Incidental durotomy: predictive risk model and external validation of natural language process identification algorithm

Abstract

<jats:sec><jats:title>OBJECTIVE</jats:title><jats:p>Incidental durotomy is a common complication of elective lumbar spine surgery seen in up to 11% of cases. Prior studies have suggested patient age and body habitus along with a history of prior surgery as being associated with an increased risk of dural tear. To date, no calculator has been developed for quantifying risk. Here, the authors’ aim was to identify independent predictors of incidental durotomy, present a novel predictive calculator, and externally validate a novel method to identify incidental durotomies using natural language processing (NLP).</jats:p></jats:sec><jats:sec><jats:title>METHODS</jats:title><jats:p>The authors retrospectively reviewed all patients who underwent elective lumbar spine procedures at a tertiary academic hospital for degenerative pathologies between July 2016 and November 2018. Data were collected regarding surgical details, patient demographic information, and patient medical comorbidities. The primary outcome was incidental durotomy, which was identified both through manual extraction and the NLP algorithm. Multivariable logistic regression was used to identify independent predictors of incidental durotomy. Bootstrapping was then employed to estimate optimism in the model, which was corrected for; this model was converted to a calculator and deployed online.</jats:p></jats:sec><jats:sec><jats:title>RESULTS</jats:title><jats:p>Of the 1279 elective lumbar surgery patients included in this study, incidental durotomy occurred in 108 (8.4%). Risk factors for incidental durotomy on multivariable logistic regression were increased surgical duration, older age, revision versus index surgery, and case starts after 4 <jats:sc>pm</jats:sc>. This model had an area under curve (AUC) of 0.73 in predicting incidental durotomies. The previously established NLP method was used to identify cases of incidental durotomy, of which it demonstrated excellent discrimination (AUC 0.97).</jats:p></jats:sec><jats:sec><jats:title>CONCLUSIONS</jats:title><jats:p>Using multivariable analysis, the authors found that increased surgical duration, older patient age, cases started after 4 <jats:sc>pm</jats:sc>, and a history of prior spine surgery are all independent positive predictors of incidental durotomy in patients undergoing elective lumbar surgery. Additionally, the authors put forth the first version of a clinical calculator for durotomy risk that could be used prospectively by spine surgeons when counseling patients about their surgical risk. Lastly, the authors presented an external validation of an NLP algorithm used to identify incidental durotomies through the review of free-text operative notes. The authors believe that these tools can aid clinicians and researchers in their efforts to prevent this costly complication in spine surgery.</jats:p></jats:sec>

Intelligence-Based Spine Care Model: A New Era of Research and Clinical Decision-Making

“…More specifically, numerous applications of such techniques have been observed in orthopedic and neurological spine surgery research. Ehresman et al 55 employed NLP algorithms to extract patient data information to identify incidental durotomies through the review of free-text operative notes. Karhade et al 56 proved that NLP may offer entities such as national spine registries and hospital quality and safety departments automated tracking of such incidental durotomies with extreme accuracy.…”

Natural language processing in low back pain and spine diseases: A systematic review

“…It is defined as an inadvertent tearing of the dura during surgery with cerebrospinal fluid (CSF) extravasation or bulging of the arachnoid [ 30 ]. The group of Karhade and Ehresman faced the problem of automatizing detection of ID events from operative notes [ 31 , 32 ].…”

“…Their model always outperformed these methodologies, also showing a higher standard net benefit at all thresholds. Ehresman et al [ 32 ] used the same model to statistically analyze 1279 patients. Also, the same research unit exploited the same pipeline in the two prediction tasks, to anticipate reoperation due to wound infection after lumbar discectomy [ 37 ] and unplanned readmissions after lumbar fusion [ 38 ].…”

“…Other examples include operative notes, obviously used for the intra-operative tasks [31][32][33][34], and post-operative ones too [37,38]. Furthermore, the article from Karhade et al [38], compared different kinds of clinical notes, including discharge summaries [22], and physicians and nursing notes.…”

“…In both cases, the model was implemented together with a Least Absolute Shrinkage and Selection Operator (LASSO) regularization. The latter was particularly employed by Karhade et al in several tasks [31][32][33]37,38]. Another used algorithm was the Support Vector Machine (SVM), employed in [23] to identify clues of axSpA and in [24] both to directly identify axSpA and to extract a feature for a multimodal random forest.…”