This study investigated the effect of anterior cruciate ligament (ACL) injury on relative acceleration of the tibia and femur during a number of tests/activities, in order to assess the feasibility of acceleration-based diagnosis of ACL injury using inertial sensors. First, a detailed finite element model of the knee joint was developed to simulate the target tests/activities, and identify those in which a large difference between the maximum acceleration peaks (MAPs) of the healthy and ACL injured knees is likely to be observed. The promising tests/activities were entered in an experimental study, where the relative accelerations of the tibiae and femurs of 20 individuals with unilateral ACL injury, allocated randomly to two groups of conscious and unconscious test conditions, were recorded. Model predictions indicated MAP ratios>1.5 for the ACL-injured to healthy knees, during the anterior drawer, Lachman, and pivot-shift tests, as well as the lunge activity. The experimental MAP results indicated acceptable test–retest reliabilities for all tests (coefficient of variation<0.25), and significant MAP differences ( p < 0.05) in the anterior drawer and pivot-shift tests, in both coconscious and unconscious conditions. The individualized MAP results indicated side-to-side differences>2 m/s2 for all subjects during unconscious pivot shift tests, and >0.5 m/s2 for eight cases out of ten during conscious anterior drawer tests. It was concluded that the pivot shift test had a great repeatability and discriminative ability for acceleration-based diagnosis of ACL injury in unconscious condition. For the conscious condition, however, the anterior drawer test was appeared to be most promising.