uSINE-PAMS Artificial Intelligence–Driven, Ultrasound-Guided Lumbar Puncture to Improve Procedural Accuracy

Traditional lumbar punctures (LPs) often fail, leading to diagnostic delays and increased risks. Ultrasound guidance provides improved success rates but faces adoption barriers due to neuraxial-ultrasound training and implementation challenges. The Ultrasound-Guided Spinal Landmark Identification With Needle Navigation System and Position and Angular Marking System (uSINE-PAMS) were designed to address these issues: uSINE is a machine-learning software for neuraxial-ultrasound guidance; PAMS is a hardware that translates ultrasound data for accurate needle insertion. A pilot study with 10 patients showed that uSINE-PAMS-guided LP achieved an 80% first-pass success rate with no complication; the median patient age was 43 years, and the median body mass index was 24.5 kg/m2. The uSINE-PAMS system showed feasibility. This pilot study showed that uSINE-PAMS-guided LP is feasible with a promising first-pass success rate at 80%. An ongoing phase 2 study (NCT05824546) of uSINE-PAMS may alter future standard of practice for LPs. This pilot study is registered under ClinicalTrials.gov (ID: NCT05824546).