A Preoperative Prediction Model for Lymph Node Metastasis in Patients with Gastric Cancer Using a Machine Learning-based Ultrasomics Approach.

OBJECTIVE: This study aimed to develop an ultrasomics model for predicting lymph node metastasis preoperative in patients with gastric cancer (GC). METHODS: This study enrolled GC patients who underwent preoperative ultrasound examination. Manual segmentation of the region of interest (ROI) was performed by an experienced radiologist to extract radiomics features using the Pyradiomics software. The Z-score algorithm was used for feature normalization, followed by the Wilcoxon test to identify the most informative features. Linear prediction models were constructed using the least absolute shrinkage and selection operator (LASSO). The performance of the ultrasomics model was evaluated using the area under curve (AUC), sensitivity, specificity, and the corresponding 95% confidence intervals (CIs). RESULTS: A total of 464 GC patients (mean age: 60.4 years ±11.3 [SD]; 328 men [70.7%]) were analyzed, of whom 291 had lymph node metastasis. The patients were randomly assigned to either the training (n=324) or test (n=140) sets, using a 7:3 ratio. An ultrasomics model that consisted of 19 radiomics features was developed using Wilcoxon and LASSO algorithms in the training set. Our ultrasomics model showed moderate performance for lymph node metastasis prediction in both the training (AUC: 0.802, 95%CI: 0.752-0.851, P<0.001) and test sets (AUC: 0.802, 95%CI: 0.724-0.879, P<0.001). The calibration curve analysis indicated good agreement between the predicted probabilities of ultrasomics and actual lymph node metastasis status. CONCLUSION: Our study highlights the potential of a machine learning-based ultrasomics model in predicting lymph node metastasis in GC patients, offering implications for personalized therapy approaches.

Shear-wave elastography predicts T-restaging and pathologic complete response of rectal cancer post neoadjuvant chemoradiotherapy.

PURPOSE: To investigate the value of shear-wave elastography (SWE) in assessing the response to neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer. METHODS: In this study, 455 participants with locally advanced rectal cancer who underwent nCRT at our hospital between September 2021 and December 2022 were prospectively enrolled. The participants were randomly divided into training and test cohorts in a 3:2 ratio. Clinical baseline data, endorectal ultrasound examination data, and SWE measurements were collected for all participants. Logistic regression models were used to predict whether rectal cancer after nCRT had a low T staging (ypT 0-2 stage, Model A) and pathological complete response (pCR) (Model B). Paired Chi-square tests were used to compare the diagnostic performances of the radiologists to those of Models A and B. RESULTS: In total, 256 participants were included. The area under the receiver operating characteristic curve of Models A and B in the test cohort were 0.94 (0.87, 1.00) and 0.88 (0.80, 0.97), respectively. The optimal diagnostic thresholds for Models A and B were 14.9 kPa for peritumoral mesangial Emean and 15.2 kPa for tumor Emean, respectively. The diagnostic performance of the radiologists was significantly lower than that of Models A and B, respectively (p < 0.05). CONCLUSION: SWE can be used as a feasible method to evaluate the treatment response of nCRT for locally advanced rectal cancer.

Deep Learning-Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging.

PURPOSE: To develop a deep neural network system for the automatic segmentation and risk stratification prediction of gastrointestinal stromal tumors (GISTs). METHODS: A total of 980 ultrasound (US) images from 245 GIST patients were retrospectively collected. These images were randomly divided (6:2:2) into a training set, a validation set, and an internal test set. Additionally, 188 US images from 47 prospective GIST patients were collected to evaluate the segmentation and diagnostic performance of the model. Five deep learning-based segmentation networks, namely, UNet, FCN, DeepLabV3+, Swin Transformer, and SegNeXt, were employed, along with the ResNet 18 classification network, to select the most suitable network combination. The performance of the segmentation models was evaluated using metrics such as the intersection over union (IoU), Dice similarity coefficient (DSC), recall, and precision. The classification performance was assessed based on accuracy and the area under the receiver operating characteristic curve (AUROC). RESULTS: Among the compared models, SegNeXt-ResNet18 exhibited the best segmentation and classification performance. On the internal test set, the proposed model achieved IoU, DSC, precision, and recall values of 82.1, 90.2, 91.7, and 88.8%, respectively. The accuracy and AUC for GIST risk prediction were 87.4 and 92.0%, respectively. On the external test set, the segmentation models exhibited IoU, DSC, precision, and recall values of 81.0, 89.5, 92.8, and 86.4%, respectively. The accuracy and AUC for GIST risk prediction were 86.7 and 92.5%, respectively. CONCLUSION: This two-stage SegNeXt-ResNet18 model achieves automatic segmentation and risk stratification prediction for GISTs and demonstrates excellent segmentation and classification performance.

Predicting the risk stratification of gastrointestinal stromal tumors using machine learning-based ultrasound radiomics.

PURPOSE: This study aimed to use conventional ultrasound features, ultrasound radiomics, and machine learning algorithms to establish a predictive model to assess the risk of post-surgical recurrence of gastrointestinal stromal tumors (GISTs). METHODS: This retrospective analysis included 230 patients with pathologically diagnosed GISTs. Radiomic features were extracted from manually annotated images. Radiomic features plus conventional ultrasound features were selected using the SelectKbest analysis of variance and stratified tenfold cross-validation recursive elimination methods. Finally, five different machine learning algorithms (logistic regression [LR], support vector machine [SVM], random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) were established to predict risk stratification of GISTs. The predictive performance of the established model was mainly evaluated based on the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy, whereas the predictive performance of the optimal machine learning algorithm and a radiologist's subjective assessment were compared using McNemar's test. RESULTS: Seven radiomics features and one conventional ultrasound feature were selected to construct the machine learning models for GIST risk classification. The mentioned five machine learning models were able to predict the malignant potential of GISTs. LR and SVM outperformed other classifiers on the test set, with LR achieving an accuracy of 0.852 (AUC, 0.881; sensitivity, 0.871; specificity, 0.826) and SVM achieving an accuracy of 0.852 (AUC, 0.879; sensitivity, 0.839; specificity, 0.870), and proved significantly better than the radiologist (accuracy, 0.691; sensitivity, 0.645; specificity, 0.813). CONCLUSION: Machine learning-based ultrasound radiomics features are able to noninvasively predict the biological risk of GISTs.

Mycobacterium porcinum Infection of Hilar and Mediastinal Lymph Nodes: A Case Report and Literature Review.

In the available reports on clinical medicine, the infection sites of Mycobacterium porcinum include wounds, bone marrow, respiratory tract, and catheters. A 61-year-old woman was admitted to our hospital; her hilar and mediastinal lymph nodes were found to be enlarged during health examination, but there was no specific discomfort. Initially, she had undergone a mediastinal lymph node biopsy and pathology, but the diagnosis was not confirmed. However, 16S rRNA gene sequencing revealed M. porcinum infection of hilar and mediastinal lymph nodes. Subsequently, she was treated with clarithromycin, amikacin, imipenem, and tigecycline. After 2 months, chest computed tomography showed a significant reduction in lymph nodes. M. porcinum infection was considered to be the cause of disease.

Use of a Convolutional Neural Network to Predict the Malignant Potential of Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Images: Visualization of the Focus of the Prediction Model.

OBJECTIVE: We established a deep convolutional neural network (CNN) model based on ultrasound images (US-CNN) for predicting the malignant potential of gastrointestinal stromal tumors (GISTs). METHODS: A total of 980 ultrasound images from 245 pathology-confirmed GIST patients after surgical operation were retrospectively collected and divided into a low (very-low-risk, low-risk) and a high (medium-risk, high-risk) malignant potential group. Eight pre-trained CNN models were used to extract the features. The CNN model with the highest accuracy in the test set was selected. The model's performance was evaluated by calculating accuracy, sensitivity, specificity, positive-predictive value (PPV), negative-predictive value (NPV) and the F1 score. Three radiologists with different experience levels also predicted the malignant potential of GISTs in the same test set. US-CNN and human assessments were compared. Subsequently, gradient-weighted class activation diagrams (Grad-CAMs) were used to visualize the model's final classification decisions. RESULTS: Among the eight transfer learning-based CNNs, ResNet18 performed best. The accuracy, sensitivity, specificity, PPV, NPV and F1 score were 0.88, 0.86, 0.89, 0.82, 0.92 and 0.90, respectively, which were significantly better than those achieved by radiologists (resident doctor: 0.66, 0.55, 0.79, 0.74, 0.62 and 0.69; attending doctor: 0.68, 0.59, 0.78, 0.70, 0.69 and 0.73; professor: 0.69, 0.63, 0.72, 0.51, 0.80 and 0.76). Model interpretation with Grad-CAMs revealed that the activated areas mainly focused on cystic necrosis and margins. CONCLUSION: The US-CNN model predicts GIST malignant potential well, which can assist in clinical treatment decision-making.

Metagenomic Next-Generation Sequencing Contributes to the Diagnosis of Pneumonia Caused by Chlamydia abortus in a Male Patient: Case Report and Literature Review.

Background: Chlamydia abortus is generally considered as the main cause of ruminants abortion, but it rarely causes human infection resulting in abortion or pneumonia. Case Presentation: We report a case of male patient with pneumonia caused by Chlamydia abortus. Results of next generation sequencing (NGS) in the bronchoalveolar lavage fluid (BALF) indicated Chlamydia abortus infection. The patient was treated with intravenous infusion of doxycycline. The clinical symptoms of this patient were ameliorated significantly, and all these improvement were indicated by laboratory parameters significantly. Shown as chest computed tomography (CT), most of the inflammation had been absorbed after doxycycline treatment. Conclusion: Chlamydia abortus mainly infects ruminants and occasionally humans. NGS has its own advantages of rapidity, sensitivity and specificity in detecting Chlamydia abortus. Doxycycline exhibits a great therapeutic effect on pneumonia caused by Chlamydia abortus.

Deep Multiview Adaptive Clustering With Semantic Invariance.

Multiview clustering has attracted significant attention in various fields, due to the superiority in mining patterns of multiview data. However, previous methods are still confronted with two challenges. First, they do not fully consider the semantic invariance of multiview data in aggregating complementary information, degrading semantic robustness of fusion representations. Second, they rely on predefined clustering strategies to mine patterns, lacking adequate explorations of data structures. To address the challenges, deep multiview adaptive clustering via semantic invariance (DMAC-SI) is proposed, which learns an adaptive clustering strategy on semantics-robust fusion representations to fully explore structures in mining patterns. Specifically, a mirror fusion architecture is devised to explore interview invariance and intrainstance invariance hidden in multiview data, which captures invariant semantics of complementary information to learn semantics-robust fusion representations. Then, a Markov decision process of multiview data partitions is proposed within the reinforcement learning framework, which learns an adaptive clustering strategy on semantics-robust fusion representations to guarantee the structure explorations in mining patterns. The two components seamlessly collaborate in an end-to-end manner to accurately partition multiview data. Finally, extensive experiment results on five benchmark datasets demonstrate that DMAC-SI outperforms the state-of-the-art methods.

Multiview Deep Forest for Overall Survival Prediction in Cancer.

Overall survival (OS) in cancer is crucial for cancer treatment. Many machine learning methods have been applied to predict OS, but there are still the challenges of dealing with multiview data and overfitting. To overcome these problems, we propose a multiview deep forest (MVDF) in this paper. MVDF can learn the features of each view and fuse them with integrated learning and multiple kernel learning. Then, a gradient boost forest based on the information bottleneck theory is proposed to reduce redundant information and avoid overfitting. In addition, a pruning strategy for a cascaded forest is used to limit the impact of outlier data. Comprehensive experiments have been carried out on a data set from West China Hospital of Sichuan University and two public data sets. Results have demonstrated that our method outperforms the compared methods in predicting overall survival.

Ultrasound radiomics model-based nomogram for predicting the risk Stratification of gastrointestinal stromal tumors.

This study aimed to develop and evaluate a nomogram based on an ultrasound radiomics model to predict the risk grade of gastrointestinal stromal tumors (GISTs). 216 GIST patients pathologically diagnosed between December 2016 and December 2021 were reviewed and divided into a training cohort (n = 163) and a validation cohort (n = 53) in a ratio of 3:1. The tumor region of interest was depicted on each patient's ultrasound image using ITK-SNAP, and the radiomics features were extracted. By filtering unstable features and using Spearman's correlation analysis, and the least absolute shrinkage and selection operator algorithm, a radiomics score was derived to predict the malignant potential of GISTs. a radiomics nomogram that combines the radiomics score and clinical ultrasound predictors was constructed and assessed in terms of calibration, discrimination, and clinical usefulness. The radiomics score from ultrasound images was significantly associated with the malignant potential of GISTs. The radiomics nomogram was superior to the clinical ultrasound nomogram and the radiomics score, and it achieved an AUC of 0.90 in the validation cohort. Based on the decision curve analysis, the radiomics nomogram was found to be more clinically significant and useful. A nomogram consisting of radiomics score and the maximum tumor diameter demonstrated the highest accuracy in the prediction of risk grade in GISTs. The outcomes of our study provide vital insights for important preoperative clinical decisions.

LEGAN: A Light and Effective Generative Adversarial Network for medical image synthesis.

Medical image synthesis plays an important role in clinical diagnosis by providing auxiliary pathological information. However, previous methods usually utilize the one-step strategy designed for wild image synthesis, which are not sensitive to local details of tissues within medical images. In addition, these methods consume a great number of computing resources in generating medical images, which seriously limits their applicability in clinical diagnosis. To address the above issues, a Light and Effective Generative Adversarial Network (LEGAN) is proposed to generate high-fidelity medical images in a lightweight manner. In particular, a coarse-to-fine paradigm is designed to imitate the painting process of humans for medical image synthesis within a two-stage generative adversarial network, which guarantees the sensitivity to local information of medical images. Furthermore, a low-rank convolutional layer is introduced to construct LEGAN for lightweight medical image synthesis, which utilizes principal components of full-rank convolutional kernels to reduce model redundancy. Additionally, a multi-stage mutual information distillation is devised to maximize dependencies of distributions between generated and real medical images in model training. Finally, extensive experiments are conducted in two typical tasks, i.e., retinal fundus image synthesis and proton density weighted MR image synthesis. The results demonstrate that LEGAN outperforms the comparison methods by a significant margin in terms of Fréchet inception distance (FID) and Number of parameters (NoP).

Two-dimensional shear wave elastography of the pancreas: measurement success rate, repeatability, and factors affecting measurement values.

PURPOSE: We aimed to evaluate the success rate, repeatability, and factors affecting the measurement values of two-dimensional ultrasonic shear wave elastography (2D-SWE) for measuring pancreatic stiffness. METHODS: This prospective study recruited 100 healthy participants. 2D-SWE was performed on the pancreatic head, body, and tail. We compared the success rates of pancreatic stiffness measurements of different body positions and ultrasonic scans, with and without probe pressurization, as well as the effects of sex, age, body mass index (BMI), and region of interest (ROI) depth on measurement values. Intra- and inter-operator repeatabilities were assessed in 20 participants. The influence of ROI depth was verified using a tissue-like phantom. RESULTS: The median 2D-SWE measurements of the pancreatic head, body, and tail were 1.44, 1.45, and 1.56 m/s, respectively. The success rates for the pancreatic head and body were significantly higher than that of the tail. The success rate for the semi-recumbent position was higher than that of the supine position (P < 0.001). The intra-operator values for same-day and inter-operator reliability were excellent. Univariate analyses showed that probe pressurization, age, BMI, and ROI depth were correlated with pancreatic shear wave velocity (SWV) (P < 0.05); only ROI depth had a significant effect on SWV values. The inclusion phantom showed that the SWV value increased as the ROI depth increased. CONCLUSIONS: 2D-SWE had a high success rate and good repeatability for measuring pancreatic head and body stiffness. The ROI depth was the main factor affecting pancreatic SWV, which increased with ROI depth.

Application of ultrasonography in predicting the biological risk of gastrointestinal stromal tumors.

OBJECTIVES: To explore and establish a reliable and noninvasive ultrasound model for predicting the biological risk of gastrointestinal stromal tumors (GISTs). MATERIALS AND METHODS: We retrospectively reviewed 266 patients with pathologically-confirmed GISTs and 191 patients were included. Data on patient sex, age, tumor location, biological risk classification, internal echo, echo homogeneity, boundary, shape, blood flow signals, presence of necrotic cystic degeneration, long diameter, and short/long (S/L) diameter ratio were collected. All patients were divided into low-, moderate-, and high-risk groups according to the modified NIH classification criteria. All indicators were analyzed by univariate analysis. The indicators with inter-group differences were used to establish regression and decision tree models to predict the biological risk of GISTs. RESULTS: There were statistically significant differences in long diameter, S/L ratio, internal echo level, echo homogeneity, boundary, shape, necrotic cystic degeneration, and blood flow signals among the low-, moderate-, and high-risk groups (all p < .05). The logistic regression model based on the echo homogeneity, shape, necrotic cystic degeneration and blood flow signals had an accuracy rate of 76.96% for predicting the biological risk, which was higher than the 72.77% of the decision tree model (based on the long diameter, the location of tumor origin, echo homogeneity, shape, and internal echo) (p = .008). In the low-risk and high-risk groups, the predicting accuracy rates of the regression model reached 87.34 and 81.82%, respectively. CONCLUSIONS: Transabdominal ultrasound is highly valuable in predicting the biological risk of GISTs. The logistic regression model has greater predictive value than the decision tree model.

A Deep Non-negative Matrix Factorization Model for Big Data Representation Learning.

Nowadays, deep representations have been attracting much attention owing to the great performance in various tasks. However, the interpretability of deep representations poses a vast challenge on real-world applications. To alleviate the challenge, a deep matrix factorization method with non-negative constraints is proposed to learn deep part-based representations of interpretability for big data in this paper. Specifically, a deep architecture with a supervisor network suppressing noise in data and a student network learning deep representations of interpretability is designed, which is an end-to-end framework for pattern mining. Furthermore, to train the deep matrix factorization architecture, an interpretability loss is defined, including a symmetric loss, an apposition loss, and a non-negative constraint loss, which can ensure the knowledge transfer from the supervisor network to the student network, enhancing the robustness of deep representations. Finally, extensive experimental results on two benchmark datasets demonstrate the superiority of the deep matrix factorization method.

Efficacy and safety of the application of extensive ablation in patients with atrioventricular re-entrant tachycardia (a retrospective study).

Radiofrequency catheter ablation (RFCA) has become the standard effective therapy for supraventricular tachycardia, but the reported success rates of ablation have differed across a large number of single-center studies. The main reason for tachycardia recurrence is accessory pathway (Ap)-mediated tachycardia, and the use of the RFCA strategy may be related to recurrence. This study compared the efficacy and safety of two different RFCA strategies for Ap-mediated tachycardia. We compared patients (group M) who underwent RFCA at multiple sites to patients (group S) who underwent RFCA at a single site during the index procedure for Ap-mediated tachycardia. The efficacy and safety were assessed in the two groups. Follow-up was conducted, and the main complications and the incidence of recurrence after RFCA procedures were recorded. Eight hundred eighty-two patients with 898 Aps were enrolled in group S, and 830 patients with 843 Aps were enrolled in group M. The cumulative number of recurrences (rates) in group M and group S at the 1st, 3rd, 6th, 12th, and 24th months after ablation were 4 (0.5%) and 17 (1.9%), p < 0.05; 5 (0.6%) and 27 (3.0%), p < 0.05; 6 (0.7%) and 34 (3.8%), p < 0.05; 6 (0.7%) and 43 (4.8%), p < 0.05; and 7 (0.8%) and 45 (5.0%), p < 0.05, respectively. Complications of chest pain, overactive vasovagal reaction, steam pop, and angina pectoris were rare in both groups. One patient in group M suffered from myocardial infarction before extensive ablation. No valve damage, cardiac tamponade, or other serious adverse events occurred in either group. The extensive ablation strategy reduced the recurrence rate and the need for subsequent ablation of the Ap without increasing the risk of complications.

Cross Modal Few-Shot Contextual Transfer for Heterogenous Image Classification.

Deep transfer learning aims at dealing with challenges in new tasks with insufficient samples. However, when it comes to few-shot learning scenarios, due to the low diversity of several known training samples, they are prone to be dominated by specificity, thus leading to one-sidedness local features instead of the reliable global feature of the actual categories they belong to. To alleviate the difficulty, we propose a cross-modal few-shot contextual transfer method that leverages the contextual information as a supplement and learns context awareness transfer in few-shot image classification scenes, which fully utilizes the information in heterogeneous data. The similarity measure in the image classification task is reformulated via fusing textual semantic modal information and visual semantic modal information extracted from images. This performs as a supplement and helps to inhibit the sample specificity. Besides, to better extract local visual features and reorganize the recognition pattern, the deep transfer scheme is also used for reusing a powerful extractor from the pre-trained model. Simulation experiments show that the introduction of cross-modal and intra-modal contextual information can effectively suppress the deviation of defining category features with few samples and improve the accuracy of few-shot image classification tasks.

Ultrasound-Targeted Microbubble Destruction Enhances Inhibitory Effect of Apatinib on Angiogenesis in Triple Negative Breast Carcinoma Xenografts.

Ultrasound-targeted microbubble destruction (UTMD) has been proven as an effective technique to assist drugs to cross the vascular wall and cell membrane. This study was aimed at evaluating the synergistic antiangiogenic and growth-inhibiting effects of apatinib (APA) and UTMD on the triple negative breast cancer (TNBC). The TNBC xenograft model was established in nude mice (n = 40) which were then randomly divided into the APA plus UTMD (APA-U) group, UTMD group, APA group, and model control (M) group (n = 10 per group). Corresponding treatment was done once daily for 14 consecutive days. The general condition and body weight of tumor-bearing nude mice were monitored. Routine blood test and detection of liver and kidney function were done after treatments. The tumor size and microcirculation were examined by two-dimensional ultrasonography (2DUS) and contrast-enhanced ultrasonography (CEUS), respectively. Then, the tumor tissues were harvested for the detection of vascular endothelial growth factor (VEGF) by immunohistochemistry and for CD31-PAS double staining to assess microvessel density (MVD) and heterogeneous vascular positivity rate. After treatments, the tumor growth and angiogenesis were significantly inhibited in the APA group and the APA-U group, and these effects were more obvious in the APA-U group. The tumor volume, CEUS parameters, VEGF expression, and MVD in the APA-U group were significantly lower than those in the APA group (P < 0.05), while there were no marked differences in the heterogeneous vascular positivity rate, body weight, and blood parameters between the two groups (P > 0.05). In the UTMD group, the tumor growth and angiogenesis were not significantly inhibited, and all the parameters were similar to those in the M group (P > 0.05). During the experiment, all mice survived and generally had good condition. In conclusion, APA combined with UTMD may exert synergistic antiangiogenic and growth-inhibiting effects on the TNBC and not increase the heterogeneous vasculature and the severity of APA-related systemic side effects.

Deep sparse transfer learning for remote smart tongue diagnosis.

People are exploring new ideas based on artificial intelligent infrastructures for immediate processing, in which the main obstacles of widely-deploying deep methods are the huge volume of neural network and the lack of training data. To meet the high computing and low latency requirements in modeling remote smart tongue diagnosis with edge computing, an efficient and compact deep neural network design is necessary, while overcoming the vast challenge on modeling its intrinsic diagnosis patterns with the lack of clinical data. To address this challenge, a deep transfer learning model is proposed for the effective tongue diagnosis, based on the proposed similar-sparse domain adaptation (SSDA) scheme. Concretely, a transfer strategy of similar data is introduced to efficiently transfer necessary knowledge, overcoming the insufficiency of clinical tongue images. Then, to generate simplified structure, the network is pruned with transferability remained in domain adaptation. Finally, a compact model combined with two sparse networks is designed to match limited edge device. Extensive experiments are conducted on the real clinical dataset. The proposed model can use fewer training data samples and parameters to produce competitive results with less power and memory consumptions, making it possible to widely run smart tongue diagnosis on low-performance infrastructures.

A Unified Smart Chinese Medicine Framework for Healthcare and Medical Services.

Smart Chinese medicine has emerged to contribute to the evolution of healthcare and medical services by applying machine learning together with advanced computing techniques like cloud computing to computer-aided diagnosis and treatment in the health engineering and informatics. Specifically, smart Chinese medicine is considered to have the potential to treat difficult and complicated diseases such as diabetes and cancers. Unfortunately, smart Chinese medicine has made very limited progress in the past few years. In this paper, we present a unified smart Chinese medicine framework based on the edge-cloud computing system. The objective of the framework is to achieve computer-aided syndrome differentiation and prescription recommendation, and thus to provide pervasive, personalized, and patient-centralized services in healthcare and medicine. To accomplish this objective, we integrate deep learning and deep reinforcement learning into the traditional Chinese medicine. Furthermore, we propose a multi-modal deep computation model for syndrome recognition that is a crucial part of syndrome differentiation. Finally, we conduct experiments to validate the proposed model by comparing with the staked auto-encoder and multi-modal deep learning model for syndrome recognition of hypertension and cold.