Utilizing a comprehensive machine learning approach to identify patients at high risk for extended length of stay following spinal deformity surgery in pediatric patients with early onset scoliosis.

PURPOSE: Early onset scoliosis (EOS) patient diversity makes outcome prediction challenging. Machine learning offers an innovative approach to analyze patient data and predict results, including LOS in pediatric spinal deformity surgery. METHODS: Children under 10 with EOS were chosen from the American College of Surgeon's NSQIP database. Extended LOS, defined as over 5 days, was predicted using feature selection and machine learning in Python. The best model, determined by the area under the curve (AUC), was optimized and used to create a risk calculator for prolonged LOS. RESULTS: The study included 1587 patients, mostly young (average age: 6.94 ± 2.58 years), with 33.1% experiencing prolonged LOS (n = 526). Most patients were female (59.2%, n = 940), with an average BMI of 17.0 ± 8.7. Factors influencing LOS were operative time, age, BMI, ASA class, levels operated on, etiology, nutritional support, pulmonary and neurologic comorbidities. The gradient boosting model performed best with a test accuracy of 0.723, AUC of 0.630, and a Brier score of 0.189, leading to a patient-specific risk calculator for prolonged LOS. CONCLUSIONS: Machine learning algorithms accurately predict extended LOS across a national patient cohort and characterize key preoperative drivers of increased LOS after PSIF in pediatric patients with EOS.

Nearly All Peer-to-Peer Reviews for CT and MRI Prior Authorization Denials for Orthopedic Specialists Are Approved.

In the event of prior authorization denial, physicians may request peer-to-peer review, which may delay treatment and increase administrative burden. The purpose of this study was to quantify the approval rate of peer-to-peer review and evaluate its efficiency in the context of advanced imaging use in an orthopedic practice. Patients at a single outpatient orthopedic clinic initially receiving an insurance denial for computed tomography or magnetic resonance imaging requiring peer-to-peer review from March to December 2022 were prospectively enrolled. Characteristics of the request, peer-to-peer review, and the reviewer and dates in the process were collected. If the study was approved after peer-to-peer review, the date of the imaging study and brief results were recorded. A total of 62 denials were included. One denial was approved prior to peer-to-peer review. Fifty-eight (of 61, 95.1%) reviews were approved, of which 51 (of 58, 87.9%) studies were completed by patients. Reviewers were always physicians (61 of 61, 100%), but of those whose specialty was known, none were orthopedic surgeons. Forty-four of 61 (72.1%) reviewers reported reviewing clinical notes in advance. The median number of days from visit to peer-to-peer review was 9.0 (interquartile range, 7.0-13.25). The median number of days from visit to imaging center appointment was 13.5 (interquartile range, 9.0-20.75) for approved studies. Of the 51 approved studies completed by patients, the results of 38 (74.5%) confirmed the suspected diagnosis. In an orthopedic specialty practice, almost all peer-to-peer reviews were approved, with the majority of the completed studies confirming the suspected diagnosis. Thus, patient care was delayed. Reform is crucial to improve the efficiency of the review process, especially in light of additional administrative and financial burden. [Orthopedics. 202x;4x(x):xx-xx.].

No difference in abstract publication rates between the open and closed American Shoulder and Elbow Surgeons meetings from 2013 to 2019.

BACKGROUND: The American Shoulder and Elbow Surgeons (ASES) society has advanced the practice of shoulder and elbow care through the exhibition of research at academic meetings. The ASES annual meeting is a closed (member-only) conference annually held in October, while the specialty day is an open (non-members included) event that takes place during the American Academy of Orthopaedic Surgeons (AAOS) meeting week in March. This study aims to compare the rate of publication for abstracts presented at the open and closed ASES meetings from 2013 to 2019. METHODS: The ASES website was searched to obtain the annual meeting and specialty day program agendas from 2013 to 2019. A standardized search protocol was employed to identify conference abstracts that went on to be published. Publications associated with an ASES abstract were analyzed through several variables including the time to publication, journal impact factor (JIF), and level of evidence. RESULTS: There was no difference between the rates of publication of the open (76.5%, 121/158) and closed (75.3%, 223/296) meetings (P = .904). The median time to publication significantly differed between the open (7 months, 95% confidence interval [CI]: 5.0-10.0) and closed (11 months, 95% CI: 9.0-13.0) meetings (P = .02). There was no difference between the median JIF between the open (2.69, 95% CI: 2.41-2.81) and closed (2.73, 95% CI: 2.41-2.81) meetings. The distribution of the level of evidence in published articles comparing the open and closed meetings did not differ significantly (P = .446). DISCUSSION: The overall quality of academic research presented at orthopedic subspecialty conferences can be objectively evaluated through abstract publication rates. Our analysis demonstrates that there is not a single significant difference among the publication rates, median JIF, and level of evidence distribution between the ASES open and closed meetings from 2013 to 2019. Impactful research is showcased at both the open and closed meetings. Societies that limit submissions from members only at annual meetings can consider soliciting research from non-members. While the quality of research would not decline if non-ASES members were invited to participate, the presence of a closed annual meeting may be a valuable tool for societies to expand their reach through member-exclusive benefits.

A critical appraisal of Evicore's guidelines for advanced diagnostic imaging of the spine for lower extremity pain with neurological features.

Background: This analysis aims to evaluate the methodological quality of Evicore's spinal imaging guidelines for lower extremity pain with neurological features with or without lower back pain by leveraging the AGREE II tool. The AGREE II tool provides a framework to assess guideline development. It is well validated and has been used to evaluate many other guidelines previously. Methods: Five appraisers used the AGREE II appraisal tool to conduct a comprehensive review of Evicore's spinal imaging guidelines for lower extremity pain with neurological features. Appraisers provided an overall assessment of the guidelines as well as specific scores pertaining to domains including scope and purpose, stakeholder involvement, rigor of development, clarity of presentation, applicability, and editorial independence. Results: Appraisers assigned numerical grades of 2, 2, 2, 3 and 4 (out of 7 total points, with 7 being the highest) for overall quality of the guidelines. Three appraisers recommended use of the guideline with modifications and two appraisers did not recommend the guideline. The AGREE II ratings had good reliability across the different raters [intraclass correlation coefficient (ICC) =0.881, 95% confidence interval (CI): 0.77, 0.94]. Conclusions: Evicore's guidelines would greatly benefit from increased identification and diversification of guideline development parties and stakeholders, increased rigor of development including a more robust discussion of the body of evidence and its strengths and limitations, and incorporation of more explicit suggestions for implementation of guideline recommendations by healthcare providers.

Propensity-Score Matched Analysis Between Extraperitoneal Single Port and Intraperitoneal Multiport Radical Prostatectomy: A Single-Institutional Experience.

OBJECTIVE: To compare the perioperative results and intermediate-term functional outcomes of single port and multiport robotic-assisted laparoscopic prostatectomy by using a propensity-score analysis. MATERIALS AND METHODS: We evaluated all patients who underwent robotic prostatectomy by 3 urologic surgeons at our institution between January 2019 and October 2020. Demographic, intraoperative, and postoperative data were collected and assessed. Patients were matched based on body mass index, Gleason group, and prostate volume using the optimal matching method. RESULTS: Overall, 98 and 165 patients underwent single port and multiport robotic prostatectomy, respectively. Following propensity-score matching, 98 multiport cases were matched 1:1 to single port cases. The median operative time was lower for multiport (111.5 vs 147.0 minutes, P = .0000). Single port had a lower median estimated blood loss (50.0 vs 75.0 mL, P = .0006), pain score on postoperative day 0 (1.0 vs 2.0, P = .0004), opioid use at postoperative day 1 (0.0 [IQR 0.0-5.0] vs 0.0 MME [IQR 0.0-7.5], P = .0058), cumulative opioid use (2.0 vs 7.0 MME, P = .0008), and lymph node yield (4.0 vs 7.0 nodes, P = .0051). Single port had a greater percentage of men regain full erectile function by 6 months (23.8% vs 4.8%, P = .002). CONCLUSION: The single port robotic system is a safe option for localized prostate cancer treatment, offering superior pain control and comparable perioperative results and intermediate-term functional outcomes compared to the multiport robotic approach.

Single-Port Robotic Radical Cystectomy with Intracorporeal Bowel Diversion: Initial Experience and Review of Surgical Outcomes.

Introduction and Objective: Scant literature is available on surgical outcomes of radical cystectomies on the new single-port (SP) system. This study compares short-term outcomes in patients undergoing radical cystectomy with those undergoing intracorporeal urinary diversion (ICUD) on the multiport (MP) vs SP platform. Methods: This institutional review board approved study used a prospective cystectomy database and nonparametric testing including chi-squared, Mann-Whitney U, and Fisher exact tests to analyze all variables stratified by surgical approach. Results: Thirty-four patients underwent radical cystectomy with ICUD from September 1, 2019, to February 8, 2021. Twenty patients were in the MP cohort, whereas 14 were in the SP group. Table 1 presents the demographics of both groups and shows no statistically significant differences. Intra- and postoperative as well as pathology data are given in Table 2. Patients in the SP group had less narcotic use (MP: 25 morphine milligram equivalent [MME] vs SP: 11.5 MME, p = 0.047) and shorter return of bowel function (MP: 3 days vs SP: 2 days, p = 0.032). Operative times were similar between both groups despite having fewer patients undergoing ileal conduit (MP: 85% vs SP: 50%, p = 0.027) in the SP group. In Table 3, we list the early short-term postoperative follow-up data for each group that showed no significant differences between the two groups with an average follow-up of 4.9 months for MP and 4.4 months for SP. Conclusions: Our initial experience with SP robotic cystectomy and ICUD appears to be safe and an effective alternative to MP cystectomies. A learning curve was involved but the overall transition from MP to SP was smooth. Operative times were similar despite fewer patients undergoing ileal diversion, shorter return of bowel function, and less narcotic use in the SP group. Further studies including longer follow-ups with multi-institutional data are underway.

Patient Satisfaction with Orthopedic Telemedicine Health Visits During the COVID-19 Pandemic.

Background:Telemedicine usage in orthopedic surgery has seen a dramatic increase as a result of the severe acute respiratory syndrome coronavirus 2 pandemic. The purpose of this study was to examine patient perceptions with telemedicine at a large orthopedic practice.Materials and Methods:An anonymous online survey was distributed to all patients who received a telemedicine health visit at our institution for musculoskeletal complaints from March 17 to June 1, 2020. Responses were scored on a 5-point Likert scale (strongly disagree, disagree, neutral, agree, and strongly agree, 1-5) and analyzed by average score and percent reaching top box.Results:A majority of patients (76.5%) were satisfied with their visit, and only 19.2% did not want telemedicine as a future option. Patients who presented for follow-up visits (4.11 vs. 3.94, p = 0.0053; 48% vs. 41%, p = 0.02) and utilized video (4.21 vs. 3.88, p < 0.001; 51% vs. 39%, p < 0.001) were more satisfied. Average satisfaction between older (>65 years) and younger patients was similar (4.06 vs. 4.06, p = 0.97), however, younger patients were more likely to reach top box (42% vs. 51%, p < 0.001). Confidence that the physician came to the correct diagnosis (r = 0.78, p < 0.001) and receiving the same information and care as an in-office visit (r = 0.60, p < 0.001) demonstrated the strongest correlation with satisfaction and desire for future telemedicine visits, respectively. Interestingly, 31.1% of patients would have sought treatment elsewhere had telemedicine not been an option.Conclusions:Overall, satisfaction rates are high for orthopedic patients undergoing telemedicine visits. Patients are more confident in telemedicine when presenting for a follow-up visit and with the use of video.

Differences in Patient and Physician Perceptions of Urgency for Musculoskeletal Conditions During the COVID-19 Pandemic.

In 2020, the coronavirus disease 2019 (COVID-19) pandemic limited musculoskeletal care to urgent or "nonelective" office visits and procedures. No guidelines exist to inform patients or physicians what meets these criteria. The purpose of this multi-institutional study was to describe the differences in perceptions of urgency for musculoskeletal complaints between patients and providers during the COVID-19 pandemic. An anonymous survey was distributed to patients who visited the authors' orthopedic clinics in January and February 2020 and practicing orthopedic surgeons. The surveys were administered in May 2020 after COVID-19 was officially labeled a pandemic and included questions regarding demographic information and perceptions of orthopedic urgency. A total of 1491 patients and 128 physicians completed the surveys. A significantly higher percentage of physicians considered the following diagnoses an appropriate indication for an urgent visit compared with patients: fracture (P<.001), acute dislocation (P<.001), infection (P<.001), neurologic compromise (P<.001), tumor (P<.001), acute tendon injury (P<.001), weakness (P<.001), inability to bear weight (P<.001), post-surgical problem (P<.001), and painful joint effusion (P<.001). There were no significant differences in the perception of urgency for the following conditions: bursitis/tendonitis (P=1.00), joint/extremity deformity without pain (P=.113), and loss of range of motion of a joint (P=.467). Younger patients and those with higher levels of education were significantly more likely to consider their conditions urgent. Patients may require additional education to prevent delay in treatment of urgent conditions-especially time-sensitive conditions such as neurologic compromise, tumors, and infections-when access to physicians is limited. [Orthopedics. 2021;44(4):e534-e538.].