Rouzrokh, Pouria

Abstract: Electronic health records (EHRs) have created great opportunities to collect various information from clinical patient encounters. However, most EHR data are stored in unstructured form (e.g., clinical notes, surgical notes, and medication instructions), and researchers need data to be in computable form (structured) to extract meaningful relationships involving variables that can influence patient outcomes. Clinical natural language processing (NLP) is the field of extracting structured data from unstructured text documents in EHRs. Clinical text has several characteristics that mandate the use of special techniques to extract structured information from them compared with generic NLP methods. In this article, we define clinical NLP models, introduce different methods of information extraction from unstructured data using NLP, and describe the basic technical aspects of how deep learning-based NLP models work. We conclude by noting the challenges of working with clinical NLP models and summarizing the general steps needed to launch an NLP project.

Background: Establishing imaging registries for large patient cohorts is challenging because manual labeling is tedious and relying solely on DICOM (digital imaging and communications in medicine) metadata can result in errors. We endeavored to establish an automated hip and pelvic radiography registry of total hip arthroplasty (THA) patients by utilizing deep-learning pipelines. The aims of the study were (1) to utilize these automated pipelines to identify all pelvic and hip radiographs with appropriate annotation of laterality and presence or absence of implants, and (2) to automatically measure acetabular component inclination and version for THA images. Methods: We retrospectively retrieved 846,988 hip and pelvic radiography DICOM files from 20,378 patients who underwent primary or revision THA performed at our institution from 2000 to 2020. Metadata for the files were screened followed by extraction of imaging data. Two deep-learning algorithms (an EfficientNetB3 classifier and a YOLOv5 object detector) were developed to automatically determine the radiographic appearance of all files. Additional deep-learning algorithms were utilized to automatically measure the acetabular angles on anteroposterior pelvic and lateral hip radiographs. Algorithm performance was compared with that of human annotators on a random test sample of 5,000 radiographs. Results: Deep-learning algorithms enabled appropriate exclusion of 209,332 DICOM files (24.7%) as misclassified non-hip/pelvic radiographs or having corrupted pixel data. The final registry was automatically curated and annotated in <8 hours and included 168,551 anteroposterior pelvic, 176,890 anteroposterior hip, 174,637 lateral hip, and 117,578 oblique hip radiographs. The algorithms achieved 99.9% accuracy, 99.6% precision, 99.5% recall, and a 99.6% F1 score in determining the radiograph appearance. Conclusions: We developed a highly accurate series of deep-learning algorithms to rapidly curate and annotate THA patient radiographs. This efficient pipeline can be utilized by other institutions or registries to construct radiography databases for patient care, longitudinal surveillance, and large-scale research. The stepwise approach for establishing a radiography registry can further be utilized as a workflow guide for other anatomic areas. Level of Evidence: Diagnostic Level IV . See Instructions for Authors for a complete description of levels of evidence.

Background: Dislocation is the most common reason for early revision following total hip arthroplasty (THA). More than 40 years ago, Lewinnek et al. proposed an acetabular “safe zone” to avoid dislocation. While novel at the time, their study was substantially limited according to modern standards. The purpose of this study was to determine optimal acetabular cup positioning during THA as well as the effect of surgical approach on the topography of the acetabular safe zone and the hazard of dislocation. Methods: Primary THAs that had been performed at a single institution from 2000 to 2017 were reviewed. Acetabular inclination and anteversion were measured using an artificial intelligence neural network; they were validated with performance testing and comparison with blinded grading by 2 orthopaedic surgeons. Patient demographics and dislocation were noted during follow-up. Multivariable Cox proportional-hazards regression, including multidimensional analysis, was performed to define the 3D topography of the acetabular safe zone and its association with surgical approach. Results: We followed 9,907 THAs in 8,081 patients (4,166 women and 3,915 men; 64 ± 13 years of age) for a mean of 5 ± 3 years (range: 2 to 16); 316 hips (3%) sustained a dislocation during follow-up. The mean acetabular inclination was 44° ± 7° and the mean anteversion was 32° ± 9°. Patients who did not sustain a dislocation had a mean anteversion of 32° ± 9° (median, 32°), with the historic ideal anteversion of 15° observed to be only in the third percentile among non-dislocating THAs (p < 0.001). Multivariable modeling demonstrated the lowest dislocation hazards at an inclination of 37° and an anteversion of 27°, with an ideal modern safe zone of 27° to 47° of inclination and 18° to 38° of anteversion. Three-dimensional analysis demonstrated a similar safe-zone location but significantly different safe-zone topography among surgical approaches (p = 0.03) and sexes (p = 0.02). Conclusions: Optimal acetabular positioning differs significantly from historic values, with increased anteversion providing decreased dislocation risk. Additionally, surgical approach and patient sex demonstrated clear effects on 3D safe-zone topography. Further study is needed to characterize the 3D interaction between acetabular positioning and spinopelvic as well as femoral-sided parameters. Level of Evidence: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.