The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index—ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a “good early outcome”. A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an “excellent early outcome”. The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months’ follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

CURRENT RESULTS OF CONVENTIONAL LUMBAR ARTHRODESIS

ABSTRACT Objective: To evaluate the peri- and postoperative results and clinical repercussions in patients undergoing decompression surgery and single-level lumbar arthrodesis using the traditional technique (OTLIF) and to compare with the results of minimally invasive techniques (MITLIF) described in the literature. Methods: Our sample consisted of 22 patients who underwent TLIF surgery using the open technique (OTLIF) in the period October 2019 to January 2021, in our hospital. We compared the patients’ functional clinical results using the Oswestry scale in the preoperative period and 15 days after surgery, analyzed variables related to the perioperative period: surgery time, length of hospital stay, blood loss, use of a suction drain, and admission to the ICU, and compared these with the results reported in the literature for patients treated by the MITLIF technique. Results: The average age was 48.95 years and the most operated level was L4-L5 (55%). The average surgery time was 112.63 min. We did not use a suction drain in the postoperative period, there was no need for a blood transfusion in any patient, and no patient was admitted to the ICU. The average hospital stay was 1 day. Regarding the Oswestry Disability Index, the mean preoperative score was 44.73 and after 15 days, it was 24.05. Conclusions: surgical treatment using the OTLIF technique for single-level lumbar degenerative disease showed largely positive results, with improvement in disability scores, short hospital stay and low incidence of complications. When properly indicated, OTLIF is an excellent and safe option for the treatment of degenerative lumbar disease. Level of evidence IV; Case series study.

The influence of baseline clinical status and surgical strategy on early good to excellent result in spinal lumbar arthrodesis: a machine learning approach

AimsTo create, using a machine learning (ML) approach, a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome.Patients and MethodsA single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a “good early outcome”. A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an “excellent early outcome”. The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC).ResultsA total of 1243 patients were included in this study. The model for predicting ODI at 6 months follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and a ROC AUC = 0.808.ConclusionThe results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Augmented Reality in Medical Practice: From Spine Surgery to Remote Assistance

Background: While performing surgeries in the OR, surgeons and assistants often need to access several information regarding surgical planning and/or procedures related to the surgery itself, or the accessory equipment to perform certain operations. The accessibility of this information often relies on the physical presence of technical and medical specialists in the OR, which is increasingly difficult due to the number of limitations imposed by the COVID emergency to avoid overcrowded environments or external personnel. Here, we analyze several scenarios where we equipped OR personnel with augmented reality (AR) glasses, allowing a remote specialist to guide OR operations through voice and ad-hoc visuals, superimposed to the field of view of the operator wearing them.Methods: This study is a preliminary case series of prospective collected data about the use of AR-assistance in spine surgery from January to July 2020. The technology has been used on a cohort of 12 patients affected by degenerative lumbar spine disease with lumbar sciatica co-morbidities. Surgeons and OR specialists were equipped with AR devices, customized with P2P videoconference commercial apps, or customized holographic apps. The devices were tested during surgeries for lumbar arthrodesis in a multicenter experience involving author's Institutions.Findings: A total number of 12 lumbar arthrodesis have been performed while using the described AR technology, with application spanning from telementoring (3), teaching (2), surgical planning superimposition and interaction with the hologram using a custom application for Microsoft hololens (1). Surgeons wearing the AR goggles reported a positive feedback as for the ergonomy, wearability and comfort during the procedure; being able to visualize a 3D reconstruction during surgery was perceived as a straightforward benefit, allowing to speed-up procedures, thus limiting post-operational complications. The possibility of remotely interacting with a specialist on the glasses was a potent added value during COVID emergency, due to limited access of non-resident personnel in the OR.Interpretation: By allowing surgeons to overlay digital medical content on actual surroundings, augmented reality surgery can be exploited easily in multiple scenarios by adapting commercially available or custom-made apps to several use cases. The possibility to observe directly the operatory theater through the eyes of the surgeon might be a game-changer, giving the chance to unexperienced surgeons to be virtually at the site of the operation, or allowing a remote experienced operator to guide wisely the unexperienced surgeon during a procedure.

Comparative short-term outcomes of enhanced recovery after surgery (ERAS) program and non-ERAS traditional care in elderly patients undergoing lumbar arthrodesis: a retrospective study

Background Enhanced recovery after surgery (ERAS) program is an evidence-based improvement over non-ERAS traditional care. The aim of the present study was to analyze the safety, feasibility, and efficacy of an ERAS program in patients over 70 years undergoing lumbar arthrodesis by comparison with non-ERAS traditional care. Methods During January 2018 to December 2018, patients enrolled received non-ERAS traditional care, while the ERAS program was implemented from January to December 2019. Demographic characteristics, comorbidities, surgical data and postoperative recovery parameters were collected from all patients. Postoperative pain scores were evaluated by visual analog scales (VAS). The clinical outcomes were length of stay (LOS), postoperative complications and postoperative pain scores. Compliance results were also collected. Result A total of 127 patients were enrolled, including 67 patients in the non-ERAS traditional care group and 60 patients in the ERAS group. The demographic characteristics and comorbidities of the two groups showed no significant differences. The LOS of patients treated with ERAS program (13.6 ± 4.0 days) was significantly less than that of patients treated with non-ERAS traditional care (15.6 ± 3.9 days) (p = 0.034). Complication rate was 8.3% in the ERAS group versus 20.9% in the non-ERAS traditional care group (p = 0.048). VAS (back) in the ERAS group was significantly lower on postoperative day (POD) 1 and POD2. Postoperative recovery parameters were improved in the ERAS group. The overall compliance with the ERAS program was 94%. Conclusions Based on our results, ERAS program is safer and more effective for elderly patients over 70 undergoing lumbar arthrodesis than non-ERAS traditional care.

Vascularized Posterior Iliac Crest Bone Grafting: Indications, Techniques, Clinical Outcomes, and Alternatives

Pseudarthrosis is a feared complication of spinal fusion procedures. Currently, the gold standard in prevention or treatment of pseudarthrosis is placement of nonvascularized iliac crest bone autograft. While rates of fusion are significantly higher in patients with use of nonvascularized bone autografts than with allografts, patients who have previously failed lumbar arthrodesis or those at a high risk for pseudarthrosis may benefit from a more robust, vascularized bone graft with enhanced osteogenicity. In this article, we discuss the use of iliac crest vascularized bone grafts as an adjunct for high-risk patients undergoing lumbosacral spine arthrodesis.