Filter

Refine by Publication

Refine by Date

—

Refine by Access

By Author

  • Print
  • Save

Browse

You are looking at 31 - 40 of 39,168 items for

  • Refine by Access: all x
Clear All
Restricted access

Outcomes and reoperation rates of adult spinal deformity patients with baseline sagittal malalignment based on the cranial axis to the hip at 2 years postoperatively

Sarthak Mohanty, Christopher Lai, Christopher Mikhail, Gabriella Greisberg, Fthimnir M. Hassan, Stephen R. Stephan, Zeeshan M. Sardar, Ronald A. Lehman Jr., and Lawrence G. Lenke

OBJECTIVE

The aim of this study was to discern whether patients with a cranial sagittal vertical axis to the hip (CrSVA-H) > 2 cm at 2 years postoperatively exhibit significantly worse patient-reported outcomes (PROs) and clinical outcomes compared with patients with CrSVA-H < 2 cm.

METHODS

This was a retrospective, 1:1 propensity score–matched (PSM) study of patients who underwent posterior spinal fusion for adult spinal deformity. All patients had a baseline sagittal imbalance of CrSVA-H > 30 mm. Two-year patient-reported and clinical outcomes were assessed in unmatched and PSM cohorts, including Scoliosis Research Society–22r (SRS-22r) and Oswestry Disability Index scores as well as reoperation rates. The study compared two cohorts based on 2-year alignment: CrSVA-H < 20 mm (aligned cohort) vs CrSVA-H > 20 mm (malaligned cohort). For the matched cohorts, binary outcome comparisons were carried out using the McNemar test, while continuous outcomes used the Wilcoxon rank-sum test. For unmatched cohorts, categorical variables were compared using chi-square/Fisher’s tests, while continuous outcomes were compared using Welch’s t-test.

RESULTS

A total of 156 patients with mean age of 63.7 (SEM 1.09) years underwent posterior spinal fusion spanning a mean of 13.5 (0.32) levels. At baseline, the mean pelvic incidence minus lumbar lordosis mismatch was 19.1° (2.01°), the T1 pelvic angle was 26.6° (1.20°), and the CrSVA-H was 74.9 (4.33) mm. The mean CrSVA-H improved from 74.9 mm to 29.2 mm (p < 0.0001). At the 2-year follow-up, 129 (78%) of 164 patients achieved CrSVA-H < 2 cm (aligned cohort). Patients who had CrSVA-H > 2 cm (malaligned cohort) at the 2-year follow-up had worse preoperative CrSVA-H (p < 0.0001). After performing PSM, 27 matched pairs were generated. In the PSM cohort, the aligned and malaligned cohorts demonstrated comparable preoperative patient-reported outcomes (PROs). However, at the 2-year postoperative follow-up, the malaligned cohort reported worse outcomes in SRS-22r function (p = 0.0275), pain (p = 0.0012), and mean total score (p = 0.0109). Moreover, when patients were stratified based on their magnitude of improvement in CrSVA-H (< 50% vs > 50%), patients with > 50% improvement in CrSVA-H had superior outcomes in SRS-22r function (p = 0.0336), pain (p = 0.0446), and mean total score (p = 0.0416). Finally, patients in the malaligned cohort had a higher 2-year reoperation rate (22% vs 7%; p = 0.0412) compared with patients in the aligned cohort.

CONCLUSIONS

Among patients who present with forward sagittal imbalance (CrSVA-H > 30 mm), patients with CrSVA-H exceeding 20 mm at the 2-year postoperative follow-up have inferior PROs and higher reoperation rates.

In Journal of Neurosurgery: Spine Publish Before Print

Restricted access

Outcomes of endoscopic treatment for early correction of craniosynostosis in children: a 26-year single-center experience

Leonardo Domínguez, Claudio Rivas-Palacios, Mario M. Barbosa, Maria Andrea Escobar, Elvira Puello Florez, and Ezequiel García-Ballestas

OBJECTIVE

Surgery is the cornerstone of craniosynostosis treatment. In this study, two widely accepted techniques are described: endoscope-assisted surgery (EAS) and open surgery (OS). The authors compared the perioperative and reconstructive outcomes of EAS and OS in children ≤ 6 months of age treated at the Napoleón Franco Pareja Children’s Hospital (Cartagena, Colombia).

METHODS

According to the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) statement, patients with defined criteria who underwent surgery to correct craniosynostosis between June 1996 and June 2022 were retrospectively enrolled. Demographic data, perioperative outcomes, and follow-up were obtained from their medical records. Student t-tests were used for significance. Cronbach’s α was used to assess agreement between estimated blood loss (EBL). Spearman’s correlation coefficient and the coefficient of determination were used to establish associations between the results of interest, and the odds ratio was used to calculate the risk ratio of blood product transfusion.

RESULTS

A total of 74 patients met the inclusion criteria; 24 (32.4%) belonged to the OS group and 50 (67.6%) to the EAS group. There was a high interobserver agreement quantifying the EBL. The EBL, transfusion of blood products, surgical time, and hospital stay were shorter in the EAS group. Surgical time was positively correlated with EBL. There were no differences between the two groups in the percentage of cranial index correction at 12 months of follow-up.

CONCLUSIONS

Surgical correction of craniosynostosis in children aged ≤ 6 months by EAS was associated with a significant decrease in EBL, transfusion requirements, surgical time, and hospital stay compared with OS. The results of cranial deformity correction in patients with scaphocephaly and acrocephaly were equivalent in both study groups.

In Journal of Neurosurgery: Pediatrics Publish Before Print

Restricted access

Radiation doses and accuracy of navigated pedicle screw placement in cervical and thoracic spine surgery: a comparison of sliding gantry CT and mobile cone-beam CT in a homogeneous cohort

Lea Baumgart, Sebastian Ille, Jan S. Kirschke, Bernhard Meyer, and Sandro M. Krieg

OBJECTIVE

Multiple solutions for navigation-guided pedicle screw placement are currently available. Intraoperative imaging techniques are invaluable for spinal surgery, but often there is little attention paid to patient radiation exposure. This study aimed to compare the applied radiation doses of sliding gantry CT (SGCT)– and mobile cone-beam CT (CBCT)–based pedicle screw placement for spinal instrumentation.

METHODS

The authors retrospectively analyzed 183 and 54 patients who underwent SGCT- or standard CBCT-based pedicle screw placement, respectively, for spinal instrumentation at their department between June 2019 and January 2020. SGCT uses an automated radiation dose adjustment.

RESULTS

Baseline characteristics, including the number of screws per patient and the number of instrumented levels, did not significantly differ between the two groups. Although the accuracy of screw placement according to Gertzbein-Robbins classification did not differ between the two groups, more screws had to be revised intraoperatively in the CBCT group (SGCT 2.7% vs CBCT 6.0%, p = 0.0036). Mean (± SD) radiation doses for the first (SGCT 484.0 ± 201.1 vs CBCT 687.4 ± 188.5 mGy*cm, p < 0.0001), second (SGCT 515.8 ± 216.3 vs CBCT 658.3 ± 220.1 mGy*cm, p < 0.0001), third (SGCT 531.3 ± 237.5 vs CBCT 641.6 ± 177.3 mGy*cm, p = 0.0140), and total (SGCT 1216.9 ± 699.3 vs CBCT 2000.3 ± 921.0 mGy*cm, p < 0.0001) scans were significantly lower for SGCT. This was also true for radiation doses per scanned level (SGCT 461.9 ± 429.3 vs CBCT 1004.1 ± 905.1 mGy*cm, p < 0.0001) and radiation doses per screw (SGCT 172.6 ± 110.1 vs CBCT 349.6 ± 273.4 mGy*cm, p < 0.0001).

CONCLUSIONS

The applied radiation doses were significantly lower using SGCT for navigated pedicle screw placement in spinal instrumentation. A modern CT scanner on a sliding gantry leads to lower radiation doses, especially through automated 3D radiation dose adjustment.

In Journal of Neurosurgery: Spine Publish Before Print

Restricted access

Real-world benefit of intracranial pressure monitoring in the management of severe traumatic brain injury: a propensity score matching analysis using a nationwide inpatient database

Keita Shibahashi, Hiroyuki Ohbe, Hiroki Matsui, and Hideo Yasunaga

OBJECTIVE

Intracranial pressure (ICP) monitoring is recommended for the management of severe traumatic brain injury (TBI). The clinical benefit of ICP monitoring remains controversial, however, with randomized controlled trials showing negative results. Therefore, this study investigated the real-world impact of ICP monitoring in managing severe TBI.

METHODS

This observational study used the Japanese Diagnosis Procedure Combination inpatient database, a nationwide inpatient database, from July 1, 2010, to March 31, 2020. The study included patients aged 18 years or older who were admitted to an intensive care or high-dependency unit with a diagnosis of severe TBI. Patients who did not survive or were discharged on admission day were excluded. Between-hospital differences in ICP monitoring were quantified using the median odds ratio (MOR). A one-to-one propensity score matching (PSM) analysis was conducted to compare patients who initiated ICP monitoring on the admission day with those who did not. Outcomes in the matched cohort were compared using mixed-effects linear regression analysis. Linear regression analysis was used to estimate interactions between ICP monitoring and the subgroups.

RESULTS

The analysis included 31,660 eligible patients from 765 hospitals. There was considerable variability in the use of ICP monitoring across hospitals (MOR 6.3, 95% confidence interval [CI] 5.7–7.1), with ICP monitoring used in 2165 patients (6.8%). PSM resulted in 1907 matched pairs with highly balanced covariates. ICP monitoring was associated with significantly lower in-hospital mortality (31.9% vs 39.1%, within-hospital difference −7.2%, 95% CI −10.3% to −4.2%) and longer length of hospital stay (median 35 vs 28 days, within-hospital difference 6.5 days, 95% CI 2.6–10.3). There was no significant difference in the proportion of patients with unfavorable outcomes (Barthel index < 60 or death) at discharge (80.3% vs 77.8%, within-hospital difference 2.1%, 95% CI −0.6% to 5.0%). Subgroup analyses demonstrated a quantitative interaction between ICP monitoring and the Japan Coma Scale (JCS) score for in-hospital mortality, with a greater risk reduction with higher JCS score (p = 0.033).

CONCLUSIONS

ICP monitoring was associated with lower in-hospital mortality in the real-world management of severe TBI. The results suggest that active ICP monitoring is associated with improved outcomes after TBI, while the indication for monitoring might be limited to the most severely ill patients.

In Journal of Neurosurgery Publish Before Print

Free access

Comparison of machine learning models to predict long-term outcomes after severe traumatic brain injury

Dooman Arefan, Matthew Pease, Shawn R. Eagle, David O. Okonkwo, and Shandong Wu

OBJECTIVE

An estimated 1.5 million people die every year worldwide from traumatic brain injury (TBI). Physicians are relatively poor at predicting long-term outcomes early in patients with severe TBI. Machine learning (ML) has shown promise at improving prediction models across a variety of neurological diseases. The authors sought to explore the following: 1) how various ML models performed compared to standard logistic regression techniques, and 2) if properly calibrated ML models could accurately predict outcomes up to 2 years posttrauma.

METHODS

A secondary analysis of a prospectively collected database of patients with severe TBI treated at a single level 1 trauma center between November 2002 and December 2018 was performed. Neurological outcomes were assessed at 3, 6, 12, and 24 months postinjury with the Glasgow Outcome Scale. The authors used ML models including support vector machine, neural network, decision tree, and naïve Bayes models to predict outcome across all 4 time points by using clinical information available on admission, and they compared performance to a logistic regression model. The authors attempted to predict unfavorable versus favorable outcomes (Glasgow Outcome Scale scores of 1–3 vs 4–5), as well as mortality. Models’ performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) with 95% confidence interval and balanced accuracy.

RESULTS

Of the 599 patients in the database, the authors included 501, 537, 469, and 395 at 3, 6, 12, and 24 months posttrauma. Across all time points, the AUCs ranged from 0.71 to 0.85 for mortality and from 0.62 to 0.82 for unfavorable outcomes with various modeling strategies. Decision tree models performed worse than all other modeling approaches for multiple time points regarding both unfavorable outcomes and mortality. There were no statistically significant differences between any other models. After proper calibration, the models had little variation (0.02–0.05) across various time points.

CONCLUSIONS

The ML models tested herein performed with equivalent success compared with logistic regression techniques for prognostication in TBI. The TBI prognostication models could predict outcomes beyond 6 months, out to 2 years postinjury.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery

Free access

Critically reading machine learning literature in neurosurgery: a reader’s guide and checklist for appraising prediction models

Sivaram Emani, Akshay Swaminathan, Ben Grobman, Julia B. Duvall, Ivan Lopez, Omar Arnaout, and Kevin T. Huang

OBJECTIVE

Machine learning (ML) has become an increasingly popular tool for use in neurosurgical research. The number of publications and interest in the field have recently seen significant expansion in both quantity and complexity. However, this also places a commensurate burden on the general neurosurgical readership to appraise this literature and decide if these algorithms can be effectively translated into practice. To this end, the authors sought to review the burgeoning neurosurgical ML literature and to develop a checklist to help readers critically review and digest this work.

METHODS

The authors performed a literature search of recent ML papers in the PubMed database with the terms "neurosurgery" AND "machine learning," with additional modifiers "trauma," "cancer," "pediatric," and "spine" also used to ensure a diverse selection of relevant papers within the field. Papers were reviewed for their ML methodology, including the formulation of the clinical problem, data acquisition, data preprocessing, model development, model validation, model performance, and model deployment.

RESULTS

The resulting checklist consists of 14 key questions for critically appraising ML models and development techniques; these are organized according to their timing along the standard ML workflow. In addition, the authors provide an overview of the ML development process, as well as a review of key terms, models, and concepts referenced in the literature.

CONCLUSIONS

ML is poised to become an increasingly important part of neurosurgical research and clinical care. The authors hope that dissemination of education on ML techniques will help neurosurgeons to critically review new research better and more effectively integrate this technology into their practices.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery

Free access

Developing nonlinear k-nearest neighbors classification algorithms to identify patients at high risk of increased length of hospital stay following spine surgery

Shane Shahrestani, Andrew K. Chan, Erica F. Bisson, Mohamad Bydon, Steven D. Glassman, Kevin T. Foley, Christopher I. Shaffrey, Eric A. Potts, Mark E. Shaffrey, Domagoj Coric, John J. Knightly, Paul Park, Michael Y. Wang, Kai-Ming Fu, Jonathan R. Slotkin, Anthony L. Asher, Michael S. Virk, Giorgos D. Michalopoulos, Jian Guan, Regis W. Haid, Nitin Agarwal, Dean Chou, and Praveen V. Mummaneni

OBJECTIVE

Spondylolisthesis is a common operative disease in the United States, but robust predictive models for patient outcomes remain limited. The development of models that accurately predict postoperative outcomes would be useful to help identify patients at risk of complicated postoperative courses and determine appropriate healthcare and resource utilization for patients. As such, the purpose of this study was to develop k-nearest neighbors (KNN) classification algorithms to identify patients at increased risk for extended hospital length of stay (LOS) following neurosurgical intervention for spondylolisthesis.

METHODS

The Quality Outcomes Database (QOD) spondylolisthesis data set was queried for patients receiving either decompression alone or decompression plus fusion for degenerative spondylolisthesis. Preoperative and perioperative variables were queried, and Mann-Whitney U-tests were performed to identify which variables would be included in the machine learning models. Two KNN models were implemented (k = 25) with a standard training set of 60%, validation set of 20%, and testing set of 20%, one with arthrodesis status (model 1) and the other without (model 2). Feature scaling was implemented during the preprocessing stage to standardize the independent features.

RESULTS

Of 608 enrolled patients, 544 met prespecified inclusion criteria. The mean age of all patients was 61.9 ± 12.1 years (± SD), and 309 (56.8%) patients were female. The model 1 KNN had an overall accuracy of 98.1%, sensitivity of 100%, specificity of 84.6%, positive predictive value (PPV) of 97.9%, and negative predictive value (NPV) of 100%. Additionally, a receiver operating characteristic (ROC) curve was plotted for model 1, showing an overall area under the curve (AUC) of 0.998. Model 2 had an overall accuracy of 99.1%, sensitivity of 100%, specificity of 92.3%, PPV of 99.0%, and NPV of 100%, with the same ROC AUC of 0.998.

CONCLUSIONS

Overall, these findings demonstrate that nonlinear KNN machine learning models have incredibly high predictive value for LOS. Important predictor variables include diabetes, osteoporosis, socioeconomic quartile, duration of surgery, estimated blood loss during surgery, patient educational status, American Society of Anesthesiologists grade, BMI, insurance status, smoking status, sex, and age. These models may be considered for external validation by spine surgeons to aid in patient selection and management, resource utilization, and preoperative surgical planning.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery

Free access

Evaluating a 3D deep learning pipeline for cerebral vessel and intracranial aneurysm segmentation from computed tomography angiography–digital subtraction angiography image pairs

Tatsat R. Patel, Aakash Patel, Sricharan S. Veeturi, Munjal Shah, Muhammad Waqas, Andre Monteiro, Ammad A. Baig, Nandor Pinter, Elad I. Levy, Adnan H. Siddiqui, and Vincent M. Tutino

OBJECTIVE

Computed tomography angiography (CTA) is the most widely used imaging modality for intracranial aneurysm (IA) management, yet it remains inferior to digital subtraction angiography (DSA) for IA detection, particularly of small IAs in the cavernous carotid region. The authors evaluated a deep learning pipeline for segmentation of vessels and IAs from CTA using coregistered, segmented DSA images as ground truth.

METHODS

Using 50 paired CTA-DSA images, the authors trained (n = 27), validated (n = 3), and tested (n = 20) a deep learning model (3D DeepMedic) for cerebrovasculature segmentation from CTA. A landmark-based coregistration algorithm was used for registration and upsampling of CTA images to paired DSA images. Segmented vessels from the DSA were used as the ground truth. Accuracy of the model for vessel segmentation was evaluated using conventional metrics (dice similarity coefficient [DSC]) and vessel segmentation–specific metrics, like connectivity-area-length (CAL). On the test cases (20 IAs), 3 expert raters attempted to detect and segment IAs. For each rater, the authors recorded the rate of IA detection, and for detected IAs, raters segmented and calculated important IA morphology parameters to quantify the differences in IA segmentation by raters to segmentations by DeepMedic. The agreement between raters, DeepMedic, and ground truth was assessed using Krippendorf’s alpha.

RESULTS

In testing, the DeepMedic model yielded a CAL of 0.971 ± 0.007 and a DSC of 0.868 ± 0.008. The model prediction delineated all IAs and resulted in average error rates of < 10% for all IA morphometrics. Conversely, average IA detection accuracy by the raters was 0.653 (undetected IAs were present to a significantly greater degree on the ICA, likely due to those in the cavernous region, and were significantly smaller). Error rates for IA morphometrics in rater-segmented cases were significantly higher than in DeepMedic-segmented cases, particularly for neck (p = 0.003) and surface area (p = 0.04). For IA morphology, agreement between the raters was acceptable for most metrics, except for the undulation index (α = 0.36) and the nonsphericity index (α = 0.69). Agreement between DeepMedic and ground truth was consistently higher compared with that between expert raters and ground truth.

CONCLUSIONS

This CTA segmentation network (DeepMedic trained on DSA-segmented vessels) provides a high-fidelity solution for CTA vessel segmentation, particularly for vessels and IAs in the carotid cavernous region.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery

Free access

Immunohistochemical markers predicting long-term recurrence following clival and spinal chordoma resection: a multicenter study

Abdul Karim Ghaith, Oluwaseun O. Akinduro, A. Yohan Alexander, Anshit Goyal, Antonio Bon-Nieves, Leonardo de Macedo Filho, Andrea Otamendi-Lopez, Karim Rizwan Nathani, Kingsley Abode-Iyamah, Mark E. Jentoft, Bernard R. Bendok, Michelle J. Clarke, Michael J. Link, Jamie J. Van Gompel, Alfredo Quiñones-Hinojosa, and Mohamad Bydon

OBJECTIVE

Chordomas are rare tumors from notochordal remnants and account for 1%–4% of all primary bone malignancies, often arising from the clivus and sacrum. Despite margin-negative resection and postoperative radiotherapy, chordomas often recur. Further, immunohistochemical (IHC) markers have not been assessed as predictive of chordoma recurrence. The authors aimed to identify the IHC markers that are predictive of postoperative long-term (≥ 1 year) chordoma recurrence by using trained multiple tree-based machine learning (ML) algorithms.

METHODS

The authors reviewed the records of patients who had undergone treatment for clival and spinal chordomas between January 2017 and June 2021 across the Mayo Clinic enterprise (Minnesota, Florida, and Arizona). Demographics, type of treatment, histopathology, and other relevant clinical factors were abstracted from each patient record. Decision tree and random forest classifiers were trained and tested to predict long-term recurrence based on unseen data using an 80/20 split.

RESULTS

One hundred fifty-one patients diagnosed and treated for chordomas were identified: 58 chordomas of the clivus, 48 chordomas of the mobile spine, and 45 chordomas sacrococcygeal in origin. Patients diagnosed with cervical chordomas were the oldest among all groups (58 ± 14 years, p = 0.009). Most patients were male (n = 91, 60.3%) and White (n = 139, 92.1%). Most patients underwent resection with or without radiation therapy (n = 129, 85.4%). Subtotal resection followed by radiation therapy (n = 51, 33.8%) was the most common treatment modality, followed by gross-total resection then radiation therapy (n = 43, 28.5%). Multivariate analysis showed that S100 and pan-cytokeratin are more likely to predict the increase in the risk of postoperative recurrence (OR 3.67, 95% CI 1.09–12.42, p= 0.03; and OR 3.74, 95% CI 0.05–2.21, p = 0.02, respectively). In the decision tree analysis, a clinical follow-up > 1897 days was found in 37% of encounters and a 90% chance of being classified for recurrence (accuracy = 77%). Random forest analysis (n = 500 trees) showed that patient age, type of surgical treatment, location of tumor, S100, pan-cytokeratin, and EMA are the factors predicting long-term recurrence.

CONCLUSIONS

The IHC and clinicopathological variables combined with tree-based ML tools successfully demonstrated a high capacity to identify recurrence patterns with an accuracy of 77%. S100, pan-cytokeratin, and EMA were the IHC drivers of recurrence. This shows the power of ML algorithms in analyzing and predicting outcomes of rare conditions of a small sample size.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery

Free access

Incorporation of a biparietal narrowing metric to improve the ability of machine learning models to detect sagittal craniosynostosis with 2D photographs

Megan G. Anderson, Dana Jungbauer, Nathan K. Leclair, Edward S. Ahn, Petronella Stoltz, Jonathan E. Martin, David S. Hersh, and Markus J. Bookland

OBJECTIVE

Sagittal craniosynostosis is the most common form of craniosynostosis and typically results in scaphocephaly, which is characterized by biparietal narrowing, compensatory frontal bossing, and an occipital prominence. The cephalic index (CI) is a simple metric for quantifying the degree of cranial narrowing and is often used to diagnose sagittal craniosynostosis. However, patients with variant forms of sagittal craniosynostosis may present with a "normal" CI, depending on the part of the suture that is closed. As machine learning (ML) algorithms are developed to assist in the diagnosis of cranial deformities, metrics that reflect the other phenotypic features of sagittal craniosynostosis are needed. In this study the authors sought to describe the posterior arc angle (PAA), a measurement of biparietal narrowing that is obtained with 2D photographs, and elucidate the role of PAA as an adjuvant to the CI in characterizing scaphocephaly and the potential relevance of PAA in new ML model development.

METHODS

The authors retrospectively reviewed 1013 craniofacial patients treated during the period from 2006 to 2021. Orthogonal top-down photographs were used to calculate the CI and PAA. Distribution densities, receiver operating characteristic (ROC) curves, and chi-square analyses were used to describe the relative predictive utility of each method for sagittal craniosynostosis.

RESULTS

In total, 1001 patients underwent paired CI and PAA measurements and a clinical head shape diagnosis (sagittal craniosynostosis, n = 122; other cranial deformity, n = 565; normocephalic, n = 314). The area under the ROC curve (AUC) for the CI was 98.5% (95% confidence interval 97.8%–99.2%, p < 0.001), with an optimum specificity of 92.6% and sensitivity of 93.4%. The PAA had an AUC of 97.4% (95% confidence interval 96.0%–98.8%, p < 0.001) with an optimum specificity of 94.9% and sensitivity of 90.2%. In 6 of 122 (4.9%) cases of sagittal craniosynostosis, the PAA was abnormal while the CI was normal. This means that adding a PAA cutoff branch to a partition model increases the detection of sagittal craniosynostosis.

CONCLUSIONS

Both CI and PAA are excellent discriminators for sagittal craniosynostosis. Using an accuracy-optimized partition model, the addition of the PAA to the CI increased model sensitivity compared to using the CI alone. Using a model that incorporates both CI and PAA could assist in the early identification and treatment of sagittal craniosynostosis via automated and semiautomated algorithms that utilize tree-based ML models.

In Neurosurgical Focus Volume 54 (2023): Issue 6 (Jun 2023): Machine Learning in Neurosurgery