Search

Physical therapy (PT) is an important component of low back pain (LBP) management. Despite established guidelines, heterogeneity in medical management remains common. We sought to understand how copayments impact timing and utilization of PT in newly diagnosed LBP. The IBM Watson Health MarketScan claims database was used in a longitudinal setting. Adult patients with LBP. The primary outcomes-of-interest were timing and overall utilization of PT services. Additional outcomes-of-interest included timing of opioid prescribing. Actual and inferred copayments based on nonnonprimary care provider visit claims were used to evaluate the relationship between PT copayment and incidence of PT initiation. Multivariable regression models were used to evaluate factors influencing PT usage. Overall, 2,467,389 patients were included. PT initiation, among those with at ≥1 PT service during the year after LBP diagnosis (30.6%), occurred at a median of 8 days postdiagnosis (IQR 1–55). Among those with at least one PT encounter, incidence of subsequent PT visits was significantly lower for those with high initial PT copayments. High initial PT copayments, while inversely correlated with PT utilization, were directly correlated with subsequent opioid use (0.77 prescriptions/patient [$0 PT copayment] versus 1.07 prescriptions/patient [$50–74 PT copayment]; 1.15 prescriptions/patient [$75+ PT copayment]). Among patients with known opioid and PT copayments, higher PT copayments were correlated with faster opioid use while higher opioid copayments were correlated with faster PT use (Spearman p<.05). For multivariable whole-cohort analyses, incidence of PT initiation among patients with inferred copayments in the 50–75th and 75–100th percentiles was significantly lower than those below the 50th percentile (HR=0.893 [95%CI 0.887–0.899] and HR=0.905 [95%CI 0.899–0.912], respectively). Higher PT copayments correlated with reduced PT utilization; higher PT copayments and lower opioid copayments were independent contributors to delayed PT initiation and higher opioid use. In patients covered by plans charging high PT copayments, opioid use was significantly higher. Copays may impact long-term adherence to PT. [ABSTRACT FROM AUTHOR]

Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art model of revision prediction of cervical spine surgery using laboratory and operative variables. Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016 and 2022 were identified (N = 3151), and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and time frame. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables. Red blood cell count, hemoglobin, hematocrit, mean corpuscular hemoglobin concentration, red blood cell distribution width, platelet count, carbon dioxide, anion gap, and calcium all were significantly associated with ≥1 revision cohorts. For the prediction of 3-month revision, the deep neural network achieved an area under the receiver operating characteristic curve of 0.833. The model demonstrated increased performance for anterior versus posterior and arthrodesis versus decompression procedures. Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables in a cervical spine surgery cohort. This work used standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of one-size-fits-all risk scores for spine procedures. [ABSTRACT FROM AUTHOR]

Type II odontoid fractures (OF) are among the most common cervical spine injuries in the geriatric population. However, there is a paucity of literature regarding their epidemiology. Additionally, the optimal management of these injuries remains controversial, and no study has evaluated the short-term outcomes of geriatric patients presenting to emergency departments (ED). This study aims to document the epidemiology of geriatric patients presenting to EDs with type II OFs and determine whether surgical management was associated with early adverse outcomes such as in-hospital mortality and discharge to skilled nursing facilities (SNF). This is a retrospective cohort study. Data was used from the 2016–2020 Nationwide Emergency Department Sample. Patient encounters corresponding to type II OFs were identified. Patients younger than 65 at the time of presentation to the ED and those with concomitant spinal pathology were excluded. The association between the surgical management of geriatric type II OFs and outcomes such as in-hospital mortality and discharge to SNFs. Patient, fracture, and surgical management characteristics were recorded. A propensity score matched cohort was constructed to reduce differences in age, comorbidities, and injury severity between patients undergoing operative and nonoperative management. Additionally, to develop a positive control for the analysis of geriatric patients with type II OFs and no other concomitant spinal pathology, a cohort of patients that had been excluded due to the presence of a concomitant spinal cord injury (SCI) was also constructed. Multivariate regressions were then performed on both the matched and unmatched cohorts to ascertain the associations between surgical treatment and in-hospital mortality, inpatient length of stay, encounter charges, and discharge to SNFs. A total of 11,325 encounters were included. The mean total charge per encounter was $60,221. 634 (5.6%) patients passed away during their encounters. In total, 1,005 (8.9%) patients were managed surgically. Surgical management of type II OFs was associated with a 316% increase in visit charge (95% CI: 291%–341%, p<.001), increased inpatient length of stay (IRR: 2.87, 95% CI: 2.62–3.12, p<.001), and increased likelihood of discharge to SNFs (OR=2.62, 95% CI: 2.26–3.05, p<.001), but decreased in-hospital mortality (OR=0.32, CI: 0.21-0.45, p<.001). The propensity score matched cohort consisted of 2,010 patients, matching each of the 1,005 that underwent surgery to 1,005 that did not. These cohorts were well balanced across age (78.24 vs 77.91 years), Elixhauser Comorbidity Index (3.68 vs 3.71), and Injury Severity Score (30.15 vs 28.93). This matching did not meaningfully alter the associations determined between surgical management and in-hospital mortality (OR=0.34, CI=0.21–0.55, p<.001) or SNF discharge (OR=2.59, CI=2.13–3.16, p<.001). Lastly, the positive control cohort of patients with concurrent SCI had higher rates of SNF discharge (50.0% vs 42.6%, p<.001), surgical management (32.3% vs 9.7%, p<.001), and in-hospital mortality (28.9% vs 5.6%, p<.001). This study lends insight into the epidemiology of geriatric type II OFs and quantifies risk factors influencing adverse outcomes. Patient informed consent should include a discussion of the protective association between definitive surgical management and in-hospital mortality against potential operative morbidity, increased lengths of hospital stay, and increased likelihood of discharge to SNFs. This information may impact patient treatment selection and decision making. [ABSTRACT FROM AUTHOR]

Background: Adult spinal deformities (ASD) are varied spinal abnormalities, often necessitating surgical intervention when associated with pain, worsening deformity, or worsening function. Predicting post-operative complications and revision surgery is critical for surgical planning and patient counseling. Due to the relatively small number of cases of ASD surgery, machine learning applications have been limited to traditional models (e.g., logistic regression or standard neural networks) and coarse clinical variables. We present the novel application of advanced models (CNN, LLM, GWAS) using complex data types (radiographs, clinical notes, genomics) for ASD outcome prediction. Methods: We developed a CNN trained on 209 ASD patients (1549 radiographs) from the Stanford Research Repository, a CNN pre-trained on VinDr-SpineXR (10,468 spine radiographs), and an LLM using free-text clinical notes from the same 209 patients, trained via Gatortron. Additionally, we conducted a GWAS using the UK Biobank, contrasting 540 surgical ASD patients with 7355 non-surgical ASD patients. Results: The LLM notably outperformed the CNN in predicting pulmonary complications (F1: 0.545 vs. 0.2881), neurological complications (F1: 0.250 vs. 0.224), and sepsis (F1: 0.382 vs. 0.132). The pre-trained CNN showed improved sepsis prediction (AUC: 0.638 vs. 0.534) but reduced performance for neurological complication prediction (AUC: 0.545 vs. 0.619). The LLM demonstrated high specificity (0.946) and positive predictive value (0.467) for neurological complications. The GWAS identified 21 significant (p < 10−5) SNPs associated with ASD surgery risk (OR: mean: 3.17, SD: 1.92, median: 2.78), with the highest odds ratio (8.06) for the LDB2 gene, which is implicated in ectoderm differentiation. Conclusions: This study exemplifies the innovative application of cutting-edge models to forecast outcomes in ASD, underscoring the utility of complex data in outcome prediction for neurosurgical conditions. It demonstrates the promise of genetic models when identifying surgical risks and supports the integration of complex machine learning tools for informed surgical decision-making in ASD. [ABSTRACT FROM AUTHOR]