Promises and Perils of Artificial Intelligence in Neurosurgery.

Artificial intelligence (AI)-facilitated clinical automation is expected to become increasingly prevalent in the near future. AI techniques may permit rapid and detailed analysis of the large quantities of clinical data generated in modern healthcare settings, at a level that is otherwise impossible by humans. Subsequently, AI may enhance clinical practice by pushing the limits of diagnostics, clinical decision making, and prognostication. Moreover, if combined with surgical robotics and other surgical adjuncts such as image guidance, AI may find its way into the operating room and permit more accurate interventions, with fewer errors. Despite the considerable hype surrounding the impending medical AI revolution, little has been written about potential downsides to increasing clinical automation. These may include both direct and indirect consequences. Directly, faulty, inadequately trained, or poorly understood algorithms may produce erroneous results, which may have wide-scale impact. Indirectly, increasing use of automation may exacerbate de-skilling of human physicians due to over-reliance, poor understanding, overconfidence, and lack of necessary vigilance of an automated clinical workflow. Many of these negative phenomena have already been witnessed in other industries that have already undergone, or are undergoing "automation revolutions," namely commercial aviation and the automotive industry. This narrative review explores the potential benefits and consequences of the anticipated medical AI revolution from a neurosurgical perspective.

Efficacy of Autogenous Bone Marrow Aspirate as a Fusion-promoting Adjunct to Anterior Cervical Discectomy and Fusion: A Single Center Retrospective Cohort Study.

Background Autogenous iliac crest bone marrow aspirate (BMA) has been shown to be a safe osteobiological adjunct to anterior cervical discectomy and fusion (ACDF), but little evidence exists to support its superiority to traditional methods. The object of this study was to retrospectively evaluate two cohorts of patients undergoing ACDF - with or without the use of BMA - in an effort to better characterize the clinical and radiographic outcomes associated with the use of BMA in ACDF. Methods The charts of all patients undergoing ACDF with a collagen-hydroxyapatite (CHA) sponge, local vertebral autograft and a polyetheretherketone (PEEK) interbody graft with or without BMA by a single staff neurosurgeon between 2011 and 2016 were retrospectively reviewed. Post-operative dynamic plain films and CT scans for each patient were reviewed and each instrumented level was independently evaluated for fusion over time. Results A total of 203 cervical levels were instrumented in 92 patients (with BMA, 52 patients, 122 levels; without BMA, 40 patients, 81 levels). The mean radiographic follow-up period was 21.4 ± 18.4 months, over which time 154 of 203 (75.6%) instrumented cervical levels were found to have fused (BMA group, 93/122 segments fused [76.2%]; non-BMA group, 61/81 segments fused [75.3%], p = 1). Kaplan-Meier survival analysis demonstrated a higher probability of fusion at any given time point for the BMA group when compared with the non-BMA group (p < 0.001, log-rank test). Conclusions BMA is a readily accessible, low-cost adjunct to ACDF that enhances the fusion rates seen with a CHA/PEEK allograft combination.

Superior Petrosal Vein Sacrifice During Microvascular Decompression: Perioperative Complication Rates and Comparison with Venous Preservation.

OBJECTIVE: To investigate potential effect of sacrifice of the superior petrosal vein (SPV) on postoperative complications after microvascular decompression (MVD). METHODS: Retrospective review of 98 consecutive patients undergoing MVD of cranial nerve V was performed. Frequency of division of the SPV during surgery was recorded, and postoperative complications and imaging were recorded and analyzed. In patients with complications, the specific anatomic variation of the superior petrosal venous complex was noted. RESULTS: Of 98 patients undergoing MVD, 83 (84.7%) had sacrifice of the SPV at the time of surgery, 12 (12.2%) had the SPV preserved, and 3 (3.1%) were revision operations. Four patients (4.8%) had complications deemed to be attributable to venous insufficiency or congestion. These included sigmoid sinus thrombosis with coincident cerebellar hemorrhage, midbrain and pontine infarction, hemiparesis with midbrain and pontine edema, and facial paresis with ischemia in the middle cerebellar peduncle. None of the patients with preserved SPV were symptomatic or had imaging changes consistent with venous congestion. CONCLUSIONS: Sacrifice of the SPV is often performed during MVD. This is associated with a complication rate that is significant in frequency and severity compared with preserving the vein. SPV sacrifice should be limited to cases where it is deemed absolutely necessary for successful cranial nerve decompression.