Search

Abstract Objective Prediction of lymph node metastasis (LNM) for intrahepatic cholangiocarcinoma (ICC) is critical for the treatment regimen and prognosis. We aim to develop and validate machine learning (ML)-based predictive models for LNM in patients with ICC. Methods A total of 345 patients with clinicopathological characteristics confirmed ICC from Jan 2007 to Jan 2019 were enrolled. The predictors of LNM were identified by the least absolute shrinkage and selection operator (LASSO) and logistic analysis. The selected variables were used for developing prediction models for LNM by six ML algorithms, including Logistic regression (LR), Gradient boosting machine (GBM), Extreme gradient boosting (XGB), Random Forest (RF), Decision tree (DT), Multilayer perceptron (MLP). We applied 10-fold cross validation as internal validation and calculated the average of the areas under the receiver operating characteristic (ROC) curve to measure the performance of all models. A feature selection approach was applied to identify importance of predictors in each model. The heat map was used to investigate the correlation of features. Finally, we established a web calculator using the best-performing model. Results In multivariate logistic regression analysis, factors including alcoholic liver disease (ALD), smoking, boundary, diameter, and white blood cell (WBC) were identified as independent predictors for LNM in patients with ICC. In internal validation, the average values of AUC of six models ranged from 0.820 to 0.908. The XGB model was identified as the best model, the average AUC was 0.908. Finally, we established a web calculator by XGB model, which was useful for clinicians to calculate the likelihood of LNM. Conclusion The proposed ML-based predicted models had a good performance to predict LNM of patients with ICC. XGB performed best. A web calculator based on the ML algorithm showed promise in assisting clinicians to predict LNM and developed individualized medical plans.

Abstract Background More efficient instruments for body constitution identification are needed for clinical practice. We aimed to develop the short-form version of the Constitution in Chinese Medicine Questionnaire (CCMQ) and evaluate for health management. Methods First, the short forms were developed through expert survey, classical test theory (CTT), and modern item response (IRT) based on the CCMQ. A combination of e-mail and manual methods was used in expert survey. Then, five indexes of CTT including criteria value-critical ratio, correlation coefficient, discrete tendency, internal consistency, and factor loading were used. And, IRT method was used through analyzing the discrimination and difficulty parameters of items. Second, the three top-ranked items of each constitution scale were selected for the simplified CCMQ, based on the three combined methods of different conditions and weights. Third, The psychometric properties such as completion time, validity (Construct, criterion, and divergent validity), and reliability (test–retest and internal consistency reliability) were evaluated. Finally, the diagnostic validity of the best short-form used receiver operating characteristic (ROC) curve. Results Three short-form editions were developed, and retained items 27, 23 and 27, which are named as WangQi nine body constitution questionnaire of Traditional Chinese Medicine (short-form) (SF-WQ9CCMQ)- A, B, and C, respectively. SF-WQ9CCMQ- A is showed the best psychometric property on Construct validity, Criterion validity, test–retest reliability and internal consistency reliability. The diagnostic validity indicated that the area under the ROC curve was 0.928 (95%CI: 0.924–0.932) for the Gentleness constitution scale, and were 0.895–0.969 and 0.911–0.981 for unbalance constitution scales using the cut-off value of the original CCMQ as 40 (“yes” standard) and 30 (“tendency” standard), respectively. Conclusions Our study successfully developed a well short-form which has good psychometric property, and excellent diagnostic validity consistent with the original. New and simplified instrument and opportunity are provided for body constitution identification, health management and primary care implementation.

Abstract The widespread application of antiandrogen therapies has aroused a significant increase in the incidence of NEPC, a lethal form of the disease lacking efficient clinical treatments. Here we identified a cell surface receptor neurokinin-1 (NK1R) as a clinically relevant driver of treatment-related NEPC (tNEPC). NK1R expression increased in prostate cancer patients, particularly higher in metastatic prostate cancer and treatment-related NEPC, implying a relation with the progression from primary luminal adenocarcinoma toward NEPC. High NK1R level was clinically correlated with accelerated tumor recurrence and poor survival. Mechanical studies identified a regulatory element in the NK1R gene transcription ending region that was recognized by AR. AR inhibition enhanced the expression of NK1R, which mediated the PKCα-AURKA/N-Myc pathway in prostate cancer cells. Functional assays demonstrated that activation of NK1R promoted the NE transdifferentiation, cell proliferation, invasion, and enzalutamide resistance in prostate cancer cells. Targeting NK1R abrogated the NE transdifferentiation process and tumorigenicity in vitro and in vivo. These findings collectively characterized the role of NK1R in tNEPC progression and suggested NK1R as a potential therapeutic target.

ObjectiveTo analyze and predict the striking velocity range of stick blunt instruments in different populations, and to provide basic data for the biomechanical analysis of blunt force injuries in forensic identification.MethodsBased on the Photron FASTCAM SA3 high-speed camera, Photron FASTCAM Viewer 4.0 and SPSS 26.0 software, the tester’s maximum striking velocity of stick blunt instruments and related factors were calculated and analyzed, and inputed to the backpropagation （BP） neural network for training. The trained and verified BP neural network was used as the prediction model.ResultsA total of 180 cases were tested and 470 pieces of data were measured. The maximum striking velocity range was 11.30-35.99 m/s. Among them, there were 122 female data, the maximum striking velocity range was 11.63-29.14 m/s; there were 348 male data, the maximum striking velocity range was 20.11-35.99 m/s. The maximum striking velocity of stick blunt instruments increased with the increase of weight and height, but there was no obvious increase trend in the male group; the maximum striking velocity decreased with age, but there was no obvious downward trend in the female group. The maximum striking velocity of stick blunt instruments has no significant correlation with the material and strike posture. The root mean square error （RMSE）, the mean absolute error （MAE） and the coefficient of determination （R2） of the prediction results by using BP neural network were 2.16, 1.63 and 0.92, respectively.ConclusionThe prediction model of BP neural network can meet the demand of predicting the maximum striking velocity of different populations.

ObjectiveTo reconstruct the cases of acceleration craniocerebral injury caused by blunt in forensic cases by finite element method （FEM）, and to study the biomechanical mechanism and quantitative evaluation method of blunt craniocerebral injury.MethodsBased on the established and validated finite element head model of Chinese people, the finite element model of common injury tool was established with reference to practical cases in the forensic identification, and the blunt craniocerebral injury cases were reconstructed by simulation software. The cases were evaluated quantitatively by analyzing the biomechanical parameters such as intracranial pressure, von Mises stress and the maximum principal strain of brain tissue.ResultsIn case 1, when the left temporal parietal was hit with a round wooden stick for the first time, the maximum intracranial pressure was 359 kPa; the maximum von Mises stress of brain tissue was 3.03 kPa at the left temporal parietal; the maximum principal strain of brain tissue was 0.016 at the left temporal parietal. When the right temporal was hit with a square wooden stick for the second time, the maximum intracranial pressure was 890 kPa; the maximum von Mises stress of brain tissue was 14.79 kPa at the bottom of right temporal lobe; the maximum principal strain of brain tissue was 0.103 at the bottom of the right temporal lobe. The linear fractures occurred at the right temporal parietal skull and the right middle cranial fossa. In case 2, when the forehead and left temporal parietal were hit with a round wooden stick, the maximum intracranial pressure was 370 kPa and 1 241 kPa respectively, the maximum von Mises stress of brain tissue was 3.66 kPa and 26.73 kPa respectively at the frontal lobe and left temporal parietal lobe, and the maximum principal strain of brain tissue was 0.021 and 0.116 respectively at the frontal lobe and left temporal parietal lobe. The linear fracture occurred at the left posterior skull of the coronary suture. The damage evaluation indicators of the simulation results of the two cases exceeded their damage threshold, and the predicted craniocerebral injury sites and fractures were basically consistent with the results of the autopsy.ConclusionThe FEM can quantitatively evaluate the degree of blunt craniocerebral injury. The FEM combined with traditional method will become a powerful tool in forensic craniocerebral injury identification and will also become an effective means to realize the visualization of forensic evidence in court.