Predicting no-shows in paediatric orthopaedic clinics

Risk Factor Analysis for Growth Arrest in Paediatric Physeal Fractures-A Prospective Study

Background: Fractures through the physis account for 18-30% of all paediatric fractures, leading to growth arrest in up to 5.5% of cases. We have limited knowledge to predict which physeal fractures result in growth arrest and subsequent deformity or limb length discrepancy. The purpose of this study is to identify factors associated with physeal growth arrest to improve patient outcomes. Methods: This prospective cohort study was designed to develop a clinical prediction model for growth arrest after physeal injury. Patients ≤ 18 years old presenting within four weeks of injury were enrolled if they had open physes and sustained a physeal fracture of the humerus, radius, ulna, femur, tibia or fibula. Patients with prior history of same-site fracture or a condition known to alter bone growth or healing were excluded. Demographic data, potential prognostic indicators, and radiographic data were collected at baseline, during healing, and at one- and two-years post-injury. Results: A total of 332 patients had at least six months of follow-up or a diagnosis of growth arrest within six months of injury. In a comparison analysis, patients who developed growth arrest were more likely to be older (12.8 years vs. 9.4 years) and injured on the right side (53.0% vs. 45.7%). Initial displacement and angulation rates were higher in the growth arrest group (59.0% vs. 47.8% and 47.0% vs. 38.8%, respectively), but the amount of angulation was similar (27.0° vs. 28.4°). Rates of growth arrest were highest in distal femoral fractures (86%). Conclusions: The incidence of growth arrest in this patient population appears higher than the past literature reports at 30.1%. However, there may be variances in diagnostic criteria for growth arrest, and the true incidence may be lower. A number of patients were approaching skeletal maturity, and any growth arrest is likely to have less clinical significance in these cases. Further prospective long-term follow-up is required to determine risk factors, incidence, and true clinical impact of growth arrest when it does occur.

Predictors of Subspecialty Appointment Scheduling and Completion for Patients Referred From a Pediatric Primary Care Clinic

Failure to complete subspecialty referrals decreases access to subspecialty care and may endanger patient safety. We conducted a retrospective analysis of new patient referrals made to the 14 most common referral departments at Boston Children's Hospital from January 1 to December 31, 2017. The sample included 2031 patient referrals. The mean wait time between referral and appointment date was 39.6 days. In all, 87% of referrals were scheduled and 84% of scheduled appointments attended, thus 73% of the original referrals were completed. In multivariate analysis, younger age, medical complexity, being a non-English speaker, and referral to a surgical subspecialty were associated with a higher likelihood of referral completion. Black and Hispanic/Latino race/ethnicity, living in a Census tract with Social Vulnerability Index (SVI) ≥ 90th percentile, and longer wait times were associated with a lower likelihood of appointment attendance. Future interventions should consider both health care system factors such as appointment wait times and community-level barriers to referral completion.

Socioeconomic, Racial, and Insurance Disparities in Clinical Outcomes After Surgery Among Patients With Idiopathic Scoliosis

BACKGROUND

Socioeconomic status (SES), race, and insurance type correlate with initial curve severity for patients with idiopathic scoliosis, but less is known regarding how these variables impact surgical outcomes. The objectives of this study were to determine the influence of SES, race, and insurance on preoperative appointment attendance, likelihood of obtaining a preoperative second opinion, brace prescription, missed 6 or 12-month postsurgical appointments, incidence of emergency department visits 0 to 90 days after surgery, and major complications within a year of surgery.

METHODS

A review of 421 patients diagnosed with idiopathic scoliosis who underwent surgery at a single high-volume pediatric spinal deformity institution between May 2015 and October 2021 was conducted. Area Deprivation Index, a quantitative measure of SES, was collected. Scores were stratified by quartile; higher scores indicated a lower SES. χ 2 tests for correlation were performed to determine whether clinical outcomes were dependent upon Area Deprivation Index, race, or insurance type; P ≤0.05 was significant.

RESULTS

The sample was 313 Caucasian (74%), 69 (16%) black, and 39 (9.3%) other patients. More patients had private versus public insurance (80% vs 20%) and were of higher SES. The likelihood of missing preoperative appointments was higher for black patients ( P = 0.037). Those with lower SES missed more postoperative appointments and received less bracing and second opinions ( P = 0.038, P = 0.017, P = 0.008, respectively). Being black and publicly insured correlated with fewer brace prescriptions ( P < 0.001, P = 0.050) and decreased rates of obtaining second opinions ( P = 0.004,  P = 0.001).

CONCLUSION

Patients with idiopathic scoliosis surgery who were Caucasian, privately insured, and of higher SES were more likely to seek preoperative second opinions, be prescribed a brace, and attend postoperative appointments. Recognition of the inherent health care disparities prevalent within each pediatric spine surgery referral region is imperative to better inform local and national institutional level programs to educate and assist patients and families most at risk for disparate access to scoliosis care.

LEVEL OF EVIDENCE

Level III; retrospective case-control study.

The Use of Machine Learning to Predict Late Arrivals at the Adult Outpatient Department

INTRODUCTION

Patient unpunctuality leads to delays in the delivery of care and increased waiting times, resulting in crowdedness. Late arrivals for adult outpatient appointments are a challenge for healthcare, contributing to negative effects on the efficiency of health services as well as wasted time, budget, and resources. This study aims to identify factors and characteristics associated with tardy arrivals at adult outpatient appointments using machine learning and artificial intelligence. The goal is to create a predictive model using machine learning models capable of predicting adult patients arriving late to their appointments. This would support effective and accurate decision-making in scheduling systems, leading to better utilization and optimization of healthcare resources.

METHODS

A retrospective cohort review of adult outpatient appointments between January 1, 2019, and December 31, 2019, was undertaken at a tertiary hospital in Riyadh. Four machine learning models were used to identify the best prediction model that could predict late-arriving patients based on multiple factors.

RESULTS

A total of 1,089,943 appointments for 342,974 patients were conducted. There were 128,121 visits (11.7%) categorized as late arrivals. The best prediction model was Random Forest, with a high accuracy of 94.88%, a recall of 99.72%, and a precision of 90.92%. The other models showed different results, such as XGBoost with an accuracy of 68.13%, Logistic Regression with an accuracy of 56.23%, and GBoosting with an accuracy of 68.24%.

CONCLUSION

This paper aims to identify the factors associated with late-arriving patients and improve resource utilization and care delivery. Despite the overall good performance of the machine learning models developed in this study, not all variables and factors included contribute significantly to the algorithms' performance. Considering additional variables could improve machine learning performance outcomes, further enhancing the practical application of the predictive model in healthcare settings.

Sociodemographic Missed-care Predictors for Pediatric Orthopaedic Telemedicine During COVID-19

BACKGROUND

Increased telehealth services may not benefit communities already lacking access to care. Race, socioeconomic status, and insurance type are known to predict missed-care opportunities (MCO) in health care. We examined differences in pediatric orthopaedic telemedicine MCOs during the COVID-19 pandemic, compared with MCOs of in-person visits in a prepandemic time frame. We hypothesized that groups with known health disparities would experience higher rates of pediatric orthopedic telemedicine MCOs.

METHODS

We retrospectively analyzed pediatric orthopaedic telemedicine MCOs during the COVID-19 pandemic lockdown (March-May 2020) and in-person pediatric orthopaedic visit MCOs during a nonpandemic timeframe (March-May 2019). We examined predictors of MCOs including race, ethnicity, language, insurance status, and other socioeconomic determinants of health.

RESULTS

There were 1448 telemedicine appointments in the pandemic cohort and 8053 in-person appointments in the prepandemic cohort. Rates of telemedicine MCOs (12.5%; n=181) were significantly lower than in-person MCOs (19.5%; n=1566; P<0.001). Telemedicine appointments with public insurance or without insurance (P<0.001) and being Black or Hispanic/Latinx (P=0.003) were associated with MCOs. There were significant differences between in-person MCOs and telemedicine MCOs among all predictors studied, except for orthopaedic subspecialty team and patient's social vulnerability index.

CONCLUSIONS

Patients with telemedicine appointments during the COVID-19 pandemic were less likely to experience MCOs than patients with in-person visits during the nonpandemic timeframe. However, when controlling for socioeconomic factors including race, ethnicity, and insurance type, disparities found for in-person visits persisted with the shift to telemedicine. Pediatric orthopaedists should be aware that the use of telemedicine does not necessarily improve access for our most vulnerable patients.

LEVEL OF EVIDENCE

Level III.

Sociodemographic and Appointment Factors Affecting Missed Opportunities to Provide Neonatal Ultrasound Imaging

PURPOSE

The aim of this study was to assess disparities in outpatient imaging missed care opportunities (IMCOs) for neonatal ultrasound by sociodemographic and appointment factors at a large urban pediatric hospital.

METHODS

A retrospective review was performed among patients aged 0 to 28 days receiving one or more outpatient appointments for head, hip, renal, or spine ultrasound at the main hospital or satellite sites from 2008 to 2018. An IMCO was defined as a missed ultrasound or cancellation <24 hours in advance. Population-average correlated logistic regression modeling estimated the odds of IMCOs for six sociodemographic (age, sex, race/ethnicity, language, insurance, and region of residence) and seven appointment (type of ultrasound, time, day, season, site, year, and distance to appointment) factors. The primary analysis included unknown values as a separate category, and the secondary analysis used multiple imputation to impute genuine categories from unknown variables.

RESULTS

The data set comprised 5,474 patients totaling 6,803 ultrasound appointments. IMCOs accounted for 4.4% of appointments. IMCOs were more likely for Black (odds ratio [OR], 3.31; P < .001) and other-race neonates (OR, 2.66; P < .001) and for patients with public insurance (OR, 1.78; P = .002). IMCOs were more likely for appointments at the main hospital compared with satellites (P < .001), during work hours (P = .021), and on weekends (P < .001). Statistical significance for primary and secondary analyses was quantitatively similar and qualitatively identical.

CONCLUSIONS

Marginalized racial groups and those with public insurance had a higher rate of IMCOs in neonatal ultrasound. This likely represents structural inequities faced by these communities, and more research is needed to identify interventions to address these inequities in care delivery for vulnerable neonatal populations.

A Machine Learning-Based Approach for Predicting Patient Punctuality in Ambulatory Care Centers

Late-arriving patients have become a prominent concern in several ambulatory care clinics across the globe. Accommodating them could lead to detrimental ramifications such as schedule disruption and increased waiting time for forthcoming patients, which, in turn, could lead to patient dissatisfaction, reduced care quality, and physician burnout. However, rescheduling late arrivals could delay access to care. This paper aims to predict the patient-specific risk of late arrival using machine learning (ML) models. Data from two different ambulatory care facilities are extracted, and a comprehensive list of predictor variables is identified or derived from the electronic medical records. A comparative analysis of four ML algorithms (logistic regression, random forests, gradient boosting machine, and artificial neural networks) that differ in their training mechanism is conducted. The results indicate that ML algorithms can accurately predict patient lateness, but a single model cannot perform best with respect to predictive performance, training time, and interpretability. Prior history of late arrivals, age, and afternoon appointments are identified as critical predictors by all the models. The ML-based approach presented in this research can serve as a decision support tool and could be integrated into the appointment system for effectively managing and mitigating tardy arrivals.