Correlative Assessment of Machine Learning-Based Cobb Angle Measurements and Human-Based Measurements in Adolescent Idiopathic and Congenital Scoliosis.

Purpose: Scoliosis is a complex spine deformity with direct functional and cosmetic impacts on the individual. The reference standard for assessing scoliosis severity is the Cobb angle which is measured on radiographs by human specialists, carrying interobserver variability and inaccuracy of measurements. These limitations may result in lack of timely referral for management at a time the scoliotic deformity progression can be saved from surgery. We aimed to create a machine learning (ML) model for automatic calculation of Cobb angles on 3-foot standing spine radiographs of children and adolescents with clinical suspicion of scoliosis across 2 clinical scenarios (idiopathic, group 1 and congenital scoliosis, group 2). Methods: We retrospectively measured Cobb angles of 130 patients who had a 3-foot spine radiograph for scoliosis within a 10-year period for either idiopathic or congenital anomaly scoliosis. Cobb angles were measured both manually by radiologists and by an ML pipeline (segmentation-based approach-Augmented U-Net model with non-square kernels). Results: Our Augmented U-Net architecture achieved a Symmetric Mean Absolute Percentage Error (SMAPE) of 11.82% amongst a combined idiopathic and congenital scoliosis cohort. When stratifying for idiopathic and congenital scoliosis individually a SMAPE of 13.02% and 11.90% were achieved, respectively. Conclusion: The ML model used in this study is promising at providing automated Cobb angle measurement in both idiopathic scoliosis and congenital scoliosis. Nevertheless, larger studies are needed in the future to confirm the results of this study prior to translation of this ML algorithm into clinical practice.

Performance of a novel eight-color flow cytometry panel for measurable residual disease assessment of chronic lymphocytic leukemia.

BACKGROUND: Measurable residual disease (MRD) is an important prognostic indicator of chronic lymphocytic leukemia (CLL). Different flow cytometric panels have been developed for the MRD assessment of CLL in Western countries; however, the application of these panels in China remains largely unexplored. METHODS: Owing to the requirements for high accuracy, reproducibility, and comparability of MRD assessment in China, we investigated the performance of a flow cytometric approach (CD45-ROR1 panel) to assess MRD in patients with CLL. The European Research Initiative on CLL (ERIC) eight-color panel was used as the "gold standard." RESULTS: The sensitivity, specificity, and concordance rate of the CD45-ROR1 panel in the MRD assessment of CLL were 100% (87/87), 88.5% (23/26), and 97.3% (110/113), respectively. Two of the three inconsistent samples were further verified using next-generation sequencing. In addition, the MRD results obtained from the CD45-ROR1 panel were positively associated with the ERIC eight-color panel results for MRD assessment (R = 0.98, p < 0.0001). MRD detection at low levels (≤1.0%) demonstrated a smaller difference between the two methods (bias, -0.11; 95% CI, -0.90 to 0.68) than that at high levels (>1%). In the reproducibility assessment, the bias was smaller at three data points (within 24, 48, and 72 h) in the CD45-ROR1 panel than in the ERIC eight-color panel. Moreover, MRD levels detected using the CD45-ROR1 panel for the same samples from different laboratories showed a strong statistical correlation (R = 0.99, p < 0.0001) with trivial interlaboratory variation (bias, 0.135; 95% CI, -0.439 to 0.709). In addition, the positivity rate of MRD in the bone marrow samples was higher than that in the peripheral blood samples. CONCLUSIONS: Collectively, this study demonstrated that the CD45-ROR1 panel is a reliable method for MRD assessment of CLL with high sensitivity, reproducibility, and reliability.

Assessment of clonality in T-cell large granular lymphocytic leukemia: flow cytometric T cell receptor Vß repertoire and T cell receptor gene rearrangement.

The usefulness of flow cytometric variable ß-chain repertoire (FC-Vß) and T-cell receptor gene rearrangement (TCR-GR) analyses for differentiating T-cell large granular lymphocytic leukemia (T-LGLL) from reactive T-large granular lymphocyte (T-LGL) lymphocytosis has been insufficiently studied to date. In this study, we analyzed the diagnostic value of TCR-GR and FC-Vß analysis in T-LGLL, and compared these results. In our study, FC-Vß analysis was positive in all cases of T-LGLL, and clonality assessment of FC-Vß had equal sensitivity and specificity to GeneScanning analysis but was more sensitive than heteroduplex analysis. Suspected T-cell clonality can best be addressed by evaluating two TCR targets (TCRß and TCRγ), either in parallel or consecutively. Signal transducer and activator of transcription 3 (STAT3) mutation may provide a diagnostic tool for classifying some cases of T-LGL lymphocytosis as true T-LGLL. Our results further demonstrate a significant correlation of STAT3 mutation with pure red cell aplasia, neutropenia, hepatomegaly, ß2-microglobulin and anemia.

Using the Chinese version of Memorial Delirium Assessment Scale to describe postoperative delirium after hip surgery.

OBJECTIVE: Memorial Delirium Assessment Scale (MDAS) assesses severity of delirium. However, whether the MDAS can be used in a Chinese population is unknown. Moreover, the optimal postoperative MDAS cutoff point for describing postoperative delirium in Chinese remains largely to be determined. We therefore performed a pilot study to validate MDAS in the Chinese language and to determine the optimal postoperative MDAS cutoff point for delirium. METHODS: Eighty-two patients (80 ± 6 years, 21.9% male), who had hip surgery under general anesthesia, were enrolled. The Confusion Assessment Method (CAM) and Mini-Mental State Examination (MMSE) were administered to the patients before surgery. The CAM and MDAS were performed on the patients on the first, second and fourth postoperative days. The reliability and validity of the MDAS were determined. A receiver operating characteristic (ROC) curve was used to determine the optimal Chinese version MDAS cutoff point for the identification of delirium. RESULTS: The Chinese version of the MDAS had satisfactory internal consistency (α = 0.910). ROC analysis obtained an average optimal MDAS cutoff point of 7.5 in describing the CAM-defined postoperative delirium, with an area under the ROC of 0.990 (95% CI 0.977-1.000, P < 0.001). CONCLUSIONS: The Chinese version of the MDAS had good reliability and validity. The patients whose postoperative Chinese version MDAS cutoff point score was 7.5 would likely have postoperative delirium. These results have established a system for a larger scale study in the future.