Quantified trends in provider reimbursement and utilization volume in colorectal cancer screenings: analysis of Medicare claims from 2000 to 2019.

AIM: Colorectal cancer (CRC) screening rates in the United States remain persistently below guideline targets, partly due to suboptimal patient utilization and provider reimbursement. To guide long-term national utilization estimates and set reasonable screening adherence targets, this study aimed to quantify trends in utilization of and reimbursement for CRC screenings using Medicare claims. METHOD: Inflation-adjusted reimbursements and utilization volume associated with each CRC screening code were abstracted from Medicare claims between 2000 and 2019. Screenings, screenings/100 000 enrolees and reimbursement/screening were analysed with linear regression and compared with the equality of slopes tests. Average reimbursement per screening was compared using analysis of variance with Dunnett's T3 multiple comparisons test. RESULTS: The growth rate of multitarget stool DNA tests (mt-sDNA)/100 000 was the highest at 170.4 screenings/year (R2 = 0.99, p ≤ 0.001), while that of faecal occult blood tests/100 000 was the lowest at -446.4 screenings/year (R2 = 0.90, p ≤ 0.001) (p ≤ 0.001). Provider reimbursements averaged $546.95 (95% CI $520.12-$573.78) per mt-sDNA screening, significantly higher than reimbursements for all invasive screenings. Only FOBTs significantly increased in reimbursement per screening at $0.62/year (R2 = 0.91, p ≤ 0.001). CONCLUSION: We derived forecastable trend numbers for utilization and provider reimbursement. Faecal immunochemical tests/100 000 and mt-sDNA screenings/100 000 increased most rapidly during the entire study period. The number of nearly all invasive screenings/100 000 decreased rapidly; the number of colonoscopies/100 000 increased slightly, probably due to superior diagnostic strength. These trends indicate the that replacement of other invasive modalities with accessible noninvasive screenings will account for much of future screening behaviour and thus reductions in CRC incidence and mortality, especially given providers' reimbursement incentive to screen average-risk patients with stool-based tests.

Automatic Segmentation and Quantification of Upper Airway Anatomic Risk Factors for Obstructive Sleep Apnea on Unprocessed Magnetic Resonance Images.

RATIONALE AND OBJECTIVES: Accurate segmentation of the upper airway lumen and surrounding soft tissue anatomy, especially tongue fat, using magnetic resonance images is crucial for evaluating the role of anatomic risk factors in the pathogenesis of obstructive sleep apnea (OSA). We present a convolutional neural network to automatically segment and quantify upper airway structures that are known OSA risk factors from unprocessed magnetic resonance images. MATERIALS AND METHODS: Four datasets (n = [31, 35, 64, 76]) with T1-weighted scans and manually delineated labels of 10 regions of interest were used for model training and validations. We investigated a modified U-Net architecture that uses multiple convolution filter sizes to achieve multi-scale feature extraction. Validations included four-fold cross-validation and leave-study-out validations to measure generalization ability of the trained models. Automatic segmentations were also used to calculate the tongue fat ratio, a biomarker of OSA. Dice coefficient, Pearson's correlation, agreement analyses, and expert-derived clinical parameters were used to evaluate segmentations and tongue fat ratio values. RESULTS: Cross-validated mean Dice coefficient across all regions of interests and scans was 0.70 ± 0.10 with highest mean Dice coefficient in the tongue (0.89) and mandible (0.81). The accuracy was consistent across all four folds. Also, leave-study-out validations obtained comparable accuracy across uniquely acquired datasets. Segmented volumes and the derived tongue fat ratio values showed high correlation with manual measurements, with differences that were not statistically significant (p < 0.05). CONCLUSION: High accuracy of automated segmentations indicate translational potential of the proposed method to replace time consuming manual segmentation tasks in clinical settings and large-scale research studies.