Machine learning-based preoperative predictive analytics for lumbar spinal stenosis

Determining Prior Authorization Approval for Lumbar Stenosis Surgery With Machine Learning

STUDY DESIGN

Medical vignettes.

OBJECTIVES

Lumbar spinal stenosis (LSS) is a degenerative condition with a high prevalence in the elderly population, that is associated with a significant economic burden and often requires spinal surgery. Prior authorization of surgical candidates is required before patients can be covered by a health plan and must be approved by medical directors (MDs), which is often subjective and clinician specific. In this study, we hypothesized that the prediction accuracy of machine learning (ML) methods regarding surgical candidates is comparable to that of a panel of MDs.

METHODS

Based on patient demographic factors, previous therapeutic history, symptoms and physical examinations and imaging findings, we propose an ML which computes the probability of spinal surgical recommendations for LSS. The model implements a random forest model trained from medical vignette data reviewed by MDs. Sets of 400 and 100 medical vignettes reviewed by MDs were used for training and testing.

RESULTS

The predictive accuracy of the machine learning model was with a root mean square error (RMSE) between model predictions and ground truth of .1123, while the average RMSE between individual MD's recommendations and ground truth was .2661. For binary classification, the AUROC and Cohen's kappa were .959 and .801, while the corresponding average metrics based on individual MD's recommendations were .844 and .564, respectively.

CONCLUSIONS

Our results suggest that ML can be used to automate prior authorization approval of surgery for LSS with performance comparable to a panel of MDs.

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.

Using Machine Learning Models to Identify Factors Associated With 30-Day Readmissions After Posterior Cervical Fusions: A Longitudinal Cohort Study

OBJECTIVE

Readmission rates after posterior cervical fusion (PCF) significantly impact patients and healthcare, with complication rates at 15%-25% and up to 12% 90-day readmission rates. In this study, we aim to test whether machine learning (ML) models that capture interfactorial interactions outperform traditional logistic regression (LR) in identifying readmission-associated factors.

METHODS

The Optum Clinformatics Data Mart database was used to identify patients who underwent PCF between 2004-2017. To determine factors associated with 30-day readmissions, 5 ML models were generated and evaluated, including a multivariate LR (MLR) model. Then, the best-performing model, Gradient Boosting Machine (GBM), was compared to the LACE (Length patient stay in the hospital, Acuity of admission of patient in the hospital, Comorbidity, and Emergency visit) index regarding potential cost savings from algorithm implementation.

RESULTS

This study included 4,130 patients, 874 of which were readmitted within 30 days. When analyzed and scaled, we found that patient discharge status, comorbidities, and number of procedure codes were factors that influenced MLR, while patient discharge status, billed admission charge, and length of stay influenced the GBM model. The GBM model significantly outperformed MLR in predicting unplanned readmissions (mean area under the receiver operating characteristic curve, 0.846 vs. 0.829; p < 0.001), while also projecting an average cost savings of 50% more than the LACE index.

CONCLUSION

Five models (GBM, XGBoost [extreme gradient boosting], RF [random forest], LASSO [least absolute shrinkage and selection operator], and MLR) were evaluated, among which, the GBM model exhibited superior predictive performance, robustness, and accuracy. Factors associated with readmissions impact LR and GBM models differently, suggesting that these models can be used complementarily. When analyzing PCF procedures, the GBM model resulted in greater predictive performance and was associated with higher theoretical cost savings for readmissions associated with PCF complications.

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

BACKGROUND

Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art model of revision prediction of cervical spine surgery using laboratory and operative variables.

METHODS

Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016 and 2022 were identified (N = 3151), and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and time frame. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables.

RESULTS

Red blood cell count, hemoglobin, hematocrit, mean corpuscular hemoglobin concentration, red blood cell distribution width, platelet count, carbon dioxide, anion gap, and calcium all were significantly associated with ≥1 revision cohorts. For the prediction of 3-month revision, the deep neural network achieved an area under the receiver operating characteristic curve of 0.833. The model demonstrated increased performance for anterior versus posterior and arthrodesis versus decompression procedures.

CONCLUSIONS

Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables in a cervical spine surgery cohort. This work used standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of one-size-fits-all risk scores for spine procedures.

Assessment of the External Validity of Dialogue Support for Predicting Lumbar Spine Surgery Outcomes in a US Cohort

STUDY DESIGN

External validation using prospectively collected data.

OBJECTIVES

To determine the model performance of "Dialogue Support" (DS) in predicting outcomes after lumbar spine surgery.

SUMMARY OF BACKGROUND DATA

To help clinicians discuss risk versus benefit with patients considering lumbar fusion surgery, DS has been made available online. As DS was created using a Swedish sample, there is a need to study how well DS performs in alternative populations.

PATIENTS AND METHODS

Preoperative data from patients enrolled in the Quality Outcomes Database were entered into DS. The probability for each patient to report satisfaction, achieve success (leg pain improvement ≥3), or have no leg pain 12 months after surgery was extracted and compared with their actual 12-month postoperative data. The ability of DS to identify patients in the Quality Outcomes Database who report satisfaction, achieve success, or have no leg pain 12 months after surgery was determined using Receiver operating characteristic curve analysis, goodness-of-fit tests, and calibration plots.

RESULTS

There was a significant improvement in all outcomes in 23,928 cases included in the analysis from baseline to 12 months postoperative. Most (84%) reported satisfaction, 67% achieved success, and 44% were pain-free 12 months postoperative. Receiver operating characteristic analysis showed that DS had a low ability to predict satisfaction [area under the curve (AUC) = 0.606], success (AUC = 0.546), and being pain-free (AUC = 0.578) at 12 months postoperative; poor fit for satisfaction (<0.001) and being pain-free ( P = 0.004), but acceptable fit for success ( P = 0.052). Calibration plots showed underestimation for satisfaction and success, but acceptable estimates for being pain-free.

CONCLUSION

DS is not directly transferable to predict satisfaction and success after lumbar surgery in a US population. This may be due to differences in patient characteristics, weights of the variables included, or the exclusion of unknown variables associated with outcomes. Future studies to better understand and improve the transferability of these models are needed.

Using Machine Learning to Predict Unplanned Hospital Utilization and Chemotherapy Management From Patient-Reported Outcome Measures

PURPOSE

Adverse effects of chemotherapy often require hospital admissions or treatment management. Identifying factors contributing to unplanned hospital utilization may improve health care quality and patients' well-being. This study aimed to assess if patient-reported outcome measures (PROMs) improve performance of machine learning (ML) models predicting hospital admissions, triage events (contacting helpline or attending hospital), and changes to chemotherapy.

MATERIALS AND METHODS

Clinical trial data were used and contained responses to three PROMs (European Organisation for Research and Treatment of Cancer Core Quality of Life Questionnaire [QLQ-C30], EuroQol Five-Dimensional Visual Analogue Scale [EQ-5D], and Functional Assessment of Cancer Therapy-General [FACT-G]) and clinical information on 508 participants undergoing chemotherapy. Six feature sets (with following variables: [1] all available; [2] clinical; [3] PROMs; [4] clinical and QLQ-C30; [5] clinical and EQ-5D; [6] clinical and FACT-G) were applied in six ML models (logistic regression [LR], decision tree, adaptive boosting, random forest [RF], support vector machines [SVMs], and neural network) to predict admissions, triage events, and chemotherapy changes.

RESULTS

The comprehensive analysis of predictive performances of the six ML models for each feature set in three different methods for handling class imbalance indicated that PROMs improved predictions of all outcomes. RF and SVMs had the highest performance for predicting admissions and changes to chemotherapy in balanced data sets, and LR in imbalanced data set. Balancing data led to the best performance compared with imbalanced data set or data set with balanced train set only.

CONCLUSION

These results endorsed the view that ML can be applied on PROM data to predict hospital utilization and chemotherapy management. If further explored, this study may contribute to health care planning and treatment personalization. Rigorous comparison of model performance affected by different imbalanced data handling methods shows best practice in ML research.

Performance of the streamlined quality outcomes database web-based calculator: internal and external validation

BACKGROUND CONTEXT

With an increasing number of web-based calculators designed to provide the probabilities of an individual achieving improvement after lumbar spine surgery, there is a need to determine the accuracy of these models.

PURPOSE

To perform an internal and external validation study of the reduced Quality Outcomes Database web-based Calculator (QOD-Calc).

STUDY DESIGN

Observational longitudinal cohort.

PATIENT SAMPLE

Patients enrolled study-wide in Quality Outcomes Database (QOD) and patients enrolled in DaneSpine at a single institution who had elective lumbar spine surgery with baseline data to complete QOD-Calc and 12-month postoperative data.

OUTCOME MEASURES

Oswestry Disability Index (ODI), Numeric Rating Scales (NRS) for back and leg pain, EuroQOL-5D (EQ-5D).

METHODS

Baseline data elements were entered into QOD-Calc to determine the probability for each patient having Any Improvement and 30% Improvement in NRS leg pain, back pain, EQ-5D and ODI. These probabilities were compared with the actual 12-month postop data for each of the QOD and DaneSpine cases. Receiver-operating characteristics analyses were performed and calibration plots created to assess model performance.

RESULTS

24,755 QOD cases and 8,105 DaneSpine lumbar cases were included in the analysis. QOD-Calc had acceptable to outstanding ability (AUC: 0.694-0.874) to predict Any Improvement in the QOD cohort and moderate to acceptable ability (AUC: 0.658-0.747) to predict 30% Improvement. QOD-Calc had acceptable to exceptional ability (AUC: 0.669-0.734) to predict Any improvement and moderate to exceptional ability (AUC: 0.619-0.862) to predict 30% Improvement in the DaneSpine cohort. AUCs for the DaneSpine cohort was consistently lower that the AUCs for the QOD validation cohort.

CONCLUSION

QOD-Calc performs well in predicting outcomes in a patient population that is similar to the patients that was used to develop it. Although still acceptable, model performance was slightly worse in a distinct population, despite the fact that the sample was more homogenous. Model performance may also be attributed to the low discrimination threshold, with close to 90% of cases reporting Any Improvement in outcome. Prediction models may need to be developed that are highly specific to the characteristics of the population.

Artificial intelligence-based analysis of associations between learning curve and clinical outcomes in endoscopic and microsurgical lumbar decompression surgery

PURPOSE

A common spine surgery procedure involves decompression of the lumbar spine. The impact of the surgeon's learning curve on relevant clinical outcomes is currently not well examined in the literature. A variety of machine learning algorithms have been investigated in this study to determine how a surgeon's learning curve and other clinical parameters will influence prolonged lengths of stay (LOS), extended operating times (OT), and complications, as well as whether these clinical parameters can be reliably predicted.

METHODS

A retrospective monocentric cohort study of patients with lumbar spinal stenosis treated with microsurgical (MSD) and full-endoscopic (FED) decompression was conducted. The study included 206 patients with lumbar spinal stenosis who underwent FED (63; 30.6%) and MSD (118; 57.3%). Prolonged LOS and OT were defined as those exceeding the 75th percentile of the cohort. Furthermore, complications were assessed as a dependent variable. Using unsupervised learning, clusters were identified in the data, which helped distinguish between the early learning curve (ELC) and the late learning curve (LLC). From 15 algorithms, the top five algorithms that best fit the data were selected for each prediction task. We calculated the accuracy of prediction (Acc) and the area under the curve (AUC). The most significant predictors were determined using a feature importance analysis.

RESULTS

For the FED group, the median number of surgeries with case surgery type at the time of surgery was 72 in the ELC group and 274 in the LLC group. FED patients did not significantly differ in outcome variables (LOS, OT, complication rate) between the ELC and LLC group. The random forest model demonstrated the highest mean accuracy and AUC across all folds for each classification task. For OT, it achieved an accuracy of 76.08% and an AUC of 0.89. For LOS, the model reached an accuracy of 83.83% and an AUC of 0.91. Lastly, in predicting complications, the random forest model attained the highest accuracy of 89.90% and an AUC of 0.94. Feature importance analysis indicated that LOS, OT, and complications were more significantly affected by patient characteristics than the surgical technique (FED versus MSD) or the surgeon's learning curve.

CONCLUSIONS

A median of 72 cases of FED surgeries led to comparable clinical outcomes in the early learning curve phase compared to experienced surgeons. These outcomes seem to be more significantly affected by patient characteristics than the learning curve or the surgical technique. Several study variables, including the learning curve, can be used to predict whether lumbar decompression surgery will result in an increased LOS, OT, or complications. To introduce the provided prediction tools into clinics, the algorithms need to be implemented into open-source software and externally validated through large-scale randomized controlled trials.

Machine Learning Predicts Decompression Levels for Lumbar Spinal Stenosis Using Canal Radiomic Features from Computed Tomography Myelography

BACKGROUND

The accurate preoperative identification of decompression levels is crucial for the success of surgery in patients with multi-level lumbar spinal stenosis (LSS). The objective of this study was to develop machine learning (ML) classifiers that can predict decompression levels using computed tomography myelography (CTM) data from LSS patients.

METHODS

A total of 1095 lumbar levels from 219 patients were included in this study. The bony spinal canal in CTM images was manually delineated, and radiomic features were extracted. The extracted data were randomly divided into training and testing datasets (8:2). Six feature selection methods combined with 12 ML algorithms were employed, resulting in a total of 72 ML classifiers. The main evaluation indicator for all classifiers was the area under the curve of the receiver operating characteristic (ROC-AUC), with the precision-recall AUC (PR-AUC) serving as the secondary indicator. The prediction outcome of ML classifiers was decompression level or not.

RESULTS

The embedding linear support vector (embeddingLSVC) was the optimal feature selection method. The feature importance analysis revealed the top 5 important features of the 15 radiomic predictors, which included 2 texture features, 2 first-order intensity features, and 1 shape feature. Except for shape features, these features might be eye-discernible but hardly quantified. The top two ML classifiers were embeddingLSVC combined with support vector machine (EmbeddingLSVC_SVM) and embeddingLSVC combined with gradient boosting (EmbeddingLSVC_GradientBoost). These classifiers achieved ROC-AUCs over 0.90 and PR-AUCs over 0.80 in independent testing among the 72 classifiers. Further comparisons indicated that EmbeddingLSVC_SVM appeared to be the optimal classifier, demonstrating superior discrimination ability, slight advantages in the Brier scores on the calibration curve, and Net benefits on the Decision Curve Analysis.

CONCLUSIONS

ML successfully extracted valuable and interpretable radiomic features from the spinal canal using CTM images, and accurately predicted decompression levels for LSS patients. The EmbeddingLSVC_SVM classifier has the potential to assist surgical decision making in clinical practice, as it showed high discrimination, advantageous calibration, and competitive utility in selecting decompression levels in LSS patients using canal radiomic features from CTM.

Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models' effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model's area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.

Development and temporal validation of clinical prediction models for 1-year disability and pain after lumbar decompressive surgery. The Norwich Lumbar Surgery Predictor (development version)

PURPOSE

To identify clinical predictors and build prediction models for 1-year patient-reported outcomes measures (PROMs) after lumbar decompressive surgery for disc herniation or spinal stenosis.

METHODS

The study included 1835 cases, with or without additional single-level fusion, from a single centre from 2008 through 2020. General linear models imputed with 37 clinical variables identified 18 significant 1-year PROM predictors for retention in development models. Interaction of surgical indication with each predictor was tested. Temporal validation was conducted at the same centre on cases through 2021. R2 was used to measure goodness-of-fit, and area under curve (AUC) used to measure classification to a satisfactory symptom state (Oswestry Disability Index (ODI) ≤ 22; back or leg pain ≤ 30 out of 100).

RESULTS

A total 1228 (67%) had complete data for inclusion in model development. Predictors of ODI were baseline PROMs (ODI, back pain, leg pain), work status, condition duration, previous lumbar operation, multiple-joint osteoarthritis, female, diabetes, current smoker, rheumatic disorder, lower limb arthroplasty, mobility aided, provider status, facet cyst, scoliosis, and age, with BMI significantly associated with stenosis. Temporal validation (n = 188) found the ODI model R2 was 0.29 (95% confidence intervals (CI) 0.18-0.40) and AUC was 0.74 (95% CI 0.67-0.81). Back and leg pain models had lower R2 (0.12-0.14) and AUC (0.68-0.69) values.

CONCLUSION

Important PROM predictors are baseline PROMs, specific co-morbidities, work status, condition duration, previous lumbar operation, female, and smoking status. The ODI model predicted the likelihood of achieving a satisfactory state of both disability and pain.

Outcome Reporting in Spine Surgery: A Review of Historical and Emerging Trends

The general objectives of spine surgery are to alleviate pain, restore neurologic function, and prevent or treat spinal deformities or instability. The accumulating expanse of outcome measures has allowed us to more objectively quantify these variables and, therefore, gauge the success of treatments, ultimately improving the quality of the delivered health care. It has become increasingly evident that spinal conditions and their accompanying interventions affect all aspects of a patient's life, including their physical, mental, emotional, and social well-being. This underscores the challenge of creating clinically relevant and accurate outcome measures in spine care, and the reason why there is a growing recognition of the importance of subjective measures such as patient-reported outcome measures, that consider a patients' health-related quality of life. Subjective measures provide valuable insights into patient experiences and perceptions of treatment outcomes, whereas objective measures provide a reproducible glimpse into key radiographic and clinical parameters that are associated with a successful outcome. In this narrative review, we provide a detailed analysis of the most common subjective and objective outcome measures employed in spine surgery, with a special focus on their current role as well as the possible future of outcome reporting.

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.

Applicability of machine learning technique in the screening of patients with mild traumatic brain injury

Even though the demand of head computed tomography (CT) in patients with mild traumatic brain injury (TBI) has progressively increased worldwide, only a small number of individuals have intracranial lesions that require neurosurgical intervention. As such, this study aims to evaluate the applicability of a machine learning (ML) technique in the screening of patients with mild TBI in the Regional University Hospital of Maringá, Paraná state, Brazil. This is an observational, descriptive, cross-sectional, and retrospective study using ML technique to develop a protocol that predicts which patients with an initial diagnosis of mild TBI should be recommended for a head CT. Among the tested models, he linear extreme gradient boosting was the best algorithm, with the highest sensitivity (0.70 ± 0.06). Our predictive model can assist in the screening of mild TBI patients, assisting health professionals to manage the resource utilization, and improve the quality and safety of patient care.

Perioperative Predictors in Patients Undergoing Lateral Lumbar Interbody Fusion for Minimum Clinically Important Difference Achievement

OBJECTIVE

To identify perioperative predictors of minimum clinically important difference (MCID) for patients undergoing lateral lumbar interbody fusion (LLIF) for the patient-reported outcome measures (PROMs) of Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS-PF), visual analog scale (VAS) back, VAS leg, Oswestry Disability Index (ODI), and Patient Health Questionnaire-9 (PHQ-9).

METHODS

Patients undergoing LLIF were identified through retrospective review of a single-surgeon database. Overall MCID achievement was determined as the number of unique patients achieving ΔPROM thresholds of PROMIS-PF = 4.5, VAS back = 2.1, VAS leg = 2.8, ODI = 14.9, and PHQ-9 = 3.0 over a 2-year postoperative period. Univariate and multivariable logistic regression were used to determine perioperative predictors for MCID achievement.

RESULTS

Two-hundred and ninety patients were identified. For PROMIS-PF MCID achievement, increased preoperative PROMIS-PF and postoperative day (POD) 1 VAS pain were significant negative predictors. For VAS back, primary fusion with revision decompression was a negative predictor, whereas increased preoperative VAS back score was a positive predictor of MCID achievement. For VAS leg, increased preoperative VAS leg score was a positive predictor. For ODI, increased POD 0 VAS pain score was a negative predictor, whereas increased preoperative ODI was a positive predictor. For PHQ-9, increased preoperative PHQ-9 score was a positive predictor.

CONCLUSIONS

In patients undergoing LLIF, perioperative predictors for MCID achievement were highly dependent on PROM. Preoperative PROM was the most consistent perioperative predictor for achieving MCID. Increased acute postoperative pain and primary fusion after failed index decompression were significant predictors of failing to achieve MCID. Surgeons may use these findings in prognostication and management of postoperative expectations.

LSS-VGG16: Diagnosis of Lumbar Spinal Stenosis With Deep Learning

STUDY DESIGN

This was a retrospective study.

OBJECTION

Lumbar Spinal Stenosis (LSS) is a disease that causes chronic low back pain and can often be confused with herniated disk. In this study, a deep learning-based classification model is proposed to make LSS diagnosis quickly and automatically with an objective tool.

SUMMARY OF BACKGROUND DATA

LSS is a disease that causes negative consequences such as low back pain, foot numbness, and pain. Diagnosis of this disease is difficult because it is confused with herniated disk and requires serious expertise. The shape and amount of this stenosis are very important in deciding the surgery and the surgical technique to be applied in these patients. When the spinal canal narrows, as a result of compression on these nerves and/or pressure on the vessels feeding the nerves, poor nutrition of the nerves causes loss of function and structure. Image processing techniques are applied in biomedical images such as MR and CT and high classification success is achieved. In this way, computer-aided diagnosis systems can be realized to help the specialist in the diagnosis of different diseases.

METHODS

To demonstrate the success of the proposed model, different deep learning methods and traditional machine learning techniques have been studied.

RESULTS

The highest classification success was obtained in the VGG16 method, with 87.70%.

CONCLUSIONS

The proposed LSS-VGG16 model reveals that a computer-aided diagnosis system can be created for the diagnosis of spinal canal stenosis. In addition, it was observed that higher classification success was achieved compared with similar studies in the literature. This shows that the proposed LSS-VGG16 model will be an important resource for scientists who will work in this field.

Predicting patient-reported outcomes following lumbar spine surgery: development and external validation of multivariable prediction models

BACKGROUND

This study aimed to develop and externally validate prediction models of spinal surgery outcomes based on a retrospective review of a prospective clinical database, uniquely comparing multivariate regression and random forest (machine learning) approaches, and identifying the most important predictors.

METHODS

Outcomes were change in back and leg pain intensity and Core Outcome Measures Index (COMI) from baseline to the last available postoperative follow-up (3-24 months), defined as minimal clinically important change (MCID) and continuous change score. Eligible patients underwent lumbar spine surgery for degenerative pathology between 2011 and 2021. Data were split by surgery date into development (N = 2691) and validation (N = 1616) sets for temporal external validation. Multivariate logistic and linear regression, and random forest classification and regression models, were fit to the development data and validated on the external data.

RESULTS

All models demonstrated good calibration in the validation data. Discrimination ability (area under the curve) for MCID ranged from 0.63 (COMI) to 0.72 (back pain) in regression, and from 0.62 (COMI) to 0.68 (back pain) in random forests. The explained variation in continuous change scores spanned 16%-28% in linear, and 15%-25% in random forests regression. The most important predictors included age, baseline scores on the respective outcome measures, type of degenerative pathology, previous spinal surgeries, smoking status, morbidity, and duration of hospital stay.

CONCLUSIONS

The developed models appear robust and generalisable across different outcomes and modelling approaches but produced only borderline acceptable discrimination ability, suggesting the need to assess further prognostic factors. External validation showed no advantage of the random forest approach.

Using Machine Learning and Deep Learning Algorithms to Predict Postoperative Outcomes Following Anterior Cervical Discectomy and Fusion

STUDY DESIGN

A retrospective cohort study from a multisite academic medical center.

OBJECTIVE

To construct, evaluate, and interpret a series of machine learning models to predict outcomes related to inpatient health care resource utilization for patients undergoing anterior cervical discectomy and fusion (ACDF).

SUMMARY OF BACKGROUND DATA

Reducing postoperative health care utilization is an important goal for improving the delivery of surgical care and serves as a metric for quality assessment. Recent data has shown marked hospital resource utilization after ACDF surgery, including readmissions, and ED visits. The burden of postoperative health care use presents a potential application of machine learning techniques, which may be capable of accurately identifying at-risk patients using patient-specific predictors.

METHODS

Patients 18-88 years old who underwent ACDF from 2011 to 2021 at a multisite academic center and had preoperative lab values within 3 months of surgery were included. Outcomes analyzed included 90-day readmissions, postoperative length of stay, and nonhome discharge. Four machine learning models-Extreme Gradient Boosted Trees, Balanced Random Forest, Elastic-Net Penalized Logistic Regression, and a Neural Network-were trained and evaluated through the Area Under the Curve estimates. Feature importance scores were computed for the highest-performing model per outcome through model-specific metrics.

RESULTS

A total of 1026 cases were included in the analysis cohort. All machine learning models were predictive for outcomes of interest, with the Random Forest algorithm consistently demonstrating the strongest average area under the curve performance, with a peak performance of 0.84 for nonhome discharge. Important features varied per outcome, though age, body mass index, American Society of Anesthesiologists classification >2, and medical comorbidities were highly weighted in the studied outcomes.

CONCLUSIONS

Machine learning models were successfully applied and predictive of postoperative health utilization after ACDF. Deployment of these tools can assist clinicians in determining high-risk patients.

LEVEL OF EVIDENCE

III.

Predictive factors for degenerative lumbar spinal stenosis: a model obtained from a machine learning algorithm technique

BACKGROUND

Degenerative lumbar spinal stenosis (DLSS) is the most common spine disease in the elderly population. It is usually associated with lumbar spine joints/or ligaments degeneration. Machine learning technique is an exclusive method for handling big data analysis; however, the development of this method for spine pathology is rare. This study aims to detect the essential variables that predict the development of symptomatic DLSS using the random forest of machine learning (ML) algorithms technique.

METHODS

A retrospective study with two groups of individuals. The first included 165 with symptomatic DLSS (sex ratio 80 M/85F), and the second included 180 individuals from the general population (sex ratio: 90 M/90F) without lumbar spinal stenosis symptoms. Lumbar spine measurements such as vertebral or spinal canal diameters from L1 to S1 were conducted on computerized tomography (CT) images. Demographic and health data of all the participants (e.g., body mass index and diabetes mellitus) were also recorded.

RESULTS

The decision tree model of ML demonstrate that the anteroposterior diameter of the bony canal at L5 (males) and L4 (females) levels have the greatest stimulus for symptomatic DLSS (scores of 1 and 0.938). In addition, combination of these variables with other lumbar spine features is mandatory for developing the DLSS.

CONCLUSIONS

Our results indicate that combination of lumbar spine characteristics such as bony canal and vertebral body dimensions rather than the presence of a sole variable is highly associated with symptomatic DLSS onset.

Artificial Intelligence for Neurosurgery : Current State and Future Directions

Artificial intelligence (AI) is a field of computer science that equips machines with human-like intelligence and enables them to learn, reason, and solve problems when presented with data in various formats. Neurosurgery is often at the forefront of innovative and disruptive technologies, which have similarly altered the course of acute and chronic diseases. In diagnostic imaging, such as X-rays, computed tomography, and magnetic resonance imaging, AI is used to analyze images. The use of robots in the field of neurosurgery is also increasing. In neurointensive care units, AI is used to analyze data and provide care to critically ill patients. Moreover, AI can be used to predict a patient's prognosis. Several AI applications have already been introduced in the field of neurosurgery, and many more are expected in the near future. Ultimately, it is our responsibility to keep pace with this evolution to provide meaningful outcomes and personalize each patient's care. Rather than blindly relying on AI in the future, neurosurgeons should gain a thorough understanding of it and use it to enhance their patient care.

Current Applications of Machine Learning in Spine: From Clinical View

STUDY DESIGN

Narrative review.

OBJECTIVES

This review aims to present current applications of machine learning (ML) in spine domain to clinicians.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text.

RESULTS

Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost.

CONCLUSIONS

ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

Machine learning predicts improvement of functional outcomes in traumatic brain injury patients after inpatient rehabilitation

Survivors of traumatic brain injury (TBI) have an unpredictable clinical course. This unpredictability makes clinical resource allocation for clinicians and anticipatory guidance for patients difficult. Historically, experienced clinicians and traditional statistical models have insufficiently considered all available clinical information to predict functional outcomes for a TBI patient. Here, we harness artificial intelligence and apply machine learning and statistical models to predict the Functional Independence Measure (FIM) scores after rehabilitation for traumatic brain injury (TBI) patients. Tree-based algorithmic analysis of 629 TBI patients admitted to a large acute rehabilitation facility showed statistically significant improvement in motor and cognitive FIM scores at discharge.

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.

Development of a machine-learning based model for predicting multidimensional outcome after surgery for degenerative disorders of the spine

BACKGROUND

It is clear that individual outcomes of spine surgery can be quite heterogeneous. When consenting a patient for surgery, it is important to be able to offer an individualized prediction regarding the likely outcome. This study used a comprehensive set of data collected over 12 years in an in-house registry to develop a parsimonious model to predict the multidimensional outcome of patients undergoing surgery for degenerative pathologies of the thoracic, lumbar or cervical spine.

METHODS

Data from 8374 patients (mean age 63.9 (14.9-96.3) y, 53.4% female) were used to develop a model to predict the 12-month scores for the Core Outcome Measures Index (COMI) and its subdomain scores. The data were split 80:20 into a training and test set. The top predictors were selected by applying recursive feature elimination based on LASSO cross validation models. Based on the 111 top predictors (contained within 20 variables), Ridge cross validation models were trained, validated, and tested for each of 9 outcome domains, for patients with either "Back" (thoracic/lumbar spine) or "Neck" (cervical spine) problems (total 18 models).

RESULTS

Among the strongest outcome predictors in most models were: preoperative scores for almost all COMI items (especially axial pain (back or neck) and peripheral pain (leg/buttock or arm/shoulder)), catastrophizing, fear avoidance beliefs, comorbidity, age, BMI, nationality, previous spine surgery, type and spinal level of intervention, number of affected levels, and surgeon seniority. The R² of the models on the validation/test sets averaged 0.16/0.13. A preliminary online tool was programmed to present the predicted outcomes for individual patients, based on their presenting characteristics. https://linkup.kws.ch/prognostictool .

CONCLUSION

The models provided estimates to enable a bespoke prediction of the outcome of surgery for individual patients with varying degenerative pathologies and baseline characteristics. The models form the basis of a simple, freely-available online prognostic tool developed to improve access to and usability of prognostic information in clinical practice. It is hoped that, following confirmation of its validity and practical utility, the tool will ultimately serve to facilitate decision-making and the management of patients' expectations.

Performance of Artificial Intelligence-Based Algorithms to Predict Prolonged Length of Stay after Lumbar Decompression Surgery

Background: Decompression of the lumbar spine is one of the most common procedures performed in spine surgery. Hospital length of stay (LOS) is a clinically relevant metric used to assess surgical success, patient outcomes, and socioeconomic impact. This study aimed to investigate a variety of machine learning and deep learning algorithms to reliably predict whether a patient undergoing decompression of lumbar spinal stenosis will experience a prolonged LOS. Methods: Patients undergoing treatment for lumbar spinal stenosis with microsurgical and full-endoscopic decompression were selected within this retrospective monocentric cohort study. Prolonged LOS was defined as an LOS greater than or equal to the 75th percentile of the cohort (normal versus prolonged stay; binary classification task). Unsupervised learning with K-means clustering was used to find clusters in the data. Hospital stay classes were predicted with logistic regression, RandomForest classifier, stochastic gradient descent (SGD) classifier, K-nearest neighbors, Decision Tree classifier, Gaussian Naive Bayes (GaussianNB), support vector machines (SVM), a custom-made convolutional neural network (CNN), multilayer perceptron artificial neural network (MLP), and radial basis function neural network (RBNN) in Python. Prediction accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors. Further, we developed a decision tree based on the Chi-square automatic interaction detection (CHAID) algorithm to investigate cut-offs of predictors for clinical decision-making. Results: 236 patients and 14 feature variables were included. K-means clustering separated data into two clusters distinguishing the data into two patient risk characteristic groups. The algorithms reached AUCs between 67.5% and 87.3% for the classification of LOS classes. Feature importance analysis of deep learning algorithms indicated that operation time was the most important feature in predicting LOS. A decision tree based on CHAID could predict 84.7% of the cases. Conclusions: Machine learning and deep learning algorithms can predict whether patients will experience an increased LOS following lumbar decompression surgery. Therefore, medical resources can be more appropriately allocated to patients who are at risk of prolonged LOS.

Machine Learning Algorithms Predict Achievement of Clinically Significant Outcomes After Orthopaedic Surgery: A Systematic Review

PURPOSE

To determine what subspecialties have applied machine learning (ML) to predict clinically significant outcomes (CSOs) within orthopaedic surgery and to determine whether the performance of these models was acceptable through assessing discrimination and other ML metrics where reported.

METHODS

The PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases were queried for articles that used ML to predict achievement of the minimal clinically important difference (MCID), patient acceptable symptomatic state (PASS), or substantial clinical benefit (SCB) after orthopaedic surgical procedures. Data pertaining to demographic characteristics, subspecialty, specific ML algorithms, and algorithm performance were analyzed.

RESULTS

Eighteen articles met the inclusion criteria. Seventeen studies developed novel algorithms, whereas one study externally validated an established algorithm. All studies used ML to predict MCID achievement, whereas 3 (16.7%) predicted SCB achievement and none predicted PASS achievement. Of the studies, 7 (38.9%) concerned outcomes after spine surgery; 6 (33.3%), after sports medicine surgery; 3 (16.7%), after total joint arthroplasty (TJA); and 2 (11.1%), after shoulder arthroplasty. No studies were found regarding trauma, hand, elbow, pediatric, or foot and ankle surgery. In spine surgery, concordance statistics (C-statistics) ranged from 0.65 to 0.92; in hip arthroscopy, 0.51 to 0.94; in TJA, 0.63 to 0.89; and in shoulder arthroplasty, 0.70 to 0.95. Most studies reported C-statistics at the upper end of these ranges, although populations were heterogeneous.

CONCLUSIONS

Currently available ML algorithms can discriminate the propensity to achieve CSOs using the MCID after spine, TJA, sports medicine, and shoulder surgery with a fair to good performance as evidenced by C-statistics ranging from 0.6 to 0.95 in most analyses. Less evidence is available on the ability of ML to predict achievement of SCB, and no evidence is available for achievement of the PASS. Such algorithms may augment shared decision-making practices and allow clinicians to provide more appropriate patient expectations using individualized risk assessments. However, these studies remain limited by variable reporting of performance metrics, CSO quantification methods, and adherence to predictive modeling guidelines, as well as limited external validation.

LEVEL OF EVIDENCE

Level III, systematic review of Level III studies.

Feasibility and Assessment of a Machine Learning-Based Predictive Model of Outcome After Lumbar Decompression Surgery

STUDY DESIGN

Retrospective study at a unique center.

OBJECTIVE

The aim of this study is twofold, to develop a virtual patients model for lumbar decompression surgery and to evaluate the precision of an artificial neural network (ANN) model designed to accurately predict the clinical outcomes of lumbar decompression surgery.

METHODS

We performed a retrospective study of complete Electronic Health Records (EHR) to identify potential unfavorable criteria for spine surgery (predictors). A cohort of synthetics EHR was created to classify patients by surgical success (green zone) or partial failure (orange zone) using an Artificial Neural Network which screens all the available predictors.

RESULTS

In the actual cohort, we included 60 patients, with complete EHR allowing efficient analysis, 26 patients were in the orange zone (43.4%) and 34 were in the green zone (56.6%). The average positive criteria amount for actual patients was 8.62 for the green zone (SD+/- 3.09) and 10.92 for the orange zone (SD 3.38). The classifier (a neural network) was trained using 10,000 virtual patients and 2000 virtual patients were used for test purposes. The 12,000 virtual patients were generated from the 60 EHR, of which half were in the green zone and half in the orange zone. The model showed an accuracy of 72% and a ROC score of 0.78. The sensitivity was 0.885 and the specificity 0.59.

CONCLUSION

Our method can be used to predict a favorable patient to have lumbar decompression surgery. However, there is still a need to further develop its ability to analyze patients in the "failure of treatment" zone to offer precise management of patient health before spinal surgery.

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 State of Machine Learning in Spine Surgery: A Systematic Review

STUDY DESIGN

This was a systematic review of existing literature.

OBJECTIVE

The objective of this study was to evaluate the current state-of-the-art trends and utilization of machine learning in the field of spine surgery.

SUMMARY OF BACKGROUND DATA

The past decade has seen a rise in the clinical use of machine learning in many fields including diagnostic radiology and oncology. While studies have been performed that specifically pertain to spinal surgery, there have been relatively few aggregate reviews of the existing scientific literature as applied to clinical spine surgery.

METHODS

This study utilized Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to review the scientific literature from 2009 to 2019 with syntax specific for machine learning and spine surgery applications. Specific data was extracted from the available literature including algorithm application, algorithms tested, database type and size, algorithm training method, and outcome of interest.

RESULTS

A total of 44 studies met inclusion criteria, of which the majority were level III evidence. Studies were grouped into 4 general types: diagnostic tools, clinical outcome prediction, surgical assessment tools, and decision support tools. Across studies, a wide swath of algorithms were used, which were trained across multiple disparate databases. There were no studies identified that assessed the ethical implementation or patient perceptions of machine learning in clinical care.

CONCLUSIONS

The results reveal the broad range of clinical applications and methods used to create machine learning algorithms for use in the field of spine surgery. Notable disparities exist in algorithm choice, database characteristics, and training methods. Ongoing research is needed to make machine learning operational on a large scale.

Predicting Clinically Relevant Patient-Reported Symptom Improvement After Carpal Tunnel Release: A Machine Learning Approach

BACKGROUND

Symptom improvement is an important goal when considering surgery for carpal tunnel syndrome. There is currently no prediction model available to predict symptom improvement for patients considering a carpal tunnel release (CTR).

OBJECTIVE

To predict using a model the probability of clinically relevant symptom improvement at 6 mo after CTR.

METHODS

We split a cohort of 2119 patients who underwent a mini-open CTR and completed the Boston Carpal Tunnel Questionnaire preoperatively and 6 mo postoperatively into training (75%) and validation (25%) data sets. Patients who improved more than the minimal clinically important difference of 0.8 at the Boston Carpal Tunnel Questionnaire-symptom severity scale were classified as "improved." Logistic regression, random forests, and gradient boosting machines were considered to train prediction models. The best model was selected based on discriminative ability (area under the curve) and calibration in the validation data set. This model was further assessed in a holdout data set (N = 397).

RESULTS

A gradient boosting machine with 5 predictors was chosen as optimal trade-off between discriminative ability and the number of predictors. In the holdout data set, this model had an area under the curve of 0.723, good calibration, sensitivity of 0.77, and specificity of 0.55. The positive predictive value was 0.50, and the negative predictive value was 0.81.

CONCLUSION

We developed a prediction model for clinically relevant symptom improvement 6 mo after a CTR, which required 5 patient-reported predictors (18 questions) and has reasonable discriminative ability and good calibration. The model is available online and might help shared decision making when patients are considering a CTR.

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 in Pituitary Surgery

Machine learning applications in neurosurgery are increasingly reported for diverse tasks such as faster and more accurate preoperative diagnosis, enhanced lesion characterization, as well as surgical outcome, complications and healthcare cost prediction. Even though the pertinent literature in pituitary surgery is less extensive with respect to other neurosurgical diseases, past research attempted to answer clinically relevant questions to better assist surgeons and clinicians. In the present chapter we review reported ML applications in pituitary surgery including differential diagnosis, preoperative lesion characterization (immunohistochemistry, cavernous sinus invasion, tumor consistency), surgical outcome and complication predictions (gross total resection, tumor recurrence, and endocrinological remission, cerebrospinal fluid leak, postoperative hyponatremia). Moreover, we briefly discuss from a practical standpoint the current barriers to clinical translation of machine learning research. On the topic of pituitary surgery, published reports can be considered mostly preliminary, requiring larger training populations and strong external validation. Thoughtful selection of clinically relevant outcomes of interest and transversal application of model development pipeline-together with accurate methodological planning and multicenter collaborations-have the potential to overcome current limitations and ultimately provide additional tools for more informed patient management.

Machine Learning and Intracranial Aneurysms: From Detection to Outcome Prediction

Machine learning (ML) is a rapidly rising research tool in biomedical sciences whose applications include segmentation, classification, disease detection, and outcome prediction. With respect to traditional statistical methods, ML algorithms have the potential to learn and improve their predictive performance when fed with large data sets without the need of being specifically programmed. In recent years, this technology has been increasingly applied for tackling clinical issues in intracranial aneurysm (IA) research. Several studies attempted to provide reliable models for enhanced aneurysm detection. Convolutional neural networks trained with variable degrees of human interaction on data from diverse imaging modalities showed high sensitivity in aneurysm detection tasks, also outperforming expert image analysis. Algorithms were also shown to differentiate ruptured from unruptured IAs, with however limited clinical relevance. For prediction of rupture and stability assessment, ML was preliminarily shown to achieve better performance compared to conventional statistical methods and existing risk scores. ML-based complication and functional outcome prediction in the event of SAH have been more extensively reported, in contrast with periprocedural outcome investigation in unruptured IA patients. ML has the potential to be a game changer in IA patient management. Currently clinical translation of experimental results is limited.

Prediction of outcome after spinal surgery-using The Dialogue Support based on the Swedish national quality register

PURPOSE

To evaluate the predictive precision of the Dialogue Support, a tool for additional help in shared decision-making before surgery of the degenerative spine.

METHODS

Data in Swespine (Swedish national quality registry) of patients operated between 2007 and 2019 found the development of prediction algorithms based on logistic regression analyses, where socio-demographic and baseline variables were included. The algorithms were tested in four diagnostic groups: lumbar disc herniation, lumbar spinal stenosis, degenerative disc disease and cervical radiculopathy. By random selection, 80% of the study population was used for the prediction of outcome and then tested against the actual outcome of the remaining 20%. Outcome measures were global assessment of pain (GA), and satisfaction with outcome.

RESULTS

Calibration plots demonstrated a high degree of concordance on a group level. On an individual level, ROC curves showed moderate predictive capacity with AUC (area under the curve) values 0.67-0.68 for global assessment and 0.6-0.67 for satisfaction.

CONCLUSION

The Dialogue Support can serve as an aid to both patient and surgeon when discussing and deciding on surgical treatment of degenerative conditions in the lumbar and cervical spine.

LEVEL OF EVIDENCE

I.

Improving patient flow during infectious disease outbreaks using machine learning for real-time prediction of patient readiness for discharge

BACKGROUND

Delays in patient flow and a shortage of hospital beds are commonplace in hospitals during periods of increased infection incidence, such as seasonal influenza and the COVID-19 pandemic. The objective of this study was to develop and evaluate the efficacy of machine learning methods at identifying and ranking the real-time readiness of individual patients for discharge, with the goal of improving patient flow within hospitals during periods of crisis.

METHODS AND PERFORMANCE

Electronic Health Record data from Oxford University Hospitals was used to train independent models to classify and rank patients' real-time readiness for discharge within 24 hours, for patient subsets according to the nature of their admission (planned or emergency) and the number of days elapsed since their admission. A strategy for the use of the models' inference is proposed, by which the model makes predictions for all patients in hospital and ranks them in order of likelihood of discharge within the following 24 hours. The 20% of patients with the highest ranking are considered as candidates for discharge and would therefore expect to have a further screening by a clinician to confirm whether they are ready for discharge or not. Performance was evaluated in terms of positive predictive value (PPV), i.e., the proportion of these patients who would have been correctly deemed as 'ready for discharge' after having the second screening by a clinician. Performance was high for patients on their first day of admission (PPV = 0.96/0.94 for planned/emergency patients respectively) but dropped for patients further into a longer admission (PPV = 0.66/0.71 for planned/emergency patients still in hospital after 7 days).

CONCLUSION

We demonstrate the efficacy of machine learning methods at making operationally focused, next-day discharge readiness predictions for all individual patients in hospital at any given moment and propose a strategy for their use within a decision-support tool during crisis periods.

Person centred care provision and care planning in chronic kidney disease: which outcomes matter? A systematic review and thematic synthesis of qualitative studies : Care planning in CKD: which outcomes matter?

RATIONALE & OBJECTIVE

Explore priorities related to outcomes and barriers of adults with chronic kidney disease (CKD) regarding person centred care and care planning.

STUDY DESIGN

Systematic review of qualitative studies.

SEARCH STRATEGY & SOURCES

In July 2018 six bibliographic databases, and reference lists of included articles were searched for qualitative studies that included adults with CKD stages 1-5, not on dialysis or conservative management, without a previous kidney transplantation.

ANALYTICAL APPROACH

Three independent reviewers extracted and inductively coded data using thematic synthesis. Reporting quality was assessed using the COREQ and the review reported according to PRISMA and ENTREQ statements.

RESULTS

Forty-six studies involving 1493 participants were eligible. The period after diagnosis of CKD is characterized by feelings of uncertainty, social isolation, financial burden, resentment and fear of the unknown. Patients show interest in ways to return to normality and remain in control of their health in order to avoid further deterioration of kidney function. However, necessary information is often unavailable or incomprehensible. Although patients and healthcare professionals share the predominant interest of whether or not dialysis or transplantation is necessary, patients value many more outcomes that are often unrecognized by their healthcare professionals. We identified 4 themes with 6 subthemes that summarize these findings: 'pursuing normality and control' ('pursuing normality'; 'a search for knowledge'); 'prioritizing outcomes' ('reaching kidney failure'; 'experienced health'; 'social life'; 'work and economic productivity'); 'predicting the future'; and 'realising what matters'. Reporting quality was moderate for most included studies.

LIMITATIONS

Exclusion of non-English articles.

CONCLUSIONS

The realisation that patients' priorities do not match those of the healthcare professionals, in combination with the prognostic ambiguity, confirms fatalistic perceptions of not being in control when living with CKD. These insights may contribute to greater understanding of patients' perspectives and a more person-centred approach in healthcare prioritization and care planning within CKD care.

Machine learning-based prediction of outcomes of the endoscopic endonasal approach in Cushing disease: is the future coming?

OBJECTIVE

Machine learning (ML) is an innovative method to analyze large and complex data sets. The aim of this study was to evaluate the use of ML to identify predictors of early postsurgical and long-term outcomes in patients treated for Cushing disease (CD).

METHODS

All consecutive patients in our center who underwent surgery for CD through the endoscopic endonasal approach were retrospectively reviewed. Study endpoints were gross-tumor removal (GTR), postsurgical remission, and long-term control of disease. Several demographic, radiological, and histological factors were assessed as potential predictors. For ML-based modeling, data were randomly divided into 2 sets with an 80% to 20% ratio for bootstrapped training and testing, respectively. Several algorithms were tested and tuned for the area under the curve (AUC).

RESULTS

The study included 151 patients. GTR was achieved in 137 patients (91%), and postsurgical hypersecretion remission was achieved in 133 patients (88%). At last follow-up, 116 patients (77%) were still in remission after surgery and in 21 patients (14%), CD was controlled with complementary treatment (overall, of 131 cases, 87% were under control at follow-up). At internal validation, the endpoints were predicted with AUCs of 0.81-1.00, accuracy of 81%-100%, and Brier scores of 0.035-0.151. Tumor size and invasiveness and histological confirmation of adrenocorticotropic hormone (ACTH)-secreting cells were the main predictors for the 3 endpoints of interest.

CONCLUSIONS

ML algorithms were used to train and internally validate robust models for all the endpoints, giving accurate outcome predictions in CD cases. This analytical method seems promising for potentially improving future patient care and counseling; however, careful clinical interpretation of the results remains necessary before any clinical adoption of ML. Moreover, further studies and increased sample sizes are definitely required before the widespread adoption of ML to the study of CD.

Prediction Models in Degenerative Spine Surgery: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

To review the existing literature of prediction models in degenerative spinal surgery.

METHODS

Review of PubMed/Medline and Embase databases was conducted to identify articles between January 1, 2000 and March 1, 2020 that reported prediction model performance for outcomes following elective degenerative spine surgery.

RESULTS

Thirty-one articles were included. Twenty studies were of thoracolumbar, 5 were of cervical, and 6 included all spine patients. Five studies were externally validated. Prediction models were developed using machine learning (42%) and logistic regression (42%) as well as other techniques. Web-based calculators were included in 45% of published articles. Various outcomes were investigated, including complications, infection, length of stay, discharge disposition, reoperation, readmission, disability score, back pain, leg pain, return to work, and opioid dependence.

CONCLUSIONS

Significant heterogeneity exists in methods used to develop prediction models of postoperative outcomes after degenerative spine surgery. Most internally validate their scores, but a few have been externally validated. Areas under the curve for most models range from 0.6 to 0.9. Techniques for development are becoming increasingly sophisticated with different machine learning tools. With further external validation, these models can be deployed online for patient, physician, and administrative use, and have the potential to optimize outcomes and maximize value in spine surgery.

Utility of prediction model score: a proposed tool to standardize the performance and generalizability of clinical predictive models based on systematic review

OBJECTIVE

The objective of this study was to evaluate the characteristics and performance of current prediction models in the fields of spine metastasis and degenerative spine disease to create a scoring system that allows direct comparison of the prediction models.

METHODS

A systematic search of PubMed and Embase was performed to identify relevant studies that included either the proposal of a prediction model or an external validation of a previously proposed prediction model with 1-year outcomes. Characteristics of the original study and discriminative performance of external validations were then assigned points based on thresholds from the overall cohort.

RESULTS

Nine prediction models were included in the spine metastasis category, while 6 prediction models were included in the degenerative spine category. After assigning the proposed utility of prediction model score to the spine metastasis prediction models, only 1 reached the grade of excellent, while 2 were graded as good, 3 as fair, and 3 as poor. Of the 6 included degenerative spine models, 1 reached the excellent grade, while 3 studies were graded as good, 1 as fair, and 1 as poor.

CONCLUSIONS

As interest in utilizing predictive analytics in spine surgery increases, there is a concomitant increase in the number of published prediction models that differ in methodology and performance. Prior to applying these models to patient care, these models must be evaluated. To begin addressing this issue, the authors proposed a grading system that compares these models based on various metrics related to their original design as well as internal and external validation. Ultimately, this may hopefully aid clinicians in determining the relative validity and usability of a given model.

Assessment of Clinical Decision Support System Efficiency in Spinal Neurosurgery for Personalized Minimally Invasive Technologies Used on Lumbar Spine

The aim of the study was to assess clinical decision support system (CDSS) in spinal surgery for personalized minimally invasive technologies on lumbar spine.

Materials and Methods

The prospective study involved 59 patients operated on using CDSS based on a personalized surgical algorithm considering patient-specific parameters of lumbar segments. Among them, 11 patients underwent total disk replacement (TDR), 25 and 23 patients had minimally invasive (MI-TLIF) and open (O-TLIF) dorsal rigid stabilization, respectively, according to an original technology. The comparative analysis was carried out using retrospective findings of 196 patients operated on involving TDR (n=42), MI-TLIF (n=79), and O-TLIF (n=75). The efficiency of CDSS medical algorithms was assessed by pain syndrome in the lumbar spine and lower limbs, as well as by patients' functional status on discharge according to ODI, 3 and 6 months after the operation.

Results

The comparison by gender characteristics and anthropometric data revealed no significant intergroup differences among the groups under study (p>0.05). Intergroup analysis of functional status by ODI, pain intensity in lower limbs and lumbar spine showed better clinical outcomes in patients operated using CDSS compared to a retrospective group (p<0.05): 6 months after TDR and O-TLIF, and 3 months after MI-TLIF.

Conclusion

The study findings demonstrated high efficiency of CDSS developed for personalized surgical treatment of patients with degenerative lumbar spine diseases taking into consideration individual biometric parameters of lumbar segments.

Predicting recovery after lumbar spinal stenosis surgery: A protocol for a historical cohort study using data from the Canadian Spine Outcomes Research Network (CSORN)

Background: Symptomatic lumbar spinal stenosis (SLSS) is a condition in which narrowing of the spinal canal results in entrapment and compression of neurovascular structures. Decompressive surgery, with or without spinal fusion, is recommended for those with severe symptoms for whom conservative management has failed. However, significant persistent pain, functional limitations, and narcotic use can affect up to one third of patients postsurgery. Aims: The aim of this study will be to identify predictors of outcomes 1-year post SLSS surgery with a focus on modifiable predictors. Methods: The Canadian Spine Outcomes Research Network (CSORN) is a large database of prospectively collected data on pre- and postsurgical outcomes among surgical patients. We include participants with a primary diagnosis of SLSS undergoing their first spine surgery. Outcomes are measured at 12 months after surgery and include back and leg pain, disability (Oswestry Disability Index, ODI), walking capacity (ODI item 4), health-related quality of life, and an overall recovery composite outcome (clinically important changes in pain, disability, and quality of life). Predictors include demographics (education level, work status, marital status, age, sex, body mass index), physical activity level, smoking status, previous conservative treatments, medication intake, depression, patient expectations, and other comorbidities. A multivariate partial least squares model is used to identify predictors of outcomes. Conclusion: Study results will inform targeted SLSS interventions, either for the selection of best candidates for surgery or the identification of targets for presurgical rehabilitation programs.

Machine learning in neurosurgery: a global survey

Background

Recent technological advances have led to the development and implementation of machine learning (ML) in various disciplines, including neurosurgery. Our goal was to conduct a comprehensive survey of neurosurgeons to assess the acceptance of and attitudes toward ML in neurosurgical practice and to identify factors associated with its use.

Methods

The online survey consisted of nine or ten mandatory questions and was distributed in February and March 2019 through the European Association of Neurosurgical Societies (EANS) and the Congress of Neurosurgeons (CNS).

Results

Out of 7280 neurosurgeons who received the survey, we received 362 responses, with a response rate of 5%, mainly in Europe and North America. In total, 103 neurosurgeons (28.5%) reported using ML in their clinical practice, and 31.1% in research. Adoption rates of ML were relatively evenly distributed, with 25.6% for North America, 30.9% for Europe, 33.3% for Latin America and the Middle East, 44.4% for Asia and Pacific and 100% for Africa with only two responses. No predictors of clinical ML use were identified, although academic settings and subspecialties neuro-oncology, functional, trauma and epilepsy predicted use of ML in research. The most common applications were for predicting outcomes and complications, as well as interpretation of imaging.

Conclusions

This report provides a global overview of the neurosurgical applications of ML. A relevant proportion of the surveyed neurosurgeons reported clinical experience with ML algorithms. Future studies should aim to clarify the role and potential benefits of ML in neurosurgery and to reconcile these potential advantages with bioethical considerations.