time of prescription and cannot account for future events like reamputation or new comorbidities that might affect mobility. Overall discrimination is modest, and the model struggles to distinguish between the lowest mobility categories (wheelchair vs. limited home ambulation).
Declared interests
The study was supported by the U.S. Department of Veterans Affairs. No other specific conflicts of interest or commercial funding sources are detailed in the provided text.
The easy way to misread this
Do not treat this model as a definitive diagnostic tool. Its overall discrimination is modest, and it has not yet been validated prospectively in a clinical setting. Use the predictions as one factor in shared decision-making, not as a sole basis for denying prosthetic components or limiting rehabilitation potential.