OBJECTIVE To construct a predictive model for evaluating the efficacy of a triple antiemetic regimen （neurokinin- 1 receptor antagonist+5-hydroxytryptamine 3 receptor antagonist+dexamethasone） for preventing nausea and vomiting induced by highly emetogenic chemotherapy （HEC） based on interpretable deep learning algorithms. METHODS Clinical data of cancer patients who received HEC and were treated with the standard triple antiemetic regimen in the oncology department of Tianjin Medical University General Hospital from January 2018 to December 2022 were collected retrospectively. Demographic， clinical and metabolism-related variables were integrated. After data pre-processing， two deep learning algorithms （deep random forest and dense neural network） and four machine learning algorithms （support vector machine， categorical boosting， random forest and decision tree） were used to build predictive models. Subsequently， model performance evaluation and model interpretability analysis were conducted. RESULTS Among the six candidate models， the deep random forest model demonstrated the best predictive performance on the test set， with an area under the receiver operating characteristic curve of 0.850， an accuracy of 0.911， a precision of 0.805， a recall of 0.783， an F1 score of 0.793， and a Brier score of 0.075. Interpretability analysis revealed that creatinine clearance rate （Ccr） was the key predictive factor， and low Ccr levels， female gender， younger age， highly emetogenic drugs （particularly cisplatin-containing chemotherapy regimens）， and anticipatory nausea and vomiting were positively correlated with the risk of HEC-related nausea and vomiting. CONCLUSIONS The deep random forest model exhibits the best performance in predicting the efficacy of triple antiemetic regimen for preventing HEC-related nausea and vomiting. The key predictors in this model primarily include Ccr，anticipatory nausea and vomiting， gender， age， and highly emetogenic drugs.

Background::Carotid intima-media thickness (IMT) and diameter, stiffness, and wave reflections, are independent and important clinical biomarkers and risk predictors for cardiovascular diseases. The purpose of the present study was to establish nationwide reference values of carotid properties for healthy Chinese adults and to explore potential clinical determinants.Methods::A total of 3053 healthy Han Chinese adults (1922 women) aged 18-79 years were enrolled at 28 collaborating tertiary centers throughout China between April 2021 and July 2022. The real-time tracking of common carotid artery walls was achieved by the radio frequency (RF) ultrasound system. The IMT, diameter, compliance coefficient, β stiffness, local pulse wave velocity (PWV), local systolic blood pressure, augmented pressure (AP), and augmentation index (AIx) were then automatically measured and reported. Data were stratified by age groups and sex. The relationships between age and carotid property parameters were analyzed by Jonckheere-Terpstra test and simple linear regressions. The major clinical determinants of carotid properties were identified by Pearson’s correlation, multiple linear regression, and analyses of covariance.Results::All the parameters of carotid properties demonstrated significantly age-related trajectories. Women showed thinner IMT, smaller carotid diameter, larger AP, and AIx than men. The β stiffness and PWV were significantly higher in men than women before forties, but the differences reversed after that. The increase rate of carotid IMT (5.5 μm/year in women and 5.8 μm/year in men) and diameter (0.03 mm/year in both men and women) were similar between men and women. For the stiffness and wave reflections, women showed significantly larger age-related variations than men as demonstrated by steeper regression slopes (all P for age by sex interaction <0.05). The blood pressures, body mass index (BMI), and triglyceride levels were identified as major clinical determinants of carotid properties with adjustment of age and sex. Conclusions::The age- and sex-specific reference values of carotid properties measured by RF ultrasound for healthy Chinese adults were established. The blood pressures, BMI, and triglyceride levels should be considered for clinical application of corresponding reference values.

Humans ; East Asian People ; Nausea/drug therapy* ; Vomiting/drug therapy* ; Antineoplastic Agents/adverse effects* ; Neoplasms/drug therapy*

Objective:To compare the clinical effects of platelet-rich plasma (PRP) and sodium hyaluronate on rotator cuff injury.Methods:From February 2022 to December 2022, 226 patients with rotator cuff injury caused by military training were treated at Department of Orthopaedics, Jinling Hospital, School of Medicine, Nanjing University. They were all male, aged (24.5±3.7) years, and their time from injury to treatment was (4.6±2.2) months. They were divided into 2 even groups according to different treatments: an observation group of 113 cases into whose subacromial space PRP was injected, and a control group of 113 cases into whose subacromial space sodium hyaluronate was injected. In both groups, the injection was performed once a week for consecutive 3 weeks. The 2 groups were compared in terms of visual analogue scale (VAS) and Constant-Murley shoulder function scale (CMS) before treatment and 4 and 8 weeks after treatment, and the levels of TNF- α and IL-6 in the shoulder synovial fluid before treatment and 8 weeks after treatment. Results:There was no statistical difference between the 2 groups in general clinical data before treatment, indicating comparability ( P>0.05). At 4 and 8 weeks after treatment, compared with the pre-treatment values, the VAS scores were significantly decreased and the Constant-Murley scores significantly increased in both groups ( P<0.001). At 4 and 8 weeks after treatment, the VAS scores in the observation group (3.1±0.9 and 1.5±0.5) were significantly lower than those in the control group (3.7±0.8 and 2.3±0.6) while the Constant-Murley scores in the observation group (58.6±4.5 and 72.2±4.1) significantly higher than those in the control group (55.2±5.3 and 67.8±5.0) ( P<0.001). At 8 weeks after treatment, the levels of TNF- α and IL-6 in the 2 groups were significantly lower than the levels before treatment ( P<0.001). At 8 weeks after treatment, the levels of TNF- α and IL-6 in the observation group [(2.9±0.9) μg/L and (0.8±0.2) μg/L] were significantly lower than those in the control group [(4.0±0.4) μg/L and (1.1±0.4) μg/L] ( P<0.001). Conclusion:Injection of PRP or sodium hyaluronate can relieve pain and improve shoulder function obviously in patients with rotator cuff injury, but PRP is superior to sodium hyaluronate in the treatment of rotator cuff injury.

Objective:To provide a basis for the selection of antiemetic regimen by establishing an artificial intelligence model for predicting chemotherapy-induced nausea and vomiting (CINV) in cancer patients receiving platinum-based chemotherapy with high emetic risk.Methods:The clinical information on cancer patients who received cisplatin or carboplatin with area under the blood concentration-time curve (AUC) ≥4 and registered in the Department of Oncology, Tianjin Medical University General Hospital from January 2018 to December 2022 was collected, including gender, age, history of alcohol consumption, history of vomiting in pregnancy, chemotherapy cycle, patient expects to have CINV, chemotherapeutic agents, antiemetic regimen, out-of-hospital antiemetic treatment, sleep of less than 7 hours on the night before chemotherapy, occurrence of CINV in the previous cycle, and creatinine clearance (Ccr). After pre-processing, the data were randomly divided into the training set and the test set. The training set was used to construct the prediction model, and the test set was used to evaluate the prediction efficiency of the model. Three algorithms, gradient boosting decision tree (GBDT), random forest (RF), and logistic regression (LR), were used to build a prediction model and evaluate the model performance, respectively. The evaluation metrics included accuracy, sensitivity, recall, F1 value (the reconciled mean of sensitivity and recall), and area under the receiver operating characteristic curve (AUROC). Finally, Shapley Additive exPlanation (SHAP) was applied to analyze the interpretability of the clinical features with predictive significance.Results:A total of 698 patients, 439 males (62.9%) with a median age of 64 (21, 84) years, were included in this study and received a total of 1 654 cycles of chemotherapy. The chemotherapy regimen contained cisplatin in 364 cases with 864 cycles of chemotherapy, and carboplatin with AUC ≥4 in 361 cases with 790 cycles of chemotherapy. The number of treatment cycles in which neurokinin-1 receptor antagonist (NK-1 RA), 5-hydroxytryptamine-3 receptor antagonist (5-HT3 RA), and dexamethasone were selected as the antiemetic regimen was 1 347, and in those with the selection of 5-HT3 RA and dexamethasone was 307. The Spearman′s correlation analysis showed no strong correlation between the feature variables in the patients, and all of them could be used for model building. GBDT optimal hyperparameters n_estimators=500, max_depth=9; RF optimal hyperparameters max_depth=5; LR optimal hyperparameters penalty=L2. Three prediction models, GBDT, RF and LR, were established based on the optimal hyperparameter training data, respectively. The accuracy of GBDT model was 0.903, sensitivity was 0.882, recall was 0.903, F1 value was 0.883, and AUROC was 0.778±0.036 (95% CI: 0.739-0.814); the accuracy of RF model was 0.885, sensitivity was 0.861, recall was 0.885, F1 value was 0.870, and AUROC was 0.679±0.041 (95% CI: 0.636-0.720); the LR model had an accuracy of 0.817, a sensitivity of 0.851, a recall of 0.817, an F1 value of 0.832, and an AUROC of 0.682±0.042 (95% CI: 0.639-0.723). Ccr, age, chemotherapy cycle, history of alcohol consumption, and patient expects to have CINV were the main features predicted by the model. The risk of CINV was negatively associated with Ccr, age, and chemotherapy cycle. And the risk of CINV was lower in patients with no history of drinking alcohol and patient expects to have CINV. Conclusion:The GBDT, RF, and LR models could all predict the risk of CINV in patients receiving platinum-based chemotherapy with high emetic risk, with the GBDT model having the best predictive effect.

Objective:To provide a basis for the selection of antiemetic regimen by establishing an artificial intelligence model for predicting chemotherapy-induced nausea and vomiting (CINV) in cancer patients receiving platinum-based chemotherapy with high emetic risk.Methods:The clinical information on cancer patients who received cisplatin or carboplatin with area under the blood concentration-time curve (AUC) ≥4 and registered in the Department of Oncology, Tianjin Medical University General Hospital from January 2018 to December 2022 was collected, including gender, age, history of alcohol consumption, history of vomiting in pregnancy, chemotherapy cycle, patient expects to have CINV, chemotherapeutic agents, antiemetic regimen, out-of-hospital antiemetic treatment, sleep of less than 7 hours on the night before chemotherapy, occurrence of CINV in the previous cycle, and creatinine clearance (Ccr). After pre-processing, the data were randomly divided into the training set and the test set. The training set was used to construct the prediction model, and the test set was used to evaluate the prediction efficiency of the model. Three algorithms, gradient boosting decision tree (GBDT), random forest (RF), and logistic regression (LR), were used to build a prediction model and evaluate the model performance, respectively. The evaluation metrics included accuracy, sensitivity, recall, F1 value (the reconciled mean of sensitivity and recall), and area under the receiver operating characteristic curve (AUROC). Finally, Shapley Additive exPlanation (SHAP) was applied to analyze the interpretability of the clinical features with predictive significance.Results:A total of 698 patients, 439 males (62.9%) with a median age of 64 (21, 84) years, were included in this study and received a total of 1 654 cycles of chemotherapy. The chemotherapy regimen contained cisplatin in 364 cases with 864 cycles of chemotherapy, and carboplatin with AUC ≥4 in 361 cases with 790 cycles of chemotherapy. The number of treatment cycles in which neurokinin-1 receptor antagonist (NK-1 RA), 5-hydroxytryptamine-3 receptor antagonist (5-HT3 RA), and dexamethasone were selected as the antiemetic regimen was 1 347, and in those with the selection of 5-HT3 RA and dexamethasone was 307. The Spearman′s correlation analysis showed no strong correlation between the feature variables in the patients, and all of them could be used for model building. GBDT optimal hyperparameters n_estimators=500, max_depth=9; RF optimal hyperparameters max_depth=5; LR optimal hyperparameters penalty=L2. Three prediction models, GBDT, RF and LR, were established based on the optimal hyperparameter training data, respectively. The accuracy of GBDT model was 0.903, sensitivity was 0.882, recall was 0.903, F1 value was 0.883, and AUROC was 0.778±0.036 (95% CI: 0.739-0.814); the accuracy of RF model was 0.885, sensitivity was 0.861, recall was 0.885, F1 value was 0.870, and AUROC was 0.679±0.041 (95% CI: 0.636-0.720); the LR model had an accuracy of 0.817, a sensitivity of 0.851, a recall of 0.817, an F1 value of 0.832, and an AUROC of 0.682±0.042 (95% CI: 0.639-0.723). Ccr, age, chemotherapy cycle, history of alcohol consumption, and patient expects to have CINV were the main features predicted by the model. The risk of CINV was negatively associated with Ccr, age, and chemotherapy cycle. And the risk of CINV was lower in patients with no history of drinking alcohol and patient expects to have CINV. Conclusion:The GBDT, RF, and LR models could all predict the risk of CINV in patients receiving platinum-based chemotherapy with high emetic risk, with the GBDT model having the best predictive effect.