Can Artificial Intelligence Improve the Readability of Patient Education Materials?

BACKGROUND: The recommended readability of online health education materials is at or below the sixth- to eighth-grade level. Nevertheless, more than a decade of research has demonstrated that most online education materials pertaining to orthopaedic surgery do not meet these recommendations. The repeated evidence of this limited progress underscores that unaddressed barriers exist to improving readability, such as the added time and cost associated with writing easily readable materials that cover complex topics. Freely available artificial intelligence (AI) platforms might facilitate the conversion of patient-education materials at scale, but to our knowledge, this has not been evaluated in orthopaedic surgery. QUESTIONS/PURPOSES: (1) Can a freely available AI dialogue platform rewrite orthopaedic patient education materials to reduce the required reading skill level from the high-school level to the sixth-grade level (which is approximately the median reading level in the United States)? (2) Were the converted materials accurate, and did they retain sufficient content detail to be informative as education materials for patients? METHODS: Descriptions of lumbar disc herniation, scoliosis, and spinal stenosis, as well as TKA and THA, were identified from educational materials published online by orthopaedic surgery specialty organizations and leading orthopaedic institutions. The descriptions were entered into an AI dialogue platform with the prompt "translate to fifth-grade reading level" to convert each group of text at or below the sixth-grade reading level. The fifth-grade reading level was selected to account for potential variation in how readability is defined by the AI platform, given that there are several widely used preexisting methods for defining readability levels. The Flesch Reading Ease score and Flesch-Kincaid grade level were determined for each description before and after AI conversion. The time to convert was also recorded. Each education material and its respective conversion was reviewed for factual inaccuracies, and each conversion was reviewed for its retention of sufficient detail for intended use as a patient education document. RESULTS: As presented to the public, the current descriptions of herniated lumbar disc, scoliosis, and stenosis had median (range) Flesch-Kincaid grade levels of 9.5 (9.1 to 10.5), 12.6 (10.8 to 15), and 10.9 (8 to 13.6), respectively. After conversion by the AI dialogue platform, the median Flesch-Kincaid grade level scores for herniated lumbar disc, scoliosis, and stenosis were 5.0 (3.3 to 8.2), 5.6 (4.1 to 7.3), and 6.9 (5 to 7.8), respectively. Similarly, descriptions of TKA and THA improved from 12.0 (11.2 to 13.5) to 6.3 (5.8 to 7.6) and from 11.6 (9.5 to 12.6) to 6.1 (5.4 to 7.1), respectively. The Flesch Reading Ease scores followed a similar trend. Seconds per sentence conversion was median 4.5 (3.3 to 4.9) and 4.5 (3.5 to 4.8) for spine conditions and arthroplasty, respectively. Evaluation of the materials that were converted for ease of reading still provided a sufficient level of nuance for patient education, and no factual errors or inaccuracies were identified. CONCLUSION: We found that a freely available AI dialogue platform can improve the reading accessibility of orthopaedic surgery online patient education materials to recommended levels quickly and effectively. Professional organizations and practices should determine whether their patient education materials exceed current recommended reading levels by using widely available measurement tools, and then apply an AI dialogue platform to facilitate converting their materials to more accessible levels if needed. Additional research is needed to determine whether this technology can be applied to additional materials meant to inform patients, such as surgical consent documents or postoperative instructions, and whether the methods presented here are applicable to non-English language materials.

Few Randomized Controlled Trials in Spine Surgery in the United States Include Sociodemographic Patient Data: A Systematic Review.

INTRODUCTION: The importance of sociodemographic factors such as race, education, and income on spine surgery outcomes has been well established, yet the representation of sociodemographic data within randomized controlled trials (RCTs) in spine literature remains undefined in the United States (U.S). METHODS: Medical literature was reviewed within PubMed for RCTs with "spine" in the title or abstract published within the last 8 years (2014 to 2021) in seven major spine journals. This yielded 128 results, and after application of inclusion criteria (RCTs concerning adult spine pathologies conducted in the U.S), 54 RCTs remained for analysis. Each article's journal of publication, year of publication, and spinal pathology was recorded. Pathologies included cervical degeneration, thoracolumbar degeneration, adult deformity, cervical trauma, and thoracolumbar trauma. Sociodemographic variables collected were race, ethnicity, insurance status, income, work status, and education. The Fisher's exact test was used to compare inclusion of sociodemographic data by journal, year, and spinal pathology. RESULTS: Sociodemographic data were included in the results and in any section of 57.4% (31/54) of RCTs. RCTs reported work status in 25.9% (14/54) of results and 38.9% (21/54) of RCTs included work status in any section. Income was included in the results and mentioned in any section in 13.0% (7/54) of RCTs. Insurance status was in the results or any section of 9.3% (5/54) and 18.5% (10/54) of RCTs, respectively. There was no association with inclusion of sociodemographic data within the results of RCTs as a factor of journal ( P = 0.337), year of publication ( P = 0.286), or spinal pathology ( P = 0.199). DISCUSSION: Despite evidence of the importance of sociodemographic factors on the natural history and treatment outcomes of myriad spine pathologies, this study identifies a surprising absence of sociodemographic data within contemporary RCTs in spine surgery. Failure to include sociodemographic factors in RCTs potentially bias the generalizability of outcome data.

Reported Events Associated With Spine Robots: An Analysis of the Food and Drug Administration's Manufacturer and User Facility Device Experience Database.

STUDY DESIGN: Cross-Sectional Analysis. OBJECTIVES: To summarize medical device reports (MDRs) between August 1, 2017 and November 30, 2021 relating to robot-assisted spine systems within the Manufacturer and User Facility Device Experience (MAUDE) database maintained by The Food and Drug Administration (FDA). METHODS: The MAUDE database was abstract for all MDRs relating to each FDA-approved robot-assisted spine system. Event descriptions were reviewed and characterized into specific event types. Outcome measures include specific robot-assisted spine systems and reported events as detailed by the MDRs. All data is de-identified and in compliance with the Health Insurance Portability and Accountability Act (HIPAA). RESULTS: There were 263 MDRs consisting of 265 reported events. Misplaced screws represented 61.5% (n = 163) of reported events. Of the 163 reported events, 57.1% (n = 93) described greater than 1 misplaced screw, 15.3% (n = 25) required return to the operating room, 8.6% (n = 14) resulted in neurologic injury, 4.3% (n = 7) resulted in dural tear, and 1.2% (n = 2) resulted in hemorrhage or bleeding. Reported events other than misplaced screws included system imprecision detected prior to screw placement (58/265, 21.9%), mechanical failure (23/265, 8.7%), and software failure (18/265, 6.8%). CONCLUSIONS: As more robot-assisted spine systems gain FDA approval and the adoption of these systems continues to grow, documenting and understanding the range of reported events associated with each "tool" is imperative to balancing patient safety with surgical innovation. This study of the MAUDE database provides a unique summary of reported events associated with robot-assisted spine systems that is not directly linked to a research setting.