Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy

Developing Machine Learning-Based Predictive Models for Hallux Valgus Recurrence Based on Measurements From Radiographs

BACKGROUND

Machine learning (ML) is increasingly used to predict the prognosis of numerous diseases. This retrospective analysis aimed to develop a prediction model using ML algorithms and to identify predictors associated with the recurrence of hallux valgus (HV) following surgery.

METHODS

A total of 198 symptomatic feet that underwent chevron osteotomy combined with a distal soft tissue procedure were enrolled and analyzed from 2 independent medical centers. The feet were grouped according to nonrecurrence or recurrence based on 1-year follow-up outcomes. Preoperative weightbearing radiographs and immediate postoperative nonweightbearing radiographs were obtained for each HV foot. Radiographic measurements (eg, HV angle and intermetatarsal angle) were acquired and used for ML model training. A total of 9 commonly used ML models were trained on the data obtained from one institute (108 feet), and tested on the other data set from another independent institute (90 feet) for external validation. Optimal feature sets for each model were identified based on a 2000-resample bootstrap-based internal validation via an exhaustive search. The performance of each model was then tested on the external validation set. The area under the curve (AUC), classification accuracy, sensitivity, and specificity of each model were calculated to evaluate the performance of each model.

RESULTS

The support vector machine (SVM) model showed the highest predictive accuracy compared to other methods, with an AUC of 0.88 and an accuracy of 75.6%. Preoperative hallux valgus angle, tibial sesamoid position, postoperative intermetatarsal angle, and postoperative tibial sesamoid position were identified as the most selected features by several ML models.

CONCLUSION

ML classifiers such as SVM could predict the recurrence of HV (an HVA >20 degrees) at a 1-year follow-up while identifying associated predictors in a multivariate manner. This study holds the potential for foot and ankle surgeons to effectively identify individuals at higher risk of HV recurrence postsurgery.

Artificial Intelligence for Clinically Meaningful Outcome Prediction in Orthopedic Research: Current Applications and Limitations

PURPOSE OF REVIEW

Patient-reported outcome measures (PROM) play a critical role in evaluating the success of treatment interventions for musculoskeletal conditions. However, predicting which patients will benefit from treatment interventions is complex and influenced by a multitude of factors. Artificial intelligence (AI) may better anticipate the propensity to achieve clinically meaningful outcomes through leveraging complex predictive analytics that allow for personalized medicine. This article provides a contemporary review of current applications of AI developed to predict clinically significant outcome (CSO) achievement after musculoskeletal treatment interventions.

RECENT FINDINGS

The highest volume of literature exists in the subspecialties of total joint arthroplasty, spine, and sports medicine, with only three studies identified in the remaining orthopedic subspecialties combined. Performance is widely variable across models, with most studies only reporting discrimination as a performance metric. Given the complexity inherent in predictive modeling for this task, including data availability, data handling, model architecture, and outcome selection, studies vary widely in their methodology and results. Importantly, the majority of studies have not been externally validated or demonstrate important methodological limitations, precluding their implementation into clinical settings. A substantial body of literature has accumulated demonstrating variable internal validity, limited scope, and low potential for clinical deployment. The majority of studies attempt to predict the MCID-the lowest bar of clinical achievement. Though a small proportion of models demonstrate promise and highlight the utility of AI, important methodological limitations need to be addressed moving forward to leverage AI-based applications for clinical deployment.

Artificial Intelligence in Spinal Imaging and Patient Care: A Review of Recent Advances

Artificial intelligence (AI) is transforming spinal imaging and patient care through automated analysis and enhanced decision-making. This review presents a clinical task-based evaluation, highlighting the specific impact of AI techniques on different aspects of spinal imaging and patient care. We first discuss how AI can potentially improve image quality through techniques like denoising or artifact reduction. We then explore how AI enables efficient quantification of anatomical measurements, spinal curvature parameters, vertebral segmentation, and disc grading. This facilitates objective, accurate interpretation and diagnosis. AI models now reliably detect key spinal pathologies, achieving expert-level performance in tasks like identifying fractures, stenosis, infections, and tumors. Beyond diagnosis, AI also assists surgical planning via synthetic computed tomography generation, augmented reality systems, and robotic guidance. Furthermore, AI image analysis combined with clinical data enables personalized predictions to guide treatment decisions, such as forecasting spine surgery outcomes. However, challenges still need to be addressed in implementing AI clinically, including model interpretability, generalizability, and data limitations. Multicenter collaboration using large, diverse datasets is critical to advance the field further. While adoption barriers persist, AI presents a transformative opportunity to revolutionize spinal imaging workflows, empowering clinicians to translate data into actionable insights for improved patient care.

Predicting osteoporotic fractures post-vertebroplasty: a machine learning approach with a web-based calculator

PURPOSE

The aim of this study was to develop and validate a machine learning (ML) model for predicting the risk of new osteoporotic vertebral compression fracture (OVCF) in patients who underwent percutaneous vertebroplasty (PVP) and to create a user-friendly web-based calculator for clinical use.

METHODS

A retrospective analysis of patients undergoing percutaneous vertebroplasty: A retrospective analysis of patients treated with PVP between June 2016 and June 2018 at Liuzhou People's Hospital was performed. The independent variables of the model were screened using Boruta and modelled using 9 algorithms. Model performance was assessed using the area under the receiver operating characteristic curve (ROC_AUC), and clinical utility was assessed by clinical decision curve analysis (DCA). The best models were analysed for interpretability using SHapley Additive exPlanations (SHAP) and the models were deployed visually using a web calculator.

RESULTS

Training and test groups were split using time. The SVM model performed best in both the training group tenfold cross-validation (CV) and validation group AUC, with an AUC of 0.77. DCA showed that the model was beneficial to patients in both the training and test sets. A network calculator developed based on the SHAP-based SVM model can be used for clinical risk assessment ( https://nicolazhang.shinyapps.io/refracture_shap/ ).

CONCLUSIONS

The SVM-based ML model was effective in predicting the risk of new-onset OVCF after PVP, and the network calculator provides a practical tool for clinical decision-making. This study contributes to personalised care in spinal surgery.

Predictors of Outcome After Surgical Decompression for mild degenerative Cervical Myelopathy -A Systematic Review

STUDY DESIGN

Systematic Reviews.

OBJECTIVES

To investigate predictors of surgical outcomes for mild Degenerative Cervical Myelopathy (DCM) by reviewing all related studies conducted at this point.

METHODS

An electronic search was carried out in PubMed, EMBASE, Scopus, and Web of Science until June 23, 2021. Full-text articles reporting surgical outcome predictors of mild DCM cases were eligible. We included studies with mild DCM which was defined as a modified Japanese Orthopaedic Association score of 15 to 17 or a Japanese Orthopaedic Association score of 13 to 16. Independent reviewers screened all the records, and discrepancies between the reviewers were solved in a session with the senior author. For risk of bias assessment, RoB 2 tool was used for randomized clinical trials and ROBINS-I for non-randomized studies.

RESULTS

After screening 6 087 manuscripts, only 8 studies met the inclusion criteria. Lower pre-operative mJOA scores and quality-of-life measurement scores were reported by multiple studies to predict better surgical outcomes compared to other groups. High-intensity pre-operative T2 magnetic resonance imaging (MRI) was also reported to predict poor outcomes. Neck pain before intervention resulted in improved patient-reported outcomes. Two studies also reported motor symptoms prior to surgery as outcome predictors.

CONCLUSION

Lower quality of life before surgery, neck pain, lower pre-operative mJOA scores, motor symptoms before surgery, female gender, gastrointestinal comorbidities, surgical procedure and surgeon's experience with specific techniques, and high signal intensity of cord in T2 MRI were the surgical outcome predictors reported in the literature. Lower Quality of Life (QoL) score and neck prior to surgery were reported as predictors of the more improved outcome, but high cord signal intensity in T2 MRI was reported as an unfavorable outcome predictor.

Enabling Personalized Medicine in Orthopaedic Surgery Through Artificial Intelligence: A Critical Analysis Review

» The application of artificial intelligence (AI) in the field of orthopaedic surgery holds potential for revolutionizing health care delivery across 3 crucial domains: (I) personalized prediction of clinical outcomes and adverse events, which may optimize patient selection, surgical planning, and enhance patient safety and outcomes; (II) diagnostic automated and semiautomated imaging analyses, which may reduce time burden and facilitate precise and timely diagnoses; and (III) forecasting of resource utilization, which may reduce health care costs and increase value for patients and institutions.» Computer vision is one of the most highly studied areas of AI within orthopaedics, with applications pertaining to fracture classification, identification of the manufacturer and model of prosthetic implants, and surveillance of prosthesis loosening and failure.» Prognostic applications of AI within orthopaedics include identifying patients who will likely benefit from a specified treatment, predicting prosthetic implant size, postoperative length of stay, discharge disposition, and surgical complications. Not only may these applications be beneficial to patients but also to institutions and payors because they may inform potential cost expenditure, improve overall hospital efficiency, and help anticipate resource utilization.» AI infrastructure development requires institutional financial commitment and a team of clinicians and data scientists with expertise in AI that can complement skill sets and knowledge. Once a team is established and a goal is determined, teams (1) obtain, curate, and label data; (2) establish a reference standard; (3) develop an AI model; (4) evaluate the performance of the AI model; (5) externally validate the model, and (6) reinforce, improve, and evaluate the model's performance until clinical implementation is possible.» Understanding the implications of AI in orthopaedics may eventually lead to wide-ranging improvements in patient care. However, AI, while holding tremendous promise, is not without methodological and ethical limitations that are essential to address. First, it is important to ensure external validity of programs before their use in a clinical setting. Investigators should maintain high quality data records and registry surveillance, exercise caution when evaluating others' reported AI applications, and increase transparency of the methodological conduct of current models to improve external validity and avoid propagating bias. By addressing these challenges and responsibly embracing the potential of AI, the medical field may eventually be able to harness its power to improve patient care and outcomes.

Machine Learning and Symptom Patterns in Degenerative Cervical Myelopathy: Web-Based Survey Study

BACKGROUND

Degenerative cervical myelopathy (DCM), a progressive spinal cord injury caused by spinal cord compression from degenerative pathology, often presents with neck pain, sensorimotor dysfunction in the upper or lower limbs, gait disturbance, and bladder or bowel dysfunction. Its symptomatology is very heterogeneous, making early detection as well as the measurement or understanding of the underlying factors and their consequences challenging. Increasingly, evidence suggests that DCM may consist of subgroups of the disease, which are yet to be defined.

OBJECTIVE

This study aimed to explore whether machine learning can identify clinically meaningful groups of patients based solely on clinical features.

METHODS

A survey was conducted wherein participants were asked to specify the clinical features they had experienced, their principal presenting complaint, and time to diagnosis as well as demographic information, including disease severity, age, and sex. K-means clustering was used to divide respondents into clusters according to their clinical features using the Euclidean distance measure and the Hartigan-Wong algorithm. The clinical significance of groups was subsequently explored by comparing their time to presentation, time with disease severity, and other demographics.

RESULTS

After a review of both ancillary and cluster data, it was determined by consensus that the optimal number of DCM response groups was 3. In Cluster 1, there were 40 respondents, and the ratio of male to female participants was 13:21. In Cluster 2, there were 92 respondents, with a male to female participant ratio of 27:65. Cluster 3 had 57 respondents, with a male to female participant ratio of 9:48. A total of 6 people did not report biological sex in Cluster 1. The mean age in this Cluster was 56.2 (SD 10.5) years; in Cluster 2, it was 54.7 (SD 9.63) years; and in Cluster 3, it was 51.8 (SD 8.4) years. Patients across clusters significantly differed in the total number of clinical features reported, with more clinical features in Cluster 3 and the least clinical features in Cluster 1 (Kruskal-Wallis rank sum test: χ22=159.46; P<.001). There was no relationship between the pattern of clinical features and severity. There were also no differences between clusters regarding time since diagnosis and time with DCM.

CONCLUSIONS

Using machine learning and patient-reported experience, 3 groups of patients with DCM were defined, which were different in the number of clinical features but not in the severity of DCM or time with DCM. Although a clearer biological basis for the clusters may have been missed, the findings are consistent with the emerging observation that DCM is a heterogeneous disease, difficult to diagnose or stratify. There is a place for machine learning methods to efficiently assist with pattern recognition. However, the challenge lies in creating quality data sets necessary to derive benefit from such approaches.

Machine Learning in Spine Surgery: A Narrative Review

Artificial intelligence and machine learning (ML) can offer revolutionary advances in their application to the field of spine surgery. Within the past 5 years, novel applications of ML have assisted in surgical decision-making, intraoperative imaging and navigation, and optimization of clinical outcomes. ML has the capacity to address many different clinical needs and improve diagnostic and surgical techniques. This review will discuss current applications of ML in the context of spine surgery by breaking down its implementation preoperatively, intraoperatively, and postoperatively. Ethical considerations to ML and challenges in ML implementation must be addressed to maximally benefit patients, spine surgeons, and the healthcare system. Areas for future research in augmented reality and mixed reality, along with limitations in generalizability and bias, will also be highlighted.

Early surgery compared to nonoperative management for mild degenerative cervical myelopathy: a cost-utility analysis

BACKGROUND CONTEXT

Degenerative cervical myelopathy (DCM) is a form of acquired spinal cord compression and contributes to reduced quality of life secondary to neurological dysfunction and pain. There remains uncertainty regarding optimal management for individuals with mild myelopathy. Specifically, owing to lacking long-term natural history studies in this population, we do not know whether these individuals should be treated with initial surgery or observation.

PURPOSE

We sought to perform a cost-utility analysis to examine early surgery for mild degenerative cervical myelopathy from the healthcare payer perspective.

STUDY DESIGN/SETTING

We utilized data from the prospective observational cohorts included in the Cervical Spondylotic Myelopathy AO Spine International and North America studies to determine health related quality of life estimates and clinical myelopathy outcomes.

PATIENT SAMPLE

We recruited all patients that underwent surgery for DCM enrolled in the Cervical Spondylotic Myelopathy AO Spine International and North America studies between December 2005 and January 2011.

OUTCOME MEASURES

Clinical assessment measures were obtained using the Modified Japanese Orthopedic Association scale and health-related quality of life measures were obtained using the Short Form-6D utility score at baseline (preoperative), 6 months, 12 months and 24 months postsurgery. Cost measures inflated to January 2015 values were obtained using pooled estimates from the hospital payer perspective for surgical patients.

METHODS

We employed a Markov state transition model with Monte Carlo microsimulation using a lifetime horizon to obtain an incremental cost utility ratio associated with early surgery for mild myelopathy. Parameter uncertainty was assessed through deterministic means using one-way and two-way sensitivity analyses and probabilistically using parameter estimate distributions with microsimulation (10,000 trials). Costs and utilities were discounted at 3% per annum.

RESULTS

Initial surgery for mild degenerative cervical myelopathy was associated with an incremental lifetime increase of 1.26 quality-adjusted life years (QALY) compared to observation. The associated cost incurred to the healthcare payer over a lifetime horizon was $12,894.56, resulting in a lifetime incremental cost-utility ratio of $10,250.71/QALY. Utilizing a willingness to pay threshold in keeping with the World Health Organization definition of "very cost-effective" ($54,000 CDN), the probabilistic sensitivity analysis demonstrated that 100% of cases were cost-effective.

CONCLUSIONS

Surgery compared to initial observation for mild degenerative cervical myelopathy was cost-effective from the Canadian healthcare payer perspective and was associated with lifetime gains in health-related quality of life.

Developing predictive models for surgical outcomes in patients with degenerative cervical myelopathy: a comparison of statistical and machine learning approaches

BACKGROUND CONTEXT

Machine learning (ML) is widely used to predict the prognosis of numerous diseases.

PURPOSE

This retrospective analysis aimed to develop a prognostic prediction model using ML algorithms and identify predictors associated with poor surgical outcomes in patients with degenerative cervical myelopathy (DCM).

STUDY DESIGN

A retrospective study.

PATIENT SAMPLE

A total of 406 symptomatic DCM patients who underwent surgical decompression were enrolled and analyzed from three independent medical centers.

OUTCOME MEASURES

We calculated the area under the curve (AUC), classification accuracy, sensitivity, and specificity of each model.

METHODS

The Japanese Orthopedic Association (JOA) score was obtained before and 1 year following decompression surgery, and patients were grouped into good and poor outcome groups based on a cut-off value of 60% based on a previous study. Two datasets were fused for training, 1 dataset was held out as an external validation set. Optimal feature-subset and hyperparameters for each model were adjusted based on a 2,000-resample bootstrap-based internal validation via exhaustive search and grid search. The performance of each model was then tested on the external validation set.

RESULTS

The Support Vector Machine (SVM) model showed the highest predictive accuracy compared to other methods, with an AUC of 0.82 and an accuracy of 75.7%. Age, sex, disease duration, and preoperative JOA score were identified as the most commonly selected features by both the ML and statistical models. Grid search optimization for hyperparameters successfully enhanced the predictive performance of each ML model, and the SVM model still had the best performance with an AUC of 0.93 and an accuracy of 86.4%.

CONCLUSIONS

Overall, the study demonstrated that ML classifiers such as SVM can effectively predict surgical outcomes for patients with DCM while identifying associated predictors in a multivariate manner.

Predictive modeling of perioperative blood transfusion in lumbar posterior interbody fusion using machine learning

Background: Accurate estimation of perioperative blood transfusion risk in lumbar posterior interbody fusion is essential to reduce the number, cost, and complications associated with blood transfusions. Machine learning algorithms have the potential to outperform traditional prediction methods in predicting perioperative blood transfusion. This study aimed to construct a machine learning-based perioperative transfusion risk prediction model for lumbar posterior interbody fusion in order to improve the efficacy of surgical decision-making. Methods: We retrospectively collected clinical data on 1905 patients who underwent lumbar posterior interbody fusion surgery at the Second Hospital of Shanxi Medical University between January 2021 and March 2023. All the data was randomly divided into a training set and a validation set, and the "feature_importances" method provided by eXtreme Gradient Boosting (XGBoost) algorithm was applied to select statistically significant features on the training set to establish five machine learning prediction models. The optimal model was identified by utilizing the area under the curve (AUC) and the probability calibration curve on the validation set. Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) were employed for interpretable analysis of the optimal model. Results: In the postoperative outcomes of patients, the number of hospital days in the transfusion group was longer than that in the non-transfusion group. Additionally, the transfusion group experienced higher total hospital costs, 90-day readmission rates, and complication rates within 90 days after surgery than the non-transfusion group. A total of 9 features were selected for the models. The XGBoost model performed best with an AUC value of 0.958. The SHAP values showed that intraoperative blood loss, intraoperative fluid infusion, and number of fused segments were the top 3 most important features affecting perioperative blood transfusion in lumbar posterior interbody fusion. The LIME algorithm was used to interpret the individualized prediction. Conclusion: Surgery, ASA class, levels fused, total intraoperative blood loss, operative time, and preoperative Hb are viable predictors of perioperative blood transfusion in lumbar posterior interbody fusion. The XGBoost model has demonstrated superior predictive efficacy compared to the traditional logistic regression model, making it a more effective decision-making tool for perioperative blood transfusion.

Prediction of Progressive Collapse in Osteoporotic Vertebral Fractures Using Conventional Statistics and Machine Learning

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

The objective of this study was to determine prognostic factors for the progression of osteoporotic vertebral fracture (OVF) following conservative treatment.

SUMMARY OF BACKGROUND DATA

Few studies have evaluated factors associated with progressive collapse (PC) of OVFs. Furthermore, machine learning has not been applied in this context.

MATERIALS AND METHODS

The study involved the PC and non-PC groups based on a compression rate of 15%. Clinical data, fracture site, OVF shape, Cobb angle, and anterior wedge angle of the fractured vertebra were evaluated. The presence of intravertebral cleft and the type of bone marrow signal change were analyzed using magnetic resonance imaging. Multivariate logistic regression analysis was performed to identify prognostic factors. In machine learning methods, decision tree and random forest models were used.

RESULTS

There were no significant differences in clinical data between the groups. The proportion of fracture shape ( P <0.001) and bone marrow signal change ( P =0.01) were significantly different between the groups. Moderate wedge shape was frequently observed in the non-PC group (31.7%), whereas the normative shape was most common in the PC group (54.7%). The Cobb angle and anterior wedge angle at diagnosis of OVFs were higher in the non-PC group (13.2±10.9, P =0.001; 14.3±6.6, P <0.001) than in the PC group (10.3±11.8, 10.4±5.5). The bone marrow signal change at the superior aspect of the vertebra was more frequently found in the PC group (42.5%) than in the non-PC group (34.9%). Machine learning revealed that vertebral shape at initial diagnosis was a main predictor of progressive vertebral collapse.

CONCLUSION

The initial shape of the vertebra and bone edema pattern on magnetic resonance imaging appear to be useful prognostic factors for progressive collapse in osteoporotic vertebral fractures.

State-of-the-art Applications of Patient-Reported Outcome Measures in Spinal Care

Patient-reported outcome measures (PROMs) assign objective measures to patient's subjective experiences of health, pain, disability, function, and quality of life. PROMs can be useful for providers in shared decision making, outcome assessment, and indicating patients for surgery. In this article, we provide an overview of the legacy PROMs used in spinal care, recent advancements in patient-reported outcomes, and future directions in PROMs. Recent advances in patient-reported outcome assessments have included standardization of measurement tools, integration of data collection into workflow, and applications of outcome measures in predictive models and decision-making tools. Continual appraisal of instruments and incorporation into artificial intelligence and machine learning analytics will continue to augment the delivery of high-value spinal care.

Machine Learning Applications in Spine Surgery

This literature review sought to identify and evaluate the current applications of artificial intelligence (AI)/machine learning (ML) in spine surgery that can effectively guide clinical decision-making and surgical planning. By using specific keywords to maximize search sensitivity, a thorough literature research was conducted in several online databases: Scopus, PubMed, and Google Scholar, and the findings were filtered according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 46 studies met the requirements and were included in this review. According to this study, AI/ML models were sufficiently accurate with a mean overall value of 74.9%, and performed best at preoperative patient selection, cost prediction, and length of stay. Performance was also good at predicting functional outcomes and postoperative mortality. Regression analysis was the most frequently utilized application whereas deep learning/artificial neural networks had the highest sensitivity score (81.5%). Despite the relatively brief history of engagement with AI/ML, as evidenced by the fact that 77.5% of studies were published after 2018, the outcomes have been promising. In light of the Big Data era, the increasing prevalence of National Registries, and the wide-ranging applications of AI, such as exemplified by ChatGPT (OpenAI, San Francisco, California), it is highly likely that the field of spine surgery will gradually adopt and integrate AI/ML into its clinical practices. Consequently, it is of great significance for spine surgeons to acquaint themselves with the fundamental principles of AI/ML, as these technologies hold the potential for substantial improvements in overall patient care.

Machine Learning Prediction Model and Risk Factor Analysis of Reoperation in Recurrent Lumbar Disc Herniation Patients After Percutaneous Endoscopic Lumbar Discectomy

OBJECTIVE

To investigate the risk factors of reoperation after percutaneous endoscopic lumbar discectomy (PELD) due to recurrent lumbar disc herniation (rLDH) and to establish a set of individualized prediction models.

METHODS

Patients who underwent PELD successfully from January 2016 to February 2022 in a single institution were enrolled in this study. Six methods of machine learning (ML) were used to establish an individualized prediction model for reoperation in rLDH patients after PELD, and these models were compared with logistics regression model to select optimal model.

RESULTS

A total of 2603 patients were enrolled in this study. 57 patients had repeated operation due to rLDH and 114 patients were selected from the remaining 2546 nonrecurrent patients as matched controls. Multivariate logistic regression analysis showed that disc herniation type (P < .001), Modic changes (type II) (P = .003), sagittal range of motion (sROM) (P = .022), facet orientation (FO) (P = .028) and fat infiltration (FI) (P = .001) were independent risk factors for reoperation in rLDH patients after PELD. The XGBoost AUC was of 90.71%, accuracy was approximately 88.87%, sensitivity was 70.81%, specificity was 97.19%. The traditional logistic regression AUC was 77.4%, accuracy was about 77.73%, sensitivity was 47.15%, specificity was 92.12%.

CONCLUSION

This study showed that disc herniation type (extrusion, sequestration), Modic changes (type II), a large sROM, a large FO and high FI were independent risk factors for reoperation in LDH patients after PELD. The prediction efficiency of XGBoost model was higher than traditional Logistic regression analysis model.

Degenerative cervical myelopathy: Where have we been? Where are we now? Where are we going?

Degenerative cervical myelopathy (DCM), a recently coined term, encompasses a group of age-related and genetically associated pathologies that affect the cervical spine, including cervical spondylotic myelopathy and ossification of the posterior longitudinal ligament (OPLL). Given the significant contribution of DCM to global disease and disability, there are worldwide efforts to promote research and innovation in this area. An AO Spine effort termed 'RECODE-DCM' was initiated to create an international multistakeholder consensus group, involving patients, caregivers, physicians and researchers, to focus on launching actionable discourse on DCM. In order to improve the management, treatment and results for DCM, the RECODE-DCM consensus group recently identified ten priority areas for translational research. The current article summarizes recent advancements in the field of DCM. We first discuss the comprehensive definition recently refined by the RECODE-DCM group, including steps taken to arrive at this definition and the supporting rationale. We then provide an overview of the recent advancements in our understanding of the pathophysiology of DCM and modalities to clinically assess and diagnose DCM. A focus will be set on advanced imaging techniques that may offer the opportunity to improve characterization and diagnosis of DCM. A summary of treatment modalities, including surgical and nonoperative options, is then provided along with future neuroprotective and neuroregenerative strategies. This review concludes with final remarks pertaining to the genetics involved in DCM and the opportunity to leverage this knowledge toward a personalized medicine approach.

Current Applications of Machine Learning for Spinal Cord Tumors

Spinal cord tumors constitute a diverse group of rare neoplasms associated with significant mortality and morbidity that pose unique clinical and surgical challenges. Diagnostic accuracy and outcome prediction are critical for informed decision making and can promote personalized medicine and facilitate optimal patient management. Machine learning has the ability to analyze and combine vast amounts of data, allowing the identification of patterns and the establishment of clinical associations, which can ultimately enhance patient care. Although artificial intelligence techniques have been explored in other areas of spine surgery, such as spinal deformity surgery, precise machine learning models for spinal tumors are lagging behind. Current applications of machine learning in spinal cord tumors include algorithms that improve diagnostic precision by predicting genetic, molecular, and histopathological profiles. Furthermore, artificial intelligence-based systems can assist surgeons with preoperative planning and surgical resection, potentially reducing the risk of recurrence and consequently improving clinical outcomes. Machine learning algorithms promote personalized medicine by enabling prognostication and risk stratification based on accurate predictions of treatment response, survival, and postoperative complications. Despite their promising potential, machine learning models require extensive validation processes and quality assessments to ensure safe and effective translation to clinical practice.

A machine learning-based prediction model for in-hospital mortality among critically ill patients with hip fracture: An internal and external validated study

INTRODUCTION

Few studies have investigated the in-hospital mortality among critically ill patients with hip fracture. This study aimed to develop and validate a model to estimate the risk of in-hospital mortality among critically ill patients with hip fracture.

METHODS

For this study, data from the Medical Information Mart for Intensive Care III (MIMIC-III) Database and electronic Intensive Care Unit (eICU) Collaborative Research Database were evaluated. Enrolled patients (n=391) in the MIMIC-III database were divided into a training (2/3, n=260) and a validation (1/3, n=131) group at random. Using machine learning algorithms such as random forest, gradient boosting machine, decision tree, and eXGBoosting machine approach, the training group was utilized to train and optimize models. The validation group was used to internally validate models and the optimal model could be obtained in terms of discrimination (area under the receiver operating characteristic curve, AUROC) and calibration (calibration curve). External validation was done in the eICU Collaborative Research Database (n=165). To encourage practical use of the model, a web-based calculator was developed according to the eXGBoosting machine approach.

RESULTS

The in-hospital death rate was 13.81% (54/391) in the MIMIC-III database and 10.91% (18/165) in the eICU Collaborative Research Database. Age, gender, anemia, mechanical ventilation, cardiac arrest, and chronic airway obstruction were the six model parameters which were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) method combined with 10-fold cross-validation. The model established using the eXGBoosting machine approach showed the highest area under curve (AUC) value (0.797, 95% CI: 0.696-0.898) and the best calibrating ability, with a calibration slope of 0.999 and intercept of -0.019. External validation also revealed favorable discrimination (AUC: 0.715, 95% CI: 0.566-0.864; accuracy: 0.788) and calibration (calibration slope: 0.805) in the eICU Collaborative Research Database. The web-based calculator could be available at https://doctorwangsj-webcalculator-main-yw69yd.streamlitapp.com/.

CONCLUSION

The model has the potential to be a pragmatic risk prediction tool that is able to identify hip fracture patients who are at a high risk of in-hospital mortality in ICU settings, guide patient risk counseling, and simplify prognosis bench-marking by controlling for baseline risk.

External validation of a predictive algorithm for in-hospital and ninety-day mortality after spinal epidural abscess

BACKGROUND CONTEXT

Mortality in patients with spinal epidural abscess (SEA) remains high. Accurate prediction of patient-specific prognosis in SEA can improve patient counseling as well as guide management decisions. There are no externally validated studies predicting short-term mortality in patients with SEA.

PURPOSE

The purpose of this study was to externally validate the Skeletal Oncology Research Group (SORG) stochastic gradient boosting algorithm for prediction of in-hospital and 90-day postdischarge mortality in SEA.

STUDY DESIGN/SETTING

Retrospective, case-control study at a tertiary care academic medical center from 2003 to 2021.

PATIENT SAMPLE

Adult patients admitted for radiologically confirmed diagnosis of SEA who did not initiate treatment at an outside institution.

OUTCOME MEASURES

In-hospital and 90-day postdischarge mortality.

METHODS

We tested the SORG stochastic gradient boosting algorithm on an independent validation cohort. We assessed its performance with discrimination, calibration, decision curve analysis, and overall performance.

RESULTS

A total of 212 patients met inclusion criteria, with a short-term mortality rate of 10.4%. The area under the receiver operating characteristic curve (AUROC) of the SORG algorithm when tested on the full validation cohort was 0.82, the calibration intercept was -0.08, the calibration slope was 0.96, and the Brier score was 0.09.

CONCLUSIONS

With a contemporaneous and geographically distinct independent cohort, we report successful external validation of a machine learning algorithm for prediction of in-hospital and 90-day postdischarge mortality in SEA.

Optimizing an existing prediction model for quality of life one-year post-intensive care unit: An exploratory analysis

BACKGROUND

This study aimed to improve the PREPARE model, an existing linear regression prediction model for long-term quality of life (QoL) of intensive care unit (ICU) survivors by incorporating additional ICU data from patients' electronic health record (EHR) and bedside monitors.

METHODS

The 1308 adult ICU patients, aged ≥16, admitted between July 2016 and January 2019 were included. Several regression-based machine learning models were fitted on a combination of patient-reported data and expert-selected EHR variables and bedside monitor data to predict change in QoL 1 year after ICU admission. Predictive performance was compared to a five-feature linear regression prediction model using only 24-hour data (R²  = 0.54, mean square error (MSE) = 0.031, mean absolute error (MAE) = 0.128).

RESULTS

The 67.9% of the included ICU survivors was male and the median age was 65.0 [IQR: 57.0-71.0]. Median length of stay (LOS) was 1 day [IQR 1.0-2.0]. The incorporation of the additional data pertaining to the entire ICU stay did not improve the predictive performance of the original linear regression model. The best performing machine learning model used seven features (R²  = 0.52, MSE = 0.032, MAE = 0.125). Pre-ICU QoL, the presence of a cerebro vascular accident (CVA) upon admission and the highest temperature measured during the ICU stay were the most important contributors to predictive performance. Pre-ICU QoL's contribution to predictive performance far exceeded that of the other predictors.

CONCLUSION

Pre-ICU QoL was by far the most important predictor for change in QoL 1 year after ICU admission. The incorporation of the numerous additional features pertaining to the entire ICU stay did not improve predictive performance although the patients' LOS was relatively short.

Comparing Bone Graft Techniques for Interbody Fusion through a Posterior Approach for Treating Mid-Thoracic Spinal Tuberculosis: A Retrospective Analysis

OBJECTIVE

Mid-thoracic spinal tuberculosis is prone to kyphotic deformities and neurologic impairment. Posterior approach can effectively restore the spinal stability by reconstructing the anterior and middle spinal columns. Titanium mesh cages (TMC), allogeneic bone (ALB), and autogenous bone (AUB) are three main bone graft struts. We aimed to compare the therapeutic efficacy of three bone graft struts, for anterior and middle column reconstruction through a posterior approach in cases of mid-thoracic spinal tuberculosis.

METHODS

Hundred and thirty seven patients with thoracic spinal tuberculosis who had undergone a posterior approach from June 2010 to December 2018 were enrolled. Of them, 46 patients were treated using a titanium mesh cage (TMC group), 44 with allogenic bone grafts (ALB group), and 47 using autogenous bone grafts (AUB group). The following were analyzed to evaluate clinical efficacy: visual analogue scale (VAS) values, erythrocyte sedimentation rate (ESR), C-reactive protein (CRP) levels, kyphotic Cobb's angle, operation duration, intraoperative blood loss, improvement in American Spinal Injury Association (ASIA) grade and in the mental component summary (MCS) and physical component summary (PCS) of Short Form-36 (SF-36), duration of bone graft fusion. The data of the three groups were compared by way of variance analysis, followed by the LSD⁃t test to compare each group. A repeated measures ANOVA was used to analyze the dates of pre-, postoperative and final follow-up.

RESULTS

The follow-up duration was at least 3 years. All patients achieved a complete cure for spinal TB. Neurological performance and quality of life were remarkably improved at the final follow-up. The intraoperative blood loss, operation time and VAS values 1 day postoperatively for TMC group and ALB group were significantly lower than those in AUB group (P < 0.05). The duration of bone graft fusion in ALB group (18.1 ± 3.7 months) was longer than that in TMC group and AUB group (9.5 ± 2.8 and 9.2 ± 1.9 months) (P < 0.05). No significant intergroup differences were observed in terms of age or preoperative, 3-months postoperative, and final follow-up indices of ESR and CRP among the three groups (P > 0.05). At the final follow-up, the correction loss was mild (2.1 ± 0.9, 2.2 ± 1.0, 2.1 ± 0.8) and Cobb's angles of the three groups were 20.1 ± 2.9, 20.5 ± 3.2, 20.9 ± 3.4, respectively, which were remarkably rectified in comparison with the preoperative measurements (P < 0.05).

CONCLUSIONS

In terms of postoperative recovery and successful fusion rate of bone graft, it seems that posterior instrumentation, debridement, and interbody fusion with titanium mesh cages are more effective and appropriate surgical methods for mid-thoracic spinal tuberculosis.

Artificial Learning and Machine Learning Applications in Spine Surgery: A Systematic Review

OBJECTIVES

This current systematic review sought to identify and evaluate all current research-based spine surgery applications of AI/ML in optimizing preoperative patient selection, as well as predicting and managing postoperative outcomes and complications.

METHODS

A comprehensive search of publications was conducted through the EMBASE, Medline, and PubMed databases using relevant keywords to maximize the sensitivity of the search. No limits were placed on level of evidence or timing of the study. Findings were reported according to the PRISMA guidelines.

RESULTS

After application of inclusion and exclusion criteria, 41 studies were included in this review. Bayesian networks had the highest average AUC (.80), and neural networks had the best accuracy (83.0%), sensitivity (81.5%), and specificity (71.8%). Preoperative planning/cost prediction models (.89,82.2%) and discharge/length of stay models (.80,78.0%) each reported significantly higher average AUC and accuracy compared to readmissions/reoperation prediction models (.67,70.2%) (P < .001, P = .005, respectively). Model performance also significantly varied across postoperative management applications for average AUC and accuracy values (P < .001, P < .027, respectively).

CONCLUSIONS

Generally, authors of the reviewed studies concluded that AI/ML offers a potentially beneficial tool for providers to optimize patient care and improve cost-efficiency. More specifically, AI/ML models performed best, on average, when optimizing preoperative patient selection and planning and predicting costs, hospital discharge, and length of stay. However, models were not as accurate in predicting postoperative complications, adverse events, and readmissions and reoperations. An understanding of AI/ML-based applications is becoming increasingly important, particularly in spine surgery, as the volume of reported literature, technology accessibility, and clinical applications continue to rapidly expand.

Cerebrospinal fluid pressure dynamics reveal signs of effective spinal canal narrowing in ambiguous spine conditions

Spinal canal narrowing with consecutive spinal cord compression is considered a key mechanism in degenerative cervical myelopathy (DCM). DCM is a common spine condition associated with progressive neurological disability, and timely decompressive surgery is recommended. However, the clinical and radiological diagnostic workup is often ambiguous, challenging confident proactive treatment recommendations. Cerebrospinal fluid pressure dynamics (CSFP) are altered by spinal canal narrowing. Therefore, we aim to explore the potential value of bedside CSFP assessments for qualitative and quantitative assessment of spinal canal narrowing in DCM. In this prospective case series, seven patients with DCM underwent bedside lumbar puncture with measurement of CSFP dynamics and routine CSF analysis (NCT02170155). The patients were enrolled when standard diagnostic algorithms did not permit a clear treatment decision. Measurements include baseline CSFP, cardiac-driven CSFP peak-to-trough amplitude (CSFPp), and the Queckenstedt's test (firm pressure on jugular veins) in neutral and reclined head position. From the Queckenstedt's test, proxies for craniospinal elastance (i.e., relative pulse pressure coefficient; RPPC-Q) were calculated analogously to infusion testing. CSFP metrics were deemed suspicious of canal narrowing when numbers were lower than the minimum value from a previously tested elderly spine-healthy cohort (N = 14). Mean age was 56 ± 13 years (range, 38–75; 2F); symptom severity was mostly mild to moderate (mean mJOA, 13.5 ± 2.6; range, 9–17). All the patients showed some extent of cervical stenosis in the MRI of unclear significance (5/7 following decompressive cervical spine surgery with an adjacent level or residual stenosis). Baseline CSFP was normal except for one patient (range, 4.7–17.4 mmHg). Normal values were found for CSFPp (0.4–1.3 mmHg) and the Queckenstedt's test in normal head positioning (9.-25.3 mmHg). During reclination, the Queckenstedt's test significantly decreased in one, and CSFPp in another case (>50% compared to normal position). RPPC-Q (0.07–0.19) aligned with lower values from spine-healthy (0.10–0.44). Routine CSF examinations showed mild total protein elevation (mean, 522 ± 108 mg/ml) without further evidence for the disturbed blood brain barrier. Intrathecal CSFP measurements allow discerning disturbed from normal CSFP dynamics in this population. Prospective longitudinal studies should further evaluate the diagnostic utility of CSFP assessments in DCM.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

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.

Machine Learning Approach in Predicting Clinically Significant Improvements After Surgery in Patients with Cervical Ossification of the Posterior Longitudinal Ligament

STUDY DESIGN

A retrospective analysis of prospectively collected data.

OBJECTIVE

This study aimed to create a prognostic model for surgical outcomes in patients with cervical ossification of the posterior longitudinal ligament (OPLL) using machine learning (ML).

SUMMARY OF BACKGROUND DATA

Determining surgical outcomes helps surgeons provide prognostic information to patients and manage their expectations. ML is a mathematical model that finds patterns from a large sample of data and makes predictions outperforming traditional statistical methods.

METHODS

Of 478 patients, 397 and 370 patients had complete follow-up information at 1 and 2 years, respectively, and were included in the analysis. A minimal clinically important difference (MCID) was defined as an acquired Japanese Orthopedic Association (JOA) score of ≥2.5 points, after which a ML model that predicts whether MCID can be achieved 1 and 2 years after surgery was created. Patient background, clinical symptoms, and imaging findings were used as variables for analysis. The ML model was created using LightGBM, XGBoost, random forest, and logistic regression, after which the accuracy and area under the receiver-operating characteristic curve (AUC) were calculated.

RESULTS

The mean JOA score was 10.3 preoperatively, 13.4 at 1 year after surgery, and 13.5 at 2 years after surgery. XGBoost showed the highest AUC (0.72) and high accuracy (67.8) for predicting MCID at 1 year, whereas random forest had the highest AUC (0.75) and accuracy (69.6) for predicting MCID at 2 years. Among the included features, total preoperative JOA score, duration of symptoms, body weight, sensory function of the lower extremity sub-score of the JOA, and age were identified as having the most significance in most of ML models.

CONCLUSION

Constructing a prognostic ML model for surgical outcomes in patients with OPLL is feasible, suggesting the potential application of ML for predictive models of spinal surgery.Level of Evidence: 4.

Estimating Health-Related Quality of Life Based on Demographic Characteristics, Questionnaires, Gait Ability, and Physical Fitness in Korean Elderly Adults

The elderly population in South Korea accounted for 15.5% of the total population in 2019. Thus, it is important to study the various elements governing the process of healthy aging. Therefore, this study investigated multiple prediction models to determine the health-related quality of life (HRQoL) in elderly adults based on the demographics, questionnaires, gait ability, and physical fitness. We performed eight physical fitness tests on 775 participants wearing shoe-type inertial measurement units and completing walking tasks at slower, preferred, and faster speeds. The HRQoL for physical and mental components was evaluated using a 36-item, short-form health survey. The prediction models based on multiple linear regression with feature importance were analyzed considering the best physical and mental components. We used 11 variables and 5 variables to form the best subset of features underlying the physical and mental components, respectively. We laid particular emphasis on evaluating the functional endurance, muscle strength, stress level, and falling risk. Furthermore, stress, insomnia severity, number of diseases, lower body strength, and fear of falling were taken into consideration in addition to mental-health-related variables. Thus, the study findings provide reliable and objective results to improve the understanding of HRQoL in elderly adults.

Use of Machine Learning and Artificial Intelligence to Drive Personalized Medicine Approaches for Spine Care

Personalized medicine is a new paradigm of healthcare in which interventions are based on individual patient characteristics rather than on "one-size-fits-all" guidelines. As epidemiological datasets continue to burgeon in size and complexity, powerful methods such as statistical machine learning and artificial intelligence (AI) become necessary to interpret and develop prognostic models from underlying data. Through such analysis, machine learning can be used to facilitate personalized medicine via its precise predictions. Additionally, other AI tools, such as natural language processing and computer vision, can play an instrumental part in personalizing the care provided to patients with spine disease. In the present report, we discuss the current strides made in incorporating AI into research on spine disease, especially traumatic spinal cord injury and degenerative spine disease. We describe studies using AI to build accurate prognostic models, extract important information from medical reports via natural language processing, and evaluate functional status in a granular manner using computer vision. Through a case illustration, we have demonstrated how these breakthroughs can facilitate an increased role for more personalized medicine and, thus, change the landscape of spine care.

Development of Machine Learning Algorithms to Predict Patient Dissatisfaction After Primary Total Knee Arthroplasty

BACKGROUND

Postoperative dissatisfaction after primary total knee arthroplasty (TKA) that requires additional care or readmission may impose a significant financial burden to healthcare systems. The purpose of the current study is to develop machine learning algorithms to predict dissatisfaction after TKA.

METHODS

A retrospective review of consecutive TKA patients between 2014 and 2016 from 1 large academic and 2 community hospitals was performed. Preoperative variables considered for prediction included demographics, medical history, flexion contracture, knee flexion, and outcome scores (patient-reported health state, Knee Society Score [KSS], and KSS-Function [KSS-F]). Recursive feature elimination was used to select features that optimized algorithm performance. Five supervised machine learning algorithms were developed by training with 10-fold cross-validation 3 times. These algorithms were subsequently applied to an independent testing set of patients and assessed by discrimination, calibration, Brier score, and decision curve analysis.

RESULTS

Of 430 patients, a total of 40 (9.0%) were dissatisfied with their outcome after primary TKA at a minimum of 2 years postoperatively. The random forest algorithm achieved the best performance in the independent testing set not used for algorithm development (c-statistic: 0.77, calibration intercept: 0.087, calibration slope: 0.74, Brier score: 0.082). The most important factors for predicting dissatisfaction were age, number of medical comorbidities, presence of one or more drug allergies, preoperative patient-reported health state score, and preoperative KSS.

CONCLUSION

The current study developed machine learning algorithms based on partially modifiable risk factors for predicting dissatisfaction after TKA. This model demonstrates good discriminative capacity for identifying those at greatest risk for dissatisfaction and may allow for preoperative health optimization.

The Role of Machine Learning in Spine Surgery: The Future Is Now

The recent influx of machine learning centered investigations in the spine surgery literature has led to increased enthusiasm as to the prospect of using artificial intelligence to create clinical decision support tools, optimize postoperative outcomes, and improve technologies used in the operating room. However, the methodology underlying machine learning in spine research is often overlooked as the subject matter is quite novel and may be foreign to practicing spine surgeons. Improper application of machine learning is a significant bioethics challenge, given the potential consequences of over- or underestimating the results of such studies for clinical decision-making processes. Proper peer review of these publications requires a baseline familiarity of the language associated with machine learning, and how it differs from classical statistical analyses. This narrative review first introduces the overall field of machine learning and its role in artificial intelligence, and defines basic terminology. In addition, common modalities for applying machine learning, including classification and regression decision trees, support vector machines, and artificial neural networks are examined in the context of examples gathered from the spine literature. Lastly, the ethical challenges associated with adapting machine learning for research related to patient care, as well as future perspectives on the potential use of machine learning in spine surgery, are discussed specifically.