Performance of hybrid artificial intelligence in determining candidacy for lumbar stenosis surgery.

PURPOSE: Lumbar spinal stenosis (LSS) is a condition affecting several hundreds of thousands of adults in the United States each year and is associated with significant economic burden. The current decision-making practice to determine surgical candidacy for LSS is often subjective and clinician specific. In this study, we hypothesize that the performance of artificial intelligence (AI) methods could prove comparable in terms of prediction accuracy to that of a panel of spine experts. METHODS: We propose a novel hybrid AI model which computes the probability of spinal surgical recommendations for LSS, based on patient demographic factors, clinical symptom manifestations, and MRI findings. The hybrid model combines a random forest model trained from medical vignette data reviewed by surgeons, with an expert Bayesian network model built from peer-reviewed literature and the expert opinions of a multidisciplinary team in spinal surgery, rehabilitation medicine, interventional and diagnostic radiology. Sets of 400 and 100 medical vignettes reviewed by surgeons were used for training and testing. RESULTS: The model demonstrated high predictive accuracy, with a root mean square error (RMSE) between model predictions and ground truth of 0.0964, while the average RMSE between individual doctor's recommendations and ground truth was 0.1940. For dichotomous classification, the AUROC and Cohen's kappa were 0.9266 and 0.6298, while the corresponding average metrics based on individual doctor's recommendations were 0.8412 and 0.5659, respectively. CONCLUSIONS: Our results suggest that AI can be used to automate the evaluation of surgical candidacy for LSS with performance comparable to a multidisciplinary panel of physicians.

Fluoroscopic Percutaneous Fixation of Periacetabular Metastatic Cancer: The Tripod Technique.

There are an increasing number of patients who present with metastatic bone disease as the survival of patients with cancer improves in recent decades. The pelvis is the second most common site for skeletal metastases. Metastatic lesions in the pelvis can be largely divided into periacetabular lesions (Enneking zone II) and non-periacetabular lesions (zones I, III, and IV). Traditionally, patients with a symptomatic zone II lesion are treated with a cemented total hip arthroplasty (THA) using variations on the traditional Harrington method. These open surgeries are accompanied by many inherent risks. Both a prolonged recovery and wide range of potential complications may delay or interrupt the adjuvant radiation and systemic therapy. It was observed that the articular surface of the hip joint was often intact and that the femoral side was frequently not involved in these patients. A novel minimally invasive technique for hip joint preservation has recently been developed. Three large-bore cannulated screws are placed percutaneously under fluoroscopy in a tripod configuration to reinforce the mechanical axis of the acetabulum. Increased stability improves pain control and permits immediate weight bearing. When the disease progresses, this construct can be easily converted to a cemented THA using the tripod screws as rebar to support an acetabular cup, as part of a staged Harrington procedure. This approach is technically demanding. A detailed guide for the tripod technique should encompass indications, preoperative preparation, operating room settings, intraoperative fluoroscopic guidance, modifications, postoperative care, and subsequent conversion to a cemented THA, if needed.

Percutaneous Screw Stabilization of Non-Periacetabular Pelvic Lesions Caused by Metastatic Cancer and Multiple Myeloma.

BACKGROUND: The pelvis is one of the most common locations for metastatic bone disease. While many of the publications that describe surgical treatments focus on periacetabular lesions (Enneking zone II), there is a lack of investigation into lesions in the non-periacetabular areas (zones I, III, and IV). We recently described a minimally invasive percutaneous screw application for metastatic zone-II lesions with excellent results. In the present study, we aimed to extend this approach to the other pelvic areas. METHODS: Twenty-two consecutive patients with painful non-periacetabular pelvic metastatic cancer were included based on retrospective chart review. There were 16 women and 6 men with an average age of 60 years (range, 36 to 81 years). The most common primary cancers were multiple myeloma (7 cases) and breast (5 cases). The most common locations were the sacrum and the ilium. A pathologic fracture was identified in 15 patients. Most of the lesions were treated with multiple large-diameter screws, except for the isolated zone-III lesions. All of the procedures were completed in a standard operating room without the need for special instruments. Radiation therapy was given to 19 patients; the average dose was 15 Gy. The studied outcomes were pain and functionality as assessed by a visual analog scale (VAS) score and the Eastern Cooperative Oncology Group score (ECOG), respectively. RESULTS: There were no surgical complications and no need for blood transfusion. The average follow-up time was 7 months (range, 0.3 to 34.0 months). Two patients died within 4 weeks of surgery due to COVID-19 infection. There was significant improvement in the postoperative VAS pain score (p < 0.0001) and the ECOG score (p < 0.05) when compared with the preoperative scores. There was no implant failure or revision surgery. Local bone-healing was observed in 12 of 14 patients (86%) who survived for >3 months after surgery. CONCLUSIONS: Percutaneous screw application is safe and effective in the treatment of metastatic non-periacetabular pelvic lesions. Given the simplicity of the technique and the instrumentation and the tolerance for concomitant treatments, this approach is worthy of broader consideration. LEVEL OF EVIDENCE: Therapeutic Level IV . See Instructions for Authors for a complete description of levels of evidence.