OBJECTIVE: We examined whether the trajectory of femorotibial cartilage loss differs between knees meeting a clinically defined virtual knee replacement (vKR) status based on patient-reported outcomes vs. those with low probability. DESIGN: vKR cases (highest 10 ​% of probabilities for having surgical KR) were selected using knee pain and quality of life criteria, developed from knees with actual KR. Knees reaching such symptom state at 48 months (M) follow-up (vKR case 60 ​M) were matched 1:1 with vKR controls (lowest 20 ​% probability) by sex, age, and baseline radiographic status. Of 65 knees displaying vKR case status at 60 ​M; 33 maintained or increased pain and QOL levels at 72 ​M (vKR+/+); 32 did not (vKR+/-). The thickness of medial and lateral tibial and femoral cartilages was determined from MRI, at up to five annual visits prior to 60 ​M. RESULTS: vKR case knees displayed substantially greater central medial femorotibial compartment cartilage thickness loss 2 years prior to reaching case status (-151 ​± ​337 [mean ​± ​SD] vs. -38 ​± ​249 ​μm; odds ratio [OR] 1.95 (95 ​% confidence interval: 1.23-3.08). Cartilage loss did not apparently differ between vKR+/+ and vKR +/- knees (p ​= ​0.73). CONCLUSIONS: Substantially greater cartilage thickness loss was detected in knees reaching vKR case status defined by patient-reported clinical criteria vs. vKR controls. This was found independently of whether this status was maintained at a later annual visit. The observed association suggests greater knee cartilage loss to be prospectively related to worse clinical outcome. It indicates further that the vKR criterion used here may be useful to explore relationships with other structural (imaging) assessments.