A Deep Learning-Based Automated Framework for Subpeak Designation on Intracranial Pressure Signals.

The intracranial pressure (ICP) signal, as monitored on patients in intensive care units, contains pulses of cardiac origin, where P1 and P2 subpeaks can often be observed. When calculable, the ratio of their relative amplitudes is an indicator of the patient's cerebral compliance. This characterization is particularly informative for the overall state of the cerebrospinal system. The aim of this study is to develop and assess the performances of a deep learning-based pipeline for P2/P1 ratio computation that only takes a raw ICP signal as an input. The output P2/P1 ratio signal can be discontinuous since P1 and P2 subpeaks are not always visible. The proposed pipeline performs four tasks, namely (i) heartbeat-induced pulse detection, (ii) pulse selection, (iii) P1 and P2 designation, and (iv) signal smoothing and outlier removal. For tasks (i) and (ii), the performance of a recurrent neural network is compared to that of a convolutional neural network. The final algorithm is evaluated on a 4344-pulse testing dataset sampled from 10 patient recordings. Pulse selection is achieved with an area under the curve of 0.90, whereas the subpeak designation algorithm identifies pulses with a P2/P1 ratio > 1 with 97.3% accuracy. Although it still needs to be evaluated on a larger number of labeled recordings, our automated P2/P1 ratio calculation framework appears to be a promising tool that can be easily embedded into bedside monitoring devices.

Clinical Outcomes and Complications After Pedicle-anchored Dynamic or Hybrid Lumbar Spine Stabilization: A Systematic Literature Review.

STUDY DESIGN: A systematic medline review. OBJECTIVE: An overview of pedicle-based dynamic stabilization devices clinical outcomes. SUMMARY OF BACKGROUND DATA: Fusion is the standard instrumentation for many pathologies of the lumbar spine. Worrying rates of failure, including adjacent segment degeneration (ASD), have consistently been reported. The interest for dynamic stabilization came from the need of minimizing the long-term complications related to the restriction of the lumbar motion. However, pedicle-based dynamic stabilization advantages and drawbacks remain controversial. MATERIALS AND METHODS: Articles about the clinical outcomes were identified by a comprehensive Medline search. The inclusion criteria were a minimum follow-up of 12 months, indications for lumbar dynamic stabilization, and assessment of clinical outcomes and adverse events. The studied parameters included self-reported outcomes (pain, disability, and satisfaction) and complications. RESULTS: A total of 46 articles fulfilling the inclusion criteria were reviewed providing results for 2026 patients with a mean follow-up of 33 months. The postoperative improvements in terms of pain and disability were significant. Subjective assessment showed an overall patient satisfaction of 83.4%. Radiographic ASD occurred in 0%-34% of patients. Device breakage occurred in 0%-30%, and device loosening in 0%-72% of patients. The global amount of revision surgeries reached 9.4% mainly for breakage, ASD, or persistent pain, not always associated with screw loosening. CONCLUSIONS: Dynamic stabilization seems as safe and effective but benefits might partly come from decompressive gestures. Reported clinical outcomes seems to be comparable with outcomes published for fusion and no clear evidence of protection of the adjacent segments emerge from this mid-term review. Technical failures are design related but also linked with patient specificities. Relationships between sagittal balance and surgery outcomes are still rarely reported. Dynamic stabilization might display advantages in selected indications, such as moderate degeneration and beginning instability associated with clinical symptoms, but further clinical studies are needed.