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.

OBJECTIVE To study the improvement effect and mechanism of Tripterygium wilfordii multiglucoside （TWM） on nephrotic syndrome in rats. METHODS The nephrotic syndrome model was established by intravenous injection of adriamycin via the tail vein. The modeling rats were randomly divided into the model group （distilled water）， prednisone group （10 mg/kg）， and TWM high- and low-dose groups （10 and 5 mg/kg， respectively）. Additionally， blank group （distilled water） without model induction was established. Each group consisted of 9 rats. Rats in each group were administered the corresponding drugs or distilled water by gavage， once a day， for 6 consecutive weeks. The histopathological morphology of kidney tissues in rats was observed； the levels of 24-hour urinary protein （24 h-UTP） and serum biochemical indicators [albumin （ALB）， blood urea nitrogen （BUN）， serum creatinine （SCr）， cholesterol （CHOL）， and triglyceride （TG）] in rats were determined； the levels of oxidative stress indicators [superoxide dismutase （SOD）， malondialdehyde （MDA）] in kidney tissue of rats were determined； expressions of hypoxia-inducible factor-1α （HIF-1α）/microRNA-155-5p （miR-155-5p）/nuclear factor erythriod 2- related factor 2 （Nrf2） signaling pathway-related mRNA and protein in the renal tissues of rats were detected. RESULTS Compared with the blank group， the rats in the model group exhibited disordered renal tissue structure， with a small amount of glomerular necrosis and edema of the renal tubular epithelial cells. 24 h-UTP， serum levels of SCr， BUN， CHOL and TG， MDA content， mRNA and protein expressions of HIF-1α and Keap1 as well as the expression of miR-155-5p in renal tissues were increased significantly （ P ＜0.05）. Serum level of ALB， SOD level in renal tissue as well as mRNA and protein expressions of Nrf2 were decreased significantly （ P ＜0.05）. Compared with the model group， TWM high-dose and low-dose groups exhibited significant improvements in renal injury， with notable reversals in the levels of the above quantitative indicators （ P ＜0.05）. CONCLUSIONS TWM can alleviate oxidative stress-induced damage and thereby improve nephrotic syndrome in rats by regulating the HIF-1α/miR-155-5p/Nrf2 signaling pathway.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveRepetitive transcranial magnetic stimulation (rTMS), a non-invasive brain stimulation technique, offers a non-pharmacological therapeutic option for the management of Alzheimer’s disease (AD). Studies have demonstrated that ferroptosis plays a pivotal role in the pathological onset and progression of AD, and the inhibition of neuronal ferroptosis can significantly ameliorate cognitive impairments associated with AD. The imbalance of calcium ion (Ca²⁺) homeostasis is intimately associated with the pathology of AD and serves as a catalyst for the induction of ferroptosis through various pathways. This study is designed to investigate whether rTMS can ameliorate AD by inhibiting neuronal ferroptosis or maintaining calcium homeostasis, ultimately establishing a theoretical and experimental framework for the utilization of rTMS in AD treatment. MethodsAPP/PS1 AD mice were subjected to both 0.5 Hz low-frequency and 20 Hz high-frequency rTMS treatments, and the efficacy of these treatments was evaluated using novel object recognition and Morris water maze tests. ELISA was employed to quantify the levels of glutathione (GSH), malondialdehyde (MDA), superoxide dismutase (SOD), Fe²⁺ within the hippocampi of mice from each group. HT-22 cells were induced to undergo ferroptosis via Erastin treatment, and subsequent to high- and low-frequency magnetic stimulation, cell viability was assessed using CCK-8 assay, while intracellular calcium ion concentration fluctuations were monitored using Fluo-4 AM. ResultsThe findings revealed that, when compared to normal mice, AD mice displayed a notable decline in cognitive function, accompanied by a substantial increase in ferroptosis levels and intracellular calcium ion concentrations. Both high-frequency and low-frequency applications of rTMS were found to significantly ameliorate cognitive impairments in AD mice, while also effectively mitigating the abnormal augmentation of neuronal ferroptosis and intracellular calcium ion levels. ConclusionThe present study underscores that both high-frequency and low-frequency rTMS exhibit efficacy in alleviating cognitive dysfunction in AD mice, potentially through the modulation of ferroptosis and intracellular calcium ion homeostasis.

Objective: To analyze the association between dietary diversity and cognitive function among the elderly using group-based trajectory model, so as to provide the basis for formulating dietary intervention strategies to prevent cognitive impairment. Methods: Based on the Chinese Longitudinal Healthy Longevity Survey (CLHLS) project, demographic information, lifestyle behaviors, psychological well-being, and activities of daily living of elderly individuals aged ≥65 years from 2008 to 2018 were collected. Dietary diversity was assessed using a food frequency questionnaire, with a score of <7 points defined as low dietary diversity. Cognitive function was evaluated using the Chinese version of the Mini-Mental State Examination (MMSE). A group-based trajectory model was established based on cognitive function scores from 2008 to 2018 to analyze the trajectories of cognitive function change. The association between dietary diversity and cognitive function was analyzed using a multinomial logistic regression model. Results: A total of 1 613 individuals were collected, with a median age was 72.00 (interquartile range, 10.00) years. There were 810 males (50.22%) and 803 females (49.78%). The group-based trajectory model analysis categorized the participants into three groups: the low-level normal group, the high-level normal group, and the slow-then-rapid decline group, comprising 796 (49.35%), 585 (36.27%), and 232 (14.38%) individuals, respectively. Among these groups, the numbers of individuals with low dietary diversity were 497 (62.44%), 311 (53.16%), and 166 (71.55%), respectively, with a statistically significant difference (P<0.05). Multinomial logistic regression analysis showed that after adjusting for demographic information, lifestyle behaviors, psychological well-being, and activities of daily living, compared with the high-level normal group, low dietary diversity was statistically associated with cognitive function in the slow-then-rapid decline group (OR=1.622, 95%CI: 1.103-2.384). Conclusion Low dietary diversity may increase the risk of cognitive impairment among the elderly.

OBJECTIVE: To propose a machine learning-based method for predicting the trajectories during manual acupuncture manipulation (MAM), aiming to improve the precision and consistency of acupuncture practitioner' operation and provide the real-time suggestions on MAM error correction. METHODS: Computer vision technology was used to analyze the hand micromotion when holding needle during acupuncture, and provide a three-dimensional coordinate description method of the index finger joints of the holding hand. Focusing on the 4 typical motions of MAM, a machine learning-based MAM trajectory predictive model was designed. By integrating the changes of phalangeal joint angle and hand skeletal information of acupuncture practitioner, the motion trajectory of the index finger joint was predicted accurately. Besides, the roles of machine learning-based MAM trajectory predictive model in the skill transmission of acupuncture manipulation were verified by stratified randomized controlled trial. RESULTS: The performance of MAM trajectory predictive model, based on the long short-term memory network (LSTM), obtained the highest stability and precision, up to 98%. The learning effect was improved when the model applied to the skill transmission of acupuncture manipulation. CONCLUSION The machine learning-based MAM predictive model provides acupuncture practitioner with precise action prediction and feedback. It is valuable and significant for the inheritance and error correction of manual operation of acupuncture.
Humans ; Acupuncture Therapy/instrumentation* ; Machine Learning ; Adult ; Male ; Female

OBJECTIVE: To investigate the effect of manual acupuncture manipulations (MAMs) on subcutaneous muscle tissue, by developing quantitative models of "lifting and thrusting" and "twisting and rotating", based on machine learning techniques. METHODS: A depth camera was used to capture the acupuncture operator's hand movements during "lifting and thrusting" and "twisting and rotating" of needle. Simultaneously, the ultrasound imaging was employed to record the muscle tissue responses of the participants. Amplitude and angular features were extracted from the movement data of operators, and muscle fascicle slope features were derived from the data of ultrasound images. The dynamic time warping barycenter averaging algorithm was adopted to align the dual-source data. Various machine learning techniques were applied to build quantitative models, and the performance of each model was compared. The most optimal model was further analyzed for its interpretability. RESULTS: Among the quantitative models built for the two types of MAMs, the random forest model demonstrated the best performance. For the quantitative model of the "lifting and thrusting" technique, the coefficient of determination (R²) was 0.825. For the "twisting and rotating" technique, R² reached 0.872. CONCLUSION Machine learning can be used to effectively develop the models and quantify the effects of MAMs on subcutaneous muscle tissue. It provides a new perspective to understand the mechanism of acupuncture therapy and lays a foundation for optimizing acupuncture technology and designing personalized treatment regimen in the future.
Humans ; Acupuncture Therapy/methods* ; Machine Learning ; Male ; Adult ; Female ; Subcutaneous Tissue/diagnostic imaging* ; Young Adult

Purpose: The aim of this study was to investigate the feasibility of an intelligent handheld ultrasound (US) device for assisting non-expert general practitioners (GPs) in detecting carotid plaques (CPs) in community populations. Methods: This prospective parallel controlled trial recruited 111 consecutive community residents. All of them underwent examinations by non-expert GPs and specialist doctors using handheld US devices (setting A, setting B, and setting C). The results of setting C with specialist doctors were considered the gold standard. Carotid intima-media thickness (CIMT) and the features of CPs were measured and recorded. The diagnostic performance of GPs in distinguishing CPs was evaluated using a receiver operating characteristic curve. Inter-observer agreement was compared using the intragroup correlation coefficient (ICC). Questionnaires were completed to evaluate clinical benefits. Results: Among the 111 community residents, 80, 96, and 112 CPs were detected in settings A, B, and C, respectively. Setting B exhibited better diagnostic performance than setting A for detecting CPs (area under the curve, 0.856 vs. 0.749; P<0.01). Setting B had better consistency with setting C than setting A in CIMT measurement and the assessment of CPs (ICC, 0.731 to 0.923). Moreover, measurements in setting B required less time than the other two settings (44.59 seconds vs. 108.87 seconds vs. 126.13 seconds, both P<0.01). Conclusion Using an intelligent handheld US device, GPs can perform CP screening and achieve a diagnostic capability comparable to that of specialist doctors.