Multivariable Prediction Models for Traumatic Spinal Cord Injury: A Systematic Review.

Background: Traumatic spinal cord injuries (TSCI) greatly affect the lives of patients and their families. Prognostication may improve treatment strategies, health care resource allocation, and counseling. Multivariable clinical prediction models (CPMs) for prognosis are tools that can estimate an absolute risk or probability that an outcome will occur. Objectives: We sought to systematically review the existing literature on CPMs for TSCI and critically examine the predictor selection methods used. Methods: We searched MEDLINE, PubMed, Embase, Scopus, and IEEE for English peer-reviewed studies and relevant references that developed multivariable CPMs to prognosticate patient-centered outcomes in adults with TSCI. Using narrative synthesis, we summarized the characteristics of the included studies and their CPMs, focusing on the predictor selection process. Results: We screened 663 titles and abstracts; of these, 21 full-text studies (2009-2020) consisting of 33 distinct CPMs were included. The data analysis domain was most commonly at a high risk of bias when assessed for methodological quality. Model presentation formats were inconsistently included with published CPMs; only two studies followed established guidelines for transparent reporting of multivariable prediction models. Authors frequently cited previous literature for their initial selection of predictors, and stepwise selection was the most frequent predictor selection method during modelling. Conclusion: Prediction modelling studies for TSCI serve clinicians who counsel patients, researchers aiming to risk-stratify participants for clinical trials, and patients coping with their injury. Poor methodological rigor in data analysis, inconsistent transparent reporting, and a lack of model presentation formats are vital areas for improvement in TSCI CPM research.

Enabling knowledge translation: implementation of a web-based tool for independent walking prediction after traumatic spinal cord injury.

Introduction: Several clinical prediction rules (CPRs) have been published, but few are easily accessible or convenient for clinicians to use in practice. We aimed to develop, implement, and describe the process of building a web-based CPR for predicting independent walking 1-year after a traumatic spinal cord injury (TSCI). Methods: Using the published and validated CPR, a front-end web application called "Ambulation" was built using HyperText Markup Language (HTML), Cascading Style Sheets (CSS), and JavaScript. A survey was created using QualtricsXM Software to gather insights on the application's usability and user experience. Website activity was monitored using Google Analytics. Ambulation was developed with a core team of seven clinicians and researchers. To refine the app's content, website design, and utility, 20 professionals from different disciplines, including persons with lived experience, were consulted. Results: After 11 revisions, Ambulation was uploaded onto a unique web domain and launched (www.ambulation.ca) as a pilot with 30 clinicians (surgeons, physiatrists, and physiotherapists). The website consists of five web pages: Home, Calculation, Team, Contact, and Privacy Policy. Responses from the user survey (n = 6) were positive and provided insight into the usability of the tool and its clinical utility (e.g., helpful in discharge planning and rehabilitation), and the overall face validity of the CPR. Since its public release on February 7, 2022, to February 28, 2023, Ambulation had 594 total users, 565 (95.1%) new users, 26 (4.4%) returning users, 363 (61.1%) engaged sessions (i.e., the number of sessions that lasted 10 seconds/longer, had one/more conversion events e.g., performing the calculation, or two/more page or screen views), and the majority of the users originating from the United States (39.9%) and Canada (38.2%). Discussion: Ambulation is a CPR for predicting independent walking 1-year after TSCI and it can assist frontline clinicians with clinical decision-making (e.g., time to surgery or rehabilitation plan), patient education and goal setting soon after injury. This tool is an example of adapting a validated CPR for independent walking into an easily accessible and usable web-based tool for use in clinical practice. This study may help inform how other CPRs can be adopted into clinical practice.

A data-driven approach to categorize patients with traumatic spinal cord injury: cluster analysis of a multicentre database.

Background: Conducting clinical trials for traumatic spinal cord injury (tSCI) presents challenges due to patient heterogeneity. Identifying clinically similar subgroups using patient demographics and baseline injury characteristics could lead to better patient-centered care and integrated care delivery. Purpose: We sought to (1) apply an unsupervised machine learning approach of cluster analysis to identify subgroups of tSCI patients using patient demographics and injury characteristics at baseline, (2) to find clinical similarity within subgroups using etiological variables and outcome variables, and (3) to create multi-dimensional labels for categorizing patients. Study design: Retrospective analysis using prospectively collected data from a large national multicenter SCI registry. Methods: A method of spectral clustering was used to identify patient subgroups based on the following baseline variables collected since admission until rehabilitation: location of the injury, severity of the injury, Functional Independence Measure (FIM) motor, and demographic data (age, and body mass index). The FIM motor score, the FIM motor score change, and the total length of stay were assessed on the subgroups as outcome variables at discharge to establish the clinical similarity of the patients within derived subgroups. Furthermore, we discussed the relevance of the identified subgroups based on the etiological variables (energy and mechanism of injury) and compared them with the literature. Our study also employed a qualitative approach to systematically describe the identified subgroups, crafting multi-dimensional labels to highlight distinguishing factors and patient-focused insights. Results: Data on 334 tSCI patients from the Rick Hansen Spinal Cord Injury Registry was analyzed. Five significantly different subgroups were identified (p-value ≤0.05) based on baseline variables. Outcome variables at discharge superimposed on these subgroups had statistically different values between them (p-value ≤0.05) and supported the notion of clinical similarity of patients within each subgroup. Conclusion: Utilizing cluster analysis, we identified five clinically similar subgroups of tSCI patients at baseline, yielding statistically significant inter-group differences in clinical outcomes. These subgroups offer a novel, data-driven categorization of tSCI patients which aligns with their demographics and injury characteristics. As it also correlates with traditional tSCI classifications, this categorization could lead to improved personalized patient-centered care.

A community-of-practice-based evaluation methodology for knowledge intensive computational methods and its application to multimorbidity decision support.

OBJECTIVE: The study has dual objectives. Our first objective (1) is to develop a community-of-practice-based evaluation methodology for knowledge-intensive computational methods. We target a whitebox analysis of the computational methods to gain insight on their functional features and inner workings. In more detail, we aim to answer evaluation questions on (i) support offered by computational methods for functional features within the application domain; and (ii) in-depth characterizations of the underlying computational processes, models, data and knowledge of the computational methods. Our second objective (2) involves applying the evaluation methodology to answer questions (i) and (ii) for knowledge-intensive clinical decision support (CDS) methods, which operationalize clinical knowledge as computer interpretable guidelines (CIG); we focus on multimorbidity CIG-based clinical decision support (MGCDS) methods that target multimorbidity treatment plans. MATERIALS AND METHODS: Our methodology directly involves the research community of practice in (a) identifying functional features within the application domain; (b) defining exemplar case studies covering these features; and (c) solving the case studies using their developed computational methods-research groups detail their solutions and functional feature support in solution reports. Next, the study authors (d) perform a qualitative analysis of the solution reports, identifying and characterizing common themes (or dimensions) among the computational methods. This methodology is well suited to perform whitebox analysis, as it directly involves the respective developers in studying inner workings and feature support of computational methods. Moreover, the established evaluation parameters (e.g., features, case studies, themes) constitute a re-usable benchmark framework, which can be used to evaluate new computational methods as they are developed. We applied our community-of-practice-based evaluation methodology on MGCDS methods. RESULTS: Six research groups submitted comprehensive solution reports for the exemplar case studies. Solutions for two of these case studies were reported by all groups. We identified four evaluation dimensions: detection of adverse interactions, management strategy representation, implementation paradigms, and human-in-the-loop support. Based on our whitebox analysis, we present answers to the evaluation questions (i) and (ii) for MGCDS methods. DISCUSSION: The proposed evaluation methodology includes features of illuminative and comparison-based approaches; focusing on understanding rather than judging/scoring or identifying gaps in current methods. It involves answering evaluation questions with direct involvement of the research community of practice, who participate in setting up evaluation parameters and solving exemplar case studies. Our methodology was successfully applied to evaluate six MGCDS knowledge-intensive computational methods. We established that, while the evaluated methods provide a multifaceted set of solutions with different benefits and drawbacks, no single MGCDS method currently provides a comprehensive solution for MGCDS. CONCLUSION: We posit that our evaluation methodology, applied here to gain new insights into MGCDS, can be used to assess other types of knowledge-intensive computational methods and answer other types of evaluation questions. Our case studies can be accessed at our GitHub repository (https://github.com/william-vw/MGCDS).

Beneficial Effects of Preoperative Exercise on the Outcomes of Lumbar Fusion Spinal Surgery.

Purpose: To determine whether there was an association between self-reported preoperative exercise and postoperative outcomes after lumbar fusion spinal surgery. Method: We performed a retrospective multivariable analysis of the prospective Canadian Spine Outcomes and Research Network (CSORN) database of 2,203 patients who had elective single-level lumbar fusion spinal surgeries. We compared adverse events and hospital length of stay between patients who reported regular exercise (twice or more per week) prior to surgery ("Regular Exercise") to those exercising infrequently (once or less per week) ("Infrequent Exercise") or those who did no exercise ("No Exercise"). For all final analyses, we compared the Regular Exercise group to the combined Infrequent Exercise or No Exercise group. Results: After making adjustments for known confounding factors, we demonstrated that patients in the Regular Exercise group had fewer adverse events (adjusted odds ratio 0.72; 95% CI: 0.57, 0.91; p = 0.006) and significantly shorter lengths of stay (adjusted mean 2.2 vs. 2.5 d, p = 0.029) than the combined Infrequent Exercise or No Exercise group. Conclusions: Patients who exercised regularly twice or more per week prior to surgery had fewer postoperative adverse events and significantly shorter hospital lengths of stay compared to patients that exercised infrequently or did no exercise. Further study is required to determine effectiveness of a targeted prehabilitation programme.

Objectif : déterminer s'il y avait une association entre les exercices préopératoires autodéclarés et les résultats postopératoires après une chirurgie de fusion lombaire. Méthodologie : analyse multivariable rétrospective de la base de données prospective Canadian Spine Outcomes and Research Network (CSORN) composée de 2 203 patients qui avaient subi une chirurgie de fusion lombaire univertébrale non urgente. Les chercheurs ont comparé les événements indésirables et la durée du séjour hospitalier entre les patients qui déclaraient faire de l'exercice régulier (au moins deux fois par semaine) avant l'opération (« exercice régulier ¼) à ceux qui n'en faisaient pas souvent (une fois ou moins par semaine; « exercice peu fréquent ¼) et qui n'en faisaient pas du tout (« absence d'exercice ¼). Pour toutes les analyses définitives, ils ont comparé le groupe qui faisait de l'exercice régulier aux groupes combinés d'exercice peu fréquent et d'absence d'exercice. Résultats : après correction pour tenir compte des facteurs confusionnels connus, les chercheurs ont démontré que les patients du groupe faisant de l'exercice régulier présentaient moins d'événements indésirables (rapport de cotes rajusté 0,72; IC à 95 % : 0,57, 0,91; p = 0,006) et leur séjour à l'hôpital était significativement plus court (moyenne corrigée 2,2 jours par rapport à 2,5 jours, p = 0,029) que dans le groupe combiné d'exercice peu fréquent et d'absence d'exercice. Conclusions : les patients qui faisaient de l'exercice régulièrement au moins deux fois par semaine avant l'opération présentaient moins d'événements indésirables après l'opération et étaient hospitalisés beaucoup moins longtemps que ceux qui ne faisaient pas beaucoup d'exercice ou n'en faisaient pas du tout. Il faudra réaliser d'autres études pour déterminer l'efficacité d'un programme de préréadaptation ciblé.

Determining minimal clinically important difference estimates following surgery for degenerative conditions of the lumbar spine: analysis of the Canadian Spine Outcomes and Research Network (CSORN) registry.

BACKGROUND CONTEXT: There is significant variability in minimal clinically important difference (MCID) criteria for lumbar spine surgery that suggests population and primary pathology specific thresholds may be required to help determine surgical success when using patient reported outcome measures (PROMs). PURPOSE: The purpose of this study was to estimate MCID thresholds for 3 commonly used PROMs after surgical intervention for each of 4 common lumbar spine pathologies. STUDY DESIGN/SETTING: Observational longitudinal study of patients from the Canadian Spine Outcomes and Research Network (CSORN) national registry. PATIENT SAMPLE: Patients undergoing surgery from 2015 to 2018 for lumbar spinal stenosis (LSS; n = 856), degenerative spondylolisthesis (DS; n = 591), disc herniation (DH; n = 520) or degenerative disc disease (DDD n = 185) were included. OUTCOME MEASURES: PROMs were collected presurgery and 1-year postsurgery: the Oswestry Disability Index (ODI), and back and leg Numeric Pain Rating Scales (NPRS). At 1-year, patients reported whether they were 'Much better'/'Better'/'Same'/'Worse'/'Much worse' compared to before their surgery. Responses to this item were used as the anchor in analyses to determine surgical MCIDs for benefit ('Much better'/'Better') and substantial benefit ('Much better'). METHODS: MCIDs for absolute and percentage change for each of the 3 PROMs were estimated using a receiving operating curve (ROC) approach, with maximization of Youden's index as primary criterion. Area under the curve (AUC) estimates, sensitivity, specificity and correct classification rates were determined. All analyses were conducted separately by pathology group. RESULTS: MCIDs for ODI change ranged from -10.0 (DDD) to -16.9 (DH) for benefit, and -13.8 (LSS) to -22.0 (DS,DH) for substantial benefit. MCID for back and leg NPRS change were -2 to -3 for each group for benefit and -4.0 for substantial benefit for all groups on back NPRS. MCID estimates for percentage change varied by PROM and pathology group, ranging from -11.1% (ODI for DDD) to -50.0% (leg NPRS for DH) for benefit and from -40.0% (ODI for DDD) to -66.6% (leg NPRS for DH) for substantial benefit. Correct classification rates for all MCID thresholds ranged from 71% to 89% and were relatively lower for absolute vs percent change for those with high or low presurgical scores. CONCLUSIONS: Our findings suggest that the use of generic MCID thresholds across pathologies in lumbar spine surgery is not recommended. For patients with relatively low or high presurgery PROM scores, MCIDs based on percentage change, rather than absolute change, appear generally preferable. These findings have applicability in clinical and research settings, and are important for future surgical prognostic work.

Minimally Invasive vs. Open Surgery for Lumbar Spinal Stenosis in Patients with Diabetes - A Canadian Spine Outcomes and Research Network Study.

STUDY DESIGN: Retrospective cohort. OBJECTIVES: To compare outcomes of minimally invasive surgery (MIS) vs open surgery (OPEN) for lumbar spinal stenosis (LSS) in patients with diabetes. METHODS: Patients with diabetes who underwent spinal decompression alone or with fusion for LSS within the Canadian Spine Outcomes and Research Network (CSORN) database were included. MIS vs OPEN outcomes were compared for 2 cohorts: (1) patients with diabetes who underwent decompression alone (N = 116; MIS n = 58 and OPEN n = 58), (2) patients with diabetes who underwent decompression with fusion (N = 108; MIS n = 54 and OPEN n = 54). Modified Oswestry Disability Index (mODI) and back and leg pain were compared at baseline, 6-18 weeks, and 1-year post-operation. The number of patients meeting minimum clinically important difference (MCID) or minimum pain/disability at 1-year was compared. RESULTS: MIS approaches had less blood loss (decompression alone difference 100 mL, P = .002; with fusion difference 244 mL, P < .001) and shorter length of stay (LOS) (decompression alone difference 1.2 days, P = .008; with fusion difference 1.2 days, P = .026). MIS compared to OPEN decompression with fusion had less patients experiencing adverse events (AEs) (difference 13 patients, P = .007). The MIS decompression with fusion group had lower 1-year mODI (difference 14.5, 95% CI [7.5, 21.0], P < .001) and back pain (difference 1.6, 95% CI [.6, 2.7], P = .002) compared to OPEN. More patients in the MIS decompression with fusion group exceeded MCID at 1-year for mODI (MIS 75.9% vs OPEN 53.7%, P = .028) and back pain (MIS 85.2% vs OPEN 70.4%, P = .017). CONCLUSIONS: MIS approaches were associated with more favorable outcomes for patients with diabetes undergoing decompression with fusion for LSS.

The effect of a quality improvement project on post-operative opioid use following outpatient spinal surgery.

Background: Prescribing opioids upon discharge after surgery is common practice; however, there are many inherent risks including dependency, diversion, and medical complications. Our prospective pre- and post-intervention study investigates the effect of a standardized analgesic prescription on the quantity of opioids prescribed and patients' level of pain and satisfaction with pain control in the early post-operative period. Methods: With the implementation of an electronic medical record, a standardized prescription was built employing multimodal analgesia and a stepwise approach to analgesics based on level of pain. Patients received an education handout pre-operatively explaining the prescription. Consecutive patients over a three-month period undergoing elective spine surgery as day or overnight stay cases who received usual care were compared to a similar cohort who received the standardized prescription and education. Patient satisfaction with post-operative pain control, post-operative pain scores, number of refills required, and opioids prescribed in oral morphine equivalents (OMEs) were compared before and after implementation of the standardized analgesic prescription. Results: Twenty-six patients received usual care (Control group) and 26 patients received the standardized prescription and education handout (Intervention group). There were significantly fewer OMEs prescribed in the Intervention group compared to the Control group. There was no difference between groups in: patient post-operative pain intensity score, post-operative satisfaction score, or number of refills required. Conclusions: This study demonstrates that a standardized prescription consisting of an appropriate amount of opioid and non-opioid analgesics is effective in reducing the OMEs prescribed post-operatively in elective spine surgery procedures, without compromising patient pain control or satisfaction or increasing the number of refills required.

A scoping review of complication prediction models in spinal surgery: An analysis of model development, validation and impact.

Background: Predictive analytics are being used increasingly in the field of spinal surgery with the development of models to predict post-surgical complications. Predictive models should be valid, generalizable, and clinically useful. The purpose of this review was to identify existing post-surgical complication prediction models for spinal surgery and to determine if these models are being adequately investigated with internal/external validation, model updating and model impact studies. Methods: This was a scoping review of studies pertaining to models for the prediction of post-surgical complication after spinal surgery published over 10 years (2010-2020). Qualitative data was extracted from the studies to include study classification, adherence to Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines and risk of bias (ROB) assessment using the Prediction model study Risk Of Bias Assessment Tool (PROBAST). Model evaluation was determined using area under the curve (AUC) when available. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement was used as a basis for the search methodology in four different databases. Results: Thirty studies were included in the scoping review and 80% (24/30) included model development with or without internal validation. Twenty percent (6/30) were exclusively external validation studies and only one study included an impact analysis in addition to model development and internal validation. Two studies referenced the TRIPOD guidelines and there was a high ROB in 100% of the studies using the PROBAST tool. Conclusions: The majority of post-surgical complication prediction models in spinal surgery have not undergone standardized model development and internal validation or adequate external validation and impact evaluation. As such there is uncertainty as to their validity, generalizability, and clinical utility. Future efforts should be made to use existing tools to ensure standardization in development and rigorous evaluation of prediction models in spinal surgery.

Postoperative recovery patterns following discectomy surgery in patients with lumbar radiculopathy.

This retrospective study of prospectively collected data aimed to identify unique pain and disability trajectories in patients following lumbar discectomy surgery. Patients of this study population presented chiefly with lumbar radiculopathy and underwent discectomy surgery from thirteen sites enrolled in the CSORN registry. Outcome variables of interest included numeric rating scales for leg/back pain and modified Oswestry disability index scores at baseline, 3, 12, and 24 months post-operatively. Latent class growth analysis was used to identify distinct courses in each outcome. Data from 524 patients revealed three unique trajectories for leg pain (excellent = 18.4%, good = 55.4%, poor = 26.3%), disability (excellent = 59.7%, fair = 35.6%, poor = 4.7%) and back pain (excellent = 13.0%, good = 56.4%, poor = 30.6%). Construct validity was supported by statistically significant differences in the proportions of patients attaining the criteria for minimal important change (MIC; 30%) or clinical success in disability (50% or Oswestry score ≤ 22) (p < 0.001). The variable proportions of patients belonging to poor outcome trajectories shows a disconnect between improved disability and persistence of pain. It will be beneficial to incorporate this information into the realm of patient expectation setting in concert with future findings of potential factors predictive of subgroup membership.

Allogeneic blood transfusions and infection risk in lumbar spine surgery: An American College of Surgeons National Surgery Quality Improvement Program Study.

BACKGROUND: Allogenic blood transfusions can lead to immunomodulation. Our purpose was to investigate whether perioperative transfusions were associated with postoperative infections and any other adverse events (AEs), after adjusting for potential confounding factors, following common elective lumbar spinal surgery procedures. STUDY DESIGN AND METHODS: We performed a multivariate, propensity-score matched, regression-adjusted retrospective analysis of the American College of Surgeons National Surgical Quality Improvement Program database between 2012 and 2016. All lumbar spinal surgery procedures were identified (n = 174,891). A transfusion group (perioperative transfusion within 72 h before, during, or after principal surgery; n = 1992) and a control group (no transfusion; n = 1992) were formed. Following adjustment for between-group baseline features, adjusted odds ratios (aOR) and 95% confidence intervals (95% CI) were calculated using a multivariate logistic regression model for any surgical site infection (SSI), superficial SSI, deep SSI, wound dehiscence, pneumonia, urinary tract infection, sepsis, any infection, mortality, and any AEs. RESULTS: Transfusion was associated with an increased risk of each specific infection, mortality, and any AEs. Statistically significant between-group differences were demonstrated with respect to any SSI (aOR: 1.48; 95% CI: 1.01-2.16), deep SSI (aOR: 1.66; 95% CI: 0.98-2.85), sepsis (aOR: 2.69; 95% CI: 1.43-5.03), wound dehiscence (aOR: 2.27; 95% CI: 0.86-6.01), any infection (aOR: 1.46; 95% CI: 1.13-1.88), any AEs (aOR: 1.80; 95% CI: 1.48-2.18), and mortality (aOR: 2.17; 95% CI: 0.77-6.36). CONCLUSION: We showed an association between transfusion and infection in lumbar spine surgery after adjustment for various applicable covariates. Sepsis had the highest association with transfusion. Our results reinforce a growing trend toward minimizing perioperative transfusions, which may lead to reduced infections following lumbar spine surgery.

A Health eLearning Ontology and Procedural Reasoning Approach for Developing Personalized Courses to Teach Patients about Their Medical Condition and Treatment.

We propose a methodological framework to support the development of personalized courses that improve patients' understanding of their condition and prescribed treatment. Inspired by Intelligent Tutoring Systems (ITSs), the framework uses an eLearning ontology to express domain and learner models and to create a course. We combine the ontology with a procedural reasoning approach and precompiled plans to operationalize a design across disease conditions. The resulting courses generated by the framework are personalized across four patient axes-condition and treatment, comprehension level, learning style based on the VARK (Visual, Aural, Read/write, Kinesthetic) presentation model, and the level of understanding of specific course content according to Bloom's taxonomy. Customizing educational materials along these learning axes stimulates and sustains patients' attention when learning about their conditions or treatment options. Our proposed framework creates a personalized course that prepares patients for their meetings with specialists and educates them about their prescribed treatment. We posit that the improvement in patients' understanding of prescribed care will result in better outcomes and we validate that the constructs of our framework are appropriate for representing content and deriving personalized courses for two use cases: anticoagulation treatment of an atrial fibrillation patient and lower back pain management to treat a lumbar degenerative disc condition. We conduct a mostly qualitative study supported by a quantitative questionnaire to investigate the acceptability of the framework among the target patient population and medical practitioners.

Using a national surgical database to predict complications following posterior lumbar surgery and comparing the area under the curve and F1-score for the assessment of prognostic capability.

BACKGROUND: With spinal surgery rates increasing in North America, models that are able to accurately predict which patients are at greater risk of developing complications are highly warranted. However, the previously published methods which have used large, multi-centre databases to develop their prediction models have relied on the receiver operator characteristics curve with the associated area under the curve (AUC) to assess their model's performance. Recently, it has been found that a precision-recall curve with the associated F1-score could provide a more realistic analysis for these models. PURPOSE: To develop a logistic regression (LR) model for the prediction of complications following posterior lumbar spine surgery and to then assess for any difference in performance of the model when using the AUC versus the F1-score. STUDY DESIGN: Retrospective review of a prospective cohort. PATIENT SAMPLE: The American College of Surgeons National Surgical Quality Improvement Program (NSQIP) registry was used. All patients that underwent posterior lumbar spine surgery between 2005 to 2016 with appropriate data were included. OUTCOME MEASURES: Both the AUC and F1-score were utilized to assess the prognostic performance of the prediction model. METHODS: In order to develop the LR model used to predict a complication during or following spine surgery, 19 variables were selected by three orthopedic spine surgeons from the NSQIP registry. Two datasets were developed for this analysis: (1) an imbalanced dataset, which was taken directly from the NSQIP registry, and (2) a down-sampled set. The purpose of the down-sampled set was to balance the data in order to evaluate whether balancing the data had an effect on model performance. The AUC and F1-score were applied to both of these datasets. RESULTS: Within the NSQIP database, 52,787 spine surgery cases were identified of which only 10% of these cases had complications during surgery. Applying the LR model showed a large difference between the AUC (0.69) and the F1 score (0.075) on the imbalanced dataset. However, no major differences existed between the AUC and F1-score when the data was balanced and the LR model was reapplied (0.69 and 0.62, AUC and F1-score, respectively). CONCLUSIONS: The F1-score detected a drastically lower performance for the prediction of complications when using the imbalanced data, but detected a performance similar to the AUC level when balancing techniques were utilized for the dataset. This difference is due to a low precision score when many false positive classifications are present, which is not identified when using the AUC value. This lowers the utility of the AUC score, as many of the datasets used in medicine are imbalanced. Therefore, we recommend using the F1-score on large, prospective databases when the data is imbalanced with a large amount of true negative classifications.

Towards a framework for comparing functionalities of multimorbidity clinical decision support: A literature-based feature set and benchmark cases.

Multimorbidity, the coexistence of two or more health conditions, has become more prevalent as mortality rates in many countries have declined and their populations have aged. Multimorbidity presents significant difficulties for Clinical Decision Support Systems (CDSS), particularly in cases where recommendations from relevant clinical guidelines offer conflicting advice. A number of research groups are developing computer-interpretable guideline (CIG) modeling formalisms that integrate recommendations from multiple Clinical Practice Guidelines (CPGs) for knowledge-based multimorbidity decision support. In this paper we describe work towards the development of a framework for comparing the different approaches to multimorbidity CIG-based clinical decision support (MGCDS). We present (1) a set of features for MGCDS, which were derived using a literature review and evaluated by physicians using a survey, and (2) a set of benchmarking case studies, which illustrate the clinical application of these features. This work represents the first necessary step in a broader research program aimed at the development of a benchmark framework that allows for standardized and comparable MGCDS evaluations, which will facilitate the assessment of functionalities of MGCDS, as well as highlight important gaps in the state-of-the-art. We also outline our future work on developing the framework, specifically, (3) a standard for reporting MGCDS solutions for the benchmark case studies, and (4) criteria for evaluating these MGCDS solutions. We plan to conduct a large-scale comparison study of existing MGCDS based on the comparative framework.

Back pain in surgically treated degenerative lumbar spondylolisthesis: what can we tell our patients?

OF BACKGROUND DATA: Surgery for degenerative lumbar spondylolisthesis (DLS) has traditionally been indicated for patients with neurogenic claudication. Surgery improves patients' disability and lower extremity symptoms, but less is known about the impact on back pain. OBJECTIVE: To evaluate changes in back pain after surgery and identify factors associated with these changes in surgically-treated DLS. STUDY DESIGN: Retrospective review of prospectively collected data. METHODS: There were 486 consecutive patients with surgically-treated DLS who were enrolled in the Canadian Spine Outcomes Research Network prospective registry and identified for this study. Patients had demographic data, clinical information, disability (Oswestry Disability Index), and back pain rating scores collected prospectively at baseline, and 12 months follow-up RESULTS: Of the 486 DLS patients, 376 (77.3%) were successfully followed at 12 months. Mean age at baseline was 66.7 (standard deviation [SD] 9.2) years old, and 63% were female. Back pain improved significantly at 12 months, compared with baseline (p<.001). Improvement in Numeric Rating Scale (NRS)-back pain ratings was on average 2.97 (SD 2.5) points at one year and clinically significant improvement in back pain was observed in 75% of patients (minimal clinically important difference (MCID) NRS-Pain 1.2 points). Multivariable logistic regression revealed five factors associated with meeting MCID NRS-back pain at 12 month follow up: higher baseline back pain, better baseline physical function (higher SF-12 Physical Component Score), symptoms duration less than 1 to 2 years, and having no intraoperative adverse events. CONCLUSIONS: Back pain improved significantly for patients treated surgically for DLS at 1-year follow-up.

Opioid use trends in patients undergoing elective thoracic and lumbar spine surgery.

Background: Opioid use in North America has increased rapidly in recent years. Preoperative opioid use is associated with several negative outcomes. Our objectives were to assess patterns of opioid use over time in Canadian patients who undergo spine surgery and to determine the effect of spine surgery on 1-year postoperative opioid use. Methods: A retrospective analysis was performed on prospectively collected data from the Canadian Spine Outcomes and Research Network for patients undergoing elective thoracic and lumbar surgery. Self-reported opioid use at baseline, before surgery and at 1 year after surgery was compared. Baseline opioid use was compared by age, sex, radiologic diagnosis and presenting complaint. All patients meeting eligibility criteria from 2008 to 2017 were included. Results: A total of 3134 patients provided baseline opioid use data. No significant change in the proportion of patients taking daily (range 32.3%-38.2%) or intermittent (range 13.7%-22.5%) opioids was found from pre-2014 to 2017. Among patients who waited more than 6 weeks for surgery, the frequency of opioid use did not differ significantly between the baseline and preoperative time points. Significantly more patients using opioids had a chief complaint of back pain or radiculopathy than neurogenic claudication (p < 0.001), and significantly more were under 65 years of age than aged 65 years or older (p < 0.001). Approximately 41% of patients on daily opioids at baseline remained so at 1 year after surgery. Conclusion: These data suggest that additional opioid reduction strategies are needed in the population of patients undergoing elective thoracic and lumbar spine surgery. Spine surgeons can be involved in identifying patients taking opioids preoperatively, emphasizing the risks of continued opioid use and referring patients to appropriate evidence-based treatment programs.

Contexte: En Amérique du Nord, l'utilisation d'opioïdes a augmenté rapidement dans les dernières années. La prise d'opioïdes en période préopératoire est associée à plusieurs issues négatives. Cette étude visait à évaluer l'évolution des tendances dans l'utilisation d'opioïdes des patients canadiens ayant subi une chirurgie spinale, et de déterminer les effets de la chirurgie sur leur utilisation 1 an après l'opération. Méthodes: Une analyse rétrospective a été réalisée à partir de données recueillies de manière prospective par le Canadian Spine Outcomes and Research Network pour les patients ayant subi une chirurgie thoracique ou une chirurgie spinale élective. On a comparé l'utilisation autodéclarée d'opioïdes au début du suivi, avant la chirurgie et 1 an après la chirurgie. L'utilisation d'opioïdes au départ a été comparée selon le sexe, l'âge, le diagnostic radiologique et le motif de consultation. Entre 2008 et 2017, tous les patients satisfaisant aux critères d'admissibilités ont été inclus dans l'étude. Résultats: Au total, 3134 patients ont fourni des données sur leur prise d'opioïdes au début du suivi. Il n'y avait pas de changement significatif dans la proportion de patients utilisant quotidiennement (32,3 % à 38,2 %) ou occasionnellement (13,7 % à 22,5 %) des opioïdes entre les patients à l'étude avant 2014 et ceux à l'étude de 2014 à 2017. Parmi les patients qui ont attendu plus de 6 semaines avant la chirurgie, la fréquence de la prise d'opioïdes n'a pas changé de manière significative entre le début du suivi et la rencontre préopératoire. Une proportion significativement plus grande de patients qui utilisaient des opioïdes consultaient principalement pour des douleurs au dos ou une radiculopathie que pour une claudication neurogène (p < 0,001), et il y avait une proportion significativement plus grande de patients de moins de 65 ans qui utilisaient des opioïdes que de patients de 65 ans ou plus (p < 0,001). Environ 41 % des patients qui prenaient quotidiennement des opioïdes au départ le faisaient aussi 1 an après la chirurgie. Conclusion: Ces données suggèrent que des stratégies supplémentaires de réduction de l'utilisation d'opioïdes sont nécessaires pour les patients qui subissent une chirurgie thoracique ou une chirurgie spinale élective. Il est possible de demander aux chirurgiens spécialisés dans ce domaine de repérer les patients qui prennent des opioïdes avant l'opération, puisque l'utilisation prolongée comporte des risques, et de les aiguiller vers un programme de traitement adéquat et fondé sur des données probantes.

Capturing adverse events in elective orthopedic surgery: comparison of administrative, surgeon and reviewer reporting

Summary: Ensuring adverse event (AE) recording is standardized and accurate is paramount for patient safety. In this discussion, we outline our comparison of AE data collected by orthopedic surgeons and independent clinical reviewers using the Spine Adverse Events Severity System (SAVES) and Orthopedic Surgical Adverse Events Severity System (OrthoSAVES) against AE data recorded by hospital administrative discharge abstract coders. In 164 spine, hip, knee and shoulder patients, reviewers recorded significantly more AEs than coders, and coders recorded significantly more AEs than surgeons. The AEs were recorded similarly by reviewers using SAVES and OrthoSAVES in 48 spine patients. Despite our small sample size and use of different AE tools, we believe it is important to highlight that coders, surgeons and reviewers recorded AEs differently. While further investigations on its utility and cost-effectiveness are necessary, we assert that it is feasible to use Ortho-SAVES to prospectively record AEs across all orthopedic subspecialties.

Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients.

BACKGROUND CONTEXT: Traumatic spinal cord injury can have a dramatic effect on a patient's life. The degree of neurologic recovery greatly influences a patient's treatment and expected quality of life. This has resulted in the development of machine learning algorithms (MLA) that use acute demographic and neurologic information to prognosticate recovery. The van Middendorp et al. (2011) (vM) logistic regression (LR) model has been established as a reference model for the prediction of walking recovery following spinal cord injury as it has been validated within many different countries. However, an examination of the way in which these prediction models are evaluated is warranted. The area under the receiver operators curve (AUROC) has been consistently used when evaluating model performance, but it has been shown that AUROC overemphasizes the most common event resulting in an inaccurate assessment when the data are imbalanced. Furthermore, there is evidence that the use of more advanced MLA, such as an unsupervised k-means model, may show superior performance compared to LR as they can handle a larger number of features. PURPOSE: The first objective of the study was to assess the performance of both an unsupervised MLA and LR model with complete admission neurologic information against the vM and Hicks models. Second, a comparison between the accuracy of the AUROC and the F1-score will be made to determine which method is superior for the assessment of diagnostic performance of prediction models on large-scale datasets. STUDY DESIGN: Retrospective review of a prospective cohort study. PATIENT SAMPLE: The Rick Hansen Spinal Cord Injury Registry (RHSCIR) was used in this study. All patients enrolled between 2004 and 2017 with complete neurologic examination and Functional Independence Measure outcome data at ≥1 year follow-up or who could walk at discharge were included. The prognostic variables included age (dichotomized at ≥65 years old); American Spinal Injury Association Impairment Scale (AIS) grade; and individual motor, light touch, and pinprick score from L2 to S1. OUTCOME MEASURES: The Functional Independence Measure locomotor score was used to assess independent walking ability at discharge or 1-year follow-up. METHODS: An unsupervised MLA with k=2 was chosen in order to identify a "walk" cluster and a "not walk" cluster. Model performance was assessed through the development of a receiver operating characteristic curve with associated AUROC and a precision-recall curve with associated F1-score. The study and the RHSCIR are supported by funding from Health Canada, Western Economic Diversification Canada, and the Governments of Alberta, British Columbia, Manitoba, and Ontario. These funders had no role in the study or study reporting and the authors have no conflicts of interest to report. RESULTS: No clinically relevant differences were found between with the use of an unsupervised MLA with a greater amount of initial neurologic information compared to the established standards for any AIS classification. Although demonstrated for all separate AIS classifications, most notably, the AUROC for the vM (0.78) and Hicks models (0.76) were found to be superior to that of the new LR model (0.72); however, the vM and Hicks models had more than double the amount of false negative classifications compared to the LR. The F1-scores between these three models were also found to be different but with the vM and Hicks models being lower than the LR (0.85, 0.81, and 0.89, respectively). CONCLUSIONS: No clinically relevant differences were found between the use of an unsupervised MLA with complete admission neurologic information compared to the previously validated standards; however, when comparing the performance of the AUROC and F1-score, the AUROC showed inaccurate prognostic performance when there was an imbalance toward a greater amount of false negatives. Importantly, the F1-score did not succumb to this imbalance. As AUROC has been used as the standard when evaluating performance of prediction models, consideration as to whether this is the most appropriate method is warranted. Future work should focus on comparing AUROC and F1-scores with other previously validated models.

Impact of resident involvement on cervical and lumbar spine surgery outcomes.

BACKGROUND CONTEXT: Resident involvement in the operating room is a vital component of their medical education. Conflicting and limited research exists regarding the effects of surgical resident participation on spine surgery patient outcomes. PURPOSE: To determine the effect of resident involvement on surgery duration, length of hospital stay and 30-day postoperative complication rates in common spinal surgery using the American College of Surgeons' National Surgical Quality Improvement Program (ACS-NSQIP) database. STUDY DESIGN: Multicenter retrospective cohort study. PATIENT SAMPLE: A total of 1,441 patients met the inclusion criteria: 1,142 patients had surgeries with an attending physician alone and 299 patients had surgeries with trainee involvement. All anterior cervical or posterior lumbar surgery patients were identified. Patients who had missing trainee involvement information, surgery for cancer, preoperative infection or dirty wound classification, spine fractures, traumatic spinal cord injury, intradural surgery, thoracic surgery, and emergency surgery were excluded. OUTCOME MEASURES: The main outcomes of interest analyzed from the ACS-NSQIP database included surgical complications, medical complications, length of hospital stay, and surgery duration. METHODS: Propensity score for risk of any complication was calculated to account for baseline characteristic differences between the attending alone and trainee present group. Multivariate logistic regression was used to investigate the impact of resident involvement on surgery duration, length of hospital stay, and 30-day postoperative complication rates. RESULTS: After adjusting using the calculated propensity score, the multivariate analysis demonstrated that there was no significant difference in any complication rates between surgeries involving trainees compared to surgeries with attending surgeons alone. Surgery times were found to be significantly longer for surgeries involving trainees. To further explore this relationship, separate analyses were performed for tertiles of predicted surgery duration, cervical or lumbar surgery, fusion or nonfusion, and inpatient or outpatient surgery. The effect of trainee involvement on increasing surgery time remained significant for medium predicted surgery duration, longer predicted surgery duration, cervical surgery, lumbar surgery, fusion surgery, and inpatient surgery. There were no significant differences reported for any other factors. CONCLUSIONS: After adjusting for confounding, we demonstrated in a national database that resident involvement in surgeries did not increase complication rates. We demonstrated that surgeries with more complex features may lead to an increase in operative time when trainees are involved. Further study is required to determine how to efficiently integrate resident involvement in surgeries without affecting their medical education.

How Do Spinal Surgeons Perceive The Impact of Factors Used in Post-Surgical Complication Risk Scores?

When deciding about surgical treatment options, an important aspect of the decision-making process is the potential risk of complications. A risk assessment performed by a spinal surgeon is based on their knowledge of the best available evidence and on their own clinical experience. The objective of this work is to demonstrate the differences in the way spine surgeons perceive the importance of attributes used to calculate risk of post-operative and quantify the differences by building individual formal models of risk perceptions. We employ a preference-learning method - ROR-UTADIS - to build surgeon-specific additive value functions for risk of complications. Comparing these functions enables the identification and discussion of differences among personal perceptions of risk factors. Our results show there exist differences in surgeons' perceived factors including primary diagnosis, type of surgery, patient's age, body mass index, or presence of comorbidities.