scholarly journals State-of-the-art reviews predictive modeling in adult spinal deformity: applications of advanced analytics

2021 ◽  
Author(s):  
Rushikesh S. Joshi ◽  
Darryl Lau ◽  
Justin K. Scheer ◽  
Miquel Serra-Burriel ◽  
Alba Vila-Casademunt ◽  
...  
Keyword(s):  
Machine Learning ◽  
Spinal Deformity ◽  
Clinical Decision Making ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Machine Learning Algorithms ◽  
Surgical Correction ◽  
Computational Techniques ◽  
Dramatic Improvement ◽  
Complication Rates

AbstractAdult spinal deformity (ASD) is a complex and heterogeneous disease that can severely impact patients’ lives. While it is clear that surgical correction can achieve significant improvement of spinopelvic parameters and quality of life measures in adults with spinal deformity, there remains a high risk of complication associated with surgical approaches to adult deformity. Over the past decade, utilization of surgical correction for ASD has increased dramatically as deformity correction techniques have become more refined and widely adopted. Along with this increase in surgical utilization, there has been a massive undertaking by spine surgeons to develop more robust models to predict postoperative outcomes in an effort to mitigate the relatively high complication rates. A large part of this revolution within spine surgery has been the gradual adoption of predictive analytics harnessing artificial intelligence through the use of machine learning algorithms. The development of predictive models to accurately prognosticate patient outcomes following ASD surgery represents a dramatic improvement over prior statistical models which are better suited for finding associations between variables than for their predictive utility. Machine learning models, which offer the ability to make more accurate and reproducible predictions, provide surgeons with a wide array of practical applications from augmenting clinical decision making to more wide-spread public health implications. The inclusion of these advanced computational techniques in spine practices will be paramount for improving the care of patients, by empowering both patients and surgeons to more specifically tailor clinical decisions to address individual health profiles and needs.

scholarly journals Male sex may not be associated with worse outcomes in primary all-posterior adult spinal deformity surgery: a multicenter analysis

2017 ◽  
Vol 43 (6) ◽  
pp. E9 ◽  
Author(s):  
David B. Bumpass ◽  
Lawrence G. Lenke ◽  
Jeffrey L. Gum ◽  
Christopher I. Shaffrey ◽  
Justin S. Smith ◽  
...  
Keyword(s):  
Sex Differences ◽  
Spinal Deformity ◽  
Operative Time ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Spine Deformity ◽  
Complication Rates ◽  
Female Patients ◽  
Male Patients

OBJECTIVEAdolescent spine deformity studies have shown that male patients require longer surgery and have greater estimated blood loss (EBL) and complications compared with female patients. No studies exist to support this relationship in adult spinal deformity (ASD). The purpose of this study was to investigate associations between sex and complications, deformity correction, and health-related quality of life (HRQOL) in patients with ASD. It was hypothesized that male ASD patients would have greater EBL, longer surgery, and more complications than female ASD patients.METHODSA multicenter ASD cohort was retrospectively queried for patients who underwent primary posterior-only instrumented fusions with a minimum of 5 levels fused. The minimum follow-up was 2 years. Primary outcomes were EBL, operative time, intra-, peri-, and postoperative complications, radiographic correction, and HRQOL outcomes (Oswestry Disability Index, SF-36, and Scoliosis Research Society-22r Questionnaire). Poisson multivariate regression was used to control for age, comorbidities, and levels fused.RESULTSNinety male and 319 female patients met the inclusion criteria. Male patients had significantly greater mean EBL (2373 ml vs 1829 ml, p = 0.01). The mean operative time, transfusion requirements, and final radiographic measurements did not differ between sexes. Similarly, changes in HRQOL showed no significant differences. Finally, there were no sex differences in the incidence of complications (total, major, or minor) at any time point after controlling for age, body mass index, comorbidities, and levels fused.CONCLUSIONSDespite higher EBL, male ASD patients did not experience more complications or require less deformity correction at the 2-year follow-up. HRQOL scores similarly showed no sex differences. These findings differ from adolescent deformity studies, and surgeons can counsel patients that sex is unlikely to influence the outcomes and complication rates of primary all-posterior ASD surgery.

scholarly journals Utility of the MISDEF2 Algorithm and Extent of Fusion in Open Adult Spinal Deformity Surgery With Minimum 2-Year Follow-up

Neurospine ◽  
2021 ◽  
Vol 18 (4) ◽  
pp. 824-832
Author(s):  
Bo Li ◽  
Gregory Hawryluk ◽  
Praveen V. Mummaneni ◽  
Michael Wang ◽  
Ratnesh Mehra ◽  
...  
Keyword(s):  
Spinal Deformity ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Class Ii ◽  
Class I ◽  
Complication Rates ◽  
Class Iii ◽  
Full Correction ◽  
Class Iv

Objective: Long-segment fusion in adult spinal deformity (ASD) is often needed, but more focal surgeries may provide significant relief with less morbidity. The minimally invasive spinal deformity surgery (MISDEF2) algorithm guides minimally invasive ASD surgery, but it may be useful in open ASD surgery. We classified ASD patients undergoing focal decompression, limited decompression and fusion, and full correction according to MISDEF2 and correlated outcomes.Methods: A retrospective study of ASD patients treated by 2 surgeons at our hospital was performed. Inclusion criteria were: age > 50, minimum 2-year follow-up, and open ASD surgery. Tumor, trauma, and infections were excluded. Patients had open surgery including focal decompression, short segment fusion, or full scoliosis correction. All patients were categorized by MISDEF2 into 4 classes based upon spinopelvic parameters. Perioperative metrics were assessed. Radiographic correction, complications and reoperation were recorded.Results: A total of 136 patients met inclusion criteria. Mean follow-up was 46 ± 15.8 months (range, 24–118 months). Forty-seven underwent full deformity correction, 71 underwent short segment fusion, and 18 underwent decompression alone. There were 24 cases of class I, 66 cases of class II, 23 cases of class III, and 23 cases of class IV patients. Patients in class I and II had perioperative complication rates of 0% and 16.7% and revision rates of 8% and 21.2% when undergoing focal decompression or limited fusion. However, class II patients undergoing full correction had higher perioperative complications rate (p = 0.03) and revision surgery rates (p = 0.047). This difference was not seen in class III patients (p > 0.05). All class IV patients underwent full correction, but they had higher perioperative complication rates (p < 0.019), comparable revision surgery rates (p = 0.27), and better radiographic realignment (p < 0.001). In addition, full deformity correction was associated with longer length of stay, increased blood loss, and longer operative time (p < 0.001).Conclusion: The MISDEF2 algorithm may help guide ASD surgical decision making even in open surgery, with focal treatment used in class I and II patients as a viable alternative and full correction implemented in class IV patients because of severe malalignment. However, class II patients with ASD undergoing full deformity correction do have higher complication rates.

scholarly journals P.089 A comparison of perioperative complication rates in adult spinal deformity correction with one versus two surgeons

2017 ◽  
Vol 44 (S2) ◽  
pp. S36-S36
Author(s):  
K Parvez ◽  
J Hsu ◽  
Z Ivanishvilli ◽  
S Boisvert ◽  
M Warren ◽  
...  
Keyword(s):  
Blood Loss ◽  
Spinal Deformity ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Radicular Pain ◽  
Complication Rates ◽  
Perioperative Morbidity ◽  
Hardware Failure ◽  
Estimated Blood Loss ◽  
One Year

Background: Morbidity can be high in the management of adult spinal deformity patients. Complications include blood loss (EBL), durotomy, radicular pain, and postoperative hardware failure. Utilization of one versus two spinal surgeons in spinal deformity correction reduces overall perioperative morbidity is unclear. Methods: All procedures were performed by surgeons at a single institution between January 2012-2015. Patients were followed for a minimum of one year and maximum of four years. We retrospectively reviewed 60 cases of adult spinal deformity. Our cohort was divided into 1 versus 2 surgeons (12 vs 48 cases). We analyzed these cases for estimated blood loss and peri-operative complications. Results: Cases involving long thoracic to pelvis correction (T3-T6) was 20.8% in the 2 surgeons group and 8.3% in the 1 surgeon group. The EBL >3.0 L for 1 versus 2 surgeon groups were 25% and 41.6% respectively. Major complications in the 1 versus 2 surgeon group were 25% and 47.9% and the revision rates were 25% versus 37.5%. The percentage of minor complications in the 1 versus 2 surgeon group was 33.3% versus 14.6%. Conclusions: Utilizing two surgeons did not reduce complication rates. Procedures performed by two surgeons were more extensive deformity corrections. The extent of correction is the likely explanation for differing complication rates.

Perioperative outcomes associated with thoracolumbar 3-column osteotomies for adult spinal deformity patients with rheumatoid arthritis

2019 ◽  
Vol 30 (6) ◽  
pp. 822-832
Author(s):  
Cecilia L. Dalle Ore ◽  
Christopher P. Ames ◽  
Vedat Deviren ◽  
Darryl Lau
Keyword(s):  
Rheumatoid Arthritis ◽  
Spinal Deformity ◽  
Perioperative Complications ◽  
Adult Spinal Deformity ◽  
Vena Cava ◽  
Deformity Correction ◽  
Perioperative Outcomes ◽  
Medical Complications ◽  
Filter Placement ◽  
Estimated Blood Loss

OBJECTIVESpinal deformity causing spinal imbalance is directly correlated to pain and disability. Prior studies suggest adult spinal deformity (ASD) patients with rheumatoid arthritis (RA) have more complex deformities and are at higher risk for complications. In this study the authors compared outcomes of ASD patients with RA following thoracolumbar 3-column osteotomies to outcomes of a matched control cohort.METHODSAll patients with RA who underwent 3-column osteotomy for thoracolumbar deformity correction performed by the senior author from 2006 to 2016 were identified retrospectively. A cohort of patients without RA who underwent 3-column osteotomies for deformity correction was matched based on multiple clinical factors. Data regarding demographics and surgical approach, along with endpoints including perioperative outcomes, reoperations, and incidence of proximal junctional kyphosis (PJK) were reviewed. Univariate analyses were used to compare patients with RA to matched controls.RESULTSEighteen ASD patients with RA were identified, and a matched cohort of 217 patients was generated. With regard to patients with RA, 11.1% were male and the mean age was 68.1 years. Vertebral column resection (VCR) was performed in 22.2% and pedicle subtraction osteotomy (PSO) in 77.8% of patients. Mean case length was 324.4 minutes and estimated blood loss (EBL) was 2053.6 ml. Complications were observed in 38.9% of patients with RA and 29.0% of patients without RA (p = 0.380), with a trend toward increased medical complications (38.9% vs 21.2%, p = 0.084). Patients with RA had a significantly higher incidence of deep vein thrombosis (DVT)/pulmonary embolism (PE) (11.1% vs 1.8%, p = 0.017) and wound infections (16.7% vs 5.1%, p = 0.046). PJK occurred in 16.7% of patients with RA, and 33.3% of RA patients underwent reoperation. Incidence rates of PJK and reoperation in matched controls were 12.9% and 25.3%, respectively (p = 0.373, p = 0.458). At follow-up, mean sagittal vertical axis (SVA) was 6.1 cm in patients with RA and 4.5 cm in matched controls (p = 0.206).CONCLUSIONSFindings from this study suggest that RA patients experience a higher incidence of medical complications, specifically DVT/PE. Preoperative lower-extremity ultrasounds, inferior vena cava (IVC) filter placement, and/or early initiation of DVT prophylaxis in RA patients may be indicated. Perioperative complications, morbidity, and long-term outcomes are otherwise similar to non-RA patients.

scholarly journals Clinician checklist for assessing suitability of machine learning applications in healthcare

2021 ◽  
Vol 28 (1) ◽  
pp. e100251
Author(s):  
Ian Scott ◽  
Stacey Carter ◽  
Enrico Coiera
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Clinical Decision Making ◽  
Improve Patient Care ◽  
Clinical Decision ◽  
Routine Care ◽  
Machine Learning Algorithms ◽  
Clinical Settings ◽  
Machine Learning Applications ◽  
Key Issues

Machine learning algorithms are being used to screen and diagnose disease, prognosticate and predict therapeutic responses. Hundreds of new algorithms are being developed, but whether they improve clinical decision making and patient outcomes remains uncertain. If clinicians are to use algorithms, they need to be reassured that key issues relating to their validity, utility, feasibility, safety and ethical use have been addressed. We propose a checklist of 10 questions that clinicians can ask of those advocating for the use of a particular algorithm, but which do not expect clinicians, as non-experts, to demonstrate mastery over what can be highly complex statistical and computational concepts. The questions are: (1) What is the purpose and context of the algorithm? (2) How good were the data used to train the algorithm? (3) Were there sufficient data to train the algorithm? (4) How well does the algorithm perform? (5) Is the algorithm transferable to new clinical settings? (6) Are the outputs of the algorithm clinically intelligible? (7) How will this algorithm fit into and complement current workflows? (8) Has use of the algorithm been shown to improve patient care and outcomes? (9) Could the algorithm cause patient harm? and (10) Does use of the algorithm raise ethical, legal or social concerns? We provide examples where an algorithm may raise concerns and apply the checklist to a recent review of diagnostic imaging applications. This checklist aims to assist clinicians in assessing algorithm readiness for routine care and identify situations where further refinement and evaluation is required prior to large-scale use.

scholarly journals Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Imogen Schofield ◽  
David C. Brodbelt ◽  
Noel Kennedy ◽  
Stijn J. M. Niessen ◽  
David B. Church ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cushing’S Syndrome ◽  
Clinical Decision Making ◽  
Predictive Performance ◽  
Clinical Decision ◽  
Cushing's Syndrome ◽  
Machine Learning Algorithms ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Clinical Records

AbstractCushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

Fluctuations in Spinal Cord Perfusion During Adult Spinal Deformity Correction Identify Neurologic Changes: Proof of Concept

2016 ◽  
Vol 85 ◽  
pp. 365.e1-365.e6 ◽  
Author(s):  
Jay D. Turner ◽  
Robert K. Eastlack ◽  
Zaman Mirzadeh ◽  
Stacie Nguyen ◽  
Jeff Pawelek ◽  
...  
Keyword(s):  
Spinal Cord ◽  
Spinal Deformity ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Proof Of Concept

Strategies for prevention of rod fracture in adult spinal deformity: cobalt chrome rod, accessory rod technique, and lateral lumbar interbody fusion

2021 ◽  
pp. 1-10
Author(s):  
Ki Young Lee ◽  
Jung-Hee Lee ◽  
Kyung-Chung Kang ◽  
Sang-Kyu Im ◽  
Hae Seong Lim ◽  
...  
Keyword(s):  
Spinal Deformity ◽  
Interbody Fusion ◽  
Sagittal Alignment ◽  
Adult Spinal Deformity ◽  
Deformity Correction ◽  
Lumbar Interbody Fusion ◽  
Patient Factors ◽  
Rod Fracture ◽  
Cobalt Chrome

OBJECTIVERestoring the proper sagittal alignment in adult spinal deformity (ASD) can improve radiological and clinical outcomes, but pseudarthrosis including rod fracture (RF) is a common problematic complication. The purpose of this study was to analyze the methods for reducing the incidence of RF in deformity correction of ASD.METHODSThe authors retrospectively selected 178 consecutive patients (mean age 70.8 years) with lumbar degenerative kyphosis (LDK) who underwent deformity correction with a minimum 2-year follow-up. Patients were classified into the non-RF group (n = 131) and the RF group (n = 47). For predicting the crucial factors of RF, patient factors, radiographic parameters, and surgical factors were analyzed.RESULTSThe overall incidence of RF was 26% (47/178 cases), occurring in 42% (42/100 cases) of pedicle subtraction osteotomy (PSO), 7% (5/67 cases) of lateral lumbar interbody fusion (LLIF) with posterior column osteotomy, 18% (23/129 cases) of cobalt chrome rods, 49% (24/49 cases) of titanium alloy rods, 6% (2/36 cases) placed with the accessory rod technique, and 32% (45/142 cases) placed with the 2-rod technique. There were no significant differences in the incidence of RF regarding patient factors between two groups. While both groups showed severe sagittal imbalance before operation, lumbar lordosis (LL) was more kyphotic and pelvic incidence (PI) minus LL (PI-LL) mismatch was greater in the RF group (p < 0.05). Postoperatively, while LL and PI-LL did not show significant differences between the two groups, LL and sagittal vertical axis correction were greater in the RF group (p < 0.05). Nonetheless, at the last follow-up, the two groups did not show significant differences in radiographic parameters except thoracolumbar junctional angles. As for surgical factors, use of the cobalt chrome rod and the accessory rod technique was significantly greater in the non-RF group (p < 0.05). As for the correction method, PSO was associated with more RFs than the other correction methods, including LLIF (p < 0.05). By logistic regression analysis, PSO, preoperative PI-LL mismatch, and the accessory rod technique were crucial factors for RF.CONCLUSIONSGreater preoperative sagittal spinopelvic malalignment including preoperative PI-LL mismatch was the crucial risk factor for RF in LDK patients 65 years or older. For restoring and maintaining sagittal alignment, use of the cobalt chrome rod, accessory rod technique, or LLIF was shown to be effective for reducing RF in ASD surgery.

Sign in / Sign up

Export Citation Format

Share Document