[Application of Deep Learning to Diagnose and Classify Adolescent Idiopathic Scoliosis].

A deep learning-based model for automatic diagnosis and classification of adolescent idiopathic scoliosis has been constructed. This model mainly included key points detection and Cobb angle measurement. 748 full-length standing spinal X-ray images were retrospectively collected, of which 602 images were used to train and validate the model, and 146 images were used to test the model performance. The results showed that the model had good diagnostic and classification performance, with an accuracy of 94.5%. Compared with experts' measurement, 94.9% of its Cobb angle measurement results were within the clinically acceptable range. The average absolute difference was 2.1°, and the consistency was also excellent (r2≥0.9552, P<0.001). In the future, this model could be applied clinically to improve doctors' diagnostic efficiency.

A novel approach for screening standard anteroposterior pelvic radiographs in children.

Anteroposterior pelvic radiography is the first-line imaging modality for diagnosing developmental dysplasia of the hip (DDH). Nonstandard radiographs with pelvic malposition make the correct diagnosis of DDH challenging. However, as the only method available for screening standard pelvic radiographs, traditional manual assessment is relatively laborious and potentially erroneous. We retrospectively collected 3,247 pelvic radiographs. There were 2,887 radiographs randomly selected to train and optimize the AI model. Then 362 radiographs were used to test the model's diagnostic performance. Its diagnostic accuracy was assessed using receiver operating characteristic (ROC) curves and measurement consistency using Bland-Altman plots. In 362 radiographs, the AI model's area under ROC curves, accuracy, sensitivity, and specificity for quality assessment was 0.993, 99.4% (360/362), 98.6% (138/140), and 100.0% (222/222), respectively. Compared with clinicians, the 95% limits of agreement (Bland-Altman analysis) for pelvic tilt index (PTI) and pelvic rotation index (PRI), as determined by the model, were -0.052-0.072 and -0.088-0.055, respectively. CONCLUSIONS: The artificial intelligence-assisted method was more efficient and highly consistent with clinical experts. This method can be used for real-time validation of the quality of pelvic radiographs in current picture archiving and communications systems (PACS). WHAT IS KNOWN: • Nonstandard pediatric radiographs with pelvic malposition make the correct diagnosis of developmental dysplasia of the hip (DDH) challenging. • Traditional manual assessment remains the only method available for screening standard pediatric pelvic radiographs, which is relatively laborious and potentially erroneous. WHAT IS NEW: • This study proposed an artificial intelligence-assisted model to assess the quality of pediatric pelvic radiographs accurately and efficiently. • We recommend the integration of the model into current picture archiving and communications systems (PACS) for real-time screening of standard pediatric pelvic radiographs.

Clinical thought-based software for diagnosing developmental dysplasia of the hip on pediatric pelvic radiographs.

Background: The common methods of radiographic diagnosis of developmental dysplasia of the hip (DDH) include measuring hip parameters and quantifying the degree of hip dislocation. However, clinical thought-based analysis of hip parameters may be a more effective way to achieve expert-like diagnoses of DDH. This study aims to develop a diagnostic strategy-based software for pediatric DDH and validate its clinical feasibility. Methods: In total, 543 anteroposterior pelvic radiographs were retrospectively collected from January 2017 to December 2021. Two independent clinicians measured four diagnostic indices to compare the diagnoses made by the software and conventional manual method. The diagnostic accuracy was evaluated using the receiver operator characteristic (ROC) curves and confusion matrix, and the consistency of parametric measurements was assessed using Bland-Altman plots. Results: In 543 cases (1,086 hips), the area under the curve, accuracy, sensitivity, and specificity of the software for diagnosing DDH were 0.988-0.994, 99.08%-99.72%, 98.07%-100.00%, and 99.59%, respectively. Compared with the expert panel, the Bland-Altman 95% limits of agreement for the acetabular index, as determined by the software, were -2.09°-2.91° (junior orthopedist) and -1.98°-2.72° (intermediate orthopedist). As for the lateral center-edge angle, the 95% limits were -3.68°-5.28° (junior orthopedist) and -2.94°-4.59° (intermediate orthopedist). Conclusions: The software can provide expert-like analysis of pelvic radiographs and obtain the radiographic diagnosis of pediatric DDH with great consistency and efficiency. Its initial success lays the groundwork for developing a full-intelligent comprehensive diagnostic system of DDH.

Chinese expert consensus on diagnosis and treatment of trauma-induced hypercoagulopathy.

Trauma-induced coagulopathy (TIC) is caused by post-traumatic tissue injury and manifests as hypercoagulability that leads to thromboembolism or hypocoagulability that leads to uncontrollable massive hemorrhage. Previous studies on TIC have mainly focused on hemorrhagic coagulopathy caused by the hypocoagulable phenotype of TIC, while recent studies have found that trauma-induced hypercoagulopathy can occur in as many as 22.2-85.1% of trauma patients, in whom it can increase the risk of thrombotic events and mortality by 2- to 4-fold. Therefore, the Chinese People's Liberation Army Professional Committee of Critical Care Medicine and the Chinese Society of Thrombosis, Hemostasis and Critical Care, Chinese Medicine Education Association jointly formulated this Chinese Expert Consensus comprising 15 recommendations for the definition, pathophysiological mechanism, assessment, prevention, and treatment of trauma-induced hypercoagulopathy.

Thromboelastography predicts risks of obstetric complication occurrence in (hypo)dysfibrinogenemia patients under non-pregnant state.

Congenital (hypo)dysfibrinogenemia patients may have obstetric complications during their pregnancies. This study aimed to evaluate thromboelastography (TEG) as a potential tool for assessing the tendency for obstetric complications in those patients in a non-pregnant state. A total of 22 female subjects with congenital (hypo)dysfibrinogenemia were recruited. Nine subjects had histories of obstetric complications and the other 13 subjects had at least one uneventful pregnancy without obstetric complications as yet. Detailed clinical investigation and phenotype/genotype detection were carried out, and both kaolin-activated TEG and functional fibrinogen TEG (FF-TEG) were applied in all subjects. Significant differences were identified in all TEG parameters except for R and angle between these two groups (P < 0.05) by covariance analysis. Receiver operating characteristic (ROC) analysis of discrimination between these two groups of patients was performed for TEG parameters. Significantly high odds ratio (OR) of obstetric complications occurrence were demonstrated in K ≥ 3.8 min, maximum amplitude (MA) ≤ 54.2 mm, comprehensive index (CI) ≤ -3 (11.67, 95% CI 1.527-89.121, P < 0.05 in all), and MA-CFF ≤ 12.1 mm (20.00, 95% confidence interval (95% CI) 1.967-203.322, P = 0.002). Moreover, MA-CFF had better prognostic performance, with a corresponding area under the receiver operating curve of 0.923 (range 0.815-1.031, P = 0.001). This study suggests that (hypo)dysfibrinogenemia patients with values outside of the cut-off values of TEG assays under non-pregnant state may have a higher risk of obstetric complications occurring when they are pregnant. No parameters under non-pregnant state in clinical laboratory have ever been reported to be risk factors for obstetric complication occurrence in (hypo)dysfibrinogenemia patients. This study explored such parameters in TEG assays and found that parameters of TEG assays under non-pregnant status might predict the occurrence of obstetric complications, which could provide physicians with important information about whether fibrinogen replacement therapy is required, so as to prevent the occurrence of obstetric complications, especially for patients who are asymptomatic in daily life.

Clinical features and molecular basis of 102 Chinese patients with congenital dysfibrinogenemia.

INTRODUCTION: Congenital dysfibrinogenemia (CD) is a rare qualitative disorder of fibrinogen (Fg) with heterogeneous clinical manifestations. We aimed to analyze clinical phenotype and molecular basis of 102 Chinese CD patients and to evaluate the application of thromboelastography (TEG). MATERIALS AND METHODS: Clinical manifestations were recorded and quantified using the consensus ISTH bleeding assessment tool. Kaolin activated TEG and functional Fg TEG were applied in 30 patients. Genetic analysis of Fg genes were performed by direct sequencing. RESULTS: 27.5% patients experienced bleeding, 3.9% had thrombosis and 68.6% were asymptomatic. Females were more prone to experience bleeding (P=0.01). Significant difference (P<0.05) in TEG results were found between patients with hot-spot mutations at AαArg35(16) and γArg301(275), but were not identified between patients with and without bleeding. Normal TEG results were found in patients with mutations at AαArg35(16), AαPro37(18) or AαArg38(19). Six novel mutations were identified, including AαGly33(14)del, AαAsp57(38)_Trp60(41)delIVS2+1_+2GTdel, AαPhe742(723)Tyr, γAsn334(308)Thr, γGly335(309)Cys and γTrp395(369)Leu. CONCLUSIONS: CD patients have similar clinical manifestations and hot-spot mutations worldwide with no ethnic difference. TEG results could not indicate the bleeding risk in patients, but priority of mutation screening at thrombin cleavage site or polymerization site on Aа chain may be given if TEG results are normal.