TIME QUANTIFIED DETECTION OF FETAL MOVEMENTS USING A NEW FETAL MOVEMENT ALGORITHM

Primarily, the objective is to develop an automated ultrasound fetal m ovement detection system that will better characterize fetal movements . Secondarily, the objective is to develop an improved method of quant ifying the performance of fetal movement detectors. We recorded 20-min ute segments of fetal movement on 101 patients using a UAMS-developed fetal movement detection algorithm (Russell algorithm) and compared th is to a Hewlett-Packard (HP) M-1350-A. Movements were recorded on a se cond-per-second basis by an expert examiner reviewing videotaped real- time ultrasound images. Videotape (86,592 seconds) was-scored and comp ared with the electronic movement-detection systems. The Russell algor ithm detected 95.53% of the discrete movements greater than 5 seconds, while the HP system (M-1350-A) detected only 86.08% of the discrete m ovements (p = 0.012). Both devices were less efficient at detecting th e short discrete movements, obtaining sensitivities of 57.39 and 35.22 , respectively. Neither system fully identifies fetal movement based o n the second-per-second system. Improved methods of quantifying perfor mance indicated that the Russell algorithm performed better than the H P on these patients.