The use of electronic PROMs provides same outcomes as paper version in a spine surgery registry. Results from a prospective cohort study

Ventriglia

Compagnone

et al. 2021

Preprint

Self Cite

Aims To create, using a machine learning (ML) approach, a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome. Materials and Methods 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 (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). Results 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 a ROC AUC = 0.808. Conclusion The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Section: Methodsmentioning

confidence: 99%

The influence of baseline clinical status and surgical strategy on early good to excellent result in spinal lumbar arthrodesis: a machine learning approach

Ventriglia

Compagnone

et al. 2021

Preprint

Self Cite

“…This study was conducted based on prospectively collected data from a retrospective-based institutional spine surgery registry -SpineReg. 29 Ethical approval was obtained from the institutional ethics committee (second amendment to the SPINEREG protocol issued on April 13, 2016) and complied with the Declaration of Helsinki. All patients gave their written informed consent to participate in the registry.…”

Section: Study Setting and Populationmentioning

confidence: 99%

The burden of preoperative fear-avoidance beliefs in workers after thoracic and lumbar spine surgery: a 2-year follow-up study

Bellosta-López

Ponzo

et al. 2023

PAIN

Self Cite

Spinal disorders are the main reasons for sick leave and early retirement among the working population in industrialized countries. When “red flags” are present, spine surgery is the treatment of choice. However, the role of psychosocial factors such as fear-avoidance beliefs in spine surgery outcomes is still debated. The study aims to investigate whether patients presenting high or low levels of fear-avoidance thoughts before the spine surgery reported different surgical results and return-to-work rates over 2 years. From an institutional spine surgery registry, workers surgically treated with a preoperative score in the Oswestry Disability Index (ODI) higher than 20/100 and provided ODI questionnaires, return-to-work status at 3-, 6-, 12-, and 24-month follow-ups were analyzed. A total of 1769 patients were stratified according to the work subscale of the Fear-Avoidance Beliefs Questionnaire (FABQ-W) in high fear (FABQ-W ≥ 34/42) or low fear (FABQ-W < 34/42). Multivariate regression was used to search for preoperative factors, which might interact with FABQ-W. The higher-fear group showed a different recovery pattern, with higher levels of disability according to the ODI (total score, absolute change, frequency of clinically relevant change, and disability categories) and lower return-to-work ratios over the 24-month follow-up. High fear, high disability, greater age, female gender, smoking, and worse physical status at baseline were associated with worse ODI outcomes 2 years after the surgery. In summary, fear-avoidance beliefs significantly influence the speed and the entity of surgical outcomes in the working population. However, the contribution of FABQ-W in predicting long-term disability levels was limited.

“…The study was conducted in a single spine surgery center and it is based on a retrospective review of prospectively collected data from the institutional registry-SpineReg [11]. The inclusion criteria were age ≥ 18 years, both genders, lumbar arthrodesis procedure identified using the ICD-9 code (8106, 8107 or 8108), a follow up assessment (ODI, SF-36 and core outcome measures index-COMI back) and the capability to read and understand the Italian language.…”

Section: Clinical and Demographic Datamentioning

confidence: 99%

The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach

Berjano

Ventriglia

et al. 2021

JPM

Self Cite

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.