Deep Learning Prediction of Cervical Spine Surgery Revision Outcomes Using Standard Laboratory and Operative Variables.

BACKGROUND: Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art model of revision prediction of cervical spine surgery using laboratory and operative variables. METHODS: Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016 and 2022 were identified (N = 3151), and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and time frame. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables. RESULTS: Red blood cell count, hemoglobin, hematocrit, mean corpuscular hemoglobin concentration, red blood cell distribution width, platelet count, carbon dioxide, anion gap, and calcium all were significantly associated with ≥1 revision cohorts. For the prediction of 3-month revision, the deep neural network achieved an area under the receiver operating characteristic curve of 0.833. The model demonstrated increased performance for anterior versus posterior and arthrodesis versus decompression procedures. CONCLUSIONS: Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables in a cervical spine surgery cohort. This work used standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of one-size-fits-all risk scores for spine procedures.

Application of multidisciplinary team conference for neuromodulation candidates facilitates patient selection and optimization.

Introduction: Psychological evaluation is required by insurance companies in the United States prior to proceeding with a spinal cord stimulation or a dorsal root ganglion stimulation trial. Since January 2017, we implemented a Multidisciplinary Team Conference for Neuromodulation in our center to facilitate the collaboration between pain physicians and psychologists and to optimize screening of neuromodulation candidates. This study aims to report the impact of this team conference on improvement of neuromodulation outcome in our center. Methods: Appropriateness of neuromodulation were discussed in the team conference after initial visit with the pain specialist and psychological evaluation. For this study, we prospectively and retrospectively collected data on neuromodulation candidates who went through the team conference and those who did not as controls. Results: We discussed 461 patients in the team conference sessions from January 2017 to July 2023. Out of these, a spinal cord stimulator or a dorsal root ganglion stimulator trial was performed in 164 patients with 80.5% (132 cases) trial success rate leading to 140 implants. Out of these implants, 26 (18.6%) explanted and 21 (15%) required revision in 41 (29.3%) patients. We performed neuraxial neuromodulation trial for 70 patients without going through the team conference from January 2016 to July 2023 with a trial success rate of 45.7% (32 cases). In this group, 7 (21.9%) and 6 (18.8%) patients underwent explant and revision. The differences between the groups were statistically significant for trial success rate (odds ratio of 4.9 with p-value of <0.01) but not for explant (odds ratio of 0.8 with p-value of 0.627) or revision (odds ratio of 0.8 with p-value of 0.595). Conclusion: Implementing Multidisciplinary Team Conference increased trial success rate in our center. Team conference provides therapeutic benefit for patients, and also provides the opportunity for an educational discussion for trainees.

Trial ultrasound-guided continuous left stellate ganglion blockade before surgical gangliolysis in a patient with a left ventricular assist device and intractable ventricular tachycardia: a pain control application to a complex hemodynamic condition.

Stellate ganglion blockade for cardiac dysrhythmia is a well-described technique but infrequently used to manage ventricular tachycardia (VT). In patients with left ventricular assist devices (LVADs), these dysrhythmias cause increased morbidity because of right ventricular dysfunction, and often severe discomfort. Continuous stellate ganglion blockade may yield valuable information on a diagnostic and therapeutic basis in preparation for definitive, permanent interventions. We describe the successful management of intractable VT with continuous left stellate ganglion blockade, followed by surgical gangliolysis in a patient with an LVAD.

Glutathione S-transferase P1 Ile105Val polymorphism, cigarette smoking and prostate cancer.

The enzyme glutathione S-transferase P1 (GSTP1) detoxifies carcinogenic products of tobacco smoke. This exploratory case-control study evaluates the possible effect modification by the GSTP1 Ile105Val polymorphism (replacement of isoleucine by valine at codon 105) on smoking and prostate cancer. Because the Val variant possesses up to a five-fold greater enzymatic activity towards the carcinogenic metabolites of tobacco smoke, the Ile allele is expected to be related to an increase in the risk of prostate cancer among smokers. GSTP1 genotype and epidemiological data were obtained from 122 cases of prostate cancer and 135 healthy males as controls. A logistic regression model was used to estimate odds ratios and 95% confidence intervals. The adjusted OR of homozygous Ile compared to other genotypes for prostate cancer was 1.21 (95% CI: 0.61-2.83). Smoking was not significantly associated with prostate cancer with an adjusted OR of 1.56 (95% CI: 0.78-3.12). However, among individuals with the Ile/Ile genotype, smoking was strongly associated with an increased risk of prostate cancer with an adjusted odds ratio of 4.09 (95% CI: 1.25-13.35). A potential multiplicative interaction was suggested between GSTP1 and smoking on the risk of prostate cancer with the adjusted OR for the interaction of 4.52 (95% CI: 1.07-19.17). To our knowledge, this is the first time that a potential effect modification by the GSTP1 Ile/Ile genotype on smoking and the risk of prostate cancer is suggested.